From: Herb Derby Date: Mon, 15 May 2017 14:49:39 +0000 (-0400) Subject: Add evenly spaced stops and unify gradient contexts X-Git-Tag: accepted/tizen/5.0/unified/20181102.025319~36^2~243 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=4de1304297d7220b223c829bf386f97815db1654;p=platform%2Fupstream%2FlibSkiaSharp.git Add evenly spaced stops and unify gradient contexts Change-Id: I17ac13b9d1ea6765e2c1a2b53aa6975eab408856 Reviewed-on: https://skia-review.googlesource.com/16713 Commit-Queue: Herb Derby Reviewed-by: Mike Klein --- diff --git a/bench/GradientBench.cpp b/bench/GradientBench.cpp index 1685c52..2d6f5d1 100644 --- a/bench/GradientBench.cpp +++ b/bench/GradientBench.cpp @@ -35,6 +35,7 @@ static const SkColor gColors[] = { }; static const SkColor gShallowColors[] = { 0xFF555555, 0xFF444444 }; +static const SkScalar gPos[] = {0.25f, 0.75f}; // We have several special-cases depending on the number (and spacing) of colors, so // try to exercise those here. @@ -43,6 +44,7 @@ static const GradData gGradData[] = { { 50, gColors, nullptr, "_hicolor" }, // many color gradient { 3, gColors, nullptr, "_3color" }, { 2, gShallowColors, nullptr, "_shallow" }, + { 2, gColors, gPos, "_pos" }, }; /// Ignores scale @@ -281,6 +283,8 @@ DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[1], SkShader::kC kRect_GeomType, 1, true); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[2], SkShader::kClamp_TileMode, kRect_GeomType, 1, true); ) +DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[4], SkShader::kClamp_TileMode, + kRect_GeomType, 1, true); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[0], SkShader::kRepeat_TileMode, kRect_GeomType, 1, true); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[1], SkShader::kRepeat_TileMode, @@ -297,6 +301,7 @@ DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[2], SkShader::kM DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[0]); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[1]); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[2]); ) +DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[4]); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[0], SkShader::kRepeat_TileMode); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[1], SkShader::kRepeat_TileMode); ) DEF_BENCH( return new GradientBench(kLinear_GradType, gGradData[2], SkShader::kRepeat_TileMode); ) diff --git a/src/core/SkRasterPipeline.h b/src/core/SkRasterPipeline.h index f5bb7d1..1579b45 100644 --- a/src/core/SkRasterPipeline.h +++ b/src/core/SkRasterPipeline.h @@ -96,6 +96,7 @@ M(bicubic_n3x) M(bicubic_n1x) M(bicubic_p1x) M(bicubic_p3x) \ M(bicubic_n3y) M(bicubic_n1y) M(bicubic_p1y) M(bicubic_p3y) \ M(save_xy) M(accumulate) \ + M(evenly_spaced_gradient) \ M(gradient) \ M(evenly_spaced_2_stop_gradient) \ M(xy_to_unit_angle) \ diff --git a/src/effects/gradients/SkGradientShader.cpp b/src/effects/gradients/SkGradientShader.cpp index 042ad45..038bea6 100644 --- a/src/effects/gradients/SkGradientShader.cpp +++ b/src/effects/gradients/SkGradientShader.cpp @@ -5,6 +5,7 @@ * found in the LICENSE file. */ +#include #include "Sk4fLinearGradient.h" #include "SkColorSpace_XYZ.h" #include "SkGradientShaderPriv.h" @@ -14,6 +15,8 @@ #include "SkRadialGradient.h" #include "SkSweepGradient.h" #include "SkTwoPointConicalGradient.h" +#include "../../jumper/SkJumper.h" + enum GradientSerializationFlags { // Bits 29:31 used for various boolean flags @@ -406,51 +409,58 @@ bool SkGradientShaderBase::onAppendStages(SkRasterPipeline* p, p->append(SkRasterPipeline::evenly_spaced_2_stop_gradient, f_and_b); } else { + auto* ctx = alloc->make(); + auto add_stop_color = [&](size_t stop, SkPM4f Fs, SkPM4f Bs) { + (ctx->fs[0])[stop] = Fs.r(); + (ctx->fs[1])[stop] = Fs.g(); + (ctx->fs[2])[stop] = Fs.b(); + (ctx->fs[3])[stop] = Fs.a(); + (ctx->bs[0])[stop] = Bs.r(); + (ctx->bs[1])[stop] = Bs.g(); + (ctx->bs[2])[stop] = Bs.b(); + (ctx->bs[3])[stop] = Bs.a(); + }; - struct Stop { float t; SkPM4f f, b; }; - struct Ctx { size_t n; Stop* stops; SkPM4f start; }; - - auto* ctx = alloc->make(); - ctx->start = prepareColor(0); - - // For each stop we calculate a bias B and a scale factor F, such that - // for any t between stops n and n+1, the color we want is B[n] + F[n]*t. - auto init_stop = [](float t_l, float t_r, SkPM4f c_l, SkPM4f c_r, Stop *stop) { - auto F = SkPM4f::From4f((c_r.to4f() - c_l.to4f()) / (t_r - t_l)); - auto B = SkPM4f::From4f(c_l.to4f() - (F.to4f() * t_l)); - *stop = {t_l, F, B}; + auto add_const_color = [&](size_t stop, SkPM4f color) { + add_stop_color(stop, SkPM4f::FromPremulRGBA(0,0,0,0), color); }; + // Note: In order to handle clamps in search, the search assumes a stop conceptully placed + // at -inf. Therefore, the max number of stops is fColorCount+1. + for (int i = 0; i < 4; i++) { + // Allocate at least at for the AVX2 gather from a YMM register. + ctx->fs[i] = alloc->makeArray(std::max(fColorCount+1, 8)); + ctx->bs[i] = alloc->makeArray(std::max(fColorCount+1, 8)); + } + if (fOrigPos == nullptr) { // Handle evenly distributed stops. - float dt = 1.0f / (fColorCount - 1); - // In the evenly distributed case, fColorCount is the number of stops. There are no - // dummy entries. - auto* stopsArray = alloc->makeArrayDefault(fColorCount); - - float t_l = 0; - SkPM4f c_l = ctx->start; - for (int i = 0; i < fColorCount - 1; i++) { - // Use multiply instead of accumulating error using repeated addition. - float t_r = (i + 1) * dt; + size_t stopCount = fColorCount; + float gapCount = stopCount - 1; + // Calculate a factor F and a bias B so that color = F*t + B when t is in range of + // the stop. Assume that the distance between stops is 1/gapCount. + auto init_stop = [&](size_t stop, SkPM4f c_l, SkPM4f c_r) { + auto Fs = SkPM4f::From4f((c_r.to4f() - c_l.to4f()) * gapCount); + auto Bs = SkPM4f::From4f(c_l.to4f() - (Fs.to4f() * (stop/gapCount))); + add_stop_color(stop, Fs, Bs); + }; + + SkPM4f c_l = prepareColor(0); + for (size_t i = 0; i < stopCount - 1; i++) { SkPM4f c_r = prepareColor(i + 1); - init_stop(t_l, t_r, c_l, c_r, &stopsArray[i]); - - t_l = t_r; + init_stop(i, c_l, c_r); c_l = c_r; } + add_const_color(stopCount - 1, c_l); - // Force the last stop. - stopsArray[fColorCount - 1].t = 1; - stopsArray[fColorCount - 1].f = SkPM4f::From4f(Sk4f{0}); - stopsArray[fColorCount - 1].b = prepareColor(fColorCount - 1); - - ctx->n = fColorCount; - ctx->stops = stopsArray; + ctx->stopCount = stopCount; + p->append(SkRasterPipeline::evenly_spaced_gradient, ctx); } else { // Handle arbitrary stops. + ctx->ts = alloc->makeArray(fColorCount+1); + // Remove the dummy stops inserted by SkGradientShaderBase::SkGradientShaderBase // because they are naturally handled by the search method. int firstStop; @@ -463,37 +473,38 @@ bool SkGradientShaderBase::onAppendStages(SkRasterPipeline* p, firstStop = 0; lastStop = 1; } - int realCount = lastStop - firstStop + 1; - // This is the maximum number of stops. There may be fewer stops because the duplicate - // points of hard stops are removed. - auto* stopsArray = alloc->makeArrayDefault(realCount); + // For each stop we calculate a bias B and a scale factor F, such that + // for any t between stops n and n+1, the color we want is B[n] + F[n]*t. + auto init_stop = [&](size_t stop, float t_l, float t_r, SkPM4f c_l, SkPM4f c_r) { + auto Fs = SkPM4f::From4f((c_r.to4f() - c_l.to4f()) / (t_r - t_l)); + auto Bs = SkPM4f::From4f(c_l.to4f() - (Fs.to4f() * t_l)); + ctx->ts[stop] = t_l; + add_stop_color(stop, Fs, Bs); + }; size_t stopCount = 0; float t_l = fOrigPos[firstStop]; SkPM4f c_l = prepareColor(firstStop); + add_const_color(stopCount++, c_l); // N.B. lastStop is the index of the last stop, not one after. for (int i = firstStop; i < lastStop; i++) { float t_r = fOrigPos[i + 1]; SkPM4f c_r = prepareColor(i + 1); if (t_l < t_r) { - init_stop(t_l, t_r, c_l, c_r, &stopsArray[stopCount]); + init_stop(stopCount, t_l, t_r, c_l, c_r); stopCount += 1; } t_l = t_r; c_l = c_r; } - stopsArray[stopCount].t = fOrigPos[lastStop]; - stopsArray[stopCount].f = SkPM4f::From4f(Sk4f{0}); - stopsArray[stopCount].b = prepareColor(lastStop); - stopCount += 1; + ctx->ts[stopCount] = t_l; + add_const_color(stopCount++, c_l); - ctx->n = stopCount; - ctx->stops = stopsArray; + ctx->stopCount = stopCount; + p->append(SkRasterPipeline::gradient, ctx); } - - p->append(SkRasterPipeline::gradient, ctx); } if (!premulGrad && !this->colorsAreOpaque()) { diff --git a/src/jumper/SkJumper.h b/src/jumper/SkJumper.h index 9c805b3..7dc88ce 100644 --- a/src/jumper/SkJumper.h +++ b/src/jumper/SkJumper.h @@ -99,4 +99,11 @@ struct SkJumper_DitherCtx { float rate; }; +struct SkJumper_GradientCtx { + size_t stopCount; + float* fs[4]; + float* bs[4]; + float* ts; +}; + #endif//SkJumper_DEFINED diff --git a/src/jumper/SkJumper_generated.S b/src/jumper/SkJumper_generated.S index 85a5c51..82dd6b3 100644 --- a/src/jumper/SkJumper_generated.S +++ b/src/jumper/SkJumper_generated.S @@ -3531,85 +3531,209 @@ _sk_matrix_perspective_aarch64: .long 0x6e32de80 // fmul v0.4s, v20.4s, v18.4s .long 0xd61f0060 // br x3 +HIDDEN _sk_evenly_spaced_gradient_aarch64 +.globl _sk_evenly_spaced_gradient_aarch64 +FUNCTION(_sk_evenly_spaced_gradient_aarch64) +_sk_evenly_spaced_gradient_aarch64: + .long 0xd10043ff // sub sp, sp, #0x10 + .long 0xaa0103e8 // mov x8, x1 + .long 0x91002109 // add x9, x8, #0x8 + .long 0xf90007e9 // str x9, [sp, #8] + .long 0xf841042a // ldr x10, [x1], #16 + .long 0xa940254b // ldp x11, x9, [x10] + .long 0xa942354c // ldp x12, x13, [x10, #32] + .long 0xa9413d4e // ldp x14, x15, [x10, #16] + .long 0xa9434550 // ldp x16, x17, [x10, #48] + .long 0xd100056b // sub x11, x11, #0x1 + .long 0x9e230161 // ucvtf s1, x11 + .long 0xf940214a // ldr x10, [x10, #64] + .long 0x4f819001 // fmul v1.4s, v0.4s, v1.s[0] + .long 0x4ea1b821 // fcvtzs v1.4s, v1.4s + .long 0x6f20a422 // uxtl2 v2.2d, v1.4s + .long 0x2f20a421 // uxtl v1.2d, v1.2s + .long 0x9e660032 // fmov x18, d1 + .long 0x9e660044 // fmov x4, d2 + .long 0x4e183c2b // mov x11, v1.d[1] + .long 0x4e183c43 // mov x3, v2.d[1] + .long 0xbc647921 // ldr s1, [x9, x4, lsl #2] + .long 0xbc6479a2 // ldr s2, [x13, x4, lsl #2] + .long 0xbc6479c3 // ldr s3, [x14, x4, lsl #2] + .long 0xbc647a11 // ldr s17, [x16, x4, lsl #2] + .long 0xbc6479f2 // ldr s18, [x15, x4, lsl #2] + .long 0xbc647a33 // ldr s19, [x17, x4, lsl #2] + .long 0xbc647994 // ldr s20, [x12, x4, lsl #2] + .long 0xbc647955 // ldr s21, [x10, x4, lsl #2] + .long 0x8b120924 // add x4, x9, x18, lsl #2 + .long 0x0d408096 // ld1 {v22.s}[0], [x4] + .long 0x8b1209a4 // add x4, x13, x18, lsl #2 + .long 0x0d408090 // ld1 {v16.s}[0], [x4] + .long 0x8b0b0924 // add x4, x9, x11, lsl #2 + .long 0x0d409096 // ld1 {v22.s}[1], [x4] + .long 0x8b1209c4 // add x4, x14, x18, lsl #2 + .long 0x0d408097 // ld1 {v23.s}[0], [x4] + .long 0x8b120a04 // add x4, x16, x18, lsl #2 + .long 0x6e140436 // mov v22.s[2], v1.s[0] + .long 0x0d408081 // ld1 {v1.s}[0], [x4] + .long 0x8b0b09a4 // add x4, x13, x11, lsl #2 + .long 0x0d409090 // ld1 {v16.s}[1], [x4] + .long 0x8b0b09c4 // add x4, x14, x11, lsl #2 + .long 0x0d409097 // ld1 {v23.s}[1], [x4] + .long 0x8b1209e4 // add x4, x15, x18, lsl #2 + .long 0x0d408098 // ld1 {v24.s}[0], [x4] + .long 0x8b120a24 // add x4, x17, x18, lsl #2 + .long 0x6e140450 // mov v16.s[2], v2.s[0] + .long 0x0d408082 // ld1 {v2.s}[0], [x4] + .long 0x8b0b0a04 // add x4, x16, x11, lsl #2 + .long 0x0d409081 // ld1 {v1.s}[1], [x4] + .long 0x8b0b09e4 // add x4, x15, x11, lsl #2 + .long 0x0d409098 // ld1 {v24.s}[1], [x4] + .long 0x8b120984 // add x4, x12, x18, lsl #2 + .long 0x8b120952 // add x18, x10, x18, lsl #2 + .long 0x6e140477 // mov v23.s[2], v3.s[0] + .long 0x0d408243 // ld1 {v3.s}[0], [x18] + .long 0x8b0b0a32 // add x18, x17, x11, lsl #2 + .long 0x6e140621 // mov v1.s[2], v17.s[0] + .long 0x0d408091 // ld1 {v17.s}[0], [x4] + .long 0x0d409242 // ld1 {v2.s}[1], [x18] + .long 0x8b0b0992 // add x18, x12, x11, lsl #2 + .long 0x6e140658 // mov v24.s[2], v18.s[0] + .long 0x0d409251 // ld1 {v17.s}[1], [x18] + .long 0x6e140662 // mov v2.s[2], v19.s[0] + .long 0xbc637932 // ldr s18, [x9, x3, lsl #2] + .long 0xbc6379b3 // ldr s19, [x13, x3, lsl #2] + .long 0x6e140691 // mov v17.s[2], v20.s[0] + .long 0xbc6379d4 // ldr s20, [x14, x3, lsl #2] + .long 0x6e1c0656 // mov v22.s[3], v18.s[0] + .long 0xbc637a12 // ldr s18, [x16, x3, lsl #2] + .long 0x6e1c0670 // mov v16.s[3], v19.s[0] + .long 0xbc6379f3 // ldr s19, [x15, x3, lsl #2] + .long 0x8b0b094b // add x11, x10, x11, lsl #2 + .long 0x0d409163 // ld1 {v3.s}[1], [x11] + .long 0x6e1c0697 // mov v23.s[3], v20.s[0] + .long 0xbc637a34 // ldr s20, [x17, x3, lsl #2] + .long 0x6e1c0641 // mov v1.s[3], v18.s[0] + .long 0xbc637992 // ldr s18, [x12, x3, lsl #2] + .long 0x6e1c0678 // mov v24.s[3], v19.s[0] + .long 0xbc637953 // ldr s19, [x10, x3, lsl #2] + .long 0xf9400503 // ldr x3, [x8, #8] + .long 0x6e1406a3 // mov v3.s[2], v21.s[0] + .long 0x6e1c0682 // mov v2.s[3], v20.s[0] + .long 0x6e1c0651 // mov v17.s[3], v18.s[0] + .long 0x6e1c0663 // mov v3.s[3], v19.s[0] + .long 0x4e20ced0 // fmla v16.4s, v22.4s, v0.4s + .long 0x4e20cee1 // fmla v1.4s, v23.4s, v0.4s + .long 0x4e20cf02 // fmla v2.4s, v24.4s, v0.4s + .long 0x4e20ce23 // fmla v3.4s, v17.4s, v0.4s + .long 0x4eb01e00 // mov v0.16b, v16.16b + .long 0x910043ff // add sp, sp, #0x10 + .long 0xd61f0060 // br x3 + HIDDEN _sk_gradient_aarch64 .globl _sk_gradient_aarch64 FUNCTION(_sk_gradient_aarch64) _sk_gradient_aarch64: - .long 0xf9400029 // ldr x9, [x1] - .long 0x91004128 // add x8, x9, #0x10 - .long 0x9100512a // add x10, x9, #0x14 - .long 0x4d40c910 // ld1r {v16.4s}, [x8] - .long 0x91006128 // add x8, x9, #0x18 - .long 0x4d40c941 // ld1r {v1.4s}, [x10] - .long 0x9100712a // add x10, x9, #0x1c - .long 0x4d40c902 // ld1r {v2.4s}, [x8] - .long 0xf9400128 // ldr x8, [x9] - .long 0x4d40c943 // ld1r {v3.4s}, [x10] - .long 0xb40006c8 // cbz x8, 2fe8 - .long 0x6dbf23e9 // stp d9, d8, [sp, #-16]! - .long 0xf9400529 // ldr x9, [x9, #8] - .long 0x6f00e413 // movi v19.2d, #0x0 - .long 0x6f00e411 // movi v17.2d, #0x0 - .long 0x6f00e412 // movi v18.2d, #0x0 - .long 0x91004129 // add x9, x9, #0x10 - .long 0x6f00e414 // movi v20.2d, #0x0 - .long 0xd100412a // sub x10, x9, #0x10 - .long 0x4d40c955 // ld1r {v21.4s}, [x10] - .long 0xd100312b // sub x11, x9, #0xc - .long 0xd100212a // sub x10, x9, #0x8 - .long 0x4d40c976 // ld1r {v22.4s}, [x11] - .long 0xd100112b // sub x11, x9, #0x4 - .long 0x4d40c957 // ld1r {v23.4s}, [x10] - .long 0xaa0903ea // mov x10, x9 - .long 0x4d40c978 // ld1r {v24.4s}, [x11] - .long 0x4ddfc959 // ld1r {v25.4s}, [x10], #4 - .long 0x9100412b // add x11, x9, #0x10 - .long 0x4ea31c7b // mov v27.16b, v3.16b - .long 0x6ea0e6a3 // fcmgt v3.4s, v21.4s, v0.4s - .long 0x4d40c97a // ld1r {v26.4s}, [x11] - .long 0x4eb41e95 // mov v21.16b, v20.16b - .long 0x4ea31c74 // mov v20.16b, v3.16b - .long 0x9100212b // add x11, x9, #0x8 - .long 0x4eb31e69 // mov v9.16b, v19.16b - .long 0x4ea31c73 // mov v19.16b, v3.16b - .long 0x6e771eb4 // bsl v20.16b, v21.16b, v23.16b - .long 0x4d40c975 // ld1r {v21.4s}, [x11] - .long 0x9100312b // add x11, x9, #0xc - .long 0x6e761d33 // bsl v19.16b, v9.16b, v22.16b - .long 0x4d40c976 // ld1r {v22.4s}, [x11] - .long 0x4d40c957 // ld1r {v23.4s}, [x10] - .long 0x4eb21e5c // mov v28.16b, v18.16b - .long 0x4eb11e3d // mov v29.16b, v17.16b - .long 0x4eb01e1e // mov v30.16b, v16.16b - .long 0x4ea11c3f // mov v31.16b, v1.16b - .long 0x4ea21c48 // mov v8.16b, v2.16b - .long 0x4ea31c72 // mov v18.16b, v3.16b - .long 0x4ea31c71 // mov v17.16b, v3.16b - .long 0x4ea31c70 // mov v16.16b, v3.16b - .long 0x4ea31c61 // mov v1.16b, v3.16b - .long 0x4ea31c62 // mov v2.16b, v3.16b - .long 0x6e7a1f63 // bsl v3.16b, v27.16b, v26.16b - .long 0x6e781f92 // bsl v18.16b, v28.16b, v24.16b - .long 0x6e791fb1 // bsl v17.16b, v29.16b, v25.16b - .long 0x6e751fe1 // bsl v1.16b, v31.16b, v21.16b - .long 0x6e761d02 // bsl v2.16b, v8.16b, v22.16b - .long 0xd1000508 // sub x8, x8, #0x1 - .long 0x6e771fd0 // bsl v16.16b, v30.16b, v23.16b - .long 0x91009129 // add x9, x9, #0x24 - .long 0xb5fffaa8 // cbnz x8, 2f30 - .long 0x6cc123e9 // ldp d9, d8, [sp], #16 - .long 0x14000005 // b 2ff8 - .long 0x6f00e414 // movi v20.2d, #0x0 - .long 0x6f00e412 // movi v18.2d, #0x0 + .long 0xd10043ff // sub sp, sp, #0x10 + .long 0x91002028 // add x8, x1, #0x8 + .long 0xf90007e8 // str x8, [sp, #8] + .long 0xf9400028 // ldr x8, [x1] + .long 0x6f00e401 // movi v1.2d, #0x0 .long 0x6f00e411 // movi v17.2d, #0x0 - .long 0x6f00e413 // movi v19.2d, #0x0 - .long 0xf9400423 // ldr x3, [x1, #8] - .long 0x4e20ce70 // fmla v16.4s, v19.4s, v0.4s - .long 0x4e20ce81 // fmla v1.4s, v20.4s, v0.4s - .long 0x4e20ce42 // fmla v2.4s, v18.4s, v0.4s - .long 0x4e20ce23 // fmla v3.4s, v17.4s, v0.4s - .long 0x91004021 // add x1, x1, #0x10 + .long 0xf9400109 // ldr x9, [x8] + .long 0xf100093f // cmp x9, #0x2 + .long 0x540001c3 // b.cc 30b0 // b.lo, b.ul, b.last + .long 0xf940250a // ldr x10, [x8, #72] + .long 0xd1000529 // sub x9, x9, #0x1 + .long 0x6f00e401 // movi v1.2d, #0x0 + .long 0x4f000422 // movi v2.4s, #0x1 + .long 0x9100114a // add x10, x10, #0x4 + .long 0x4ddfc943 // ld1r {v3.4s}, [x10], #4 + .long 0xd1000529 // sub x9, x9, #0x1 + .long 0x6e23e403 // fcmge v3.4s, v0.4s, v3.4s + .long 0x4e221c63 // and v3.16b, v3.16b, v2.16b + .long 0x4ea18461 // add v1.4s, v3.4s, v1.4s + .long 0xb5ffff69 // cbnz x9, 3090 + .long 0x6f20a431 // uxtl2 v17.2d, v1.4s + .long 0x2f20a421 // uxtl v1.2d, v1.2s + .long 0xa940b10a // ldp x10, x12, [x8, #8] + .long 0xa942b90d // ldp x13, x14, [x8, #40] + .long 0x9e66002b // fmov x11, d1 + .long 0xa941c10f // ldp x15, x16, [x8, #24] + .long 0x8b0b0952 // add x18, x10, x11, lsl #2 + .long 0xa943a111 // ldp x17, x8, [x8, #56] + .long 0x0d408252 // ld1 {v18.s}[0], [x18] + .long 0x8b0b09b2 // add x18, x13, x11, lsl #2 + .long 0x0d408250 // ld1 {v16.s}[0], [x18] + .long 0x8b0b0992 // add x18, x12, x11, lsl #2 + .long 0x0d408253 // ld1 {v19.s}[0], [x18] + .long 0x8b0b09d2 // add x18, x14, x11, lsl #2 + .long 0x4e183c29 // mov x9, v1.d[1] + .long 0x0d408241 // ld1 {v1.s}[0], [x18] + .long 0x8b0b09f2 // add x18, x15, x11, lsl #2 + .long 0x0d408254 // ld1 {v20.s}[0], [x18] + .long 0x8b0b0a32 // add x18, x17, x11, lsl #2 + .long 0x0d408242 // ld1 {v2.s}[0], [x18] + .long 0x8b0b0a12 // add x18, x16, x11, lsl #2 + .long 0x8b0b090b // add x11, x8, x11, lsl #2 + .long 0x0d408163 // ld1 {v3.s}[0], [x11] + .long 0x8b09094b // add x11, x10, x9, lsl #2 + .long 0x0d409172 // ld1 {v18.s}[1], [x11] + .long 0x8b0909ab // add x11, x13, x9, lsl #2 + .long 0x0d409170 // ld1 {v16.s}[1], [x11] + .long 0x8b09098b // add x11, x12, x9, lsl #2 + .long 0x0d409173 // ld1 {v19.s}[1], [x11] + .long 0x8b0909cb // add x11, x14, x9, lsl #2 + .long 0x0d409161 // ld1 {v1.s}[1], [x11] + .long 0x8b0909eb // add x11, x15, x9, lsl #2 + .long 0x0d408255 // ld1 {v21.s}[0], [x18] + .long 0x9e660232 // fmov x18, d17 + .long 0x0d409174 // ld1 {v20.s}[1], [x11] + .long 0x4e183e2b // mov x11, v17.d[1] + .long 0xbc6b7951 // ldr s17, [x10, x11, lsl #2] + .long 0x8b12094a // add x10, x10, x18, lsl #2 + .long 0x4d408152 // ld1 {v18.s}[2], [x10] + .long 0x8b1209aa // add x10, x13, x18, lsl #2 + .long 0xbc6b79b6 // ldr s22, [x13, x11, lsl #2] + .long 0x4d408150 // ld1 {v16.s}[2], [x10] + .long 0x8b12098a // add x10, x12, x18, lsl #2 + .long 0x4d408153 // ld1 {v19.s}[2], [x10] + .long 0x8b1209ca // add x10, x14, x18, lsl #2 + .long 0x4d408141 // ld1 {v1.s}[2], [x10] + .long 0x8b090a2a // add x10, x17, x9, lsl #2 + .long 0xbc6b7997 // ldr s23, [x12, x11, lsl #2] + .long 0x8b1209ec // add x12, x15, x18, lsl #2 + .long 0x0d409142 // ld1 {v2.s}[1], [x10] + .long 0x8b090a0a // add x10, x16, x9, lsl #2 + .long 0x8b090909 // add x9, x8, x9, lsl #2 + .long 0x6e1c0632 // mov v18.s[3], v17.s[0] + .long 0xbc6b79d1 // ldr s17, [x14, x11, lsl #2] + .long 0x6e1c06d0 // mov v16.s[3], v22.s[0] + .long 0xbc6b79f6 // ldr s22, [x15, x11, lsl #2] + .long 0x0d409155 // ld1 {v21.s}[1], [x10] + .long 0x4d408194 // ld1 {v20.s}[2], [x12] + .long 0x0d409123 // ld1 {v3.s}[1], [x9] + .long 0xf94007e1 // ldr x1, [sp, #8] + .long 0x8b120a2d // add x13, x17, x18, lsl #2 + .long 0x8b120a0e // add x14, x16, x18, lsl #2 + .long 0x8b12090f // add x15, x8, x18, lsl #2 + .long 0x6e1c06f3 // mov v19.s[3], v23.s[0] + .long 0xbc6b7a37 // ldr s23, [x17, x11, lsl #2] + .long 0x6e1c0621 // mov v1.s[3], v17.s[0] + .long 0xbc6b7a11 // ldr s17, [x16, x11, lsl #2] + .long 0x4d4081a2 // ld1 {v2.s}[2], [x13] + .long 0x4d4081d5 // ld1 {v21.s}[2], [x14] + .long 0x6e1c06d4 // mov v20.s[3], v22.s[0] + .long 0xbc6b7916 // ldr s22, [x8, x11, lsl #2] + .long 0x4d4081e3 // ld1 {v3.s}[2], [x15] + .long 0xf8408423 // ldr x3, [x1], #8 + .long 0x6e1c06e2 // mov v2.s[3], v23.s[0] + .long 0x6e1c0635 // mov v21.s[3], v17.s[0] + .long 0x6e1c06c3 // mov v3.s[3], v22.s[0] + .long 0x4e20ce50 // fmla v16.4s, v18.4s, v0.4s + .long 0x4e20ce61 // fmla v1.4s, v19.4s, v0.4s + .long 0x4e20ce82 // fmla v2.4s, v20.4s, v0.4s + .long 0x4e20cea3 // fmla v3.4s, v21.4s, v0.4s .long 0x4eb01e00 // mov v0.16b, v16.16b + .long 0x910043ff // add sp, sp, #0x10 .long 0xd61f0060 // br x3 HIDDEN _sk_evenly_spaced_2_stop_gradient_aarch64 @@ -7924,90 +8048,146 @@ _sk_matrix_perspective_vfp4: .long 0xe8bd4010 // pop {r4, lr} .long 0xe12fff1c // bx ip +HIDDEN _sk_evenly_spaced_gradient_vfp4 +.globl _sk_evenly_spaced_gradient_vfp4 +FUNCTION(_sk_evenly_spaced_gradient_vfp4) +_sk_evenly_spaced_gradient_vfp4: + .long 0xe92d47f0 // push {r4, r5, r6, r7, r8, r9, sl, lr} + .long 0xed2d8b0a // vpush {d8-d12} + .long 0xe8911008 // ldm r1, {r3, ip} + .long 0xe2811008 // add r1, r1, #8 + .long 0xe8934010 // ldm r3, {r4, lr} + .long 0xe2444001 // sub r4, r4, #1 + .long 0xe5937010 // ldr r7, [r3, #16] + .long 0xe593a020 // ldr sl, [r3, #32] + .long 0xee804b90 // vdup.32 d16, r4 + .long 0xe593900c // ldr r9, [r3, #12] + .long 0xf3fb06a0 // vcvt.f32.u32 d16, d16 + .long 0xe5938008 // ldr r8, [r3, #8] + .long 0xf3400d90 // vmul.f32 d16, d16, d0 + .long 0xf3fb0720 // vcvt.s32.f32 d16, d16 + .long 0xee304b90 // vmov.32 r4, d16[1] + .long 0xe0875104 // add r5, r7, r4, lsl #2 + .long 0xe08a6104 // add r6, sl, r4, lsl #2 + .long 0xedd59a00 // vldr s19, [r5] + .long 0xee105b90 // vmov.32 r5, d16[0] + .long 0xedd63a00 // vldr s7, [r6] + .long 0xe0896104 // add r6, r9, r4, lsl #2 + .long 0xedd6aa00 // vldr s21, [r6] + .long 0xe0896105 // add r6, r9, r5, lsl #2 + .long 0xe0877105 // add r7, r7, r5, lsl #2 + .long 0xe5939018 // ldr r9, [r3, #24] + .long 0xed96aa00 // vldr s20, [r6] + .long 0xe593601c // ldr r6, [r3, #28] + .long 0xed979a00 // vldr s18, [r7] + .long 0xe0867104 // add r7, r6, r4, lsl #2 + .long 0xe5933014 // ldr r3, [r3, #20] + .long 0xe0866105 // add r6, r6, r5, lsl #2 + .long 0xedd72a00 // vldr s5, [r7] + .long 0xe0887104 // add r7, r8, r4, lsl #2 + .long 0xedd7ba00 // vldr s23, [r7] + .long 0xe0887105 // add r7, r8, r5, lsl #2 + .long 0xe08a8105 // add r8, sl, r5, lsl #2 + .long 0xed962a00 // vldr s4, [r6] + .long 0xed97ba00 // vldr s22, [r7] + .long 0xe0897104 // add r7, r9, r4, lsl #2 + .long 0xed983a00 // vldr s6, [r8] + .long 0xf2002c1a // vfma.f32 d2, d0, d10 + .long 0xedd71a00 // vldr s3, [r7] + .long 0xe08e7104 // add r7, lr, r4, lsl #2 + .long 0xf2003c19 // vfma.f32 d3, d0, d9 + .long 0xedd7ca00 // vldr s25, [r7] + .long 0xe08e7105 // add r7, lr, r5, lsl #2 + .long 0xed97ca00 // vldr s24, [r7] + .long 0xe0837105 // add r7, r3, r5, lsl #2 + .long 0xe0833104 // add r3, r3, r4, lsl #2 + .long 0xedd38a00 // vldr s17, [r3] + .long 0xe0893105 // add r3, r9, r5, lsl #2 + .long 0xed978a00 // vldr s16, [r7] + .long 0xed931a00 // vldr s2, [r3] + .long 0xf2008c1c // vfma.f32 d8, d0, d12 + .long 0xf2001c1b // vfma.f32 d1, d0, d11 + .long 0xf2280118 // vorr d0, d8, d8 + .long 0xecbd8b0a // vpop {d8-d12} + .long 0xe8bd47f0 // pop {r4, r5, r6, r7, r8, r9, sl, lr} + .long 0xe12fff1c // bx ip + HIDDEN _sk_gradient_vfp4 .globl _sk_gradient_vfp4 FUNCTION(_sk_gradient_vfp4) _sk_gradient_vfp4: - .long 0xe92d4010 // push {r4, lr} - .long 0xe591e000 // ldr lr, [r1] - .long 0xe28e3014 // add r3, lr, #20 - .long 0xe1a0400e // mov r4, lr - .long 0xf4a33c9f // vld1.32 {d3[]}, [r3 :32] - .long 0xe28e3010 // add r3, lr, #16 - .long 0xf4a32c9f // vld1.32 {d2[]}, [r3 :32] - .long 0xe28e3008 // add r3, lr, #8 - .long 0xf4e30c9f // vld1.32 {d16[]}, [r3 :32] - .long 0xe494c00c // ldr ip, [r4], #12 - .long 0xf4a41c9f // vld1.32 {d1[]}, [r4 :32] - .long 0xe35c0000 // cmp ip, #0 - .long 0x0a000036 // beq 3618 - .long 0xe59e3004 // ldr r3, [lr, #4] + .long 0xe92d4ff0 // push {r4, r5, r6, r7, r8, r9, sl, fp, lr} + .long 0xe24dd004 // sub sp, sp, #4 + .long 0xed2d8b0a // vpush {d8-d12} + .long 0xe591c000 // ldr ip, [r1] + .long 0xf2c00010 // vmov.i32 d16, #0 + .long 0xe59c3000 // ldr r3, [ip] + .long 0xe3530002 // cmp r3, #2 + .long 0x3a00000b // bcc 3644 + .long 0xe59c4024 // ldr r4, [ip, #36] .long 0xf2c01010 // vmov.i32 d17, #0 - .long 0xf2c07010 // vmov.i32 d23, #0 - .long 0xf2c08010 // vmov.i32 d24, #0 - .long 0xe2833020 // add r3, r3, #32 - .long 0xf2c06010 // vmov.i32 d22, #0 - .long 0xe2434018 // sub r4, r3, #24 - .long 0xf4e33c9f // vld1.32 {d19[]}, [r3 :32] - .long 0xe25cc001 // subs ip, ip, #1 - .long 0xf4e4dc9f // vld1.32 {d29[]}, [r4 :32] - .long 0xe2434014 // sub r4, r3, #20 - .long 0xf4e45c9f // vld1.32 {d21[]}, [r4 :32] - .long 0xe243400c // sub r4, r3, #12 - .long 0xf4e44c9f // vld1.32 {d20[]}, [r4 :32] - .long 0xe2434020 // sub r4, r3, #32 - .long 0xf4e42c9f // vld1.32 {d18[]}, [r4 :32] - .long 0xe2434004 // sub r4, r3, #4 - .long 0xf3622e80 // vcgt.f32 d18, d18, d0 - .long 0xf4e4bc9f // vld1.32 {d27[]}, [r4 :32] - .long 0xe2434008 // sub r4, r3, #8 - .long 0xf4e4cc9f // vld1.32 {d28[]}, [r4 :32] - .long 0xe2434010 // sub r4, r3, #16 - .long 0xf262a1b2 // vorr d26, d18, d18 - .long 0xf4e4ec9f // vld1.32 {d30[]}, [r4 :32] - .long 0xe243401c // sub r4, r3, #28 - .long 0xf352a13b // vbsl d26, d2, d27 - .long 0xe2833024 // add r3, r3, #36 - .long 0xf262b1b2 // vorr d27, d18, d18 - .long 0xf26291b2 // vorr d25, d18, d18 - .long 0xf351b13c // vbsl d27, d1, d28 - .long 0xf262c1b2 // vorr d28, d18, d18 - .long 0xf3539133 // vbsl d25, d3, d19 - .long 0xf350c1b4 // vbsl d28, d16, d20 - .long 0xf4e40c9f // vld1.32 {d16[]}, [r4 :32] - .long 0xf26241b2 // vorr d20, d18, d18 - .long 0xf26231b2 // vorr d19, d18, d18 - .long 0xf35841b5 // vbsl d20, d24, d21 - .long 0xf26251b2 // vorr d21, d18, d18 - .long 0xf35121b0 // vbsl d18, d17, d16 - .long 0xf35731be // vbsl d19, d23, d30 - .long 0xf35651bd // vbsl d21, d22, d29 - .long 0xf26211b2 // vorr d17, d18, d18 - .long 0xf22931b9 // vorr d3, d25, d25 - .long 0xf22a21ba // vorr d2, d26, d26 - .long 0xf22b11bb // vorr d1, d27, d27 - .long 0xf26c01bc // vorr d16, d28, d28 - .long 0xf26371b3 // vorr d23, d19, d19 - .long 0xf26481b4 // vorr d24, d20, d20 - .long 0xf26561b5 // vorr d22, d21, d21 - .long 0x1affffd3 // bne 3554 - .long 0xf26c01bc // vorr d16, d28, d28 - .long 0xf22b11bb // vorr d1, d27, d27 - .long 0xf22a21ba // vorr d2, d26, d26 - .long 0xf22931b9 // vorr d3, d25, d25 - .long 0xea000003 // b 3628 - .long 0xf2c05010 // vmov.i32 d21, #0 - .long 0xf2c04010 // vmov.i32 d20, #0 - .long 0xf2c03010 // vmov.i32 d19, #0 - .long 0xf2c02010 // vmov.i32 d18, #0 - .long 0xf2400c32 // vfma.f32 d16, d0, d18 + .long 0xf2c02011 // vmov.i32 d18, #1 + .long 0xe243e001 // sub lr, r3, #1 + .long 0xf2c00010 // vmov.i32 d16, #0 + .long 0xe2843004 // add r3, r4, #4 + .long 0xf4e33c9d // vld1.32 {d19[]}, [r3 :32]! + .long 0xe25ee001 // subs lr, lr, #1 + .long 0xf3403e23 // vcge.f32 d19, d0, d19 + .long 0xf35231b1 // vbsl d19, d18, d17 + .long 0xf26308a0 // vadd.i32 d16, d19, d16 + .long 0x1afffff9 // bne 362c + .long 0xee303b90 // vmov.32 r3, d16[1] + .long 0xe59c7010 // ldr r7, [ip, #16] + .long 0xee10eb90 // vmov.32 lr, d16[0] + .long 0xe59c600c // ldr r6, [ip, #12] + .long 0xe59c5020 // ldr r5, [ip, #32] + .long 0xe59c8008 // ldr r8, [ip, #8] + .long 0xe59c9004 // ldr r9, [ip, #4] + .long 0xe0874103 // add r4, r7, r3, lsl #2 + .long 0xe085a10e // add sl, r5, lr, lsl #2 + .long 0xedd49a00 // vldr s19, [r4] + .long 0xe087410e // add r4, r7, lr, lsl #2 + .long 0xe59c7018 // ldr r7, [ip, #24] + .long 0xed949a00 // vldr s18, [r4] + .long 0xe0864103 // add r4, r6, r3, lsl #2 + .long 0xedd4aa00 // vldr s21, [r4] + .long 0xe086410e // add r4, r6, lr, lsl #2 + .long 0xed94aa00 // vldr s20, [r4] + .long 0xe0854103 // add r4, r5, r3, lsl #2 + .long 0xe0885103 // add r5, r8, r3, lsl #2 + .long 0xedd43a00 // vldr s7, [r4] + .long 0xe59c401c // ldr r4, [ip, #28] + .long 0xedd5ba00 // vldr s23, [r5] + .long 0xe088510e // add r5, r8, lr, lsl #2 + .long 0xe0846103 // add r6, r4, r3, lsl #2 + .long 0xe084b10e // add fp, r4, lr, lsl #2 + .long 0xe59c4014 // ldr r4, [ip, #20] + .long 0xedd62a00 // vldr s5, [r6] + .long 0xe089610e // add r6, r9, lr, lsl #2 + .long 0xe0899103 // add r9, r9, r3, lsl #2 + .long 0xed95ba00 // vldr s22, [r5] + .long 0xe0875103 // add r5, r7, r3, lsl #2 + .long 0xe0843103 // add r3, r4, r3, lsl #2 + .long 0xedd9ca00 // vldr s25, [r9] + .long 0xedd51a00 // vldr s3, [r5] + .long 0xe084510e // add r5, r4, lr, lsl #2 + .long 0xedd38a00 // vldr s17, [r3] + .long 0xe087310e // add r3, r7, lr, lsl #2 + .long 0xed96ca00 // vldr s24, [r6] + .long 0xed958a00 // vldr s16, [r5] + .long 0xed931a00 // vldr s2, [r3] + .long 0xf2008c1c // vfma.f32 d8, d0, d12 + .long 0xed9b2a00 // vldr s4, [fp] + .long 0xed9a3a00 // vldr s6, [sl] + .long 0xf2001c1b // vfma.f32 d1, d0, d11 .long 0xe5913004 // ldr r3, [r1, #4] - .long 0xf2001c35 // vfma.f32 d1, d0, d21 + .long 0xf2002c1a // vfma.f32 d2, d0, d10 + .long 0xf2003c19 // vfma.f32 d3, d0, d9 .long 0xe2811008 // add r1, r1, #8 - .long 0xf2002c34 // vfma.f32 d2, d0, d20 - .long 0xf2003c33 // vfma.f32 d3, d0, d19 - .long 0xf22001b0 // vorr d0, d16, d16 - .long 0xe8bd4010 // pop {r4, lr} + .long 0xf2280118 // vorr d0, d8, d8 + .long 0xecbd8b0a // vpop {d8-d12} + .long 0xe28dd004 // add sp, sp, #4 + .long 0xe8bd4ff0 // pop {r4, r5, r6, r7, r8, r9, sl, fp, lr} .long 0xe12fff13 // bx r3 HIDDEN _sk_evenly_spaced_2_stop_gradient_vfp4 @@ -8039,6 +8219,7 @@ _sk_evenly_spaced_2_stop_gradient_vfp4: .long 0xf22001b0 // vorr d0, d16, d16 .long 0xe8bd4010 // pop {r4, lr} .long 0xe12fff1c // bx ip + .long 0xe320f000 // nop {0} HIDDEN _sk_xy_to_unit_angle_vfp4 .globl _sk_xy_to_unit_angle_vfp4 @@ -8545,14 +8726,14 @@ _sk_seed_shader_hsw: .byte 197,249,110,199 // vmovd %edi,%xmm0 .byte 196,226,125,88,192 // vpbroadcastd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,97,69,0,0 // vbroadcastss 0x4561(%rip),%ymm1 # 4624 <_sk_callback_hsw+0x127> + .byte 196,226,125,24,13,189,70,0,0 // vbroadcastss 0x46bd(%rip),%ymm1 # 4780 <_sk_callback_hsw+0x128> .byte 197,252,88,193 // vaddps %ymm1,%ymm0,%ymm0 .byte 197,252,88,2 // vaddps (%rdx),%ymm0,%ymm0 .byte 196,226,125,24,16 // vbroadcastss (%rax),%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 197,236,88,201 // vaddps %ymm1,%ymm2,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,21,69,69,0,0 // vbroadcastss 0x4545(%rip),%ymm2 # 4628 <_sk_callback_hsw+0x12b> + .byte 196,226,125,24,21,161,70,0,0 // vbroadcastss 0x46a1(%rip),%ymm2 # 4784 <_sk_callback_hsw+0x12c> .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 .byte 197,220,87,228 // vxorps %ymm4,%ymm4,%ymm4 .byte 197,212,87,237 // vxorps %ymm5,%ymm5,%ymm5 @@ -8573,13 +8754,13 @@ _sk_dither_hsw: .byte 76,139,0 // mov (%rax),%r8 .byte 196,66,125,88,8 // vpbroadcastd (%r8),%ymm9 .byte 196,65,61,239,201 // vpxor %ymm9,%ymm8,%ymm9 - .byte 196,98,125,88,21,4,69,0,0 // vpbroadcastd 0x4504(%rip),%ymm10 # 462c <_sk_callback_hsw+0x12f> + .byte 196,98,125,88,21,96,70,0,0 // vpbroadcastd 0x4660(%rip),%ymm10 # 4788 <_sk_callback_hsw+0x130> .byte 196,65,53,219,218 // vpand %ymm10,%ymm9,%ymm11 .byte 196,193,37,114,243,5 // vpslld $0x5,%ymm11,%ymm11 .byte 196,65,61,219,210 // vpand %ymm10,%ymm8,%ymm10 .byte 196,193,45,114,242,4 // vpslld $0x4,%ymm10,%ymm10 - .byte 196,98,125,88,37,233,68,0,0 // vpbroadcastd 0x44e9(%rip),%ymm12 # 4630 <_sk_callback_hsw+0x133> - .byte 196,98,125,88,45,228,68,0,0 // vpbroadcastd 0x44e4(%rip),%ymm13 # 4634 <_sk_callback_hsw+0x137> + .byte 196,98,125,88,37,69,70,0,0 // vpbroadcastd 0x4645(%rip),%ymm12 # 478c <_sk_callback_hsw+0x134> + .byte 196,98,125,88,45,64,70,0,0 // vpbroadcastd 0x4640(%rip),%ymm13 # 4790 <_sk_callback_hsw+0x138> .byte 196,65,53,219,245 // vpand %ymm13,%ymm9,%ymm14 .byte 196,193,13,114,246,2 // vpslld $0x2,%ymm14,%ymm14 .byte 196,65,61,219,237 // vpand %ymm13,%ymm8,%ymm13 @@ -8594,8 +8775,8 @@ _sk_dither_hsw: .byte 196,65,61,235,194 // vpor %ymm10,%ymm8,%ymm8 .byte 196,65,61,235,193 // vpor %ymm9,%ymm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,150,68,0,0 // vbroadcastss 0x4496(%rip),%ymm9 # 4638 <_sk_callback_hsw+0x13b> - .byte 196,98,125,24,21,145,68,0,0 // vbroadcastss 0x4491(%rip),%ymm10 # 463c <_sk_callback_hsw+0x13f> + .byte 196,98,125,24,13,242,69,0,0 // vbroadcastss 0x45f2(%rip),%ymm9 # 4794 <_sk_callback_hsw+0x13c> + .byte 196,98,125,24,21,237,69,0,0 // vbroadcastss 0x45ed(%rip),%ymm10 # 4798 <_sk_callback_hsw+0x140> .byte 196,66,61,184,209 // vfmadd231ps %ymm9,%ymm8,%ymm10 .byte 196,98,125,24,64,8 // vbroadcastss 0x8(%rax),%ymm8 .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 @@ -8657,7 +8838,7 @@ HIDDEN _sk_srcatop_hsw FUNCTION(_sk_srcatop_hsw) _sk_srcatop_hsw: .byte 197,252,89,199 // vmulps %ymm7,%ymm0,%ymm0 - .byte 196,98,125,24,5,5,68,0,0 // vbroadcastss 0x4405(%rip),%ymm8 # 4640 <_sk_callback_hsw+0x143> + .byte 196,98,125,24,5,97,69,0,0 // vbroadcastss 0x4561(%rip),%ymm8 # 479c <_sk_callback_hsw+0x144> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,226,61,184,196 // vfmadd231ps %ymm4,%ymm8,%ymm0 .byte 197,244,89,207 // vmulps %ymm7,%ymm1,%ymm1 @@ -8673,7 +8854,7 @@ HIDDEN _sk_dstatop_hsw .globl _sk_dstatop_hsw FUNCTION(_sk_dstatop_hsw) _sk_dstatop_hsw: - .byte 196,98,125,24,5,216,67,0,0 // vbroadcastss 0x43d8(%rip),%ymm8 # 4644 <_sk_callback_hsw+0x147> + .byte 196,98,125,24,5,52,69,0,0 // vbroadcastss 0x4534(%rip),%ymm8 # 47a0 <_sk_callback_hsw+0x148> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 196,226,101,184,196 // vfmadd231ps %ymm4,%ymm3,%ymm0 @@ -8712,7 +8893,7 @@ HIDDEN _sk_srcout_hsw .globl _sk_srcout_hsw FUNCTION(_sk_srcout_hsw) _sk_srcout_hsw: - .byte 196,98,125,24,5,127,67,0,0 // vbroadcastss 0x437f(%rip),%ymm8 # 4648 <_sk_callback_hsw+0x14b> + .byte 196,98,125,24,5,219,68,0,0 // vbroadcastss 0x44db(%rip),%ymm8 # 47a4 <_sk_callback_hsw+0x14c> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -8725,7 +8906,7 @@ HIDDEN _sk_dstout_hsw .globl _sk_dstout_hsw FUNCTION(_sk_dstout_hsw) _sk_dstout_hsw: - .byte 196,226,125,24,5,98,67,0,0 // vbroadcastss 0x4362(%rip),%ymm0 # 464c <_sk_callback_hsw+0x14f> + .byte 196,226,125,24,5,190,68,0,0 // vbroadcastss 0x44be(%rip),%ymm0 # 47a8 <_sk_callback_hsw+0x150> .byte 197,252,92,219 // vsubps %ymm3,%ymm0,%ymm3 .byte 197,228,89,196 // vmulps %ymm4,%ymm3,%ymm0 .byte 197,228,89,205 // vmulps %ymm5,%ymm3,%ymm1 @@ -8738,7 +8919,7 @@ HIDDEN _sk_srcover_hsw .globl _sk_srcover_hsw FUNCTION(_sk_srcover_hsw) _sk_srcover_hsw: - .byte 196,98,125,24,5,69,67,0,0 // vbroadcastss 0x4345(%rip),%ymm8 # 4650 <_sk_callback_hsw+0x153> + .byte 196,98,125,24,5,161,68,0,0 // vbroadcastss 0x44a1(%rip),%ymm8 # 47ac <_sk_callback_hsw+0x154> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,93,184,192 // vfmadd231ps %ymm8,%ymm4,%ymm0 .byte 196,194,85,184,200 // vfmadd231ps %ymm8,%ymm5,%ymm1 @@ -8751,7 +8932,7 @@ HIDDEN _sk_dstover_hsw .globl _sk_dstover_hsw FUNCTION(_sk_dstover_hsw) _sk_dstover_hsw: - .byte 196,98,125,24,5,36,67,0,0 // vbroadcastss 0x4324(%rip),%ymm8 # 4654 <_sk_callback_hsw+0x157> + .byte 196,98,125,24,5,128,68,0,0 // vbroadcastss 0x4480(%rip),%ymm8 # 47b0 <_sk_callback_hsw+0x158> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 196,226,61,168,196 // vfmadd213ps %ymm4,%ymm8,%ymm0 .byte 196,226,61,168,205 // vfmadd213ps %ymm5,%ymm8,%ymm1 @@ -8775,7 +8956,7 @@ HIDDEN _sk_multiply_hsw .globl _sk_multiply_hsw FUNCTION(_sk_multiply_hsw) _sk_multiply_hsw: - .byte 196,98,125,24,5,239,66,0,0 // vbroadcastss 0x42ef(%rip),%ymm8 # 4658 <_sk_callback_hsw+0x15b> + .byte 196,98,125,24,5,75,68,0,0 // vbroadcastss 0x444b(%rip),%ymm8 # 47b4 <_sk_callback_hsw+0x15c> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,208 // vmulps %ymm0,%ymm9,%ymm10 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -8823,7 +9004,7 @@ HIDDEN _sk_xor__hsw .globl _sk_xor__hsw FUNCTION(_sk_xor__hsw) _sk_xor__hsw: - .byte 196,98,125,24,5,106,66,0,0 // vbroadcastss 0x426a(%rip),%ymm8 # 465c <_sk_callback_hsw+0x15f> + .byte 196,98,125,24,5,198,67,0,0 // vbroadcastss 0x43c6(%rip),%ymm8 # 47b8 <_sk_callback_hsw+0x160> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -8857,7 +9038,7 @@ _sk_darken_hsw: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,95,209 // vmaxps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,242,65,0,0 // vbroadcastss 0x41f2(%rip),%ymm8 # 4660 <_sk_callback_hsw+0x163> + .byte 196,98,125,24,5,78,67,0,0 // vbroadcastss 0x434e(%rip),%ymm8 # 47bc <_sk_callback_hsw+0x164> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -8882,7 +9063,7 @@ _sk_lighten_hsw: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,161,65,0,0 // vbroadcastss 0x41a1(%rip),%ymm8 # 4664 <_sk_callback_hsw+0x167> + .byte 196,98,125,24,5,253,66,0,0 // vbroadcastss 0x42fd(%rip),%ymm8 # 47c0 <_sk_callback_hsw+0x168> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -8910,7 +9091,7 @@ _sk_difference_hsw: .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,68,65,0,0 // vbroadcastss 0x4144(%rip),%ymm8 # 4668 <_sk_callback_hsw+0x16b> + .byte 196,98,125,24,5,160,66,0,0 // vbroadcastss 0x42a0(%rip),%ymm8 # 47c4 <_sk_callback_hsw+0x16c> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -8932,7 +9113,7 @@ _sk_exclusion_hsw: .byte 197,236,89,214 // vmulps %ymm6,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,2,65,0,0 // vbroadcastss 0x4102(%rip),%ymm8 # 466c <_sk_callback_hsw+0x16f> + .byte 196,98,125,24,5,94,66,0,0 // vbroadcastss 0x425e(%rip),%ymm8 # 47c8 <_sk_callback_hsw+0x170> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -8942,7 +9123,7 @@ HIDDEN _sk_colorburn_hsw .globl _sk_colorburn_hsw FUNCTION(_sk_colorburn_hsw) _sk_colorburn_hsw: - .byte 196,98,125,24,5,240,64,0,0 // vbroadcastss 0x40f0(%rip),%ymm8 # 4670 <_sk_callback_hsw+0x173> + .byte 196,98,125,24,5,76,66,0,0 // vbroadcastss 0x424c(%rip),%ymm8 # 47cc <_sk_callback_hsw+0x174> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,216 // vmulps %ymm0,%ymm9,%ymm11 .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 @@ -9000,7 +9181,7 @@ HIDDEN _sk_colordodge_hsw FUNCTION(_sk_colordodge_hsw) _sk_colordodge_hsw: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 - .byte 196,98,125,24,13,251,63,0,0 // vbroadcastss 0x3ffb(%rip),%ymm9 # 4674 <_sk_callback_hsw+0x177> + .byte 196,98,125,24,13,87,65,0,0 // vbroadcastss 0x4157(%rip),%ymm9 # 47d0 <_sk_callback_hsw+0x178> .byte 197,52,92,215 // vsubps %ymm7,%ymm9,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,52,92,203 // vsubps %ymm3,%ymm9,%ymm9 @@ -9053,7 +9234,7 @@ HIDDEN _sk_hardlight_hsw .globl _sk_hardlight_hsw FUNCTION(_sk_hardlight_hsw) _sk_hardlight_hsw: - .byte 196,98,125,24,5,28,63,0,0 // vbroadcastss 0x3f1c(%rip),%ymm8 # 4678 <_sk_callback_hsw+0x17b> + .byte 196,98,125,24,5,120,64,0,0 // vbroadcastss 0x4078(%rip),%ymm8 # 47d4 <_sk_callback_hsw+0x17c> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -9104,7 +9285,7 @@ HIDDEN _sk_overlay_hsw .globl _sk_overlay_hsw FUNCTION(_sk_overlay_hsw) _sk_overlay_hsw: - .byte 196,98,125,24,5,84,62,0,0 // vbroadcastss 0x3e54(%rip),%ymm8 # 467c <_sk_callback_hsw+0x17f> + .byte 196,98,125,24,5,176,63,0,0 // vbroadcastss 0x3fb0(%rip),%ymm8 # 47d8 <_sk_callback_hsw+0x180> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -9165,10 +9346,10 @@ _sk_softlight_hsw: .byte 196,65,20,88,197 // vaddps %ymm13,%ymm13,%ymm8 .byte 196,65,60,88,192 // vaddps %ymm8,%ymm8,%ymm8 .byte 196,66,61,168,192 // vfmadd213ps %ymm8,%ymm8,%ymm8 - .byte 196,98,125,24,29,95,61,0,0 // vbroadcastss 0x3d5f(%rip),%ymm11 # 4684 <_sk_callback_hsw+0x187> + .byte 196,98,125,24,29,187,62,0,0 // vbroadcastss 0x3ebb(%rip),%ymm11 # 47e0 <_sk_callback_hsw+0x188> .byte 196,65,20,88,227 // vaddps %ymm11,%ymm13,%ymm12 .byte 196,65,28,89,192 // vmulps %ymm8,%ymm12,%ymm8 - .byte 196,98,125,24,37,80,61,0,0 // vbroadcastss 0x3d50(%rip),%ymm12 # 4688 <_sk_callback_hsw+0x18b> + .byte 196,98,125,24,37,172,62,0,0 // vbroadcastss 0x3eac(%rip),%ymm12 # 47e4 <_sk_callback_hsw+0x18c> .byte 196,66,21,184,196 // vfmadd231ps %ymm12,%ymm13,%ymm8 .byte 196,65,124,82,245 // vrsqrtps %ymm13,%ymm14 .byte 196,65,124,83,246 // vrcpps %ymm14,%ymm14 @@ -9178,7 +9359,7 @@ _sk_softlight_hsw: .byte 197,4,194,255,2 // vcmpleps %ymm7,%ymm15,%ymm15 .byte 196,67,13,74,240,240 // vblendvps %ymm15,%ymm8,%ymm14,%ymm14 .byte 197,116,88,249 // vaddps %ymm1,%ymm1,%ymm15 - .byte 196,98,125,24,5,19,61,0,0 // vbroadcastss 0x3d13(%rip),%ymm8 # 4680 <_sk_callback_hsw+0x183> + .byte 196,98,125,24,5,111,62,0,0 // vbroadcastss 0x3e6f(%rip),%ymm8 # 47dc <_sk_callback_hsw+0x184> .byte 196,65,60,92,237 // vsubps %ymm13,%ymm8,%ymm13 .byte 197,132,92,195 // vsubps %ymm3,%ymm15,%ymm0 .byte 196,98,125,168,235 // vfmadd213ps %ymm3,%ymm0,%ymm13 @@ -9291,11 +9472,11 @@ _sk_hue_hsw: .byte 196,65,28,89,210 // vmulps %ymm10,%ymm12,%ymm10 .byte 196,65,44,94,214 // vdivps %ymm14,%ymm10,%ymm10 .byte 196,67,45,74,224,240 // vblendvps %ymm15,%ymm8,%ymm10,%ymm12 - .byte 196,98,125,24,53,23,59,0,0 // vbroadcastss 0x3b17(%rip),%ymm14 # 468c <_sk_callback_hsw+0x18f> - .byte 196,98,125,24,61,18,59,0,0 // vbroadcastss 0x3b12(%rip),%ymm15 # 4690 <_sk_callback_hsw+0x193> + .byte 196,98,125,24,53,115,60,0,0 // vbroadcastss 0x3c73(%rip),%ymm14 # 47e8 <_sk_callback_hsw+0x190> + .byte 196,98,125,24,61,110,60,0,0 // vbroadcastss 0x3c6e(%rip),%ymm15 # 47ec <_sk_callback_hsw+0x194> .byte 196,65,84,89,239 // vmulps %ymm15,%ymm5,%ymm13 .byte 196,66,93,184,238 // vfmadd231ps %ymm14,%ymm4,%ymm13 - .byte 196,226,125,24,5,3,59,0,0 // vbroadcastss 0x3b03(%rip),%ymm0 # 4694 <_sk_callback_hsw+0x197> + .byte 196,226,125,24,5,95,60,0,0 // vbroadcastss 0x3c5f(%rip),%ymm0 # 47f0 <_sk_callback_hsw+0x198> .byte 196,98,77,184,232 // vfmadd231ps %ymm0,%ymm6,%ymm13 .byte 196,65,116,89,215 // vmulps %ymm15,%ymm1,%ymm10 .byte 196,66,53,184,214 // vfmadd231ps %ymm14,%ymm9,%ymm10 @@ -9350,7 +9531,7 @@ _sk_hue_hsw: .byte 196,193,124,95,192 // vmaxps %ymm8,%ymm0,%ymm0 .byte 196,65,36,95,200 // vmaxps %ymm8,%ymm11,%ymm9 .byte 196,65,116,95,192 // vmaxps %ymm8,%ymm1,%ymm8 - .byte 196,226,125,24,13,240,57,0,0 // vbroadcastss 0x39f0(%rip),%ymm1 # 4698 <_sk_callback_hsw+0x19b> + .byte 196,226,125,24,13,76,59,0,0 // vbroadcastss 0x3b4c(%rip),%ymm1 # 47f4 <_sk_callback_hsw+0x19c> .byte 197,116,92,215 // vsubps %ymm7,%ymm1,%ymm10 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 197,116,92,219 // vsubps %ymm3,%ymm1,%ymm11 @@ -9404,11 +9585,11 @@ _sk_saturation_hsw: .byte 196,65,28,89,210 // vmulps %ymm10,%ymm12,%ymm10 .byte 196,65,44,94,214 // vdivps %ymm14,%ymm10,%ymm10 .byte 196,67,45,74,224,240 // vblendvps %ymm15,%ymm8,%ymm10,%ymm12 - .byte 196,98,125,24,53,7,57,0,0 // vbroadcastss 0x3907(%rip),%ymm14 # 469c <_sk_callback_hsw+0x19f> - .byte 196,98,125,24,61,2,57,0,0 // vbroadcastss 0x3902(%rip),%ymm15 # 46a0 <_sk_callback_hsw+0x1a3> + .byte 196,98,125,24,53,99,58,0,0 // vbroadcastss 0x3a63(%rip),%ymm14 # 47f8 <_sk_callback_hsw+0x1a0> + .byte 196,98,125,24,61,94,58,0,0 // vbroadcastss 0x3a5e(%rip),%ymm15 # 47fc <_sk_callback_hsw+0x1a4> .byte 196,65,84,89,239 // vmulps %ymm15,%ymm5,%ymm13 .byte 196,66,93,184,238 // vfmadd231ps %ymm14,%ymm4,%ymm13 - .byte 196,226,125,24,5,243,56,0,0 // vbroadcastss 0x38f3(%rip),%ymm0 # 46a4 <_sk_callback_hsw+0x1a7> + .byte 196,226,125,24,5,79,58,0,0 // vbroadcastss 0x3a4f(%rip),%ymm0 # 4800 <_sk_callback_hsw+0x1a8> .byte 196,98,77,184,232 // vfmadd231ps %ymm0,%ymm6,%ymm13 .byte 196,65,116,89,215 // vmulps %ymm15,%ymm1,%ymm10 .byte 196,66,53,184,214 // vfmadd231ps %ymm14,%ymm9,%ymm10 @@ -9463,7 +9644,7 @@ _sk_saturation_hsw: .byte 196,193,124,95,192 // vmaxps %ymm8,%ymm0,%ymm0 .byte 196,65,36,95,200 // vmaxps %ymm8,%ymm11,%ymm9 .byte 196,65,116,95,192 // vmaxps %ymm8,%ymm1,%ymm8 - .byte 196,226,125,24,13,224,55,0,0 // vbroadcastss 0x37e0(%rip),%ymm1 # 46a8 <_sk_callback_hsw+0x1ab> + .byte 196,226,125,24,13,60,57,0,0 // vbroadcastss 0x393c(%rip),%ymm1 # 4804 <_sk_callback_hsw+0x1ac> .byte 197,116,92,215 // vsubps %ymm7,%ymm1,%ymm10 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 197,116,92,219 // vsubps %ymm3,%ymm1,%ymm11 @@ -9491,11 +9672,11 @@ _sk_color_hsw: .byte 197,108,89,199 // vmulps %ymm7,%ymm2,%ymm8 .byte 197,116,89,215 // vmulps %ymm7,%ymm1,%ymm10 .byte 197,52,89,223 // vmulps %ymm7,%ymm9,%ymm11 - .byte 196,98,125,24,45,121,55,0,0 // vbroadcastss 0x3779(%rip),%ymm13 # 46ac <_sk_callback_hsw+0x1af> - .byte 196,98,125,24,53,116,55,0,0 // vbroadcastss 0x3774(%rip),%ymm14 # 46b0 <_sk_callback_hsw+0x1b3> + .byte 196,98,125,24,45,213,56,0,0 // vbroadcastss 0x38d5(%rip),%ymm13 # 4808 <_sk_callback_hsw+0x1b0> + .byte 196,98,125,24,53,208,56,0,0 // vbroadcastss 0x38d0(%rip),%ymm14 # 480c <_sk_callback_hsw+0x1b4> .byte 196,65,84,89,230 // vmulps %ymm14,%ymm5,%ymm12 .byte 196,66,93,184,229 // vfmadd231ps %ymm13,%ymm4,%ymm12 - .byte 196,98,125,24,61,101,55,0,0 // vbroadcastss 0x3765(%rip),%ymm15 # 46b4 <_sk_callback_hsw+0x1b7> + .byte 196,98,125,24,61,193,56,0,0 // vbroadcastss 0x38c1(%rip),%ymm15 # 4810 <_sk_callback_hsw+0x1b8> .byte 196,66,77,184,231 // vfmadd231ps %ymm15,%ymm6,%ymm12 .byte 196,65,44,89,206 // vmulps %ymm14,%ymm10,%ymm9 .byte 196,66,61,184,205 // vfmadd231ps %ymm13,%ymm8,%ymm9 @@ -9551,7 +9732,7 @@ _sk_color_hsw: .byte 196,193,116,95,206 // vmaxps %ymm14,%ymm1,%ymm1 .byte 196,65,44,95,198 // vmaxps %ymm14,%ymm10,%ymm8 .byte 196,65,124,95,206 // vmaxps %ymm14,%ymm0,%ymm9 - .byte 196,226,125,24,5,71,54,0,0 // vbroadcastss 0x3647(%rip),%ymm0 # 46b8 <_sk_callback_hsw+0x1bb> + .byte 196,226,125,24,5,163,55,0,0 // vbroadcastss 0x37a3(%rip),%ymm0 # 4814 <_sk_callback_hsw+0x1bc> .byte 197,124,92,215 // vsubps %ymm7,%ymm0,%ymm10 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 197,124,92,219 // vsubps %ymm3,%ymm0,%ymm11 @@ -9579,11 +9760,11 @@ _sk_luminosity_hsw: .byte 197,100,89,196 // vmulps %ymm4,%ymm3,%ymm8 .byte 197,100,89,213 // vmulps %ymm5,%ymm3,%ymm10 .byte 197,100,89,222 // vmulps %ymm6,%ymm3,%ymm11 - .byte 196,98,125,24,45,224,53,0,0 // vbroadcastss 0x35e0(%rip),%ymm13 # 46bc <_sk_callback_hsw+0x1bf> - .byte 196,98,125,24,53,219,53,0,0 // vbroadcastss 0x35db(%rip),%ymm14 # 46c0 <_sk_callback_hsw+0x1c3> + .byte 196,98,125,24,45,60,55,0,0 // vbroadcastss 0x373c(%rip),%ymm13 # 4818 <_sk_callback_hsw+0x1c0> + .byte 196,98,125,24,53,55,55,0,0 // vbroadcastss 0x3737(%rip),%ymm14 # 481c <_sk_callback_hsw+0x1c4> .byte 196,65,116,89,230 // vmulps %ymm14,%ymm1,%ymm12 .byte 196,66,109,184,229 // vfmadd231ps %ymm13,%ymm2,%ymm12 - .byte 196,98,125,24,61,204,53,0,0 // vbroadcastss 0x35cc(%rip),%ymm15 # 46c4 <_sk_callback_hsw+0x1c7> + .byte 196,98,125,24,61,40,55,0,0 // vbroadcastss 0x3728(%rip),%ymm15 # 4820 <_sk_callback_hsw+0x1c8> .byte 196,66,53,184,231 // vfmadd231ps %ymm15,%ymm9,%ymm12 .byte 196,65,44,89,206 // vmulps %ymm14,%ymm10,%ymm9 .byte 196,66,61,184,205 // vfmadd231ps %ymm13,%ymm8,%ymm9 @@ -9639,7 +9820,7 @@ _sk_luminosity_hsw: .byte 196,193,116,95,206 // vmaxps %ymm14,%ymm1,%ymm1 .byte 196,65,44,95,198 // vmaxps %ymm14,%ymm10,%ymm8 .byte 196,65,124,95,206 // vmaxps %ymm14,%ymm0,%ymm9 - .byte 196,226,125,24,5,174,52,0,0 // vbroadcastss 0x34ae(%rip),%ymm0 # 46c8 <_sk_callback_hsw+0x1cb> + .byte 196,226,125,24,5,10,54,0,0 // vbroadcastss 0x360a(%rip),%ymm0 # 4824 <_sk_callback_hsw+0x1cc> .byte 197,124,92,215 // vsubps %ymm7,%ymm0,%ymm10 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 197,124,92,219 // vsubps %ymm3,%ymm0,%ymm11 @@ -9672,7 +9853,7 @@ HIDDEN _sk_clamp_1_hsw .globl _sk_clamp_1_hsw FUNCTION(_sk_clamp_1_hsw) _sk_clamp_1_hsw: - .byte 196,98,125,24,5,74,52,0,0 // vbroadcastss 0x344a(%rip),%ymm8 # 46cc <_sk_callback_hsw+0x1cf> + .byte 196,98,125,24,5,166,53,0,0 // vbroadcastss 0x35a6(%rip),%ymm8 # 4828 <_sk_callback_hsw+0x1d0> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 @@ -9684,7 +9865,7 @@ HIDDEN _sk_clamp_a_hsw .globl _sk_clamp_a_hsw FUNCTION(_sk_clamp_a_hsw) _sk_clamp_a_hsw: - .byte 196,98,125,24,5,45,52,0,0 // vbroadcastss 0x342d(%rip),%ymm8 # 46d0 <_sk_callback_hsw+0x1d3> + .byte 196,98,125,24,5,137,53,0,0 // vbroadcastss 0x3589(%rip),%ymm8 # 482c <_sk_callback_hsw+0x1d4> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 197,252,93,195 // vminps %ymm3,%ymm0,%ymm0 .byte 197,244,93,203 // vminps %ymm3,%ymm1,%ymm1 @@ -9770,7 +9951,7 @@ FUNCTION(_sk_unpremul_hsw) _sk_unpremul_hsw: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,65,100,194,200,0 // vcmpeqps %ymm8,%ymm3,%ymm9 - .byte 196,98,125,24,21,117,51,0,0 // vbroadcastss 0x3375(%rip),%ymm10 # 46d4 <_sk_callback_hsw+0x1d7> + .byte 196,98,125,24,21,209,52,0,0 // vbroadcastss 0x34d1(%rip),%ymm10 # 4830 <_sk_callback_hsw+0x1d8> .byte 197,44,94,211 // vdivps %ymm3,%ymm10,%ymm10 .byte 196,67,45,74,192,144 // vblendvps %ymm9,%ymm8,%ymm10,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 @@ -9783,16 +9964,16 @@ HIDDEN _sk_from_srgb_hsw .globl _sk_from_srgb_hsw FUNCTION(_sk_from_srgb_hsw) _sk_from_srgb_hsw: - .byte 196,98,125,24,5,86,51,0,0 // vbroadcastss 0x3356(%rip),%ymm8 # 46d8 <_sk_callback_hsw+0x1db> + .byte 196,98,125,24,5,178,52,0,0 // vbroadcastss 0x34b2(%rip),%ymm8 # 4834 <_sk_callback_hsw+0x1dc> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 197,124,89,208 // vmulps %ymm0,%ymm0,%ymm10 - .byte 196,98,125,24,29,72,51,0,0 // vbroadcastss 0x3348(%rip),%ymm11 # 46dc <_sk_callback_hsw+0x1df> - .byte 196,98,125,24,37,67,51,0,0 // vbroadcastss 0x3343(%rip),%ymm12 # 46e0 <_sk_callback_hsw+0x1e3> + .byte 196,98,125,24,29,164,52,0,0 // vbroadcastss 0x34a4(%rip),%ymm11 # 4838 <_sk_callback_hsw+0x1e0> + .byte 196,98,125,24,37,159,52,0,0 // vbroadcastss 0x349f(%rip),%ymm12 # 483c <_sk_callback_hsw+0x1e4> .byte 196,65,124,40,236 // vmovaps %ymm12,%ymm13 .byte 196,66,125,168,235 // vfmadd213ps %ymm11,%ymm0,%ymm13 - .byte 196,98,125,24,53,52,51,0,0 // vbroadcastss 0x3334(%rip),%ymm14 # 46e4 <_sk_callback_hsw+0x1e7> + .byte 196,98,125,24,53,144,52,0,0 // vbroadcastss 0x3490(%rip),%ymm14 # 4840 <_sk_callback_hsw+0x1e8> .byte 196,66,45,168,238 // vfmadd213ps %ymm14,%ymm10,%ymm13 - .byte 196,98,125,24,21,42,51,0,0 // vbroadcastss 0x332a(%rip),%ymm10 # 46e8 <_sk_callback_hsw+0x1eb> + .byte 196,98,125,24,21,134,52,0,0 // vbroadcastss 0x3486(%rip),%ymm10 # 4844 <_sk_callback_hsw+0x1ec> .byte 196,193,124,194,194,1 // vcmpltps %ymm10,%ymm0,%ymm0 .byte 196,195,21,74,193,0 // vblendvps %ymm0,%ymm9,%ymm13,%ymm0 .byte 196,65,116,89,200 // vmulps %ymm8,%ymm1,%ymm9 @@ -9818,16 +9999,16 @@ _sk_to_srgb_hsw: .byte 197,124,82,192 // vrsqrtps %ymm0,%ymm8 .byte 196,65,124,83,200 // vrcpps %ymm8,%ymm9 .byte 196,65,124,82,208 // vrsqrtps %ymm8,%ymm10 - .byte 196,98,125,24,5,196,50,0,0 // vbroadcastss 0x32c4(%rip),%ymm8 # 46ec <_sk_callback_hsw+0x1ef> + .byte 196,98,125,24,5,32,52,0,0 // vbroadcastss 0x3420(%rip),%ymm8 # 4848 <_sk_callback_hsw+0x1f0> .byte 196,65,124,89,216 // vmulps %ymm8,%ymm0,%ymm11 - .byte 196,98,125,24,37,186,50,0,0 // vbroadcastss 0x32ba(%rip),%ymm12 # 46f0 <_sk_callback_hsw+0x1f3> - .byte 196,98,125,24,45,181,50,0,0 // vbroadcastss 0x32b5(%rip),%ymm13 # 46f4 <_sk_callback_hsw+0x1f7> + .byte 196,98,125,24,37,22,52,0,0 // vbroadcastss 0x3416(%rip),%ymm12 # 484c <_sk_callback_hsw+0x1f4> + .byte 196,98,125,24,45,17,52,0,0 // vbroadcastss 0x3411(%rip),%ymm13 # 4850 <_sk_callback_hsw+0x1f8> .byte 196,66,21,168,204 // vfmadd213ps %ymm12,%ymm13,%ymm9 - .byte 196,98,125,24,53,171,50,0,0 // vbroadcastss 0x32ab(%rip),%ymm14 # 46f8 <_sk_callback_hsw+0x1fb> + .byte 196,98,125,24,53,7,52,0,0 // vbroadcastss 0x3407(%rip),%ymm14 # 4854 <_sk_callback_hsw+0x1fc> .byte 196,66,13,184,202 // vfmadd231ps %ymm10,%ymm14,%ymm9 - .byte 196,98,125,24,21,161,50,0,0 // vbroadcastss 0x32a1(%rip),%ymm10 # 46fc <_sk_callback_hsw+0x1ff> + .byte 196,98,125,24,21,253,51,0,0 // vbroadcastss 0x33fd(%rip),%ymm10 # 4858 <_sk_callback_hsw+0x200> .byte 196,65,44,93,201 // vminps %ymm9,%ymm10,%ymm9 - .byte 196,98,125,24,61,151,50,0,0 // vbroadcastss 0x3297(%rip),%ymm15 # 4700 <_sk_callback_hsw+0x203> + .byte 196,98,125,24,61,243,51,0,0 // vbroadcastss 0x33f3(%rip),%ymm15 # 485c <_sk_callback_hsw+0x204> .byte 196,193,124,194,199,1 // vcmpltps %ymm15,%ymm0,%ymm0 .byte 196,195,53,74,195,0 // vblendvps %ymm0,%ymm11,%ymm9,%ymm0 .byte 197,124,82,201 // vrsqrtps %ymm1,%ymm9 @@ -9860,26 +10041,26 @@ _sk_rgb_to_hsl_hsw: .byte 197,124,93,201 // vminps %ymm1,%ymm0,%ymm9 .byte 197,52,93,202 // vminps %ymm2,%ymm9,%ymm9 .byte 196,65,60,92,209 // vsubps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,29,17,50,0,0 // vbroadcastss 0x3211(%rip),%ymm11 # 4704 <_sk_callback_hsw+0x207> + .byte 196,98,125,24,29,109,51,0,0 // vbroadcastss 0x336d(%rip),%ymm11 # 4860 <_sk_callback_hsw+0x208> .byte 196,65,36,94,218 // vdivps %ymm10,%ymm11,%ymm11 .byte 197,116,92,226 // vsubps %ymm2,%ymm1,%ymm12 .byte 197,116,194,234,1 // vcmpltps %ymm2,%ymm1,%ymm13 - .byte 196,98,125,24,53,254,49,0,0 // vbroadcastss 0x31fe(%rip),%ymm14 # 4708 <_sk_callback_hsw+0x20b> + .byte 196,98,125,24,53,90,51,0,0 // vbroadcastss 0x335a(%rip),%ymm14 # 4864 <_sk_callback_hsw+0x20c> .byte 196,65,4,87,255 // vxorps %ymm15,%ymm15,%ymm15 .byte 196,67,5,74,238,208 // vblendvps %ymm13,%ymm14,%ymm15,%ymm13 .byte 196,66,37,168,229 // vfmadd213ps %ymm13,%ymm11,%ymm12 .byte 197,236,92,208 // vsubps %ymm0,%ymm2,%ymm2 .byte 197,124,92,233 // vsubps %ymm1,%ymm0,%ymm13 - .byte 196,98,125,24,53,229,49,0,0 // vbroadcastss 0x31e5(%rip),%ymm14 # 4710 <_sk_callback_hsw+0x213> + .byte 196,98,125,24,53,65,51,0,0 // vbroadcastss 0x3341(%rip),%ymm14 # 486c <_sk_callback_hsw+0x214> .byte 196,66,37,168,238 // vfmadd213ps %ymm14,%ymm11,%ymm13 - .byte 196,98,125,24,53,211,49,0,0 // vbroadcastss 0x31d3(%rip),%ymm14 # 470c <_sk_callback_hsw+0x20f> + .byte 196,98,125,24,53,47,51,0,0 // vbroadcastss 0x332f(%rip),%ymm14 # 4868 <_sk_callback_hsw+0x210> .byte 196,194,37,168,214 // vfmadd213ps %ymm14,%ymm11,%ymm2 .byte 197,188,194,201,0 // vcmpeqps %ymm1,%ymm8,%ymm1 .byte 196,227,21,74,202,16 // vblendvps %ymm1,%ymm2,%ymm13,%ymm1 .byte 197,188,194,192,0 // vcmpeqps %ymm0,%ymm8,%ymm0 .byte 196,195,117,74,196,0 // vblendvps %ymm0,%ymm12,%ymm1,%ymm0 .byte 196,193,60,88,201 // vaddps %ymm9,%ymm8,%ymm1 - .byte 196,98,125,24,29,182,49,0,0 // vbroadcastss 0x31b6(%rip),%ymm11 # 4718 <_sk_callback_hsw+0x21b> + .byte 196,98,125,24,29,18,51,0,0 // vbroadcastss 0x3312(%rip),%ymm11 # 4874 <_sk_callback_hsw+0x21c> .byte 196,193,116,89,211 // vmulps %ymm11,%ymm1,%ymm2 .byte 197,36,194,218,1 // vcmpltps %ymm2,%ymm11,%ymm11 .byte 196,65,12,92,224 // vsubps %ymm8,%ymm14,%ymm12 @@ -9889,7 +10070,7 @@ _sk_rgb_to_hsl_hsw: .byte 197,172,94,201 // vdivps %ymm1,%ymm10,%ymm1 .byte 196,195,125,74,199,128 // vblendvps %ymm8,%ymm15,%ymm0,%ymm0 .byte 196,195,117,74,207,128 // vblendvps %ymm8,%ymm15,%ymm1,%ymm1 - .byte 196,98,125,24,5,121,49,0,0 // vbroadcastss 0x3179(%rip),%ymm8 # 4714 <_sk_callback_hsw+0x217> + .byte 196,98,125,24,5,213,50,0,0 // vbroadcastss 0x32d5(%rip),%ymm8 # 4870 <_sk_callback_hsw+0x218> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9906,30 +10087,30 @@ _sk_hsl_to_rgb_hsw: .byte 197,252,17,92,36,128 // vmovups %ymm3,-0x80(%rsp) .byte 197,252,40,233 // vmovaps %ymm1,%ymm5 .byte 197,252,40,224 // vmovaps %ymm0,%ymm4 - .byte 196,98,125,24,5,70,49,0,0 // vbroadcastss 0x3146(%rip),%ymm8 # 471c <_sk_callback_hsw+0x21f> + .byte 196,98,125,24,5,162,50,0,0 // vbroadcastss 0x32a2(%rip),%ymm8 # 4878 <_sk_callback_hsw+0x220> .byte 197,60,194,202,2 // vcmpleps %ymm2,%ymm8,%ymm9 .byte 197,84,89,210 // vmulps %ymm2,%ymm5,%ymm10 .byte 196,65,84,92,218 // vsubps %ymm10,%ymm5,%ymm11 .byte 196,67,45,74,203,144 // vblendvps %ymm9,%ymm11,%ymm10,%ymm9 .byte 197,52,88,210 // vaddps %ymm2,%ymm9,%ymm10 - .byte 196,98,125,24,13,41,49,0,0 // vbroadcastss 0x3129(%rip),%ymm9 # 4720 <_sk_callback_hsw+0x223> + .byte 196,98,125,24,13,133,50,0,0 // vbroadcastss 0x3285(%rip),%ymm9 # 487c <_sk_callback_hsw+0x224> .byte 196,66,109,170,202 // vfmsub213ps %ymm10,%ymm2,%ymm9 - .byte 196,98,125,24,29,31,49,0,0 // vbroadcastss 0x311f(%rip),%ymm11 # 4724 <_sk_callback_hsw+0x227> + .byte 196,98,125,24,29,123,50,0,0 // vbroadcastss 0x327b(%rip),%ymm11 # 4880 <_sk_callback_hsw+0x228> .byte 196,65,92,88,219 // vaddps %ymm11,%ymm4,%ymm11 .byte 196,67,125,8,227,1 // vroundps $0x1,%ymm11,%ymm12 .byte 196,65,36,92,252 // vsubps %ymm12,%ymm11,%ymm15 .byte 196,65,44,92,217 // vsubps %ymm9,%ymm10,%ymm11 - .byte 196,98,125,24,45,9,49,0,0 // vbroadcastss 0x3109(%rip),%ymm13 # 472c <_sk_callback_hsw+0x22f> + .byte 196,98,125,24,45,101,50,0,0 // vbroadcastss 0x3265(%rip),%ymm13 # 4888 <_sk_callback_hsw+0x230> .byte 196,193,4,89,197 // vmulps %ymm13,%ymm15,%ymm0 - .byte 196,98,125,24,53,255,48,0,0 // vbroadcastss 0x30ff(%rip),%ymm14 # 4730 <_sk_callback_hsw+0x233> + .byte 196,98,125,24,53,91,50,0,0 // vbroadcastss 0x325b(%rip),%ymm14 # 488c <_sk_callback_hsw+0x234> .byte 197,12,92,224 // vsubps %ymm0,%ymm14,%ymm12 .byte 196,66,37,168,225 // vfmadd213ps %ymm9,%ymm11,%ymm12 - .byte 196,226,125,24,29,229,48,0,0 // vbroadcastss 0x30e5(%rip),%ymm3 # 4728 <_sk_callback_hsw+0x22b> + .byte 196,226,125,24,29,65,50,0,0 // vbroadcastss 0x3241(%rip),%ymm3 # 4884 <_sk_callback_hsw+0x22c> .byte 196,193,100,194,255,2 // vcmpleps %ymm15,%ymm3,%ymm7 .byte 196,195,29,74,249,112 // vblendvps %ymm7,%ymm9,%ymm12,%ymm7 .byte 196,65,60,194,231,2 // vcmpleps %ymm15,%ymm8,%ymm12 .byte 196,227,45,74,255,192 // vblendvps %ymm12,%ymm7,%ymm10,%ymm7 - .byte 196,98,125,24,37,208,48,0,0 // vbroadcastss 0x30d0(%rip),%ymm12 # 4734 <_sk_callback_hsw+0x237> + .byte 196,98,125,24,37,44,50,0,0 // vbroadcastss 0x322c(%rip),%ymm12 # 4890 <_sk_callback_hsw+0x238> .byte 196,65,28,194,255,2 // vcmpleps %ymm15,%ymm12,%ymm15 .byte 196,194,37,168,193 // vfmadd213ps %ymm9,%ymm11,%ymm0 .byte 196,99,125,74,255,240 // vblendvps %ymm15,%ymm7,%ymm0,%ymm15 @@ -9945,7 +10126,7 @@ _sk_hsl_to_rgb_hsw: .byte 197,156,194,192,2 // vcmpleps %ymm0,%ymm12,%ymm0 .byte 196,194,37,168,249 // vfmadd213ps %ymm9,%ymm11,%ymm7 .byte 196,227,69,74,201,0 // vblendvps %ymm0,%ymm1,%ymm7,%ymm1 - .byte 196,226,125,24,5,124,48,0,0 // vbroadcastss 0x307c(%rip),%ymm0 # 4738 <_sk_callback_hsw+0x23b> + .byte 196,226,125,24,5,216,49,0,0 // vbroadcastss 0x31d8(%rip),%ymm0 # 4894 <_sk_callback_hsw+0x23c> .byte 197,220,88,192 // vaddps %ymm0,%ymm4,%ymm0 .byte 196,227,125,8,224,1 // vroundps $0x1,%ymm0,%ymm4 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 @@ -9999,7 +10180,7 @@ _sk_scale_u8_hsw: .byte 197,122,126,0 // vmovq (%rax),%xmm8 .byte 196,66,125,49,192 // vpmovzxbd %xmm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,188,47,0,0 // vbroadcastss 0x2fbc(%rip),%ymm9 # 473c <_sk_callback_hsw+0x23f> + .byte 196,98,125,24,13,24,49,0,0 // vbroadcastss 0x3118(%rip),%ymm9 # 4898 <_sk_callback_hsw+0x240> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -10051,7 +10232,7 @@ _sk_lerp_u8_hsw: .byte 197,122,126,0 // vmovq (%rax),%xmm8 .byte 196,66,125,49,192 // vpmovzxbd %xmm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,41,47,0,0 // vbroadcastss 0x2f29(%rip),%ymm9 # 4740 <_sk_callback_hsw+0x243> + .byte 196,98,125,24,13,133,48,0,0 // vbroadcastss 0x3085(%rip),%ymm9 # 489c <_sk_callback_hsw+0x244> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,226,61,168,196 // vfmadd213ps %ymm4,%ymm8,%ymm0 @@ -10087,20 +10268,20 @@ _sk_lerp_565_hsw: .byte 15,133,169,0,0,0 // jne 1923 <_sk_lerp_565_hsw+0xb7> .byte 196,65,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm8 .byte 196,66,125,51,192 // vpmovzxwd %xmm8,%ymm8 - .byte 196,98,125,88,13,182,46,0,0 // vpbroadcastd 0x2eb6(%rip),%ymm9 # 4744 <_sk_callback_hsw+0x247> + .byte 196,98,125,88,13,18,48,0,0 // vpbroadcastd 0x3012(%rip),%ymm9 # 48a0 <_sk_callback_hsw+0x248> .byte 196,65,61,219,201 // vpand %ymm9,%ymm8,%ymm9 .byte 196,65,124,91,201 // vcvtdq2ps %ymm9,%ymm9 - .byte 196,98,125,24,21,167,46,0,0 // vbroadcastss 0x2ea7(%rip),%ymm10 # 4748 <_sk_callback_hsw+0x24b> + .byte 196,98,125,24,21,3,48,0,0 // vbroadcastss 0x3003(%rip),%ymm10 # 48a4 <_sk_callback_hsw+0x24c> .byte 196,65,52,89,202 // vmulps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,88,21,157,46,0,0 // vpbroadcastd 0x2e9d(%rip),%ymm10 # 474c <_sk_callback_hsw+0x24f> + .byte 196,98,125,88,21,249,47,0,0 // vpbroadcastd 0x2ff9(%rip),%ymm10 # 48a8 <_sk_callback_hsw+0x250> .byte 196,65,61,219,210 // vpand %ymm10,%ymm8,%ymm10 .byte 196,65,124,91,210 // vcvtdq2ps %ymm10,%ymm10 - .byte 196,98,125,24,29,142,46,0,0 // vbroadcastss 0x2e8e(%rip),%ymm11 # 4750 <_sk_callback_hsw+0x253> + .byte 196,98,125,24,29,234,47,0,0 // vbroadcastss 0x2fea(%rip),%ymm11 # 48ac <_sk_callback_hsw+0x254> .byte 196,65,44,89,211 // vmulps %ymm11,%ymm10,%ymm10 - .byte 196,98,125,88,29,132,46,0,0 // vpbroadcastd 0x2e84(%rip),%ymm11 # 4754 <_sk_callback_hsw+0x257> + .byte 196,98,125,88,29,224,47,0,0 // vpbroadcastd 0x2fe0(%rip),%ymm11 # 48b0 <_sk_callback_hsw+0x258> .byte 196,65,61,219,195 // vpand %ymm11,%ymm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,29,117,46,0,0 // vbroadcastss 0x2e75(%rip),%ymm11 # 4758 <_sk_callback_hsw+0x25b> + .byte 196,98,125,24,29,209,47,0,0 // vbroadcastss 0x2fd1(%rip),%ymm11 # 48b4 <_sk_callback_hsw+0x25c> .byte 196,65,60,89,195 // vmulps %ymm11,%ymm8,%ymm8 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,226,53,168,196 // vfmadd213ps %ymm4,%ymm9,%ymm0 @@ -10141,7 +10322,7 @@ _sk_lerp_565_hsw: .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) - .byte 233,255,255,255,225 // jmpq ffffffffe200199c <_sk_callback_hsw+0xffffffffe1ffd49f> + .byte 233,255,255,255,225 // jmpq ffffffffe200199c <_sk_callback_hsw+0xffffffffe1ffd344> .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) @@ -10170,21 +10351,21 @@ _sk_load_tables_hsw: .byte 77,133,192 // test %r8,%r8 .byte 117,105 // jne 1a2e <_sk_load_tables_hsw+0x7e> .byte 196,193,126,111,25 // vmovdqu (%r9),%ymm3 - .byte 197,229,219,13,46,48,0,0 // vpand 0x302e(%rip),%ymm3,%ymm1 # 4a00 <_sk_callback_hsw+0x503> + .byte 197,229,219,13,142,49,0,0 // vpand 0x318e(%rip),%ymm3,%ymm1 # 4b60 <_sk_callback_hsw+0x508> .byte 196,65,61,118,192 // vpcmpeqd %ymm8,%ymm8,%ymm8 .byte 72,139,72,8 // mov 0x8(%rax),%rcx .byte 76,139,72,16 // mov 0x10(%rax),%r9 .byte 197,237,118,210 // vpcmpeqd %ymm2,%ymm2,%ymm2 .byte 196,226,109,146,4,137 // vgatherdps %ymm2,(%rcx,%ymm1,4),%ymm0 - .byte 196,226,101,0,21,46,48,0,0 // vpshufb 0x302e(%rip),%ymm3,%ymm2 # 4a20 <_sk_callback_hsw+0x523> + .byte 196,226,101,0,21,142,49,0,0 // vpshufb 0x318e(%rip),%ymm3,%ymm2 # 4b80 <_sk_callback_hsw+0x528> .byte 196,65,53,118,201 // vpcmpeqd %ymm9,%ymm9,%ymm9 .byte 196,194,53,146,12,145 // vgatherdps %ymm9,(%r9,%ymm2,4),%ymm1 .byte 72,139,64,24 // mov 0x18(%rax),%rax - .byte 196,98,101,0,13,54,48,0,0 // vpshufb 0x3036(%rip),%ymm3,%ymm9 # 4a40 <_sk_callback_hsw+0x543> + .byte 196,98,101,0,13,150,49,0,0 // vpshufb 0x3196(%rip),%ymm3,%ymm9 # 4ba0 <_sk_callback_hsw+0x548> .byte 196,162,61,146,20,136 // vgatherdps %ymm8,(%rax,%ymm9,4),%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,58,45,0,0 // vbroadcastss 0x2d3a(%rip),%ymm8 # 475c <_sk_callback_hsw+0x25f> + .byte 196,98,125,24,5,150,46,0,0 // vbroadcastss 0x2e96(%rip),%ymm8 # 48b8 <_sk_callback_hsw+0x260> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,137,193 // mov %r8,%rcx @@ -10223,7 +10404,7 @@ _sk_load_tables_u16_be_hsw: .byte 197,185,108,200 // vpunpcklqdq %xmm0,%xmm8,%xmm1 .byte 197,185,109,208 // vpunpckhqdq %xmm0,%xmm8,%xmm2 .byte 197,49,108,195 // vpunpcklqdq %xmm3,%xmm9,%xmm8 - .byte 197,121,111,21,194,48,0,0 // vmovdqa 0x30c2(%rip),%xmm10 # 4b80 <_sk_callback_hsw+0x683> + .byte 197,121,111,21,34,50,0,0 // vmovdqa 0x3222(%rip),%xmm10 # 4ce0 <_sk_callback_hsw+0x688> .byte 196,193,113,219,194 // vpand %xmm10,%xmm1,%xmm0 .byte 196,226,125,51,200 // vpmovzxwd %xmm0,%ymm1 .byte 196,65,37,118,219 // vpcmpeqd %ymm11,%ymm11,%ymm11 @@ -10245,7 +10426,7 @@ _sk_load_tables_u16_be_hsw: .byte 197,185,235,219 // vpor %xmm3,%xmm8,%xmm3 .byte 196,226,125,51,219 // vpmovzxwd %xmm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,51,44,0,0 // vbroadcastss 0x2c33(%rip),%ymm8 # 4760 <_sk_callback_hsw+0x263> + .byte 196,98,125,24,5,143,45,0,0 // vbroadcastss 0x2d8f(%rip),%ymm8 # 48bc <_sk_callback_hsw+0x264> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10305,7 +10486,7 @@ _sk_load_tables_rgb_u16_be_hsw: .byte 197,185,108,218 // vpunpcklqdq %xmm2,%xmm8,%xmm3 .byte 197,185,109,210 // vpunpckhqdq %xmm2,%xmm8,%xmm2 .byte 197,121,108,193 // vpunpcklqdq %xmm1,%xmm0,%xmm8 - .byte 197,121,111,13,98,47,0,0 // vmovdqa 0x2f62(%rip),%xmm9 # 4b90 <_sk_callback_hsw+0x693> + .byte 197,121,111,13,194,48,0,0 // vmovdqa 0x30c2(%rip),%xmm9 # 4cf0 <_sk_callback_hsw+0x698> .byte 196,193,97,219,193 // vpand %xmm9,%xmm3,%xmm0 .byte 196,226,125,51,200 // vpmovzxwd %xmm0,%ymm1 .byte 197,229,118,219 // vpcmpeqd %ymm3,%ymm3,%ymm3 @@ -10322,7 +10503,7 @@ _sk_load_tables_rgb_u16_be_hsw: .byte 196,98,125,51,194 // vpmovzxwd %xmm2,%ymm8 .byte 196,162,101,146,20,128 // vgatherdps %ymm3,(%rax,%ymm8,4),%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,225,42,0,0 // vbroadcastss 0x2ae1(%rip),%ymm3 # 4764 <_sk_callback_hsw+0x267> + .byte 196,226,125,24,29,61,44,0,0 // vbroadcastss 0x2c3d(%rip),%ymm3 # 48c0 <_sk_callback_hsw+0x268> .byte 255,224 // jmpq *%rax .byte 196,129,121,110,4,72 // vmovd (%r8,%r9,2),%xmm0 .byte 196,129,121,196,68,72,4,2 // vpinsrw $0x2,0x4(%r8,%r9,2),%xmm0,%xmm0 @@ -10369,7 +10550,7 @@ _sk_byte_tables_hsw: .byte 65,84 // push %r12 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,31,42,0,0 // vbroadcastss 0x2a1f(%rip),%ymm8 # 4768 <_sk_callback_hsw+0x26b> + .byte 196,98,125,24,5,123,43,0,0 // vbroadcastss 0x2b7b(%rip),%ymm8 # 48c4 <_sk_callback_hsw+0x26c> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,195,249,22,192,1 // vpextrq $0x1,%xmm0,%r8 @@ -10406,7 +10587,7 @@ _sk_byte_tables_hsw: .byte 196,227,121,32,197,7 // vpinsrb $0x7,%ebp,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,112,41,0,0 // vbroadcastss 0x2970(%rip),%ymm9 # 476c <_sk_callback_hsw+0x26f> + .byte 196,98,125,24,13,204,42,0,0 // vbroadcastss 0x2acc(%rip),%ymm9 # 48c8 <_sk_callback_hsw+0x270> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -10567,7 +10748,7 @@ _sk_byte_tables_rgb_hsw: .byte 196,227,121,32,197,7 // vpinsrb $0x7,%ebp,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,169,38,0,0 // vbroadcastss 0x26a9(%rip),%ymm9 # 4770 <_sk_callback_hsw+0x273> + .byte 196,98,125,24,13,5,40,0,0 // vbroadcastss 0x2805(%rip),%ymm9 # 48cc <_sk_callback_hsw+0x274> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -10730,33 +10911,33 @@ _sk_parametric_r_hsw: .byte 196,66,125,168,211 // vfmadd213ps %ymm11,%ymm0,%ymm10 .byte 196,226,125,24,0 // vbroadcastss (%rax),%ymm0 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,92,36,0,0 // vbroadcastss 0x245c(%rip),%ymm12 # 4774 <_sk_callback_hsw+0x277> - .byte 196,98,125,24,45,87,36,0,0 // vbroadcastss 0x2457(%rip),%ymm13 # 4778 <_sk_callback_hsw+0x27b> + .byte 196,98,125,24,37,184,37,0,0 // vbroadcastss 0x25b8(%rip),%ymm12 # 48d0 <_sk_callback_hsw+0x278> + .byte 196,98,125,24,45,179,37,0,0 // vbroadcastss 0x25b3(%rip),%ymm13 # 48d4 <_sk_callback_hsw+0x27c> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,77,36,0,0 // vbroadcastss 0x244d(%rip),%ymm13 # 477c <_sk_callback_hsw+0x27f> + .byte 196,98,125,24,45,169,37,0,0 // vbroadcastss 0x25a9(%rip),%ymm13 # 48d8 <_sk_callback_hsw+0x280> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,67,36,0,0 // vbroadcastss 0x2443(%rip),%ymm13 # 4780 <_sk_callback_hsw+0x283> + .byte 196,98,125,24,45,159,37,0,0 // vbroadcastss 0x259f(%rip),%ymm13 # 48dc <_sk_callback_hsw+0x284> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,57,36,0,0 // vbroadcastss 0x2439(%rip),%ymm11 # 4784 <_sk_callback_hsw+0x287> + .byte 196,98,125,24,29,149,37,0,0 // vbroadcastss 0x2595(%rip),%ymm11 # 48e0 <_sk_callback_hsw+0x288> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,47,36,0,0 // vbroadcastss 0x242f(%rip),%ymm12 # 4788 <_sk_callback_hsw+0x28b> + .byte 196,98,125,24,37,139,37,0,0 // vbroadcastss 0x258b(%rip),%ymm12 # 48e4 <_sk_callback_hsw+0x28c> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,37,36,0,0 // vbroadcastss 0x2425(%rip),%ymm12 # 478c <_sk_callback_hsw+0x28f> + .byte 196,98,125,24,37,129,37,0,0 // vbroadcastss 0x2581(%rip),%ymm12 # 48e8 <_sk_callback_hsw+0x290> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 196,99,125,8,208,1 // vroundps $0x1,%ymm0,%ymm10 .byte 196,65,124,92,210 // vsubps %ymm10,%ymm0,%ymm10 - .byte 196,98,125,24,29,6,36,0,0 // vbroadcastss 0x2406(%rip),%ymm11 # 4790 <_sk_callback_hsw+0x293> + .byte 196,98,125,24,29,98,37,0,0 // vbroadcastss 0x2562(%rip),%ymm11 # 48ec <_sk_callback_hsw+0x294> .byte 196,193,124,88,195 // vaddps %ymm11,%ymm0,%ymm0 - .byte 196,98,125,24,29,252,35,0,0 // vbroadcastss 0x23fc(%rip),%ymm11 # 4794 <_sk_callback_hsw+0x297> + .byte 196,98,125,24,29,88,37,0,0 // vbroadcastss 0x2558(%rip),%ymm11 # 48f0 <_sk_callback_hsw+0x298> .byte 196,98,45,172,216 // vfnmadd213ps %ymm0,%ymm10,%ymm11 - .byte 196,226,125,24,5,242,35,0,0 // vbroadcastss 0x23f2(%rip),%ymm0 # 4798 <_sk_callback_hsw+0x29b> + .byte 196,226,125,24,5,78,37,0,0 // vbroadcastss 0x254e(%rip),%ymm0 # 48f4 <_sk_callback_hsw+0x29c> .byte 196,193,124,92,194 // vsubps %ymm10,%ymm0,%ymm0 - .byte 196,98,125,24,21,232,35,0,0 // vbroadcastss 0x23e8(%rip),%ymm10 # 479c <_sk_callback_hsw+0x29f> + .byte 196,98,125,24,21,68,37,0,0 // vbroadcastss 0x2544(%rip),%ymm10 # 48f8 <_sk_callback_hsw+0x2a0> .byte 197,172,94,192 // vdivps %ymm0,%ymm10,%ymm0 .byte 197,164,88,192 // vaddps %ymm0,%ymm11,%ymm0 - .byte 196,98,125,24,21,219,35,0,0 // vbroadcastss 0x23db(%rip),%ymm10 # 47a0 <_sk_callback_hsw+0x2a3> + .byte 196,98,125,24,21,55,37,0,0 // vbroadcastss 0x2537(%rip),%ymm10 # 48fc <_sk_callback_hsw+0x2a4> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -10764,7 +10945,7 @@ _sk_parametric_r_hsw: .byte 196,195,125,74,193,128 // vblendvps %ymm8,%ymm9,%ymm0,%ymm0 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,124,95,192 // vmaxps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,178,35,0,0 // vbroadcastss 0x23b2(%rip),%ymm8 # 47a4 <_sk_callback_hsw+0x2a7> + .byte 196,98,125,24,5,14,37,0,0 // vbroadcastss 0x250e(%rip),%ymm8 # 4900 <_sk_callback_hsw+0x2a8> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10784,33 +10965,33 @@ _sk_parametric_g_hsw: .byte 196,66,117,168,211 // vfmadd213ps %ymm11,%ymm1,%ymm10 .byte 196,226,125,24,8 // vbroadcastss (%rax),%ymm1 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,106,35,0,0 // vbroadcastss 0x236a(%rip),%ymm12 # 47a8 <_sk_callback_hsw+0x2ab> - .byte 196,98,125,24,45,101,35,0,0 // vbroadcastss 0x2365(%rip),%ymm13 # 47ac <_sk_callback_hsw+0x2af> + .byte 196,98,125,24,37,198,36,0,0 // vbroadcastss 0x24c6(%rip),%ymm12 # 4904 <_sk_callback_hsw+0x2ac> + .byte 196,98,125,24,45,193,36,0,0 // vbroadcastss 0x24c1(%rip),%ymm13 # 4908 <_sk_callback_hsw+0x2b0> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,91,35,0,0 // vbroadcastss 0x235b(%rip),%ymm13 # 47b0 <_sk_callback_hsw+0x2b3> + .byte 196,98,125,24,45,183,36,0,0 // vbroadcastss 0x24b7(%rip),%ymm13 # 490c <_sk_callback_hsw+0x2b4> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,81,35,0,0 // vbroadcastss 0x2351(%rip),%ymm13 # 47b4 <_sk_callback_hsw+0x2b7> + .byte 196,98,125,24,45,173,36,0,0 // vbroadcastss 0x24ad(%rip),%ymm13 # 4910 <_sk_callback_hsw+0x2b8> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,71,35,0,0 // vbroadcastss 0x2347(%rip),%ymm11 # 47b8 <_sk_callback_hsw+0x2bb> + .byte 196,98,125,24,29,163,36,0,0 // vbroadcastss 0x24a3(%rip),%ymm11 # 4914 <_sk_callback_hsw+0x2bc> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,61,35,0,0 // vbroadcastss 0x233d(%rip),%ymm12 # 47bc <_sk_callback_hsw+0x2bf> + .byte 196,98,125,24,37,153,36,0,0 // vbroadcastss 0x2499(%rip),%ymm12 # 4918 <_sk_callback_hsw+0x2c0> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,51,35,0,0 // vbroadcastss 0x2333(%rip),%ymm12 # 47c0 <_sk_callback_hsw+0x2c3> + .byte 196,98,125,24,37,143,36,0,0 // vbroadcastss 0x248f(%rip),%ymm12 # 491c <_sk_callback_hsw+0x2c4> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,116,89,202 // vmulps %ymm10,%ymm1,%ymm1 .byte 196,99,125,8,209,1 // vroundps $0x1,%ymm1,%ymm10 .byte 196,65,116,92,210 // vsubps %ymm10,%ymm1,%ymm10 - .byte 196,98,125,24,29,20,35,0,0 // vbroadcastss 0x2314(%rip),%ymm11 # 47c4 <_sk_callback_hsw+0x2c7> + .byte 196,98,125,24,29,112,36,0,0 // vbroadcastss 0x2470(%rip),%ymm11 # 4920 <_sk_callback_hsw+0x2c8> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,10,35,0,0 // vbroadcastss 0x230a(%rip),%ymm11 # 47c8 <_sk_callback_hsw+0x2cb> + .byte 196,98,125,24,29,102,36,0,0 // vbroadcastss 0x2466(%rip),%ymm11 # 4924 <_sk_callback_hsw+0x2cc> .byte 196,98,45,172,217 // vfnmadd213ps %ymm1,%ymm10,%ymm11 - .byte 196,226,125,24,13,0,35,0,0 // vbroadcastss 0x2300(%rip),%ymm1 # 47cc <_sk_callback_hsw+0x2cf> + .byte 196,226,125,24,13,92,36,0,0 // vbroadcastss 0x245c(%rip),%ymm1 # 4928 <_sk_callback_hsw+0x2d0> .byte 196,193,116,92,202 // vsubps %ymm10,%ymm1,%ymm1 - .byte 196,98,125,24,21,246,34,0,0 // vbroadcastss 0x22f6(%rip),%ymm10 # 47d0 <_sk_callback_hsw+0x2d3> + .byte 196,98,125,24,21,82,36,0,0 // vbroadcastss 0x2452(%rip),%ymm10 # 492c <_sk_callback_hsw+0x2d4> .byte 197,172,94,201 // vdivps %ymm1,%ymm10,%ymm1 .byte 197,164,88,201 // vaddps %ymm1,%ymm11,%ymm1 - .byte 196,98,125,24,21,233,34,0,0 // vbroadcastss 0x22e9(%rip),%ymm10 # 47d4 <_sk_callback_hsw+0x2d7> + .byte 196,98,125,24,21,69,36,0,0 // vbroadcastss 0x2445(%rip),%ymm10 # 4930 <_sk_callback_hsw+0x2d8> .byte 196,193,116,89,202 // vmulps %ymm10,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -10818,7 +10999,7 @@ _sk_parametric_g_hsw: .byte 196,195,117,74,201,128 // vblendvps %ymm8,%ymm9,%ymm1,%ymm1 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,116,95,200 // vmaxps %ymm8,%ymm1,%ymm1 - .byte 196,98,125,24,5,192,34,0,0 // vbroadcastss 0x22c0(%rip),%ymm8 # 47d8 <_sk_callback_hsw+0x2db> + .byte 196,98,125,24,5,28,36,0,0 // vbroadcastss 0x241c(%rip),%ymm8 # 4934 <_sk_callback_hsw+0x2dc> .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10838,33 +11019,33 @@ _sk_parametric_b_hsw: .byte 196,66,109,168,211 // vfmadd213ps %ymm11,%ymm2,%ymm10 .byte 196,226,125,24,16 // vbroadcastss (%rax),%ymm2 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,120,34,0,0 // vbroadcastss 0x2278(%rip),%ymm12 # 47dc <_sk_callback_hsw+0x2df> - .byte 196,98,125,24,45,115,34,0,0 // vbroadcastss 0x2273(%rip),%ymm13 # 47e0 <_sk_callback_hsw+0x2e3> + .byte 196,98,125,24,37,212,35,0,0 // vbroadcastss 0x23d4(%rip),%ymm12 # 4938 <_sk_callback_hsw+0x2e0> + .byte 196,98,125,24,45,207,35,0,0 // vbroadcastss 0x23cf(%rip),%ymm13 # 493c <_sk_callback_hsw+0x2e4> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,105,34,0,0 // vbroadcastss 0x2269(%rip),%ymm13 # 47e4 <_sk_callback_hsw+0x2e7> + .byte 196,98,125,24,45,197,35,0,0 // vbroadcastss 0x23c5(%rip),%ymm13 # 4940 <_sk_callback_hsw+0x2e8> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,95,34,0,0 // vbroadcastss 0x225f(%rip),%ymm13 # 47e8 <_sk_callback_hsw+0x2eb> + .byte 196,98,125,24,45,187,35,0,0 // vbroadcastss 0x23bb(%rip),%ymm13 # 4944 <_sk_callback_hsw+0x2ec> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,85,34,0,0 // vbroadcastss 0x2255(%rip),%ymm11 # 47ec <_sk_callback_hsw+0x2ef> + .byte 196,98,125,24,29,177,35,0,0 // vbroadcastss 0x23b1(%rip),%ymm11 # 4948 <_sk_callback_hsw+0x2f0> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,75,34,0,0 // vbroadcastss 0x224b(%rip),%ymm12 # 47f0 <_sk_callback_hsw+0x2f3> + .byte 196,98,125,24,37,167,35,0,0 // vbroadcastss 0x23a7(%rip),%ymm12 # 494c <_sk_callback_hsw+0x2f4> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,65,34,0,0 // vbroadcastss 0x2241(%rip),%ymm12 # 47f4 <_sk_callback_hsw+0x2f7> + .byte 196,98,125,24,37,157,35,0,0 // vbroadcastss 0x239d(%rip),%ymm12 # 4950 <_sk_callback_hsw+0x2f8> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 196,99,125,8,210,1 // vroundps $0x1,%ymm2,%ymm10 .byte 196,65,108,92,210 // vsubps %ymm10,%ymm2,%ymm10 - .byte 196,98,125,24,29,34,34,0,0 // vbroadcastss 0x2222(%rip),%ymm11 # 47f8 <_sk_callback_hsw+0x2fb> + .byte 196,98,125,24,29,126,35,0,0 // vbroadcastss 0x237e(%rip),%ymm11 # 4954 <_sk_callback_hsw+0x2fc> .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 - .byte 196,98,125,24,29,24,34,0,0 // vbroadcastss 0x2218(%rip),%ymm11 # 47fc <_sk_callback_hsw+0x2ff> + .byte 196,98,125,24,29,116,35,0,0 // vbroadcastss 0x2374(%rip),%ymm11 # 4958 <_sk_callback_hsw+0x300> .byte 196,98,45,172,218 // vfnmadd213ps %ymm2,%ymm10,%ymm11 - .byte 196,226,125,24,21,14,34,0,0 // vbroadcastss 0x220e(%rip),%ymm2 # 4800 <_sk_callback_hsw+0x303> + .byte 196,226,125,24,21,106,35,0,0 // vbroadcastss 0x236a(%rip),%ymm2 # 495c <_sk_callback_hsw+0x304> .byte 196,193,108,92,210 // vsubps %ymm10,%ymm2,%ymm2 - .byte 196,98,125,24,21,4,34,0,0 // vbroadcastss 0x2204(%rip),%ymm10 # 4804 <_sk_callback_hsw+0x307> + .byte 196,98,125,24,21,96,35,0,0 // vbroadcastss 0x2360(%rip),%ymm10 # 4960 <_sk_callback_hsw+0x308> .byte 197,172,94,210 // vdivps %ymm2,%ymm10,%ymm2 .byte 197,164,88,210 // vaddps %ymm2,%ymm11,%ymm2 - .byte 196,98,125,24,21,247,33,0,0 // vbroadcastss 0x21f7(%rip),%ymm10 # 4808 <_sk_callback_hsw+0x30b> + .byte 196,98,125,24,21,83,35,0,0 // vbroadcastss 0x2353(%rip),%ymm10 # 4964 <_sk_callback_hsw+0x30c> .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 197,253,91,210 // vcvtps2dq %ymm2,%ymm2 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -10872,7 +11053,7 @@ _sk_parametric_b_hsw: .byte 196,195,109,74,209,128 // vblendvps %ymm8,%ymm9,%ymm2,%ymm2 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,108,95,208 // vmaxps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,206,33,0,0 // vbroadcastss 0x21ce(%rip),%ymm8 # 480c <_sk_callback_hsw+0x30f> + .byte 196,98,125,24,5,42,35,0,0 // vbroadcastss 0x232a(%rip),%ymm8 # 4968 <_sk_callback_hsw+0x310> .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10892,33 +11073,33 @@ _sk_parametric_a_hsw: .byte 196,66,101,168,211 // vfmadd213ps %ymm11,%ymm3,%ymm10 .byte 196,226,125,24,24 // vbroadcastss (%rax),%ymm3 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,134,33,0,0 // vbroadcastss 0x2186(%rip),%ymm12 # 4810 <_sk_callback_hsw+0x313> - .byte 196,98,125,24,45,129,33,0,0 // vbroadcastss 0x2181(%rip),%ymm13 # 4814 <_sk_callback_hsw+0x317> + .byte 196,98,125,24,37,226,34,0,0 // vbroadcastss 0x22e2(%rip),%ymm12 # 496c <_sk_callback_hsw+0x314> + .byte 196,98,125,24,45,221,34,0,0 // vbroadcastss 0x22dd(%rip),%ymm13 # 4970 <_sk_callback_hsw+0x318> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,119,33,0,0 // vbroadcastss 0x2177(%rip),%ymm13 # 4818 <_sk_callback_hsw+0x31b> + .byte 196,98,125,24,45,211,34,0,0 // vbroadcastss 0x22d3(%rip),%ymm13 # 4974 <_sk_callback_hsw+0x31c> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,109,33,0,0 // vbroadcastss 0x216d(%rip),%ymm13 # 481c <_sk_callback_hsw+0x31f> + .byte 196,98,125,24,45,201,34,0,0 // vbroadcastss 0x22c9(%rip),%ymm13 # 4978 <_sk_callback_hsw+0x320> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,99,33,0,0 // vbroadcastss 0x2163(%rip),%ymm11 # 4820 <_sk_callback_hsw+0x323> + .byte 196,98,125,24,29,191,34,0,0 // vbroadcastss 0x22bf(%rip),%ymm11 # 497c <_sk_callback_hsw+0x324> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,89,33,0,0 // vbroadcastss 0x2159(%rip),%ymm12 # 4824 <_sk_callback_hsw+0x327> + .byte 196,98,125,24,37,181,34,0,0 // vbroadcastss 0x22b5(%rip),%ymm12 # 4980 <_sk_callback_hsw+0x328> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,79,33,0,0 // vbroadcastss 0x214f(%rip),%ymm12 # 4828 <_sk_callback_hsw+0x32b> + .byte 196,98,125,24,37,171,34,0,0 // vbroadcastss 0x22ab(%rip),%ymm12 # 4984 <_sk_callback_hsw+0x32c> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 196,99,125,8,211,1 // vroundps $0x1,%ymm3,%ymm10 .byte 196,65,100,92,210 // vsubps %ymm10,%ymm3,%ymm10 - .byte 196,98,125,24,29,48,33,0,0 // vbroadcastss 0x2130(%rip),%ymm11 # 482c <_sk_callback_hsw+0x32f> + .byte 196,98,125,24,29,140,34,0,0 // vbroadcastss 0x228c(%rip),%ymm11 # 4988 <_sk_callback_hsw+0x330> .byte 196,193,100,88,219 // vaddps %ymm11,%ymm3,%ymm3 - .byte 196,98,125,24,29,38,33,0,0 // vbroadcastss 0x2126(%rip),%ymm11 # 4830 <_sk_callback_hsw+0x333> + .byte 196,98,125,24,29,130,34,0,0 // vbroadcastss 0x2282(%rip),%ymm11 # 498c <_sk_callback_hsw+0x334> .byte 196,98,45,172,219 // vfnmadd213ps %ymm3,%ymm10,%ymm11 - .byte 196,226,125,24,29,28,33,0,0 // vbroadcastss 0x211c(%rip),%ymm3 # 4834 <_sk_callback_hsw+0x337> + .byte 196,226,125,24,29,120,34,0,0 // vbroadcastss 0x2278(%rip),%ymm3 # 4990 <_sk_callback_hsw+0x338> .byte 196,193,100,92,218 // vsubps %ymm10,%ymm3,%ymm3 - .byte 196,98,125,24,21,18,33,0,0 // vbroadcastss 0x2112(%rip),%ymm10 # 4838 <_sk_callback_hsw+0x33b> + .byte 196,98,125,24,21,110,34,0,0 // vbroadcastss 0x226e(%rip),%ymm10 # 4994 <_sk_callback_hsw+0x33c> .byte 197,172,94,219 // vdivps %ymm3,%ymm10,%ymm3 .byte 197,164,88,219 // vaddps %ymm3,%ymm11,%ymm3 - .byte 196,98,125,24,21,5,33,0,0 // vbroadcastss 0x2105(%rip),%ymm10 # 483c <_sk_callback_hsw+0x33f> + .byte 196,98,125,24,21,97,34,0,0 // vbroadcastss 0x2261(%rip),%ymm10 # 4998 <_sk_callback_hsw+0x340> .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 197,253,91,219 // vcvtps2dq %ymm3,%ymm3 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -10926,7 +11107,7 @@ _sk_parametric_a_hsw: .byte 196,195,101,74,217,128 // vblendvps %ymm8,%ymm9,%ymm3,%ymm3 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,100,95,216 // vmaxps %ymm8,%ymm3,%ymm3 - .byte 196,98,125,24,5,220,32,0,0 // vbroadcastss 0x20dc(%rip),%ymm8 # 4840 <_sk_callback_hsw+0x343> + .byte 196,98,125,24,5,56,34,0,0 // vbroadcastss 0x2238(%rip),%ymm8 # 499c <_sk_callback_hsw+0x344> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10935,26 +11116,26 @@ HIDDEN _sk_lab_to_xyz_hsw .globl _sk_lab_to_xyz_hsw FUNCTION(_sk_lab_to_xyz_hsw) _sk_lab_to_xyz_hsw: - .byte 196,98,125,24,5,206,32,0,0 // vbroadcastss 0x20ce(%rip),%ymm8 # 4844 <_sk_callback_hsw+0x347> - .byte 196,98,125,24,13,201,32,0,0 // vbroadcastss 0x20c9(%rip),%ymm9 # 4848 <_sk_callback_hsw+0x34b> - .byte 196,98,125,24,21,196,32,0,0 // vbroadcastss 0x20c4(%rip),%ymm10 # 484c <_sk_callback_hsw+0x34f> + .byte 196,98,125,24,5,42,34,0,0 // vbroadcastss 0x222a(%rip),%ymm8 # 49a0 <_sk_callback_hsw+0x348> + .byte 196,98,125,24,13,37,34,0,0 // vbroadcastss 0x2225(%rip),%ymm9 # 49a4 <_sk_callback_hsw+0x34c> + .byte 196,98,125,24,21,32,34,0,0 // vbroadcastss 0x2220(%rip),%ymm10 # 49a8 <_sk_callback_hsw+0x350> .byte 196,194,53,168,202 // vfmadd213ps %ymm10,%ymm9,%ymm1 .byte 196,194,53,168,210 // vfmadd213ps %ymm10,%ymm9,%ymm2 - .byte 196,98,125,24,13,181,32,0,0 // vbroadcastss 0x20b5(%rip),%ymm9 # 4850 <_sk_callback_hsw+0x353> + .byte 196,98,125,24,13,17,34,0,0 // vbroadcastss 0x2211(%rip),%ymm9 # 49ac <_sk_callback_hsw+0x354> .byte 196,66,125,184,200 // vfmadd231ps %ymm8,%ymm0,%ymm9 - .byte 196,226,125,24,5,171,32,0,0 // vbroadcastss 0x20ab(%rip),%ymm0 # 4854 <_sk_callback_hsw+0x357> + .byte 196,226,125,24,5,7,34,0,0 // vbroadcastss 0x2207(%rip),%ymm0 # 49b0 <_sk_callback_hsw+0x358> .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 - .byte 196,98,125,24,5,162,32,0,0 // vbroadcastss 0x20a2(%rip),%ymm8 # 4858 <_sk_callback_hsw+0x35b> + .byte 196,98,125,24,5,254,33,0,0 // vbroadcastss 0x21fe(%rip),%ymm8 # 49b4 <_sk_callback_hsw+0x35c> .byte 196,98,117,168,192 // vfmadd213ps %ymm0,%ymm1,%ymm8 - .byte 196,98,125,24,13,152,32,0,0 // vbroadcastss 0x2098(%rip),%ymm9 # 485c <_sk_callback_hsw+0x35f> + .byte 196,98,125,24,13,244,33,0,0 // vbroadcastss 0x21f4(%rip),%ymm9 # 49b8 <_sk_callback_hsw+0x360> .byte 196,98,109,172,200 // vfnmadd213ps %ymm0,%ymm2,%ymm9 .byte 196,193,60,89,200 // vmulps %ymm8,%ymm8,%ymm1 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 - .byte 196,226,125,24,21,133,32,0,0 // vbroadcastss 0x2085(%rip),%ymm2 # 4860 <_sk_callback_hsw+0x363> + .byte 196,226,125,24,21,225,33,0,0 // vbroadcastss 0x21e1(%rip),%ymm2 # 49bc <_sk_callback_hsw+0x364> .byte 197,108,194,209,1 // vcmpltps %ymm1,%ymm2,%ymm10 - .byte 196,98,125,24,29,123,32,0,0 // vbroadcastss 0x207b(%rip),%ymm11 # 4864 <_sk_callback_hsw+0x367> + .byte 196,98,125,24,29,215,33,0,0 // vbroadcastss 0x21d7(%rip),%ymm11 # 49c0 <_sk_callback_hsw+0x368> .byte 196,65,60,88,195 // vaddps %ymm11,%ymm8,%ymm8 - .byte 196,98,125,24,37,113,32,0,0 // vbroadcastss 0x2071(%rip),%ymm12 # 4868 <_sk_callback_hsw+0x36b> + .byte 196,98,125,24,37,205,33,0,0 // vbroadcastss 0x21cd(%rip),%ymm12 # 49c4 <_sk_callback_hsw+0x36c> .byte 196,65,60,89,196 // vmulps %ymm12,%ymm8,%ymm8 .byte 196,99,61,74,193,160 // vblendvps %ymm10,%ymm1,%ymm8,%ymm8 .byte 197,252,89,200 // vmulps %ymm0,%ymm0,%ymm1 @@ -10969,9 +11150,9 @@ _sk_lab_to_xyz_hsw: .byte 196,65,52,88,203 // vaddps %ymm11,%ymm9,%ymm9 .byte 196,65,52,89,204 // vmulps %ymm12,%ymm9,%ymm9 .byte 196,227,53,74,208,32 // vblendvps %ymm2,%ymm0,%ymm9,%ymm2 - .byte 196,226,125,24,5,38,32,0,0 // vbroadcastss 0x2026(%rip),%ymm0 # 486c <_sk_callback_hsw+0x36f> + .byte 196,226,125,24,5,130,33,0,0 // vbroadcastss 0x2182(%rip),%ymm0 # 49c8 <_sk_callback_hsw+0x370> .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 - .byte 196,98,125,24,5,29,32,0,0 // vbroadcastss 0x201d(%rip),%ymm8 # 4870 <_sk_callback_hsw+0x373> + .byte 196,98,125,24,5,121,33,0,0 // vbroadcastss 0x2179(%rip),%ymm8 # 49cc <_sk_callback_hsw+0x374> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10989,7 +11170,7 @@ _sk_load_a8_hsw: .byte 197,250,126,0 // vmovq (%rax),%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,242,31,0,0 // vbroadcastss 0x1ff2(%rip),%ymm1 # 4874 <_sk_callback_hsw+0x377> + .byte 196,226,125,24,13,78,33,0,0 // vbroadcastss 0x214e(%rip),%ymm1 # 49d0 <_sk_callback_hsw+0x378> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -11054,7 +11235,7 @@ _sk_gather_a8_hsw: .byte 196,227,121,32,192,7 // vpinsrb $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,253,30,0,0 // vbroadcastss 0x1efd(%rip),%ymm1 # 4878 <_sk_callback_hsw+0x37b> + .byte 196,226,125,24,13,89,32,0,0 // vbroadcastss 0x2059(%rip),%ymm1 # 49d4 <_sk_callback_hsw+0x37c> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -11072,7 +11253,7 @@ FUNCTION(_sk_store_a8_hsw) _sk_store_a8_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,216,30,0,0 // vbroadcastss 0x1ed8(%rip),%ymm8 # 487c <_sk_callback_hsw+0x37f> + .byte 196,98,125,24,5,52,32,0,0 // vbroadcastss 0x2034(%rip),%ymm8 # 49d8 <_sk_callback_hsw+0x380> .byte 196,65,100,89,192 // vmulps %ymm8,%ymm3,%ymm8 .byte 196,65,125,91,192 // vcvtps2dq %ymm8,%ymm8 .byte 196,67,125,25,193,1 // vextractf128 $0x1,%ymm8,%xmm9 @@ -11139,10 +11320,10 @@ _sk_load_g8_hsw: .byte 197,250,126,0 // vmovq (%rax),%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,14,30,0,0 // vbroadcastss 0x1e0e(%rip),%ymm1 # 4880 <_sk_callback_hsw+0x383> + .byte 196,226,125,24,13,106,31,0,0 // vbroadcastss 0x1f6a(%rip),%ymm1 # 49dc <_sk_callback_hsw+0x384> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,3,30,0,0 // vbroadcastss 0x1e03(%rip),%ymm3 # 4884 <_sk_callback_hsw+0x387> + .byte 196,226,125,24,29,95,31,0,0 // vbroadcastss 0x1f5f(%rip),%ymm3 # 49e0 <_sk_callback_hsw+0x388> .byte 76,137,193 // mov %r8,%rcx .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 @@ -11204,10 +11385,10 @@ _sk_gather_g8_hsw: .byte 196,227,121,32,192,7 // vpinsrb $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,24,29,0,0 // vbroadcastss 0x1d18(%rip),%ymm1 # 4888 <_sk_callback_hsw+0x38b> + .byte 196,226,125,24,13,116,30,0,0 // vbroadcastss 0x1e74(%rip),%ymm1 # 49e4 <_sk_callback_hsw+0x38c> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,13,29,0,0 // vbroadcastss 0x1d0d(%rip),%ymm3 # 488c <_sk_callback_hsw+0x38f> + .byte 196,226,125,24,29,105,30,0,0 // vbroadcastss 0x1e69(%rip),%ymm3 # 49e8 <_sk_callback_hsw+0x390> .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 .byte 91 // pop %rbx @@ -11263,14 +11444,14 @@ _sk_gather_i8_hsw: .byte 73,139,64,8 // mov 0x8(%r8),%rax .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 .byte 196,226,117,144,28,128 // vpgatherdd %ymm1,(%rax,%ymm0,4),%ymm3 - .byte 197,229,219,5,17,30,0,0 // vpand 0x1e11(%rip),%ymm3,%ymm0 # 4a60 <_sk_callback_hsw+0x563> + .byte 197,229,219,5,113,31,0,0 // vpand 0x1f71(%rip),%ymm3,%ymm0 # 4bc0 <_sk_callback_hsw+0x568> .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,52,28,0,0 // vbroadcastss 0x1c34(%rip),%ymm8 # 4890 <_sk_callback_hsw+0x393> + .byte 196,98,125,24,5,144,29,0,0 // vbroadcastss 0x1d90(%rip),%ymm8 # 49ec <_sk_callback_hsw+0x394> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,226,101,0,13,22,30,0,0 // vpshufb 0x1e16(%rip),%ymm3,%ymm1 # 4a80 <_sk_callback_hsw+0x583> + .byte 196,226,101,0,13,118,31,0,0 // vpshufb 0x1f76(%rip),%ymm3,%ymm1 # 4be0 <_sk_callback_hsw+0x588> .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,226,101,0,21,36,30,0,0 // vpshufb 0x1e24(%rip),%ymm3,%ymm2 # 4aa0 <_sk_callback_hsw+0x5a3> + .byte 196,226,101,0,21,132,31,0,0 // vpshufb 0x1f84(%rip),%ymm3,%ymm2 # 4c00 <_sk_callback_hsw+0x5a8> .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 @@ -11294,23 +11475,23 @@ _sk_load_565_hsw: .byte 117,114 // jne 2d1c <_sk_load_565_hsw+0x7c> .byte 196,193,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm0 .byte 196,226,125,51,208 // vpmovzxwd %xmm0,%ymm2 - .byte 196,226,125,88,5,214,27,0,0 // vpbroadcastd 0x1bd6(%rip),%ymm0 # 4894 <_sk_callback_hsw+0x397> + .byte 196,226,125,88,5,50,29,0,0 // vpbroadcastd 0x1d32(%rip),%ymm0 # 49f0 <_sk_callback_hsw+0x398> .byte 197,237,219,192 // vpand %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,201,27,0,0 // vbroadcastss 0x1bc9(%rip),%ymm1 # 4898 <_sk_callback_hsw+0x39b> + .byte 196,226,125,24,13,37,29,0,0 // vbroadcastss 0x1d25(%rip),%ymm1 # 49f4 <_sk_callback_hsw+0x39c> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,192,27,0,0 // vpbroadcastd 0x1bc0(%rip),%ymm1 # 489c <_sk_callback_hsw+0x39f> + .byte 196,226,125,88,13,28,29,0,0 // vpbroadcastd 0x1d1c(%rip),%ymm1 # 49f8 <_sk_callback_hsw+0x3a0> .byte 197,237,219,201 // vpand %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,179,27,0,0 // vbroadcastss 0x1bb3(%rip),%ymm3 # 48a0 <_sk_callback_hsw+0x3a3> + .byte 196,226,125,24,29,15,29,0,0 // vbroadcastss 0x1d0f(%rip),%ymm3 # 49fc <_sk_callback_hsw+0x3a4> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,88,29,170,27,0,0 // vpbroadcastd 0x1baa(%rip),%ymm3 # 48a4 <_sk_callback_hsw+0x3a7> + .byte 196,226,125,88,29,6,29,0,0 // vpbroadcastd 0x1d06(%rip),%ymm3 # 4a00 <_sk_callback_hsw+0x3a8> .byte 197,237,219,211 // vpand %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,157,27,0,0 // vbroadcastss 0x1b9d(%rip),%ymm3 # 48a8 <_sk_callback_hsw+0x3ab> + .byte 196,226,125,24,29,249,28,0,0 // vbroadcastss 0x1cf9(%rip),%ymm3 # 4a04 <_sk_callback_hsw+0x3ac> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,146,27,0,0 // vbroadcastss 0x1b92(%rip),%ymm3 # 48ac <_sk_callback_hsw+0x3af> + .byte 196,226,125,24,29,238,28,0,0 // vbroadcastss 0x1cee(%rip),%ymm3 # 4a08 <_sk_callback_hsw+0x3b0> .byte 255,224 // jmpq *%rax .byte 65,137,200 // mov %ecx,%r8d .byte 65,128,224,7 // and $0x7,%r8b @@ -11401,23 +11582,23 @@ _sk_gather_565_hsw: .byte 65,15,183,4,88 // movzwl (%r8,%rbx,2),%eax .byte 197,249,196,192,7 // vpinsrw $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,51,208 // vpmovzxwd %xmm0,%ymm2 - .byte 196,226,125,88,5,85,26,0,0 // vpbroadcastd 0x1a55(%rip),%ymm0 # 48b0 <_sk_callback_hsw+0x3b3> + .byte 196,226,125,88,5,177,27,0,0 // vpbroadcastd 0x1bb1(%rip),%ymm0 # 4a0c <_sk_callback_hsw+0x3b4> .byte 197,237,219,192 // vpand %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,72,26,0,0 // vbroadcastss 0x1a48(%rip),%ymm1 # 48b4 <_sk_callback_hsw+0x3b7> + .byte 196,226,125,24,13,164,27,0,0 // vbroadcastss 0x1ba4(%rip),%ymm1 # 4a10 <_sk_callback_hsw+0x3b8> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,63,26,0,0 // vpbroadcastd 0x1a3f(%rip),%ymm1 # 48b8 <_sk_callback_hsw+0x3bb> + .byte 196,226,125,88,13,155,27,0,0 // vpbroadcastd 0x1b9b(%rip),%ymm1 # 4a14 <_sk_callback_hsw+0x3bc> .byte 197,237,219,201 // vpand %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,50,26,0,0 // vbroadcastss 0x1a32(%rip),%ymm3 # 48bc <_sk_callback_hsw+0x3bf> + .byte 196,226,125,24,29,142,27,0,0 // vbroadcastss 0x1b8e(%rip),%ymm3 # 4a18 <_sk_callback_hsw+0x3c0> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,88,29,41,26,0,0 // vpbroadcastd 0x1a29(%rip),%ymm3 # 48c0 <_sk_callback_hsw+0x3c3> + .byte 196,226,125,88,29,133,27,0,0 // vpbroadcastd 0x1b85(%rip),%ymm3 # 4a1c <_sk_callback_hsw+0x3c4> .byte 197,237,219,211 // vpand %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,28,26,0,0 // vbroadcastss 0x1a1c(%rip),%ymm3 # 48c4 <_sk_callback_hsw+0x3c7> + .byte 196,226,125,24,29,120,27,0,0 // vbroadcastss 0x1b78(%rip),%ymm3 # 4a20 <_sk_callback_hsw+0x3c8> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,17,26,0,0 // vbroadcastss 0x1a11(%rip),%ymm3 # 48c8 <_sk_callback_hsw+0x3cb> + .byte 196,226,125,24,29,109,27,0,0 // vbroadcastss 0x1b6d(%rip),%ymm3 # 4a24 <_sk_callback_hsw+0x3cc> .byte 91 // pop %rbx .byte 65,92 // pop %r12 .byte 65,94 // pop %r14 @@ -11430,11 +11611,11 @@ FUNCTION(_sk_store_565_hsw) _sk_store_565_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,254,25,0,0 // vbroadcastss 0x19fe(%rip),%ymm8 # 48cc <_sk_callback_hsw+0x3cf> + .byte 196,98,125,24,5,90,27,0,0 // vbroadcastss 0x1b5a(%rip),%ymm8 # 4a28 <_sk_callback_hsw+0x3d0> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,53,114,241,11 // vpslld $0xb,%ymm9,%ymm9 - .byte 196,98,125,24,21,233,25,0,0 // vbroadcastss 0x19e9(%rip),%ymm10 # 48d0 <_sk_callback_hsw+0x3d3> + .byte 196,98,125,24,21,69,27,0,0 // vbroadcastss 0x1b45(%rip),%ymm10 # 4a2c <_sk_callback_hsw+0x3d4> .byte 196,65,116,89,210 // vmulps %ymm10,%ymm1,%ymm10 .byte 196,65,125,91,210 // vcvtps2dq %ymm10,%ymm10 .byte 196,193,45,114,242,5 // vpslld $0x5,%ymm10,%ymm10 @@ -11502,25 +11683,25 @@ _sk_load_4444_hsw: .byte 15,133,138,0,0,0 // jne 3038 <_sk_load_4444_hsw+0x98> .byte 196,193,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm0 .byte 196,226,125,51,216 // vpmovzxwd %xmm0,%ymm3 - .byte 196,226,125,88,5,18,25,0,0 // vpbroadcastd 0x1912(%rip),%ymm0 # 48d4 <_sk_callback_hsw+0x3d7> + .byte 196,226,125,88,5,110,26,0,0 // vpbroadcastd 0x1a6e(%rip),%ymm0 # 4a30 <_sk_callback_hsw+0x3d8> .byte 197,229,219,192 // vpand %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,5,25,0,0 // vbroadcastss 0x1905(%rip),%ymm1 # 48d8 <_sk_callback_hsw+0x3db> + .byte 196,226,125,24,13,97,26,0,0 // vbroadcastss 0x1a61(%rip),%ymm1 # 4a34 <_sk_callback_hsw+0x3dc> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,252,24,0,0 // vpbroadcastd 0x18fc(%rip),%ymm1 # 48dc <_sk_callback_hsw+0x3df> + .byte 196,226,125,88,13,88,26,0,0 // vpbroadcastd 0x1a58(%rip),%ymm1 # 4a38 <_sk_callback_hsw+0x3e0> .byte 197,229,219,201 // vpand %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,239,24,0,0 // vbroadcastss 0x18ef(%rip),%ymm2 # 48e0 <_sk_callback_hsw+0x3e3> + .byte 196,226,125,24,21,75,26,0,0 // vbroadcastss 0x1a4b(%rip),%ymm2 # 4a3c <_sk_callback_hsw+0x3e4> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,88,21,230,24,0,0 // vpbroadcastd 0x18e6(%rip),%ymm2 # 48e4 <_sk_callback_hsw+0x3e7> + .byte 196,226,125,88,21,66,26,0,0 // vpbroadcastd 0x1a42(%rip),%ymm2 # 4a40 <_sk_callback_hsw+0x3e8> .byte 197,229,219,210 // vpand %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,217,24,0,0 // vbroadcastss 0x18d9(%rip),%ymm8 # 48e8 <_sk_callback_hsw+0x3eb> + .byte 196,98,125,24,5,53,26,0,0 // vbroadcastss 0x1a35(%rip),%ymm8 # 4a44 <_sk_callback_hsw+0x3ec> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,88,5,207,24,0,0 // vpbroadcastd 0x18cf(%rip),%ymm8 # 48ec <_sk_callback_hsw+0x3ef> + .byte 196,98,125,88,5,43,26,0,0 // vpbroadcastd 0x1a2b(%rip),%ymm8 # 4a48 <_sk_callback_hsw+0x3f0> .byte 196,193,101,219,216 // vpand %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,193,24,0,0 // vbroadcastss 0x18c1(%rip),%ymm8 # 48f0 <_sk_callback_hsw+0x3f3> + .byte 196,98,125,24,5,29,26,0,0 // vbroadcastss 0x1a1d(%rip),%ymm8 # 4a4c <_sk_callback_hsw+0x3f4> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -11613,25 +11794,25 @@ _sk_gather_4444_hsw: .byte 65,15,183,4,88 // movzwl (%r8,%rbx,2),%eax .byte 197,249,196,192,7 // vpinsrw $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,51,216 // vpmovzxwd %xmm0,%ymm3 - .byte 196,226,125,88,5,121,23,0,0 // vpbroadcastd 0x1779(%rip),%ymm0 # 48f4 <_sk_callback_hsw+0x3f7> + .byte 196,226,125,88,5,213,24,0,0 // vpbroadcastd 0x18d5(%rip),%ymm0 # 4a50 <_sk_callback_hsw+0x3f8> .byte 197,229,219,192 // vpand %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,108,23,0,0 // vbroadcastss 0x176c(%rip),%ymm1 # 48f8 <_sk_callback_hsw+0x3fb> + .byte 196,226,125,24,13,200,24,0,0 // vbroadcastss 0x18c8(%rip),%ymm1 # 4a54 <_sk_callback_hsw+0x3fc> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,99,23,0,0 // vpbroadcastd 0x1763(%rip),%ymm1 # 48fc <_sk_callback_hsw+0x3ff> + .byte 196,226,125,88,13,191,24,0,0 // vpbroadcastd 0x18bf(%rip),%ymm1 # 4a58 <_sk_callback_hsw+0x400> .byte 197,229,219,201 // vpand %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,86,23,0,0 // vbroadcastss 0x1756(%rip),%ymm2 # 4900 <_sk_callback_hsw+0x403> + .byte 196,226,125,24,21,178,24,0,0 // vbroadcastss 0x18b2(%rip),%ymm2 # 4a5c <_sk_callback_hsw+0x404> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,88,21,77,23,0,0 // vpbroadcastd 0x174d(%rip),%ymm2 # 4904 <_sk_callback_hsw+0x407> + .byte 196,226,125,88,21,169,24,0,0 // vpbroadcastd 0x18a9(%rip),%ymm2 # 4a60 <_sk_callback_hsw+0x408> .byte 197,229,219,210 // vpand %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,64,23,0,0 // vbroadcastss 0x1740(%rip),%ymm8 # 4908 <_sk_callback_hsw+0x40b> + .byte 196,98,125,24,5,156,24,0,0 // vbroadcastss 0x189c(%rip),%ymm8 # 4a64 <_sk_callback_hsw+0x40c> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,88,5,54,23,0,0 // vpbroadcastd 0x1736(%rip),%ymm8 # 490c <_sk_callback_hsw+0x40f> + .byte 196,98,125,88,5,146,24,0,0 // vpbroadcastd 0x1892(%rip),%ymm8 # 4a68 <_sk_callback_hsw+0x410> .byte 196,193,101,219,216 // vpand %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,40,23,0,0 // vbroadcastss 0x1728(%rip),%ymm8 # 4910 <_sk_callback_hsw+0x413> + .byte 196,98,125,24,5,132,24,0,0 // vbroadcastss 0x1884(%rip),%ymm8 # 4a6c <_sk_callback_hsw+0x414> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -11646,7 +11827,7 @@ FUNCTION(_sk_store_4444_hsw) _sk_store_4444_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,14,23,0,0 // vbroadcastss 0x170e(%rip),%ymm8 # 4914 <_sk_callback_hsw+0x417> + .byte 196,98,125,24,5,106,24,0,0 // vbroadcastss 0x186a(%rip),%ymm8 # 4a70 <_sk_callback_hsw+0x418> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,53,114,241,12 // vpslld $0xc,%ymm9,%ymm9 @@ -11722,14 +11903,14 @@ _sk_load_8888_hsw: .byte 77,133,192 // test %r8,%r8 .byte 117,88 // jne 3351 <_sk_load_8888_hsw+0x6d> .byte 196,193,126,111,25 // vmovdqu (%r9),%ymm3 - .byte 197,229,219,5,186,23,0,0 // vpand 0x17ba(%rip),%ymm3,%ymm0 # 4ac0 <_sk_callback_hsw+0x5c3> + .byte 197,229,219,5,26,25,0,0 // vpand 0x191a(%rip),%ymm3,%ymm0 # 4c20 <_sk_callback_hsw+0x5c8> .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,5,22,0,0 // vbroadcastss 0x1605(%rip),%ymm8 # 4918 <_sk_callback_hsw+0x41b> + .byte 196,98,125,24,5,97,23,0,0 // vbroadcastss 0x1761(%rip),%ymm8 # 4a74 <_sk_callback_hsw+0x41c> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,226,101,0,13,191,23,0,0 // vpshufb 0x17bf(%rip),%ymm3,%ymm1 # 4ae0 <_sk_callback_hsw+0x5e3> + .byte 196,226,101,0,13,31,25,0,0 // vpshufb 0x191f(%rip),%ymm3,%ymm1 # 4c40 <_sk_callback_hsw+0x5e8> .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,226,101,0,21,205,23,0,0 // vpshufb 0x17cd(%rip),%ymm3,%ymm2 # 4b00 <_sk_callback_hsw+0x603> + .byte 196,226,101,0,21,45,25,0,0 // vpshufb 0x192d(%rip),%ymm3,%ymm2 # 4c60 <_sk_callback_hsw+0x608> .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 @@ -11761,14 +11942,14 @@ _sk_gather_8888_hsw: .byte 197,245,254,192 // vpaddd %ymm0,%ymm1,%ymm0 .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 .byte 196,194,117,144,28,128 // vpgatherdd %ymm1,(%r8,%ymm0,4),%ymm3 - .byte 197,229,219,5,123,23,0,0 // vpand 0x177b(%rip),%ymm3,%ymm0 # 4b20 <_sk_callback_hsw+0x623> + .byte 197,229,219,5,219,24,0,0 // vpand 0x18db(%rip),%ymm3,%ymm0 # 4c80 <_sk_callback_hsw+0x628> .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,106,21,0,0 // vbroadcastss 0x156a(%rip),%ymm8 # 491c <_sk_callback_hsw+0x41f> + .byte 196,98,125,24,5,198,22,0,0 // vbroadcastss 0x16c6(%rip),%ymm8 # 4a78 <_sk_callback_hsw+0x420> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,226,101,0,13,128,23,0,0 // vpshufb 0x1780(%rip),%ymm3,%ymm1 # 4b40 <_sk_callback_hsw+0x643> + .byte 196,226,101,0,13,224,24,0,0 // vpshufb 0x18e0(%rip),%ymm3,%ymm1 # 4ca0 <_sk_callback_hsw+0x648> .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,226,101,0,21,142,23,0,0 // vpshufb 0x178e(%rip),%ymm3,%ymm2 # 4b60 <_sk_callback_hsw+0x663> + .byte 196,226,101,0,21,238,24,0,0 // vpshufb 0x18ee(%rip),%ymm3,%ymm2 # 4cc0 <_sk_callback_hsw+0x668> .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 @@ -11785,7 +11966,7 @@ _sk_store_8888_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 .byte 76,3,8 // add (%rax),%r9 - .byte 196,98,125,24,5,26,21,0,0 // vbroadcastss 0x151a(%rip),%ymm8 # 4920 <_sk_callback_hsw+0x423> + .byte 196,98,125,24,5,118,22,0,0 // vbroadcastss 0x1676(%rip),%ymm8 # 4a7c <_sk_callback_hsw+0x424> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,65,116,89,208 // vmulps %ymm8,%ymm1,%ymm10 @@ -11982,7 +12163,7 @@ _sk_load_u16_be_hsw: .byte 197,241,235,192 // vpor %xmm0,%xmm1,%xmm0 .byte 196,226,125,51,192 // vpmovzxwd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,21,17,18,0,0 // vbroadcastss 0x1211(%rip),%ymm10 # 4924 <_sk_callback_hsw+0x427> + .byte 196,98,125,24,21,109,19,0,0 // vbroadcastss 0x136d(%rip),%ymm10 # 4a80 <_sk_callback_hsw+0x428> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,185,109,202 // vpunpckhqdq %xmm2,%xmm8,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -12066,7 +12247,7 @@ _sk_load_rgb_u16_be_hsw: .byte 197,241,235,192 // vpor %xmm0,%xmm1,%xmm0 .byte 196,226,125,51,192 // vpmovzxwd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,21,162,16,0,0 // vbroadcastss 0x10a2(%rip),%ymm10 # 4928 <_sk_callback_hsw+0x42b> + .byte 196,98,125,24,21,254,17,0,0 // vbroadcastss 0x11fe(%rip),%ymm10 # 4a84 <_sk_callback_hsw+0x42c> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,185,109,202 // vpunpckhqdq %xmm2,%xmm8,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -12083,7 +12264,7 @@ _sk_load_rgb_u16_be_hsw: .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,86,16,0,0 // vbroadcastss 0x1056(%rip),%ymm3 # 492c <_sk_callback_hsw+0x42f> + .byte 196,226,125,24,29,178,17,0,0 // vbroadcastss 0x11b2(%rip),%ymm3 # 4a88 <_sk_callback_hsw+0x430> .byte 255,224 // jmpq *%rax .byte 196,193,121,110,4,64 // vmovd (%r8,%rax,2),%xmm0 .byte 196,193,121,196,68,64,4,2 // vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 @@ -12126,7 +12307,7 @@ _sk_store_u16_be_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,189,0,0,0,0 // lea 0x0(,%rdi,4),%rax - .byte 196,98,125,24,5,147,15,0,0 // vbroadcastss 0xf93(%rip),%ymm8 # 4930 <_sk_callback_hsw+0x433> + .byte 196,98,125,24,5,239,16,0,0 // vbroadcastss 0x10ef(%rip),%ymm8 # 4a8c <_sk_callback_hsw+0x434> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,67,125,25,202,1 // vextractf128 $0x1,%ymm9,%xmm10 @@ -12386,11 +12567,11 @@ HIDDEN _sk_luminance_to_alpha_hsw .globl _sk_luminance_to_alpha_hsw FUNCTION(_sk_luminance_to_alpha_hsw) _sk_luminance_to_alpha_hsw: - .byte 196,226,125,24,29,227,11,0,0 // vbroadcastss 0xbe3(%rip),%ymm3 # 4934 <_sk_callback_hsw+0x437> - .byte 196,98,125,24,5,222,11,0,0 // vbroadcastss 0xbde(%rip),%ymm8 # 4938 <_sk_callback_hsw+0x43b> + .byte 196,226,125,24,29,63,13,0,0 // vbroadcastss 0xd3f(%rip),%ymm3 # 4a90 <_sk_callback_hsw+0x438> + .byte 196,98,125,24,5,58,13,0,0 // vbroadcastss 0xd3a(%rip),%ymm8 # 4a94 <_sk_callback_hsw+0x43c> .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 196,226,125,184,203 // vfmadd231ps %ymm3,%ymm0,%ymm1 - .byte 196,226,125,24,29,207,11,0,0 // vbroadcastss 0xbcf(%rip),%ymm3 # 493c <_sk_callback_hsw+0x43f> + .byte 196,226,125,24,29,43,13,0,0 // vbroadcastss 0xd2b(%rip),%ymm3 # 4a98 <_sk_callback_hsw+0x440> .byte 196,226,109,168,217 // vfmadd213ps %ymm1,%ymm2,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -12524,54 +12705,144 @@ _sk_matrix_perspective_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax +HIDDEN _sk_evenly_spaced_gradient_hsw +.globl _sk_evenly_spaced_gradient_hsw +FUNCTION(_sk_evenly_spaced_gradient_hsw) +_sk_evenly_spaced_gradient_hsw: + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 76,139,8 // mov (%rax),%r9 + .byte 76,139,64,8 // mov 0x8(%rax),%r8 + .byte 77,137,202 // mov %r9,%r10 + .byte 73,255,202 // dec %r10 + .byte 120,7 // js 3fa8 <_sk_evenly_spaced_gradient_hsw+0x18> + .byte 196,193,242,42,202 // vcvtsi2ss %r10,%xmm1,%xmm1 + .byte 235,22 // jmp 3fbe <_sk_evenly_spaced_gradient_hsw+0x2e> + .byte 77,137,211 // mov %r10,%r11 + .byte 73,209,235 // shr %r11 + .byte 65,131,226,1 // and $0x1,%r10d + .byte 77,9,218 // or %r11,%r10 + .byte 196,193,242,42,202 // vcvtsi2ss %r10,%xmm1,%xmm1 + .byte 197,242,88,201 // vaddss %xmm1,%xmm1,%xmm1 + .byte 196,226,125,24,201 // vbroadcastss %xmm1,%ymm1 + .byte 197,244,89,200 // vmulps %ymm0,%ymm1,%ymm1 + .byte 197,126,91,217 // vcvttps2dq %ymm1,%ymm11 + .byte 73,131,249,8 // cmp $0x8,%r9 + .byte 119,70 // ja 4017 <_sk_evenly_spaced_gradient_hsw+0x87> + .byte 196,66,37,22,0 // vpermps (%r8),%ymm11,%ymm8 + .byte 76,139,64,40 // mov 0x28(%rax),%r8 + .byte 196,66,37,22,8 // vpermps (%r8),%ymm11,%ymm9 + .byte 76,139,64,16 // mov 0x10(%rax),%r8 + .byte 76,139,72,24 // mov 0x18(%rax),%r9 + .byte 196,194,37,22,8 // vpermps (%r8),%ymm11,%ymm1 + .byte 76,139,64,48 // mov 0x30(%rax),%r8 + .byte 196,66,37,22,16 // vpermps (%r8),%ymm11,%ymm10 + .byte 196,194,37,22,17 // vpermps (%r9),%ymm11,%ymm2 + .byte 76,139,64,56 // mov 0x38(%rax),%r8 + .byte 196,66,37,22,32 // vpermps (%r8),%ymm11,%ymm12 + .byte 76,139,64,32 // mov 0x20(%rax),%r8 + .byte 196,194,37,22,24 // vpermps (%r8),%ymm11,%ymm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 196,98,37,22,40 // vpermps (%rax),%ymm11,%ymm13 + .byte 235,110 // jmp 4085 <_sk_evenly_spaced_gradient_hsw+0xf5> + .byte 196,65,13,118,246 // vpcmpeqd %ymm14,%ymm14,%ymm14 + .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 + .byte 196,2,117,146,4,152 // vgatherdps %ymm1,(%r8,%ymm11,4),%ymm8 + .byte 76,139,64,40 // mov 0x28(%rax),%r8 + .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 + .byte 196,2,117,146,12,152 // vgatherdps %ymm1,(%r8,%ymm11,4),%ymm9 + .byte 76,139,64,16 // mov 0x10(%rax),%r8 + .byte 76,139,72,24 // mov 0x18(%rax),%r9 + .byte 197,237,118,210 // vpcmpeqd %ymm2,%ymm2,%ymm2 + .byte 196,130,109,146,12,152 // vgatherdps %ymm2,(%r8,%ymm11,4),%ymm1 + .byte 76,139,64,48 // mov 0x30(%rax),%r8 + .byte 197,237,118,210 // vpcmpeqd %ymm2,%ymm2,%ymm2 + .byte 196,2,109,146,20,152 // vgatherdps %ymm2,(%r8,%ymm11,4),%ymm10 + .byte 197,229,118,219 // vpcmpeqd %ymm3,%ymm3,%ymm3 + .byte 196,130,101,146,20,153 // vgatherdps %ymm3,(%r9,%ymm11,4),%ymm2 + .byte 76,139,64,56 // mov 0x38(%rax),%r8 + .byte 197,229,118,219 // vpcmpeqd %ymm3,%ymm3,%ymm3 + .byte 196,2,101,146,36,152 // vgatherdps %ymm3,(%r8,%ymm11,4),%ymm12 + .byte 76,139,64,32 // mov 0x20(%rax),%r8 + .byte 196,65,21,118,237 // vpcmpeqd %ymm13,%ymm13,%ymm13 + .byte 196,130,21,146,28,152 // vgatherdps %ymm13,(%r8,%ymm11,4),%ymm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 196,34,13,146,44,152 // vgatherdps %ymm14,(%rax,%ymm11,4),%ymm13 + .byte 196,66,125,168,193 // vfmadd213ps %ymm9,%ymm0,%ymm8 + .byte 196,194,125,168,202 // vfmadd213ps %ymm10,%ymm0,%ymm1 + .byte 196,194,125,168,212 // vfmadd213ps %ymm12,%ymm0,%ymm2 + .byte 196,194,125,168,221 // vfmadd213ps %ymm13,%ymm0,%ymm3 + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 + .byte 255,224 // jmpq *%rax + HIDDEN _sk_gradient_hsw .globl _sk_gradient_hsw FUNCTION(_sk_gradient_hsw) _sk_gradient_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,64,16 // vbroadcastss 0x10(%rax),%ymm8 - .byte 196,98,125,24,88,20 // vbroadcastss 0x14(%rax),%ymm11 - .byte 196,98,125,24,80,24 // vbroadcastss 0x18(%rax),%ymm10 - .byte 196,98,125,24,72,28 // vbroadcastss 0x1c(%rax),%ymm9 .byte 76,139,0 // mov (%rax),%r8 - .byte 77,133,192 // test %r8,%r8 - .byte 15,132,143,0,0,0 // je 4045 <_sk_gradient_hsw+0xb5> - .byte 72,139,64,8 // mov 0x8(%rax),%rax - .byte 72,131,192,32 // add $0x20,%rax - .byte 196,65,28,87,228 // vxorps %ymm12,%ymm12,%ymm12 - .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 - .byte 197,236,87,210 // vxorps %ymm2,%ymm2,%ymm2 - .byte 197,244,87,201 // vxorps %ymm1,%ymm1,%ymm1 - .byte 196,98,125,24,104,224 // vbroadcastss -0x20(%rax),%ymm13 - .byte 196,65,124,194,237,1 // vcmpltps %ymm13,%ymm0,%ymm13 - .byte 196,98,125,24,112,228 // vbroadcastss -0x1c(%rax),%ymm14 - .byte 196,67,13,74,228,208 // vblendvps %ymm13,%ymm12,%ymm14,%ymm12 - .byte 196,98,125,24,112,232 // vbroadcastss -0x18(%rax),%ymm14 - .byte 196,227,13,74,201,208 // vblendvps %ymm13,%ymm1,%ymm14,%ymm1 - .byte 196,98,125,24,112,236 // vbroadcastss -0x14(%rax),%ymm14 - .byte 196,227,13,74,210,208 // vblendvps %ymm13,%ymm2,%ymm14,%ymm2 - .byte 196,98,125,24,112,240 // vbroadcastss -0x10(%rax),%ymm14 - .byte 196,227,13,74,219,208 // vblendvps %ymm13,%ymm3,%ymm14,%ymm3 - .byte 196,98,125,24,112,244 // vbroadcastss -0xc(%rax),%ymm14 - .byte 196,67,13,74,192,208 // vblendvps %ymm13,%ymm8,%ymm14,%ymm8 - .byte 196,98,125,24,112,248 // vbroadcastss -0x8(%rax),%ymm14 - .byte 196,67,13,74,219,208 // vblendvps %ymm13,%ymm11,%ymm14,%ymm11 - .byte 196,98,125,24,112,252 // vbroadcastss -0x4(%rax),%ymm14 - .byte 196,67,13,74,210,208 // vblendvps %ymm13,%ymm10,%ymm14,%ymm10 - .byte 196,98,125,24,48 // vbroadcastss (%rax),%ymm14 - .byte 196,67,13,74,201,208 // vblendvps %ymm13,%ymm9,%ymm14,%ymm9 - .byte 72,131,192,36 // add $0x24,%rax - .byte 73,255,200 // dec %r8 - .byte 117,140 // jne 3fcf <_sk_gradient_hsw+0x3f> - .byte 235,17 // jmp 4056 <_sk_gradient_hsw+0xc6> + .byte 73,131,248,1 // cmp $0x1,%r8 + .byte 15,134,180,0,0,0 // jbe 4164 <_sk_gradient_hsw+0xc3> + .byte 76,139,72,72 // mov 0x48(%rax),%r9 .byte 197,244,87,201 // vxorps %ymm1,%ymm1,%ymm1 - .byte 197,236,87,210 // vxorps %ymm2,%ymm2,%ymm2 - .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 - .byte 196,65,28,87,228 // vxorps %ymm12,%ymm12,%ymm12 - .byte 196,66,125,184,196 // vfmadd231ps %ymm12,%ymm0,%ymm8 + .byte 65,186,1,0,0,0 // mov $0x1,%r10d + .byte 196,226,125,24,21,213,9,0,0 // vbroadcastss 0x9d5(%rip),%ymm2 # 4a9c <_sk_callback_hsw+0x444> + .byte 196,65,53,239,201 // vpxor %ymm9,%ymm9,%ymm9 + .byte 196,130,125,24,28,145 // vbroadcastss (%r9,%r10,4),%ymm3 + .byte 197,228,194,216,2 // vcmpleps %ymm0,%ymm3,%ymm3 + .byte 196,227,117,74,218,48 // vblendvps %ymm3,%ymm2,%ymm1,%ymm3 + .byte 196,65,101,254,201 // vpaddd %ymm9,%ymm3,%ymm9 + .byte 73,255,194 // inc %r10 + .byte 77,57,208 // cmp %r10,%r8 + .byte 117,226 // jne 40cc <_sk_gradient_hsw+0x2b> + .byte 76,139,72,8 // mov 0x8(%rax),%r9 + .byte 73,131,248,8 // cmp $0x8,%r8 + .byte 118,121 // jbe 416d <_sk_gradient_hsw+0xcc> + .byte 196,65,13,118,246 // vpcmpeqd %ymm14,%ymm14,%ymm14 + .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 + .byte 196,2,117,146,4,137 // vgatherdps %ymm1,(%r9,%ymm9,4),%ymm8 + .byte 76,139,64,40 // mov 0x28(%rax),%r8 + .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 + .byte 196,2,117,146,20,136 // vgatherdps %ymm1,(%r8,%ymm9,4),%ymm10 + .byte 76,139,64,16 // mov 0x10(%rax),%r8 + .byte 76,139,72,24 // mov 0x18(%rax),%r9 + .byte 197,237,118,210 // vpcmpeqd %ymm2,%ymm2,%ymm2 + .byte 196,130,109,146,12,136 // vgatherdps %ymm2,(%r8,%ymm9,4),%ymm1 + .byte 76,139,64,48 // mov 0x30(%rax),%r8 + .byte 197,237,118,210 // vpcmpeqd %ymm2,%ymm2,%ymm2 + .byte 196,2,109,146,28,136 // vgatherdps %ymm2,(%r8,%ymm9,4),%ymm11 + .byte 197,229,118,219 // vpcmpeqd %ymm3,%ymm3,%ymm3 + .byte 196,130,101,146,20,137 // vgatherdps %ymm3,(%r9,%ymm9,4),%ymm2 + .byte 76,139,64,56 // mov 0x38(%rax),%r8 + .byte 197,229,118,219 // vpcmpeqd %ymm3,%ymm3,%ymm3 + .byte 196,2,101,146,36,136 // vgatherdps %ymm3,(%r8,%ymm9,4),%ymm12 + .byte 76,139,64,32 // mov 0x20(%rax),%r8 + .byte 196,65,21,118,237 // vpcmpeqd %ymm13,%ymm13,%ymm13 + .byte 196,130,21,146,28,136 // vgatherdps %ymm13,(%r8,%ymm9,4),%ymm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 196,34,13,146,44,136 // vgatherdps %ymm14,(%rax,%ymm9,4),%ymm13 + .byte 235,77 // jmp 41b1 <_sk_gradient_hsw+0x110> + .byte 76,139,72,8 // mov 0x8(%rax),%r9 + .byte 196,65,52,87,201 // vxorps %ymm9,%ymm9,%ymm9 + .byte 196,66,53,22,1 // vpermps (%r9),%ymm9,%ymm8 + .byte 76,139,64,40 // mov 0x28(%rax),%r8 + .byte 196,66,53,22,16 // vpermps (%r8),%ymm9,%ymm10 + .byte 76,139,64,16 // mov 0x10(%rax),%r8 + .byte 76,139,72,24 // mov 0x18(%rax),%r9 + .byte 196,194,53,22,8 // vpermps (%r8),%ymm9,%ymm1 + .byte 76,139,64,48 // mov 0x30(%rax),%r8 + .byte 196,66,53,22,24 // vpermps (%r8),%ymm9,%ymm11 + .byte 196,194,53,22,17 // vpermps (%r9),%ymm9,%ymm2 + .byte 76,139,64,56 // mov 0x38(%rax),%r8 + .byte 196,66,53,22,32 // vpermps (%r8),%ymm9,%ymm12 + .byte 76,139,64,32 // mov 0x20(%rax),%r8 + .byte 196,194,53,22,24 // vpermps (%r8),%ymm9,%ymm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 196,98,53,22,40 // vpermps (%rax),%ymm9,%ymm13 + .byte 196,66,125,168,194 // vfmadd213ps %ymm10,%ymm0,%ymm8 .byte 196,194,125,168,203 // vfmadd213ps %ymm11,%ymm0,%ymm1 - .byte 196,194,125,168,210 // vfmadd213ps %ymm10,%ymm0,%ymm2 - .byte 196,194,125,168,217 // vfmadd213ps %ymm9,%ymm0,%ymm3 + .byte 196,194,125,168,212 // vfmadd213ps %ymm12,%ymm0,%ymm2 + .byte 196,194,125,168,221 // vfmadd213ps %ymm13,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 .byte 255,224 // jmpq *%rax @@ -12610,24 +12881,24 @@ _sk_xy_to_unit_angle_hsw: .byte 196,65,52,95,226 // vmaxps %ymm10,%ymm9,%ymm12 .byte 196,65,36,94,220 // vdivps %ymm12,%ymm11,%ymm11 .byte 196,65,36,89,227 // vmulps %ymm11,%ymm11,%ymm12 - .byte 196,98,125,24,45,79,8,0,0 // vbroadcastss 0x84f(%rip),%ymm13 # 4940 <_sk_callback_hsw+0x443> - .byte 196,98,125,24,53,74,8,0,0 // vbroadcastss 0x84a(%rip),%ymm14 # 4944 <_sk_callback_hsw+0x447> + .byte 196,98,125,24,45,84,8,0,0 // vbroadcastss 0x854(%rip),%ymm13 # 4aa0 <_sk_callback_hsw+0x448> + .byte 196,98,125,24,53,79,8,0,0 // vbroadcastss 0x84f(%rip),%ymm14 # 4aa4 <_sk_callback_hsw+0x44c> .byte 196,66,29,184,245 // vfmadd231ps %ymm13,%ymm12,%ymm14 - .byte 196,98,125,24,45,64,8,0,0 // vbroadcastss 0x840(%rip),%ymm13 # 4948 <_sk_callback_hsw+0x44b> + .byte 196,98,125,24,45,69,8,0,0 // vbroadcastss 0x845(%rip),%ymm13 # 4aa8 <_sk_callback_hsw+0x450> .byte 196,66,29,184,238 // vfmadd231ps %ymm14,%ymm12,%ymm13 - .byte 196,98,125,24,53,54,8,0,0 // vbroadcastss 0x836(%rip),%ymm14 # 494c <_sk_callback_hsw+0x44f> + .byte 196,98,125,24,53,59,8,0,0 // vbroadcastss 0x83b(%rip),%ymm14 # 4aac <_sk_callback_hsw+0x454> .byte 196,66,29,184,245 // vfmadd231ps %ymm13,%ymm12,%ymm14 .byte 196,65,36,89,222 // vmulps %ymm14,%ymm11,%ymm11 .byte 196,65,52,194,202,1 // vcmpltps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,24,21,33,8,0,0 // vbroadcastss 0x821(%rip),%ymm10 # 4950 <_sk_callback_hsw+0x453> + .byte 196,98,125,24,21,38,8,0,0 // vbroadcastss 0x826(%rip),%ymm10 # 4ab0 <_sk_callback_hsw+0x458> .byte 196,65,44,92,211 // vsubps %ymm11,%ymm10,%ymm10 .byte 196,67,37,74,202,144 // vblendvps %ymm9,%ymm10,%ymm11,%ymm9 .byte 196,193,124,194,192,1 // vcmpltps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,21,11,8,0,0 // vbroadcastss 0x80b(%rip),%ymm10 # 4954 <_sk_callback_hsw+0x457> + .byte 196,98,125,24,21,16,8,0,0 // vbroadcastss 0x810(%rip),%ymm10 # 4ab4 <_sk_callback_hsw+0x45c> .byte 196,65,44,92,209 // vsubps %ymm9,%ymm10,%ymm10 .byte 196,195,53,74,194,0 // vblendvps %ymm0,%ymm10,%ymm9,%ymm0 .byte 196,65,116,194,200,1 // vcmpltps %ymm8,%ymm1,%ymm9 - .byte 196,98,125,24,21,245,7,0,0 // vbroadcastss 0x7f5(%rip),%ymm10 # 4958 <_sk_callback_hsw+0x45b> + .byte 196,98,125,24,21,250,7,0,0 // vbroadcastss 0x7fa(%rip),%ymm10 # 4ab8 <_sk_callback_hsw+0x460> .byte 197,44,92,208 // vsubps %ymm0,%ymm10,%ymm10 .byte 196,195,125,74,194,144 // vblendvps %ymm9,%ymm10,%ymm0,%ymm0 .byte 196,65,124,194,200,3 // vcmpunordps %ymm8,%ymm0,%ymm9 @@ -12651,7 +12922,7 @@ HIDDEN _sk_save_xy_hsw FUNCTION(_sk_save_xy_hsw) _sk_save_xy_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,190,7,0,0 // vbroadcastss 0x7be(%rip),%ymm8 # 495c <_sk_callback_hsw+0x45f> + .byte 196,98,125,24,5,195,7,0,0 // vbroadcastss 0x7c3(%rip),%ymm8 # 4abc <_sk_callback_hsw+0x464> .byte 196,65,124,88,200 // vaddps %ymm8,%ymm0,%ymm9 .byte 196,67,125,8,209,1 // vroundps $0x1,%ymm9,%ymm10 .byte 196,65,52,92,202 // vsubps %ymm10,%ymm9,%ymm9 @@ -12685,9 +12956,9 @@ HIDDEN _sk_bilinear_nx_hsw FUNCTION(_sk_bilinear_nx_hsw) _sk_bilinear_nx_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,82,7,0,0 // vbroadcastss 0x752(%rip),%ymm0 # 4960 <_sk_callback_hsw+0x463> + .byte 196,226,125,24,5,87,7,0,0 // vbroadcastss 0x757(%rip),%ymm0 # 4ac0 <_sk_callback_hsw+0x468> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,73,7,0,0 // vbroadcastss 0x749(%rip),%ymm8 # 4964 <_sk_callback_hsw+0x467> + .byte 196,98,125,24,5,78,7,0,0 // vbroadcastss 0x74e(%rip),%ymm8 # 4ac4 <_sk_callback_hsw+0x46c> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -12698,7 +12969,7 @@ HIDDEN _sk_bilinear_px_hsw FUNCTION(_sk_bilinear_px_hsw) _sk_bilinear_px_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,49,7,0,0 // vbroadcastss 0x731(%rip),%ymm0 # 4968 <_sk_callback_hsw+0x46b> + .byte 196,226,125,24,5,54,7,0,0 // vbroadcastss 0x736(%rip),%ymm0 # 4ac8 <_sk_callback_hsw+0x470> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -12710,9 +12981,9 @@ HIDDEN _sk_bilinear_ny_hsw FUNCTION(_sk_bilinear_ny_hsw) _sk_bilinear_ny_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,21,7,0,0 // vbroadcastss 0x715(%rip),%ymm1 # 496c <_sk_callback_hsw+0x46f> + .byte 196,226,125,24,13,26,7,0,0 // vbroadcastss 0x71a(%rip),%ymm1 # 4acc <_sk_callback_hsw+0x474> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,11,7,0,0 // vbroadcastss 0x70b(%rip),%ymm8 # 4970 <_sk_callback_hsw+0x473> + .byte 196,98,125,24,5,16,7,0,0 // vbroadcastss 0x710(%rip),%ymm8 # 4ad0 <_sk_callback_hsw+0x478> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -12723,7 +12994,7 @@ HIDDEN _sk_bilinear_py_hsw FUNCTION(_sk_bilinear_py_hsw) _sk_bilinear_py_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,243,6,0,0 // vbroadcastss 0x6f3(%rip),%ymm1 # 4974 <_sk_callback_hsw+0x477> + .byte 196,226,125,24,13,248,6,0,0 // vbroadcastss 0x6f8(%rip),%ymm1 # 4ad4 <_sk_callback_hsw+0x47c> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -12735,13 +13006,13 @@ HIDDEN _sk_bicubic_n3x_hsw FUNCTION(_sk_bicubic_n3x_hsw) _sk_bicubic_n3x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,214,6,0,0 // vbroadcastss 0x6d6(%rip),%ymm0 # 4978 <_sk_callback_hsw+0x47b> + .byte 196,226,125,24,5,219,6,0,0 // vbroadcastss 0x6db(%rip),%ymm0 # 4ad8 <_sk_callback_hsw+0x480> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,205,6,0,0 // vbroadcastss 0x6cd(%rip),%ymm8 # 497c <_sk_callback_hsw+0x47f> + .byte 196,98,125,24,5,210,6,0,0 // vbroadcastss 0x6d2(%rip),%ymm8 # 4adc <_sk_callback_hsw+0x484> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,190,6,0,0 // vbroadcastss 0x6be(%rip),%ymm10 # 4980 <_sk_callback_hsw+0x483> - .byte 196,98,125,24,29,185,6,0,0 // vbroadcastss 0x6b9(%rip),%ymm11 # 4984 <_sk_callback_hsw+0x487> + .byte 196,98,125,24,21,195,6,0,0 // vbroadcastss 0x6c3(%rip),%ymm10 # 4ae0 <_sk_callback_hsw+0x488> + .byte 196,98,125,24,29,190,6,0,0 // vbroadcastss 0x6be(%rip),%ymm11 # 4ae4 <_sk_callback_hsw+0x48c> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,36,89,193 // vmulps %ymm9,%ymm11,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -12753,16 +13024,16 @@ HIDDEN _sk_bicubic_n1x_hsw FUNCTION(_sk_bicubic_n1x_hsw) _sk_bicubic_n1x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,156,6,0,0 // vbroadcastss 0x69c(%rip),%ymm0 # 4988 <_sk_callback_hsw+0x48b> + .byte 196,226,125,24,5,161,6,0,0 // vbroadcastss 0x6a1(%rip),%ymm0 # 4ae8 <_sk_callback_hsw+0x490> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,147,6,0,0 // vbroadcastss 0x693(%rip),%ymm8 # 498c <_sk_callback_hsw+0x48f> + .byte 196,98,125,24,5,152,6,0,0 // vbroadcastss 0x698(%rip),%ymm8 # 4aec <_sk_callback_hsw+0x494> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,137,6,0,0 // vbroadcastss 0x689(%rip),%ymm9 # 4990 <_sk_callback_hsw+0x493> - .byte 196,98,125,24,21,132,6,0,0 // vbroadcastss 0x684(%rip),%ymm10 # 4994 <_sk_callback_hsw+0x497> + .byte 196,98,125,24,13,142,6,0,0 // vbroadcastss 0x68e(%rip),%ymm9 # 4af0 <_sk_callback_hsw+0x498> + .byte 196,98,125,24,21,137,6,0,0 // vbroadcastss 0x689(%rip),%ymm10 # 4af4 <_sk_callback_hsw+0x49c> .byte 196,66,61,168,209 // vfmadd213ps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,13,122,6,0,0 // vbroadcastss 0x67a(%rip),%ymm9 # 4998 <_sk_callback_hsw+0x49b> + .byte 196,98,125,24,13,127,6,0,0 // vbroadcastss 0x67f(%rip),%ymm9 # 4af8 <_sk_callback_hsw+0x4a0> .byte 196,66,61,184,202 // vfmadd231ps %ymm10,%ymm8,%ymm9 - .byte 196,98,125,24,21,112,6,0,0 // vbroadcastss 0x670(%rip),%ymm10 # 499c <_sk_callback_hsw+0x49f> + .byte 196,98,125,24,21,117,6,0,0 // vbroadcastss 0x675(%rip),%ymm10 # 4afc <_sk_callback_hsw+0x4a4> .byte 196,66,61,184,209 // vfmadd231ps %ymm9,%ymm8,%ymm10 .byte 197,124,17,144,128,0,0,0 // vmovups %ymm10,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -12773,14 +13044,14 @@ HIDDEN _sk_bicubic_p1x_hsw FUNCTION(_sk_bicubic_p1x_hsw) _sk_bicubic_p1x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,88,6,0,0 // vbroadcastss 0x658(%rip),%ymm8 # 49a0 <_sk_callback_hsw+0x4a3> + .byte 196,98,125,24,5,93,6,0,0 // vbroadcastss 0x65d(%rip),%ymm8 # 4b00 <_sk_callback_hsw+0x4a8> .byte 197,188,88,0 // vaddps (%rax),%ymm8,%ymm0 .byte 197,124,16,72,64 // vmovups 0x40(%rax),%ymm9 - .byte 196,98,125,24,21,74,6,0,0 // vbroadcastss 0x64a(%rip),%ymm10 # 49a4 <_sk_callback_hsw+0x4a7> - .byte 196,98,125,24,29,69,6,0,0 // vbroadcastss 0x645(%rip),%ymm11 # 49a8 <_sk_callback_hsw+0x4ab> + .byte 196,98,125,24,21,79,6,0,0 // vbroadcastss 0x64f(%rip),%ymm10 # 4b04 <_sk_callback_hsw+0x4ac> + .byte 196,98,125,24,29,74,6,0,0 // vbroadcastss 0x64a(%rip),%ymm11 # 4b08 <_sk_callback_hsw+0x4b0> .byte 196,66,53,168,218 // vfmadd213ps %ymm10,%ymm9,%ymm11 .byte 196,66,53,168,216 // vfmadd213ps %ymm8,%ymm9,%ymm11 - .byte 196,98,125,24,5,54,6,0,0 // vbroadcastss 0x636(%rip),%ymm8 # 49ac <_sk_callback_hsw+0x4af> + .byte 196,98,125,24,5,59,6,0,0 // vbroadcastss 0x63b(%rip),%ymm8 # 4b0c <_sk_callback_hsw+0x4b4> .byte 196,66,53,184,195 // vfmadd231ps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -12791,12 +13062,12 @@ HIDDEN _sk_bicubic_p3x_hsw FUNCTION(_sk_bicubic_p3x_hsw) _sk_bicubic_p3x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,30,6,0,0 // vbroadcastss 0x61e(%rip),%ymm0 # 49b0 <_sk_callback_hsw+0x4b3> + .byte 196,226,125,24,5,35,6,0,0 // vbroadcastss 0x623(%rip),%ymm0 # 4b10 <_sk_callback_hsw+0x4b8> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,11,6,0,0 // vbroadcastss 0x60b(%rip),%ymm10 # 49b4 <_sk_callback_hsw+0x4b7> - .byte 196,98,125,24,29,6,6,0,0 // vbroadcastss 0x606(%rip),%ymm11 # 49b8 <_sk_callback_hsw+0x4bb> + .byte 196,98,125,24,21,16,6,0,0 // vbroadcastss 0x610(%rip),%ymm10 # 4b14 <_sk_callback_hsw+0x4bc> + .byte 196,98,125,24,29,11,6,0,0 // vbroadcastss 0x60b(%rip),%ymm11 # 4b18 <_sk_callback_hsw+0x4c0> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,52,89,195 // vmulps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -12808,13 +13079,13 @@ HIDDEN _sk_bicubic_n3y_hsw FUNCTION(_sk_bicubic_n3y_hsw) _sk_bicubic_n3y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,233,5,0,0 // vbroadcastss 0x5e9(%rip),%ymm1 # 49bc <_sk_callback_hsw+0x4bf> + .byte 196,226,125,24,13,238,5,0,0 // vbroadcastss 0x5ee(%rip),%ymm1 # 4b1c <_sk_callback_hsw+0x4c4> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,223,5,0,0 // vbroadcastss 0x5df(%rip),%ymm8 # 49c0 <_sk_callback_hsw+0x4c3> + .byte 196,98,125,24,5,228,5,0,0 // vbroadcastss 0x5e4(%rip),%ymm8 # 4b20 <_sk_callback_hsw+0x4c8> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,208,5,0,0 // vbroadcastss 0x5d0(%rip),%ymm10 # 49c4 <_sk_callback_hsw+0x4c7> - .byte 196,98,125,24,29,203,5,0,0 // vbroadcastss 0x5cb(%rip),%ymm11 # 49c8 <_sk_callback_hsw+0x4cb> + .byte 196,98,125,24,21,213,5,0,0 // vbroadcastss 0x5d5(%rip),%ymm10 # 4b24 <_sk_callback_hsw+0x4cc> + .byte 196,98,125,24,29,208,5,0,0 // vbroadcastss 0x5d0(%rip),%ymm11 # 4b28 <_sk_callback_hsw+0x4d0> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,36,89,193 // vmulps %ymm9,%ymm11,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -12826,16 +13097,16 @@ HIDDEN _sk_bicubic_n1y_hsw FUNCTION(_sk_bicubic_n1y_hsw) _sk_bicubic_n1y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,174,5,0,0 // vbroadcastss 0x5ae(%rip),%ymm1 # 49cc <_sk_callback_hsw+0x4cf> + .byte 196,226,125,24,13,179,5,0,0 // vbroadcastss 0x5b3(%rip),%ymm1 # 4b2c <_sk_callback_hsw+0x4d4> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,164,5,0,0 // vbroadcastss 0x5a4(%rip),%ymm8 # 49d0 <_sk_callback_hsw+0x4d3> + .byte 196,98,125,24,5,169,5,0,0 // vbroadcastss 0x5a9(%rip),%ymm8 # 4b30 <_sk_callback_hsw+0x4d8> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,154,5,0,0 // vbroadcastss 0x59a(%rip),%ymm9 # 49d4 <_sk_callback_hsw+0x4d7> - .byte 196,98,125,24,21,149,5,0,0 // vbroadcastss 0x595(%rip),%ymm10 # 49d8 <_sk_callback_hsw+0x4db> + .byte 196,98,125,24,13,159,5,0,0 // vbroadcastss 0x59f(%rip),%ymm9 # 4b34 <_sk_callback_hsw+0x4dc> + .byte 196,98,125,24,21,154,5,0,0 // vbroadcastss 0x59a(%rip),%ymm10 # 4b38 <_sk_callback_hsw+0x4e0> .byte 196,66,61,168,209 // vfmadd213ps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,13,139,5,0,0 // vbroadcastss 0x58b(%rip),%ymm9 # 49dc <_sk_callback_hsw+0x4df> + .byte 196,98,125,24,13,144,5,0,0 // vbroadcastss 0x590(%rip),%ymm9 # 4b3c <_sk_callback_hsw+0x4e4> .byte 196,66,61,184,202 // vfmadd231ps %ymm10,%ymm8,%ymm9 - .byte 196,98,125,24,21,129,5,0,0 // vbroadcastss 0x581(%rip),%ymm10 # 49e0 <_sk_callback_hsw+0x4e3> + .byte 196,98,125,24,21,134,5,0,0 // vbroadcastss 0x586(%rip),%ymm10 # 4b40 <_sk_callback_hsw+0x4e8> .byte 196,66,61,184,209 // vfmadd231ps %ymm9,%ymm8,%ymm10 .byte 197,124,17,144,160,0,0,0 // vmovups %ymm10,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -12846,14 +13117,14 @@ HIDDEN _sk_bicubic_p1y_hsw FUNCTION(_sk_bicubic_p1y_hsw) _sk_bicubic_p1y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,105,5,0,0 // vbroadcastss 0x569(%rip),%ymm8 # 49e4 <_sk_callback_hsw+0x4e7> + .byte 196,98,125,24,5,110,5,0,0 // vbroadcastss 0x56e(%rip),%ymm8 # 4b44 <_sk_callback_hsw+0x4ec> .byte 197,188,88,72,32 // vaddps 0x20(%rax),%ymm8,%ymm1 .byte 197,124,16,72,96 // vmovups 0x60(%rax),%ymm9 - .byte 196,98,125,24,21,90,5,0,0 // vbroadcastss 0x55a(%rip),%ymm10 # 49e8 <_sk_callback_hsw+0x4eb> - .byte 196,98,125,24,29,85,5,0,0 // vbroadcastss 0x555(%rip),%ymm11 # 49ec <_sk_callback_hsw+0x4ef> + .byte 196,98,125,24,21,95,5,0,0 // vbroadcastss 0x55f(%rip),%ymm10 # 4b48 <_sk_callback_hsw+0x4f0> + .byte 196,98,125,24,29,90,5,0,0 // vbroadcastss 0x55a(%rip),%ymm11 # 4b4c <_sk_callback_hsw+0x4f4> .byte 196,66,53,168,218 // vfmadd213ps %ymm10,%ymm9,%ymm11 .byte 196,66,53,168,216 // vfmadd213ps %ymm8,%ymm9,%ymm11 - .byte 196,98,125,24,5,70,5,0,0 // vbroadcastss 0x546(%rip),%ymm8 # 49f0 <_sk_callback_hsw+0x4f3> + .byte 196,98,125,24,5,75,5,0,0 // vbroadcastss 0x54b(%rip),%ymm8 # 4b50 <_sk_callback_hsw+0x4f8> .byte 196,66,53,184,195 // vfmadd231ps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -12864,12 +13135,12 @@ HIDDEN _sk_bicubic_p3y_hsw FUNCTION(_sk_bicubic_p3y_hsw) _sk_bicubic_p3y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,46,5,0,0 // vbroadcastss 0x52e(%rip),%ymm1 # 49f4 <_sk_callback_hsw+0x4f7> + .byte 196,226,125,24,13,51,5,0,0 // vbroadcastss 0x533(%rip),%ymm1 # 4b54 <_sk_callback_hsw+0x4fc> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,26,5,0,0 // vbroadcastss 0x51a(%rip),%ymm10 # 49f8 <_sk_callback_hsw+0x4fb> - .byte 196,98,125,24,29,21,5,0,0 // vbroadcastss 0x515(%rip),%ymm11 # 49fc <_sk_callback_hsw+0x4ff> + .byte 196,98,125,24,21,31,5,0,0 // vbroadcastss 0x51f(%rip),%ymm10 # 4b58 <_sk_callback_hsw+0x500> + .byte 196,98,125,24,29,26,5,0,0 // vbroadcastss 0x51a(%rip),%ymm11 # 4b5c <_sk_callback_hsw+0x504> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,52,89,195 // vmulps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -12993,25 +13264,25 @@ BALIGN4 .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 46d5 <.literal4+0xb1> + .byte 71,225,61 // rex.RXB loope 4831 <.literal4+0xb1> .byte 0,0 // add %al,(%rax) .byte 128,63,154 // cmpb $0x9a,(%rdi) .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 46e5 <.literal4+0xc1> + .byte 71,225,61 // rex.RXB loope 4841 <.literal4+0xc1> .byte 0,0 // add %al,(%rax) .byte 128,63,154 // cmpb $0x9a,(%rdi) .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 46f5 <.literal4+0xd1> + .byte 71,225,61 // rex.RXB loope 4851 <.literal4+0xd1> .byte 0,0 // add %al,(%rax) .byte 128,63,154 // cmpb $0x9a,(%rdi) .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 4705 <.literal4+0xe1> + .byte 71,225,61 // rex.RXB loope 4861 <.literal4+0xe1> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -13061,7 +13332,7 @@ BALIGN4 .byte 190,129,128,128,59 // mov $0x3b808081,%esi .byte 129,128,128,59,0,248,0,0,8,33 // addl $0x21080000,-0x7ffc480(%rax) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4755 <.literal4+0x131> + .byte 224,7 // loopne 48b1 <.literal4+0x131> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -13077,10 +13348,10 @@ BALIGN4 .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) .byte 0,52,255 // add %dh,(%rdi,%rdi,8) .byte 255 // (bad) - .byte 127,0 // jg 477c <.literal4+0x158> + .byte 127,0 // jg 48d8 <.literal4+0x158> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 47f5 <.literal4+0x1d1> + .byte 119,115 // ja 4951 <.literal4+0x1d1> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -13094,10 +13365,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 47b0 <.literal4+0x18c> + .byte 127,0 // jg 490c <.literal4+0x18c> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4829 <.literal4+0x205> + .byte 119,115 // ja 4985 <.literal4+0x205> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -13111,10 +13382,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 47e4 <.literal4+0x1c0> + .byte 127,0 // jg 4940 <.literal4+0x1c0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 485d <.literal4+0x239> + .byte 119,115 // ja 49b9 <.literal4+0x239> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -13128,10 +13399,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4818 <.literal4+0x1f4> + .byte 127,0 // jg 4974 <.literal4+0x1f4> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4891 <.literal4+0x26d> + .byte 119,115 // ja 49ed <.literal4+0x26d> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -13144,7 +13415,7 @@ BALIGN4 .byte 0,75,0 // add %cl,0x0(%rbx) .byte 0,128,63,0,0,200 // add %al,-0x37ffffc1(%rax) .byte 66,0,0 // rex.X add %al,(%rax) - .byte 127,67 // jg 488f <.literal4+0x26b> + .byte 127,67 // jg 49eb <.literal4+0x26b> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -13156,10 +13427,10 @@ BALIGN4 .byte 190,80,128,3,62 // mov $0x3e038050,%esi .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 48af <.literal4+0x28b> + .byte 118,63 // jbe 4a0b <.literal4+0x28b> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 48c3 <.literal4+0x29f> + .byte 127,67 // jg 4a1f <.literal4+0x29f> .byte 129,128,128,59,0,0,128,63,129,128 // addl $0x80813f80,0x3b80(%rax) .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,128,63,129,128,128 // add %al,-0x7f7f7ec1(%rax) @@ -13168,7 +13439,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 48a5 <.literal4+0x281> + .byte 224,7 // loopne 4a01 <.literal4+0x281> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -13180,7 +13451,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 48c1 <.literal4+0x29d> + .byte 224,7 // loopne 4a1d <.literal4+0x29d> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -13191,7 +13462,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 4916 <.literal4+0x2f2> + .byte 124,66 // jl 4a72 <.literal4+0x2f2> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 137,136,136,55,0,15 // mov %ecx,0xf003788(%rax) @@ -13209,9 +13480,9 @@ BALIGN4 .byte 137,136,136,59,15,0 // mov %ecx,0xf3b88(%rax) .byte 0,0 // add %al,(%rax) .byte 137,136,136,61,0,0 // mov %ecx,0x3d88(%rax) - .byte 112,65 // jo 4959 <.literal4+0x335> + .byte 112,65 // jo 4ab5 <.literal4+0x335> .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 4967 <.literal4+0x343> + .byte 127,67 // jg 4ac3 <.literal4+0x343> .byte 128,0,128 // addb $0x80,(%rax) .byte 55 // (bad) .byte 128,0,128 // addb $0x80,(%rax) @@ -13219,7 +13490,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 255 // (bad) - .byte 127,71 // jg 497b <.literal4+0x357> + .byte 127,71 // jg 4ad7 <.literal4+0x357> .byte 208 // (bad) .byte 179,89 // mov $0x59,%bl .byte 62,89 // ds pop %rcx @@ -13227,9 +13498,12 @@ BALIGN4 .byte 55 // (bad) .byte 63 // (bad) .byte 152 // cwtl - .byte 221,147,61,111,43,231 // fstl -0x18d490c3(%rbx) - .byte 187,159,215,202,60 // mov $0x3ccad79f,%ebx - .byte 212 // (bad) + .byte 221,147,61,1,0,0 // fstl 0x13d(%rbx) + .byte 0,111,43 // add %ch,0x2b(%rdi) + .byte 231,187 // out %eax,$0xbb + .byte 159 // lahf + .byte 215 // xlat %ds:(%rbx) + .byte 202,60,212 // lret $0xd43c .byte 100,84 // fs push %rsp .byte 189,169,240,34,62 // mov $0x3e22f0a9,%ebp .byte 0,0 // add %al,(%rax) @@ -13316,16 +13590,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004a28 <_sk_callback_hsw+0xa00052b> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004b88 <_sk_callback_hsw+0xa000530> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004a30 <_sk_callback_hsw+0x12000533> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004b90 <_sk_callback_hsw+0x12000538> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004a38 <_sk_callback_hsw+0x1a00053b> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004b98 <_sk_callback_hsw+0x1a000540> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004a40 <_sk_callback_hsw+0x3000543> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004ba0 <_sk_callback_hsw+0x3000548> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -13368,16 +13642,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004a88 <_sk_callback_hsw+0xa00058b> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004be8 <_sk_callback_hsw+0xa000590> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004a90 <_sk_callback_hsw+0x12000593> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004bf0 <_sk_callback_hsw+0x12000598> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004a98 <_sk_callback_hsw+0x1a00059b> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004bf8 <_sk_callback_hsw+0x1a0005a0> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004aa0 <_sk_callback_hsw+0x30005a3> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004c00 <_sk_callback_hsw+0x30005a8> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -13420,16 +13694,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004ae8 <_sk_callback_hsw+0xa0005eb> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004c48 <_sk_callback_hsw+0xa0005f0> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004af0 <_sk_callback_hsw+0x120005f3> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004c50 <_sk_callback_hsw+0x120005f8> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004af8 <_sk_callback_hsw+0x1a0005fb> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004c58 <_sk_callback_hsw+0x1a000600> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004b00 <_sk_callback_hsw+0x3000603> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004c60 <_sk_callback_hsw+0x3000608> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -13472,16 +13746,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004b48 <_sk_callback_hsw+0xa00064b> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004ca8 <_sk_callback_hsw+0xa000650> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004b50 <_sk_callback_hsw+0x12000653> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004cb0 <_sk_callback_hsw+0x12000658> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004b58 <_sk_callback_hsw+0x1a00065b> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004cb8 <_sk_callback_hsw+0x1a000660> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004b60 <_sk_callback_hsw+0x3000663> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004cc0 <_sk_callback_hsw+0x3000668> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -13602,14 +13876,14 @@ _sk_seed_shader_avx: .byte 197,249,112,192,0 // vpshufd $0x0,%xmm0,%xmm0 .byte 196,227,125,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,191,92,0,0 // vbroadcastss 0x5cbf(%rip),%ymm1 # 5d88 <_sk_callback_avx+0x128> + .byte 196,226,125,24,13,167,98,0,0 // vbroadcastss 0x62a7(%rip),%ymm1 # 6370 <_sk_callback_avx+0x126> .byte 197,252,88,193 // vaddps %ymm1,%ymm0,%ymm0 .byte 197,252,88,2 // vaddps (%rdx),%ymm0,%ymm0 .byte 196,226,125,24,16 // vbroadcastss (%rax),%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 197,236,88,201 // vaddps %ymm1,%ymm2,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,21,163,92,0,0 // vbroadcastss 0x5ca3(%rip),%ymm2 # 5d8c <_sk_callback_avx+0x12c> + .byte 196,226,125,24,21,139,98,0,0 // vbroadcastss 0x628b(%rip),%ymm2 # 6374 <_sk_callback_avx+0x12a> .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 .byte 197,220,87,228 // vxorps %ymm4,%ymm4,%ymm4 .byte 197,212,87,237 // vxorps %ymm5,%ymm5,%ymm5 @@ -13631,7 +13905,7 @@ _sk_dither_avx: .byte 76,139,0 // mov (%rax),%r8 .byte 196,66,125,24,8 // vbroadcastss (%r8),%ymm9 .byte 196,65,60,87,209 // vxorps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,29,91,92,0,0 // vbroadcastss 0x5c5b(%rip),%ymm11 # 5d90 <_sk_callback_avx+0x130> + .byte 196,98,125,24,29,67,98,0,0 // vbroadcastss 0x6243(%rip),%ymm11 # 6378 <_sk_callback_avx+0x12e> .byte 196,65,44,84,203 // vandps %ymm11,%ymm10,%ymm9 .byte 196,193,25,114,241,5 // vpslld $0x5,%xmm9,%xmm12 .byte 196,67,125,25,201,1 // vextractf128 $0x1,%ymm9,%xmm9 @@ -13642,8 +13916,8 @@ _sk_dither_avx: .byte 196,67,125,25,219,1 // vextractf128 $0x1,%ymm11,%xmm11 .byte 196,193,33,114,243,4 // vpslld $0x4,%xmm11,%xmm11 .byte 196,67,29,24,219,1 // vinsertf128 $0x1,%xmm11,%ymm12,%ymm11 - .byte 196,98,125,24,37,28,92,0,0 // vbroadcastss 0x5c1c(%rip),%ymm12 # 5d94 <_sk_callback_avx+0x134> - .byte 196,98,125,24,45,23,92,0,0 // vbroadcastss 0x5c17(%rip),%ymm13 # 5d98 <_sk_callback_avx+0x138> + .byte 196,98,125,24,37,4,98,0,0 // vbroadcastss 0x6204(%rip),%ymm12 # 637c <_sk_callback_avx+0x132> + .byte 196,98,125,24,45,255,97,0,0 // vbroadcastss 0x61ff(%rip),%ymm13 # 6380 <_sk_callback_avx+0x136> .byte 196,65,44,84,245 // vandps %ymm13,%ymm10,%ymm14 .byte 196,193,1,114,246,2 // vpslld $0x2,%xmm14,%xmm15 .byte 196,67,125,25,246,1 // vextractf128 $0x1,%ymm14,%xmm14 @@ -13670,9 +13944,9 @@ _sk_dither_avx: .byte 196,65,60,86,193 // vorps %ymm9,%ymm8,%ymm8 .byte 196,65,60,86,194 // vorps %ymm10,%ymm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,130,91,0,0 // vbroadcastss 0x5b82(%rip),%ymm9 # 5d9c <_sk_callback_avx+0x13c> + .byte 196,98,125,24,13,106,97,0,0 // vbroadcastss 0x616a(%rip),%ymm9 # 6384 <_sk_callback_avx+0x13a> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,120,91,0,0 // vbroadcastss 0x5b78(%rip),%ymm9 # 5da0 <_sk_callback_avx+0x140> + .byte 196,98,125,24,13,96,97,0,0 // vbroadcastss 0x6160(%rip),%ymm9 # 6388 <_sk_callback_avx+0x13e> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 196,98,125,24,72,8 // vbroadcastss 0x8(%rax),%ymm9 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 @@ -13734,7 +14008,7 @@ HIDDEN _sk_srcatop_avx FUNCTION(_sk_srcatop_avx) _sk_srcatop_avx: .byte 197,252,89,199 // vmulps %ymm7,%ymm0,%ymm0 - .byte 196,98,125,24,5,236,90,0,0 // vbroadcastss 0x5aec(%rip),%ymm8 # 5da4 <_sk_callback_avx+0x144> + .byte 196,98,125,24,5,212,96,0,0 // vbroadcastss 0x60d4(%rip),%ymm8 # 638c <_sk_callback_avx+0x142> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,204 // vmulps %ymm4,%ymm8,%ymm9 .byte 197,180,88,192 // vaddps %ymm0,%ymm9,%ymm0 @@ -13755,7 +14029,7 @@ HIDDEN _sk_dstatop_avx FUNCTION(_sk_dstatop_avx) _sk_dstatop_avx: .byte 197,100,89,196 // vmulps %ymm4,%ymm3,%ymm8 - .byte 196,98,125,24,13,174,90,0,0 // vbroadcastss 0x5aae(%rip),%ymm9 # 5da8 <_sk_callback_avx+0x148> + .byte 196,98,125,24,13,150,96,0,0 // vbroadcastss 0x6096(%rip),%ymm9 # 6390 <_sk_callback_avx+0x146> .byte 197,52,92,207 // vsubps %ymm7,%ymm9,%ymm9 .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 .byte 197,188,88,192 // vaddps %ymm0,%ymm8,%ymm0 @@ -13797,7 +14071,7 @@ HIDDEN _sk_srcout_avx .globl _sk_srcout_avx FUNCTION(_sk_srcout_avx) _sk_srcout_avx: - .byte 196,98,125,24,5,77,90,0,0 // vbroadcastss 0x5a4d(%rip),%ymm8 # 5dac <_sk_callback_avx+0x14c> + .byte 196,98,125,24,5,53,96,0,0 // vbroadcastss 0x6035(%rip),%ymm8 # 6394 <_sk_callback_avx+0x14a> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -13810,7 +14084,7 @@ HIDDEN _sk_dstout_avx .globl _sk_dstout_avx FUNCTION(_sk_dstout_avx) _sk_dstout_avx: - .byte 196,226,125,24,5,48,90,0,0 // vbroadcastss 0x5a30(%rip),%ymm0 # 5db0 <_sk_callback_avx+0x150> + .byte 196,226,125,24,5,24,96,0,0 // vbroadcastss 0x6018(%rip),%ymm0 # 6398 <_sk_callback_avx+0x14e> .byte 197,252,92,219 // vsubps %ymm3,%ymm0,%ymm3 .byte 197,228,89,196 // vmulps %ymm4,%ymm3,%ymm0 .byte 197,228,89,205 // vmulps %ymm5,%ymm3,%ymm1 @@ -13823,7 +14097,7 @@ HIDDEN _sk_srcover_avx .globl _sk_srcover_avx FUNCTION(_sk_srcover_avx) _sk_srcover_avx: - .byte 196,98,125,24,5,19,90,0,0 // vbroadcastss 0x5a13(%rip),%ymm8 # 5db4 <_sk_callback_avx+0x154> + .byte 196,98,125,24,5,251,95,0,0 // vbroadcastss 0x5ffb(%rip),%ymm8 # 639c <_sk_callback_avx+0x152> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,204 // vmulps %ymm4,%ymm8,%ymm9 .byte 197,180,88,192 // vaddps %ymm0,%ymm9,%ymm0 @@ -13840,7 +14114,7 @@ HIDDEN _sk_dstover_avx .globl _sk_dstover_avx FUNCTION(_sk_dstover_avx) _sk_dstover_avx: - .byte 196,98,125,24,5,230,89,0,0 // vbroadcastss 0x59e6(%rip),%ymm8 # 5db8 <_sk_callback_avx+0x158> + .byte 196,98,125,24,5,206,95,0,0 // vbroadcastss 0x5fce(%rip),%ymm8 # 63a0 <_sk_callback_avx+0x156> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,252,88,196 // vaddps %ymm4,%ymm0,%ymm0 @@ -13868,7 +14142,7 @@ HIDDEN _sk_multiply_avx .globl _sk_multiply_avx FUNCTION(_sk_multiply_avx) _sk_multiply_avx: - .byte 196,98,125,24,5,165,89,0,0 // vbroadcastss 0x59a5(%rip),%ymm8 # 5dbc <_sk_callback_avx+0x15c> + .byte 196,98,125,24,5,141,95,0,0 // vbroadcastss 0x5f8d(%rip),%ymm8 # 63a4 <_sk_callback_avx+0x15a> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,208 // vmulps %ymm0,%ymm9,%ymm10 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -13928,7 +14202,7 @@ HIDDEN _sk_xor__avx .globl _sk_xor__avx FUNCTION(_sk_xor__avx) _sk_xor__avx: - .byte 196,98,125,24,5,244,88,0,0 // vbroadcastss 0x58f4(%rip),%ymm8 # 5dc0 <_sk_callback_avx+0x160> + .byte 196,98,125,24,5,220,94,0,0 // vbroadcastss 0x5edc(%rip),%ymm8 # 63a8 <_sk_callback_avx+0x15e> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -13965,7 +14239,7 @@ _sk_darken_avx: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,95,209 // vmaxps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,116,88,0,0 // vbroadcastss 0x5874(%rip),%ymm8 # 5dc4 <_sk_callback_avx+0x164> + .byte 196,98,125,24,5,92,94,0,0 // vbroadcastss 0x5e5c(%rip),%ymm8 # 63ac <_sk_callback_avx+0x162> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -13991,7 +14265,7 @@ _sk_lighten_avx: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,32,88,0,0 // vbroadcastss 0x5820(%rip),%ymm8 # 5dc8 <_sk_callback_avx+0x168> + .byte 196,98,125,24,5,8,94,0,0 // vbroadcastss 0x5e08(%rip),%ymm8 # 63b0 <_sk_callback_avx+0x166> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -14020,7 +14294,7 @@ _sk_difference_avx: .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,192,87,0,0 // vbroadcastss 0x57c0(%rip),%ymm8 # 5dcc <_sk_callback_avx+0x16c> + .byte 196,98,125,24,5,168,93,0,0 // vbroadcastss 0x5da8(%rip),%ymm8 # 63b4 <_sk_callback_avx+0x16a> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -14043,7 +14317,7 @@ _sk_exclusion_avx: .byte 197,236,89,214 // vmulps %ymm6,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,123,87,0,0 // vbroadcastss 0x577b(%rip),%ymm8 # 5dd0 <_sk_callback_avx+0x170> + .byte 196,98,125,24,5,99,93,0,0 // vbroadcastss 0x5d63(%rip),%ymm8 # 63b8 <_sk_callback_avx+0x16e> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -14054,7 +14328,7 @@ HIDDEN _sk_colorburn_avx .globl _sk_colorburn_avx FUNCTION(_sk_colorburn_avx) _sk_colorburn_avx: - .byte 196,98,125,24,5,102,87,0,0 // vbroadcastss 0x5766(%rip),%ymm8 # 5dd4 <_sk_callback_avx+0x174> + .byte 196,98,125,24,5,78,93,0,0 // vbroadcastss 0x5d4e(%rip),%ymm8 # 63bc <_sk_callback_avx+0x172> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,216 // vmulps %ymm0,%ymm9,%ymm11 .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 @@ -14116,7 +14390,7 @@ HIDDEN _sk_colordodge_avx FUNCTION(_sk_colordodge_avx) _sk_colordodge_avx: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 - .byte 196,98,125,24,13,98,86,0,0 // vbroadcastss 0x5662(%rip),%ymm9 # 5dd8 <_sk_callback_avx+0x178> + .byte 196,98,125,24,13,74,92,0,0 // vbroadcastss 0x5c4a(%rip),%ymm9 # 63c0 <_sk_callback_avx+0x176> .byte 197,52,92,215 // vsubps %ymm7,%ymm9,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,52,92,203 // vsubps %ymm3,%ymm9,%ymm9 @@ -14173,7 +14447,7 @@ HIDDEN _sk_hardlight_avx .globl _sk_hardlight_avx FUNCTION(_sk_hardlight_avx) _sk_hardlight_avx: - .byte 196,98,125,24,5,116,85,0,0 // vbroadcastss 0x5574(%rip),%ymm8 # 5ddc <_sk_callback_avx+0x17c> + .byte 196,98,125,24,5,92,91,0,0 // vbroadcastss 0x5b5c(%rip),%ymm8 # 63c4 <_sk_callback_avx+0x17a> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,200 // vmulps %ymm0,%ymm10,%ymm9 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -14228,7 +14502,7 @@ HIDDEN _sk_overlay_avx .globl _sk_overlay_avx FUNCTION(_sk_overlay_avx) _sk_overlay_avx: - .byte 196,98,125,24,5,157,84,0,0 // vbroadcastss 0x549d(%rip),%ymm8 # 5de0 <_sk_callback_avx+0x180> + .byte 196,98,125,24,5,133,90,0,0 // vbroadcastss 0x5a85(%rip),%ymm8 # 63c8 <_sk_callback_avx+0x17e> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,200 // vmulps %ymm0,%ymm10,%ymm9 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -14294,10 +14568,10 @@ _sk_softlight_avx: .byte 196,65,60,88,192 // vaddps %ymm8,%ymm8,%ymm8 .byte 196,65,60,89,216 // vmulps %ymm8,%ymm8,%ymm11 .byte 196,65,60,88,195 // vaddps %ymm11,%ymm8,%ymm8 - .byte 196,98,125,24,29,148,83,0,0 // vbroadcastss 0x5394(%rip),%ymm11 # 5de8 <_sk_callback_avx+0x188> + .byte 196,98,125,24,29,124,89,0,0 // vbroadcastss 0x597c(%rip),%ymm11 # 63d0 <_sk_callback_avx+0x186> .byte 196,65,28,88,235 // vaddps %ymm11,%ymm12,%ymm13 .byte 196,65,20,89,192 // vmulps %ymm8,%ymm13,%ymm8 - .byte 196,98,125,24,45,133,83,0,0 // vbroadcastss 0x5385(%rip),%ymm13 # 5dec <_sk_callback_avx+0x18c> + .byte 196,98,125,24,45,109,89,0,0 // vbroadcastss 0x596d(%rip),%ymm13 # 63d4 <_sk_callback_avx+0x18a> .byte 196,65,28,89,245 // vmulps %ymm13,%ymm12,%ymm14 .byte 196,65,12,88,192 // vaddps %ymm8,%ymm14,%ymm8 .byte 196,65,124,82,244 // vrsqrtps %ymm12,%ymm14 @@ -14308,7 +14582,7 @@ _sk_softlight_avx: .byte 197,4,194,255,2 // vcmpleps %ymm7,%ymm15,%ymm15 .byte 196,67,13,74,240,240 // vblendvps %ymm15,%ymm8,%ymm14,%ymm14 .byte 197,116,88,249 // vaddps %ymm1,%ymm1,%ymm15 - .byte 196,98,125,24,5,67,83,0,0 // vbroadcastss 0x5343(%rip),%ymm8 # 5de4 <_sk_callback_avx+0x184> + .byte 196,98,125,24,5,43,89,0,0 // vbroadcastss 0x592b(%rip),%ymm8 # 63cc <_sk_callback_avx+0x182> .byte 196,65,60,92,228 // vsubps %ymm12,%ymm8,%ymm12 .byte 197,132,92,195 // vsubps %ymm3,%ymm15,%ymm0 .byte 196,65,124,89,228 // vmulps %ymm12,%ymm0,%ymm12 @@ -14435,12 +14709,12 @@ _sk_hue_avx: .byte 196,65,28,89,219 // vmulps %ymm11,%ymm12,%ymm11 .byte 196,65,36,94,222 // vdivps %ymm14,%ymm11,%ymm11 .byte 196,67,37,74,224,240 // vblendvps %ymm15,%ymm8,%ymm11,%ymm12 - .byte 196,98,125,24,53,18,81,0,0 // vbroadcastss 0x5112(%rip),%ymm14 # 5df0 <_sk_callback_avx+0x190> + .byte 196,98,125,24,53,250,86,0,0 // vbroadcastss 0x56fa(%rip),%ymm14 # 63d8 <_sk_callback_avx+0x18e> .byte 196,65,92,89,222 // vmulps %ymm14,%ymm4,%ymm11 - .byte 196,98,125,24,61,8,81,0,0 // vbroadcastss 0x5108(%rip),%ymm15 # 5df4 <_sk_callback_avx+0x194> + .byte 196,98,125,24,61,240,86,0,0 // vbroadcastss 0x56f0(%rip),%ymm15 # 63dc <_sk_callback_avx+0x192> .byte 196,65,84,89,239 // vmulps %ymm15,%ymm5,%ymm13 .byte 196,65,36,88,221 // vaddps %ymm13,%ymm11,%ymm11 - .byte 196,226,125,24,5,249,80,0,0 // vbroadcastss 0x50f9(%rip),%ymm0 # 5df8 <_sk_callback_avx+0x198> + .byte 196,226,125,24,5,225,86,0,0 // vbroadcastss 0x56e1(%rip),%ymm0 # 63e0 <_sk_callback_avx+0x196> .byte 197,76,89,232 // vmulps %ymm0,%ymm6,%ymm13 .byte 196,65,36,88,221 // vaddps %ymm13,%ymm11,%ymm11 .byte 196,65,52,89,238 // vmulps %ymm14,%ymm9,%ymm13 @@ -14501,7 +14775,7 @@ _sk_hue_avx: .byte 196,65,36,95,208 // vmaxps %ymm8,%ymm11,%ymm10 .byte 196,195,109,74,209,240 // vblendvps %ymm15,%ymm9,%ymm2,%ymm2 .byte 196,193,108,95,208 // vmaxps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,210,79,0,0 // vbroadcastss 0x4fd2(%rip),%ymm8 # 5dfc <_sk_callback_avx+0x19c> + .byte 196,98,125,24,5,186,85,0,0 // vbroadcastss 0x55ba(%rip),%ymm8 # 63e4 <_sk_callback_avx+0x19a> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,180,89,201 // vmulps %ymm1,%ymm9,%ymm1 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -14558,12 +14832,12 @@ _sk_saturation_avx: .byte 196,65,28,89,219 // vmulps %ymm11,%ymm12,%ymm11 .byte 196,65,36,94,222 // vdivps %ymm14,%ymm11,%ymm11 .byte 196,67,37,74,224,240 // vblendvps %ymm15,%ymm8,%ymm11,%ymm12 - .byte 196,98,125,24,53,224,78,0,0 // vbroadcastss 0x4ee0(%rip),%ymm14 # 5e00 <_sk_callback_avx+0x1a0> + .byte 196,98,125,24,53,200,84,0,0 // vbroadcastss 0x54c8(%rip),%ymm14 # 63e8 <_sk_callback_avx+0x19e> .byte 196,65,92,89,222 // vmulps %ymm14,%ymm4,%ymm11 - .byte 196,98,125,24,61,214,78,0,0 // vbroadcastss 0x4ed6(%rip),%ymm15 # 5e04 <_sk_callback_avx+0x1a4> + .byte 196,98,125,24,61,190,84,0,0 // vbroadcastss 0x54be(%rip),%ymm15 # 63ec <_sk_callback_avx+0x1a2> .byte 196,65,84,89,239 // vmulps %ymm15,%ymm5,%ymm13 .byte 196,65,36,88,221 // vaddps %ymm13,%ymm11,%ymm11 - .byte 196,226,125,24,5,199,78,0,0 // vbroadcastss 0x4ec7(%rip),%ymm0 # 5e08 <_sk_callback_avx+0x1a8> + .byte 196,226,125,24,5,175,84,0,0 // vbroadcastss 0x54af(%rip),%ymm0 # 63f0 <_sk_callback_avx+0x1a6> .byte 197,76,89,232 // vmulps %ymm0,%ymm6,%ymm13 .byte 196,65,36,88,221 // vaddps %ymm13,%ymm11,%ymm11 .byte 196,65,52,89,238 // vmulps %ymm14,%ymm9,%ymm13 @@ -14624,7 +14898,7 @@ _sk_saturation_avx: .byte 196,65,36,95,208 // vmaxps %ymm8,%ymm11,%ymm10 .byte 196,195,109,74,209,240 // vblendvps %ymm15,%ymm9,%ymm2,%ymm2 .byte 196,193,108,95,208 // vmaxps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,160,77,0,0 // vbroadcastss 0x4da0(%rip),%ymm8 # 5e0c <_sk_callback_avx+0x1ac> + .byte 196,98,125,24,5,136,83,0,0 // vbroadcastss 0x5388(%rip),%ymm8 # 63f4 <_sk_callback_avx+0x1aa> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,180,89,201 // vmulps %ymm1,%ymm9,%ymm1 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -14653,12 +14927,12 @@ _sk_color_avx: .byte 197,252,17,68,36,168 // vmovups %ymm0,-0x58(%rsp) .byte 197,124,89,199 // vmulps %ymm7,%ymm0,%ymm8 .byte 197,116,89,207 // vmulps %ymm7,%ymm1,%ymm9 - .byte 196,98,125,24,45,54,77,0,0 // vbroadcastss 0x4d36(%rip),%ymm13 # 5e10 <_sk_callback_avx+0x1b0> + .byte 196,98,125,24,45,30,83,0,0 // vbroadcastss 0x531e(%rip),%ymm13 # 63f8 <_sk_callback_avx+0x1ae> .byte 196,65,92,89,213 // vmulps %ymm13,%ymm4,%ymm10 - .byte 196,98,125,24,53,44,77,0,0 // vbroadcastss 0x4d2c(%rip),%ymm14 # 5e14 <_sk_callback_avx+0x1b4> + .byte 196,98,125,24,53,20,83,0,0 // vbroadcastss 0x5314(%rip),%ymm14 # 63fc <_sk_callback_avx+0x1b2> .byte 196,65,84,89,222 // vmulps %ymm14,%ymm5,%ymm11 .byte 196,65,44,88,211 // vaddps %ymm11,%ymm10,%ymm10 - .byte 196,98,125,24,61,29,77,0,0 // vbroadcastss 0x4d1d(%rip),%ymm15 # 5e18 <_sk_callback_avx+0x1b8> + .byte 196,98,125,24,61,5,83,0,0 // vbroadcastss 0x5305(%rip),%ymm15 # 6400 <_sk_callback_avx+0x1b6> .byte 196,65,76,89,223 // vmulps %ymm15,%ymm6,%ymm11 .byte 196,193,44,88,195 // vaddps %ymm11,%ymm10,%ymm0 .byte 196,65,60,89,221 // vmulps %ymm13,%ymm8,%ymm11 @@ -14721,7 +14995,7 @@ _sk_color_avx: .byte 196,65,44,95,207 // vmaxps %ymm15,%ymm10,%ymm9 .byte 196,195,37,74,192,0 // vblendvps %ymm0,%ymm8,%ymm11,%ymm0 .byte 196,65,124,95,199 // vmaxps %ymm15,%ymm0,%ymm8 - .byte 196,226,125,24,5,228,75,0,0 // vbroadcastss 0x4be4(%rip),%ymm0 # 5e1c <_sk_callback_avx+0x1bc> + .byte 196,226,125,24,5,204,81,0,0 // vbroadcastss 0x51cc(%rip),%ymm0 # 6404 <_sk_callback_avx+0x1ba> .byte 197,124,92,215 // vsubps %ymm7,%ymm0,%ymm10 .byte 197,172,89,84,36,168 // vmulps -0x58(%rsp),%ymm10,%ymm2 .byte 197,124,92,219 // vsubps %ymm3,%ymm0,%ymm11 @@ -14751,12 +15025,12 @@ _sk_luminosity_avx: .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 .byte 197,100,89,196 // vmulps %ymm4,%ymm3,%ymm8 .byte 197,100,89,205 // vmulps %ymm5,%ymm3,%ymm9 - .byte 196,98,125,24,45,118,75,0,0 // vbroadcastss 0x4b76(%rip),%ymm13 # 5e20 <_sk_callback_avx+0x1c0> + .byte 196,98,125,24,45,94,81,0,0 // vbroadcastss 0x515e(%rip),%ymm13 # 6408 <_sk_callback_avx+0x1be> .byte 196,65,108,89,213 // vmulps %ymm13,%ymm2,%ymm10 - .byte 196,98,125,24,53,108,75,0,0 // vbroadcastss 0x4b6c(%rip),%ymm14 # 5e24 <_sk_callback_avx+0x1c4> + .byte 196,98,125,24,53,84,81,0,0 // vbroadcastss 0x5154(%rip),%ymm14 # 640c <_sk_callback_avx+0x1c2> .byte 196,65,116,89,222 // vmulps %ymm14,%ymm1,%ymm11 .byte 196,65,44,88,211 // vaddps %ymm11,%ymm10,%ymm10 - .byte 196,98,125,24,61,93,75,0,0 // vbroadcastss 0x4b5d(%rip),%ymm15 # 5e28 <_sk_callback_avx+0x1c8> + .byte 196,98,125,24,61,69,81,0,0 // vbroadcastss 0x5145(%rip),%ymm15 # 6410 <_sk_callback_avx+0x1c6> .byte 196,65,28,89,223 // vmulps %ymm15,%ymm12,%ymm11 .byte 196,193,44,88,195 // vaddps %ymm11,%ymm10,%ymm0 .byte 196,65,60,89,221 // vmulps %ymm13,%ymm8,%ymm11 @@ -14819,7 +15093,7 @@ _sk_luminosity_avx: .byte 196,65,44,95,207 // vmaxps %ymm15,%ymm10,%ymm9 .byte 196,195,37,74,192,0 // vblendvps %ymm0,%ymm8,%ymm11,%ymm0 .byte 196,65,124,95,199 // vmaxps %ymm15,%ymm0,%ymm8 - .byte 196,226,125,24,5,36,74,0,0 // vbroadcastss 0x4a24(%rip),%ymm0 # 5e2c <_sk_callback_avx+0x1cc> + .byte 196,226,125,24,5,12,80,0,0 // vbroadcastss 0x500c(%rip),%ymm0 # 6414 <_sk_callback_avx+0x1ca> .byte 197,124,92,215 // vsubps %ymm7,%ymm0,%ymm10 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 197,124,92,219 // vsubps %ymm3,%ymm0,%ymm11 @@ -14855,7 +15129,7 @@ HIDDEN _sk_clamp_1_avx .globl _sk_clamp_1_avx FUNCTION(_sk_clamp_1_avx) _sk_clamp_1_avx: - .byte 196,98,125,24,5,183,73,0,0 // vbroadcastss 0x49b7(%rip),%ymm8 # 5e30 <_sk_callback_avx+0x1d0> + .byte 196,98,125,24,5,159,79,0,0 // vbroadcastss 0x4f9f(%rip),%ymm8 # 6418 <_sk_callback_avx+0x1ce> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 @@ -14867,7 +15141,7 @@ HIDDEN _sk_clamp_a_avx .globl _sk_clamp_a_avx FUNCTION(_sk_clamp_a_avx) _sk_clamp_a_avx: - .byte 196,98,125,24,5,154,73,0,0 // vbroadcastss 0x499a(%rip),%ymm8 # 5e34 <_sk_callback_avx+0x1d4> + .byte 196,98,125,24,5,130,79,0,0 // vbroadcastss 0x4f82(%rip),%ymm8 # 641c <_sk_callback_avx+0x1d2> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 197,252,93,195 // vminps %ymm3,%ymm0,%ymm0 .byte 197,244,93,203 // vminps %ymm3,%ymm1,%ymm1 @@ -14953,7 +15227,7 @@ FUNCTION(_sk_unpremul_avx) _sk_unpremul_avx: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,65,100,194,200,0 // vcmpeqps %ymm8,%ymm3,%ymm9 - .byte 196,98,125,24,21,226,72,0,0 // vbroadcastss 0x48e2(%rip),%ymm10 # 5e38 <_sk_callback_avx+0x1d8> + .byte 196,98,125,24,21,202,78,0,0 // vbroadcastss 0x4eca(%rip),%ymm10 # 6420 <_sk_callback_avx+0x1d6> .byte 197,44,94,211 // vdivps %ymm3,%ymm10,%ymm10 .byte 196,67,45,74,192,144 // vblendvps %ymm9,%ymm8,%ymm10,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 @@ -14966,17 +15240,17 @@ HIDDEN _sk_from_srgb_avx .globl _sk_from_srgb_avx FUNCTION(_sk_from_srgb_avx) _sk_from_srgb_avx: - .byte 196,98,125,24,5,195,72,0,0 // vbroadcastss 0x48c3(%rip),%ymm8 # 5e3c <_sk_callback_avx+0x1dc> + .byte 196,98,125,24,5,171,78,0,0 // vbroadcastss 0x4eab(%rip),%ymm8 # 6424 <_sk_callback_avx+0x1da> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 197,124,89,208 // vmulps %ymm0,%ymm0,%ymm10 - .byte 196,98,125,24,29,181,72,0,0 // vbroadcastss 0x48b5(%rip),%ymm11 # 5e40 <_sk_callback_avx+0x1e0> + .byte 196,98,125,24,29,157,78,0,0 // vbroadcastss 0x4e9d(%rip),%ymm11 # 6428 <_sk_callback_avx+0x1de> .byte 196,65,124,89,227 // vmulps %ymm11,%ymm0,%ymm12 - .byte 196,98,125,24,45,171,72,0,0 // vbroadcastss 0x48ab(%rip),%ymm13 # 5e44 <_sk_callback_avx+0x1e4> + .byte 196,98,125,24,45,147,78,0,0 // vbroadcastss 0x4e93(%rip),%ymm13 # 642c <_sk_callback_avx+0x1e2> .byte 196,65,28,88,229 // vaddps %ymm13,%ymm12,%ymm12 .byte 196,65,44,89,212 // vmulps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,156,72,0,0 // vbroadcastss 0x489c(%rip),%ymm12 # 5e48 <_sk_callback_avx+0x1e8> + .byte 196,98,125,24,37,132,78,0,0 // vbroadcastss 0x4e84(%rip),%ymm12 # 6430 <_sk_callback_avx+0x1e6> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,53,146,72,0,0 // vbroadcastss 0x4892(%rip),%ymm14 # 5e4c <_sk_callback_avx+0x1ec> + .byte 196,98,125,24,53,122,78,0,0 // vbroadcastss 0x4e7a(%rip),%ymm14 # 6434 <_sk_callback_avx+0x1ea> .byte 196,193,124,194,198,1 // vcmpltps %ymm14,%ymm0,%ymm0 .byte 196,195,45,74,193,0 // vblendvps %ymm0,%ymm9,%ymm10,%ymm0 .byte 196,65,116,89,200 // vmulps %ymm8,%ymm1,%ymm9 @@ -15005,18 +15279,18 @@ _sk_to_srgb_avx: .byte 197,124,82,192 // vrsqrtps %ymm0,%ymm8 .byte 196,65,124,83,200 // vrcpps %ymm8,%ymm9 .byte 196,65,124,82,208 // vrsqrtps %ymm8,%ymm10 - .byte 196,98,125,24,5,29,72,0,0 // vbroadcastss 0x481d(%rip),%ymm8 # 5e50 <_sk_callback_avx+0x1f0> + .byte 196,98,125,24,5,5,78,0,0 // vbroadcastss 0x4e05(%rip),%ymm8 # 6438 <_sk_callback_avx+0x1ee> .byte 196,65,124,89,216 // vmulps %ymm8,%ymm0,%ymm11 - .byte 196,98,125,24,37,19,72,0,0 // vbroadcastss 0x4813(%rip),%ymm12 # 5e54 <_sk_callback_avx+0x1f4> + .byte 196,98,125,24,37,251,77,0,0 // vbroadcastss 0x4dfb(%rip),%ymm12 # 643c <_sk_callback_avx+0x1f2> .byte 196,65,52,89,204 // vmulps %ymm12,%ymm9,%ymm9 - .byte 196,98,125,24,45,9,72,0,0 // vbroadcastss 0x4809(%rip),%ymm13 # 5e58 <_sk_callback_avx+0x1f8> + .byte 196,98,125,24,45,241,77,0,0 // vbroadcastss 0x4df1(%rip),%ymm13 # 6440 <_sk_callback_avx+0x1f6> .byte 196,65,52,88,205 // vaddps %ymm13,%ymm9,%ymm9 - .byte 196,98,125,24,53,255,71,0,0 // vbroadcastss 0x47ff(%rip),%ymm14 # 5e5c <_sk_callback_avx+0x1fc> + .byte 196,98,125,24,53,231,77,0,0 // vbroadcastss 0x4de7(%rip),%ymm14 # 6444 <_sk_callback_avx+0x1fa> .byte 196,65,44,89,214 // vmulps %ymm14,%ymm10,%ymm10 .byte 196,65,44,88,201 // vaddps %ymm9,%ymm10,%ymm9 - .byte 196,98,125,24,21,240,71,0,0 // vbroadcastss 0x47f0(%rip),%ymm10 # 5e60 <_sk_callback_avx+0x200> + .byte 196,98,125,24,21,216,77,0,0 // vbroadcastss 0x4dd8(%rip),%ymm10 # 6448 <_sk_callback_avx+0x1fe> .byte 196,65,44,93,201 // vminps %ymm9,%ymm10,%ymm9 - .byte 196,98,125,24,61,230,71,0,0 // vbroadcastss 0x47e6(%rip),%ymm15 # 5e64 <_sk_callback_avx+0x204> + .byte 196,98,125,24,61,206,77,0,0 // vbroadcastss 0x4dce(%rip),%ymm15 # 644c <_sk_callback_avx+0x202> .byte 196,193,124,194,199,1 // vcmpltps %ymm15,%ymm0,%ymm0 .byte 196,195,53,74,195,0 // vblendvps %ymm0,%ymm11,%ymm9,%ymm0 .byte 197,124,82,201 // vrsqrtps %ymm1,%ymm9 @@ -15053,7 +15327,7 @@ _sk_rgb_to_hsl_avx: .byte 197,124,93,201 // vminps %ymm1,%ymm0,%ymm9 .byte 197,52,93,202 // vminps %ymm2,%ymm9,%ymm9 .byte 196,65,60,92,209 // vsubps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,29,76,71,0,0 // vbroadcastss 0x474c(%rip),%ymm11 # 5e68 <_sk_callback_avx+0x208> + .byte 196,98,125,24,29,52,77,0,0 // vbroadcastss 0x4d34(%rip),%ymm11 # 6450 <_sk_callback_avx+0x206> .byte 196,65,36,94,218 // vdivps %ymm10,%ymm11,%ymm11 .byte 197,116,92,226 // vsubps %ymm2,%ymm1,%ymm12 .byte 196,65,28,89,227 // vmulps %ymm11,%ymm12,%ymm12 @@ -15063,19 +15337,19 @@ _sk_rgb_to_hsl_avx: .byte 196,193,108,89,211 // vmulps %ymm11,%ymm2,%ymm2 .byte 197,252,92,201 // vsubps %ymm1,%ymm0,%ymm1 .byte 196,193,116,89,203 // vmulps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,37,71,0,0 // vbroadcastss 0x4725(%rip),%ymm11 # 5e74 <_sk_callback_avx+0x214> + .byte 196,98,125,24,29,13,77,0,0 // vbroadcastss 0x4d0d(%rip),%ymm11 # 645c <_sk_callback_avx+0x212> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,19,71,0,0 // vbroadcastss 0x4713(%rip),%ymm11 # 5e70 <_sk_callback_avx+0x210> + .byte 196,98,125,24,29,251,76,0,0 // vbroadcastss 0x4cfb(%rip),%ymm11 # 6458 <_sk_callback_avx+0x20e> .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 .byte 196,227,117,74,202,224 // vblendvps %ymm14,%ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,21,251,70,0,0 // vbroadcastss 0x46fb(%rip),%ymm2 # 5e6c <_sk_callback_avx+0x20c> + .byte 196,226,125,24,21,227,76,0,0 // vbroadcastss 0x4ce3(%rip),%ymm2 # 6454 <_sk_callback_avx+0x20a> .byte 196,65,12,87,246 // vxorps %ymm14,%ymm14,%ymm14 .byte 196,227,13,74,210,208 // vblendvps %ymm13,%ymm2,%ymm14,%ymm2 .byte 197,188,194,192,0 // vcmpeqps %ymm0,%ymm8,%ymm0 .byte 196,193,108,88,212 // vaddps %ymm12,%ymm2,%ymm2 .byte 196,227,117,74,194,0 // vblendvps %ymm0,%ymm2,%ymm1,%ymm0 .byte 196,193,60,88,201 // vaddps %ymm9,%ymm8,%ymm1 - .byte 196,98,125,24,37,226,70,0,0 // vbroadcastss 0x46e2(%rip),%ymm12 # 5e7c <_sk_callback_avx+0x21c> + .byte 196,98,125,24,37,202,76,0,0 // vbroadcastss 0x4cca(%rip),%ymm12 # 6464 <_sk_callback_avx+0x21a> .byte 196,193,116,89,212 // vmulps %ymm12,%ymm1,%ymm2 .byte 197,28,194,226,1 // vcmpltps %ymm2,%ymm12,%ymm12 .byte 196,65,36,92,216 // vsubps %ymm8,%ymm11,%ymm11 @@ -15085,7 +15359,7 @@ _sk_rgb_to_hsl_avx: .byte 197,172,94,201 // vdivps %ymm1,%ymm10,%ymm1 .byte 196,195,125,74,198,128 // vblendvps %ymm8,%ymm14,%ymm0,%ymm0 .byte 196,195,117,74,206,128 // vblendvps %ymm8,%ymm14,%ymm1,%ymm1 - .byte 196,98,125,24,5,165,70,0,0 // vbroadcastss 0x46a5(%rip),%ymm8 # 5e78 <_sk_callback_avx+0x218> + .byte 196,98,125,24,5,141,76,0,0 // vbroadcastss 0x4c8d(%rip),%ymm8 # 6460 <_sk_callback_avx+0x216> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -15102,7 +15376,7 @@ _sk_hsl_to_rgb_avx: .byte 197,252,17,92,36,128 // vmovups %ymm3,-0x80(%rsp) .byte 197,252,40,225 // vmovaps %ymm1,%ymm4 .byte 197,252,40,216 // vmovaps %ymm0,%ymm3 - .byte 196,98,125,24,5,114,70,0,0 // vbroadcastss 0x4672(%rip),%ymm8 # 5e80 <_sk_callback_avx+0x220> + .byte 196,98,125,24,5,90,76,0,0 // vbroadcastss 0x4c5a(%rip),%ymm8 # 6468 <_sk_callback_avx+0x21e> .byte 197,60,194,202,2 // vcmpleps %ymm2,%ymm8,%ymm9 .byte 197,92,89,210 // vmulps %ymm2,%ymm4,%ymm10 .byte 196,65,92,92,218 // vsubps %ymm10,%ymm4,%ymm11 @@ -15110,23 +15384,23 @@ _sk_hsl_to_rgb_avx: .byte 197,52,88,210 // vaddps %ymm2,%ymm9,%ymm10 .byte 197,108,88,202 // vaddps %ymm2,%ymm2,%ymm9 .byte 196,65,52,92,202 // vsubps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,24,29,76,70,0,0 // vbroadcastss 0x464c(%rip),%ymm11 # 5e84 <_sk_callback_avx+0x224> + .byte 196,98,125,24,29,52,76,0,0 // vbroadcastss 0x4c34(%rip),%ymm11 # 646c <_sk_callback_avx+0x222> .byte 196,65,100,88,219 // vaddps %ymm11,%ymm3,%ymm11 .byte 196,67,125,8,227,1 // vroundps $0x1,%ymm11,%ymm12 .byte 196,65,36,92,252 // vsubps %ymm12,%ymm11,%ymm15 .byte 196,65,44,92,217 // vsubps %ymm9,%ymm10,%ymm11 - .byte 196,98,125,24,37,54,70,0,0 // vbroadcastss 0x4636(%rip),%ymm12 # 5e8c <_sk_callback_avx+0x22c> + .byte 196,98,125,24,37,30,76,0,0 // vbroadcastss 0x4c1e(%rip),%ymm12 # 6474 <_sk_callback_avx+0x22a> .byte 196,193,4,89,196 // vmulps %ymm12,%ymm15,%ymm0 - .byte 196,98,125,24,45,44,70,0,0 // vbroadcastss 0x462c(%rip),%ymm13 # 5e90 <_sk_callback_avx+0x230> + .byte 196,98,125,24,45,20,76,0,0 // vbroadcastss 0x4c14(%rip),%ymm13 # 6478 <_sk_callback_avx+0x22e> .byte 197,20,92,240 // vsubps %ymm0,%ymm13,%ymm14 .byte 196,65,36,89,246 // vmulps %ymm14,%ymm11,%ymm14 .byte 196,65,52,88,246 // vaddps %ymm14,%ymm9,%ymm14 - .byte 196,226,125,24,13,13,70,0,0 // vbroadcastss 0x460d(%rip),%ymm1 # 5e88 <_sk_callback_avx+0x228> + .byte 196,226,125,24,13,245,75,0,0 // vbroadcastss 0x4bf5(%rip),%ymm1 # 6470 <_sk_callback_avx+0x226> .byte 196,193,116,194,255,2 // vcmpleps %ymm15,%ymm1,%ymm7 .byte 196,195,13,74,249,112 // vblendvps %ymm7,%ymm9,%ymm14,%ymm7 .byte 196,65,60,194,247,2 // vcmpleps %ymm15,%ymm8,%ymm14 .byte 196,227,45,74,255,224 // vblendvps %ymm14,%ymm7,%ymm10,%ymm7 - .byte 196,98,125,24,53,248,69,0,0 // vbroadcastss 0x45f8(%rip),%ymm14 # 5e94 <_sk_callback_avx+0x234> + .byte 196,98,125,24,53,224,75,0,0 // vbroadcastss 0x4be0(%rip),%ymm14 # 647c <_sk_callback_avx+0x232> .byte 196,65,12,194,255,2 // vcmpleps %ymm15,%ymm14,%ymm15 .byte 196,193,124,89,195 // vmulps %ymm11,%ymm0,%ymm0 .byte 197,180,88,192 // vaddps %ymm0,%ymm9,%ymm0 @@ -15145,7 +15419,7 @@ _sk_hsl_to_rgb_avx: .byte 197,164,89,247 // vmulps %ymm7,%ymm11,%ymm6 .byte 197,180,88,246 // vaddps %ymm6,%ymm9,%ymm6 .byte 196,227,77,74,237,0 // vblendvps %ymm0,%ymm5,%ymm6,%ymm5 - .byte 196,226,125,24,5,154,69,0,0 // vbroadcastss 0x459a(%rip),%ymm0 # 5e98 <_sk_callback_avx+0x238> + .byte 196,226,125,24,5,130,75,0,0 // vbroadcastss 0x4b82(%rip),%ymm0 # 6480 <_sk_callback_avx+0x236> .byte 197,228,88,192 // vaddps %ymm0,%ymm3,%ymm0 .byte 196,227,125,8,216,1 // vroundps $0x1,%ymm0,%ymm3 .byte 197,252,92,195 // vsubps %ymm3,%ymm0,%ymm0 @@ -15204,7 +15478,7 @@ _sk_scale_u8_avx: .byte 196,66,121,49,192 // vpmovzxbd %xmm8,%xmm8 .byte 196,67,53,24,192,1 // vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,195,68,0,0 // vbroadcastss 0x44c3(%rip),%ymm9 # 5e9c <_sk_callback_avx+0x23c> + .byte 196,98,125,24,13,171,74,0,0 // vbroadcastss 0x4aab(%rip),%ymm9 # 6484 <_sk_callback_avx+0x23a> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -15263,7 +15537,7 @@ _sk_lerp_u8_avx: .byte 196,66,121,49,192 // vpmovzxbd %xmm8,%xmm8 .byte 196,67,53,24,192,1 // vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,15,68,0,0 // vbroadcastss 0x440f(%rip),%ymm9 # 5ea0 <_sk_callback_avx+0x240> + .byte 196,98,125,24,13,247,73,0,0 // vbroadcastss 0x49f7(%rip),%ymm9 # 6488 <_sk_callback_avx+0x23e> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 @@ -15306,20 +15580,20 @@ _sk_lerp_565_avx: .byte 196,65,57,105,201 // vpunpckhwd %xmm9,%xmm8,%xmm9 .byte 196,66,121,51,192 // vpmovzxwd %xmm8,%xmm8 .byte 196,67,61,24,193,1 // vinsertf128 $0x1,%xmm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,121,67,0,0 // vbroadcastss 0x4379(%rip),%ymm9 # 5ea4 <_sk_callback_avx+0x244> + .byte 196,98,125,24,13,97,73,0,0 // vbroadcastss 0x4961(%rip),%ymm9 # 648c <_sk_callback_avx+0x242> .byte 196,65,60,84,201 // vandps %ymm9,%ymm8,%ymm9 .byte 196,65,124,91,201 // vcvtdq2ps %ymm9,%ymm9 - .byte 196,98,125,24,21,106,67,0,0 // vbroadcastss 0x436a(%rip),%ymm10 # 5ea8 <_sk_callback_avx+0x248> + .byte 196,98,125,24,21,82,73,0,0 // vbroadcastss 0x4952(%rip),%ymm10 # 6490 <_sk_callback_avx+0x246> .byte 196,65,52,89,202 // vmulps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,24,21,96,67,0,0 // vbroadcastss 0x4360(%rip),%ymm10 # 5eac <_sk_callback_avx+0x24c> + .byte 196,98,125,24,21,72,73,0,0 // vbroadcastss 0x4948(%rip),%ymm10 # 6494 <_sk_callback_avx+0x24a> .byte 196,65,60,84,210 // vandps %ymm10,%ymm8,%ymm10 .byte 196,65,124,91,210 // vcvtdq2ps %ymm10,%ymm10 - .byte 196,98,125,24,29,81,67,0,0 // vbroadcastss 0x4351(%rip),%ymm11 # 5eb0 <_sk_callback_avx+0x250> + .byte 196,98,125,24,29,57,73,0,0 // vbroadcastss 0x4939(%rip),%ymm11 # 6498 <_sk_callback_avx+0x24e> .byte 196,65,44,89,211 // vmulps %ymm11,%ymm10,%ymm10 - .byte 196,98,125,24,29,71,67,0,0 // vbroadcastss 0x4347(%rip),%ymm11 # 5eb4 <_sk_callback_avx+0x254> + .byte 196,98,125,24,29,47,73,0,0 // vbroadcastss 0x492f(%rip),%ymm11 # 649c <_sk_callback_avx+0x252> .byte 196,65,60,84,195 // vandps %ymm11,%ymm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,29,56,67,0,0 // vbroadcastss 0x4338(%rip),%ymm11 # 5eb8 <_sk_callback_avx+0x258> + .byte 196,98,125,24,29,32,73,0,0 // vbroadcastss 0x4920(%rip),%ymm11 # 64a0 <_sk_callback_avx+0x256> .byte 196,65,60,89,195 // vmulps %ymm11,%ymm8,%ymm8 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 @@ -15366,7 +15640,7 @@ _sk_lerp_565_avx: .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) - .byte 233,255,255,255,225 // jmpq ffffffffe2001c50 <_sk_callback_avx+0xffffffffe1ffbff0> + .byte 233,255,255,255,225 // jmpq ffffffffe2001c50 <_sk_callback_avx+0xffffffffe1ffba06> .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) @@ -15399,7 +15673,7 @@ _sk_load_tables_avx: .byte 65,85 // push %r13 .byte 65,84 // push %r12 .byte 83 // push %rbx - .byte 197,124,40,13,22,69,0,0 // vmovaps 0x4516(%rip),%ymm9 # 61a0 <_sk_callback_avx+0x540> + .byte 197,124,40,13,246,74,0,0 // vmovaps 0x4af6(%rip),%ymm9 # 6780 <_sk_callback_avx+0x536> .byte 196,193,60,84,193 // vandps %ymm9,%ymm8,%ymm0 .byte 196,193,249,126,193 // vmovq %xmm0,%r9 .byte 69,137,203 // mov %r9d,%r11d @@ -15491,7 +15765,7 @@ _sk_load_tables_avx: .byte 196,193,97,114,210,24 // vpsrld $0x18,%xmm10,%xmm3 .byte 196,227,61,24,219,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,67,64,0,0 // vbroadcastss 0x4043(%rip),%ymm8 # 5ebc <_sk_callback_avx+0x25c> + .byte 196,98,125,24,5,43,70,0,0 // vbroadcastss 0x462b(%rip),%ymm8 # 64a4 <_sk_callback_avx+0x25a> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -15583,7 +15857,7 @@ _sk_load_tables_u16_be_avx: .byte 197,177,108,208 // vpunpcklqdq %xmm0,%xmm9,%xmm2 .byte 197,177,109,200 // vpunpckhqdq %xmm0,%xmm9,%xmm1 .byte 196,65,57,108,212 // vpunpcklqdq %xmm12,%xmm8,%xmm10 - .byte 197,121,111,29,86,66,0,0 // vmovdqa 0x4256(%rip),%xmm11 # 6220 <_sk_callback_avx+0x5c0> + .byte 197,121,111,29,54,72,0,0 // vmovdqa 0x4836(%rip),%xmm11 # 6800 <_sk_callback_avx+0x5b6> .byte 196,193,105,219,195 // vpand %xmm11,%xmm2,%xmm0 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 196,193,121,105,209 // vpunpckhwd %xmm9,%xmm0,%xmm2 @@ -15682,7 +15956,7 @@ _sk_load_tables_u16_be_avx: .byte 196,226,121,51,219 // vpmovzxwd %xmm3,%xmm3 .byte 196,195,101,24,216,1 // vinsertf128 $0x1,%xmm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,244,60,0,0 // vbroadcastss 0x3cf4(%rip),%ymm8 # 5ec0 <_sk_callback_avx+0x260> + .byte 196,98,125,24,5,220,66,0,0 // vbroadcastss 0x42dc(%rip),%ymm8 # 64a8 <_sk_callback_avx+0x25e> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -15754,7 +16028,7 @@ _sk_load_tables_rgb_u16_be_avx: .byte 197,185,108,202 // vpunpcklqdq %xmm2,%xmm8,%xmm1 .byte 197,185,109,210 // vpunpckhqdq %xmm2,%xmm8,%xmm2 .byte 197,121,108,195 // vpunpcklqdq %xmm3,%xmm0,%xmm8 - .byte 197,121,111,13,79,63,0,0 // vmovdqa 0x3f4f(%rip),%xmm9 # 6230 <_sk_callback_avx+0x5d0> + .byte 197,121,111,13,47,69,0,0 // vmovdqa 0x452f(%rip),%xmm9 # 6810 <_sk_callback_avx+0x5c6> .byte 196,193,113,219,193 // vpand %xmm9,%xmm1,%xmm0 .byte 196,65,41,239,210 // vpxor %xmm10,%xmm10,%xmm10 .byte 196,193,121,105,202 // vpunpckhwd %xmm10,%xmm0,%xmm1 @@ -15846,7 +16120,7 @@ _sk_load_tables_rgb_u16_be_avx: .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 .byte 196,195,109,24,208,1 // vinsertf128 $0x1,%xmm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,6,58,0,0 // vbroadcastss 0x3a06(%rip),%ymm3 # 5ec4 <_sk_callback_avx+0x264> + .byte 196,226,125,24,29,238,63,0,0 // vbroadcastss 0x3fee(%rip),%ymm3 # 64ac <_sk_callback_avx+0x262> .byte 91 // pop %rbx .byte 65,92 // pop %r12 .byte 65,93 // pop %r13 @@ -15899,7 +16173,7 @@ _sk_byte_tables_avx: .byte 65,84 // push %r12 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,58,57,0,0 // vbroadcastss 0x393a(%rip),%ymm8 # 5ec8 <_sk_callback_avx+0x268> + .byte 196,98,125,24,5,34,63,0,0 // vbroadcastss 0x3f22(%rip),%ymm8 # 64b0 <_sk_callback_avx+0x266> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,195,249,22,192,1 // vpextrq $0x1,%xmm0,%r8 @@ -15936,7 +16210,7 @@ _sk_byte_tables_avx: .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,53,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,136,56,0,0 // vbroadcastss 0x3888(%rip),%ymm9 # 5ecc <_sk_callback_avx+0x26c> + .byte 196,98,125,24,13,112,62,0,0 // vbroadcastss 0x3e70(%rip),%ymm9 # 64b4 <_sk_callback_avx+0x26a> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -16098,7 +16372,7 @@ _sk_byte_tables_rgb_avx: .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,53,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,174,53,0,0 // vbroadcastss 0x35ae(%rip),%ymm9 # 5ed0 <_sk_callback_avx+0x270> + .byte 196,98,125,24,13,150,59,0,0 // vbroadcastss 0x3b96(%rip),%ymm9 # 64b8 <_sk_callback_avx+0x26e> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -16395,36 +16669,36 @@ _sk_parametric_r_avx: .byte 196,193,124,88,195 // vaddps %ymm11,%ymm0,%ymm0 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,216 // vcvtdq2ps %ymm0,%ymm11 - .byte 196,98,125,24,37,12,49,0,0 // vbroadcastss 0x310c(%rip),%ymm12 # 5ed4 <_sk_callback_avx+0x274> + .byte 196,98,125,24,37,244,54,0,0 // vbroadcastss 0x36f4(%rip),%ymm12 # 64bc <_sk_callback_avx+0x272> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,2,49,0,0 // vbroadcastss 0x3102(%rip),%ymm12 # 5ed8 <_sk_callback_avx+0x278> + .byte 196,98,125,24,37,234,54,0,0 // vbroadcastss 0x36ea(%rip),%ymm12 # 64c0 <_sk_callback_avx+0x276> .byte 196,193,124,84,196 // vandps %ymm12,%ymm0,%ymm0 - .byte 196,98,125,24,37,248,48,0,0 // vbroadcastss 0x30f8(%rip),%ymm12 # 5edc <_sk_callback_avx+0x27c> + .byte 196,98,125,24,37,224,54,0,0 // vbroadcastss 0x36e0(%rip),%ymm12 # 64c4 <_sk_callback_avx+0x27a> .byte 196,193,124,86,196 // vorps %ymm12,%ymm0,%ymm0 - .byte 196,98,125,24,37,238,48,0,0 // vbroadcastss 0x30ee(%rip),%ymm12 # 5ee0 <_sk_callback_avx+0x280> + .byte 196,98,125,24,37,214,54,0,0 // vbroadcastss 0x36d6(%rip),%ymm12 # 64c8 <_sk_callback_avx+0x27e> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,228,48,0,0 // vbroadcastss 0x30e4(%rip),%ymm12 # 5ee4 <_sk_callback_avx+0x284> + .byte 196,98,125,24,37,204,54,0,0 // vbroadcastss 0x36cc(%rip),%ymm12 # 64cc <_sk_callback_avx+0x282> .byte 196,65,124,89,228 // vmulps %ymm12,%ymm0,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,213,48,0,0 // vbroadcastss 0x30d5(%rip),%ymm12 # 5ee8 <_sk_callback_avx+0x288> + .byte 196,98,125,24,37,189,54,0,0 // vbroadcastss 0x36bd(%rip),%ymm12 # 64d0 <_sk_callback_avx+0x286> .byte 196,193,124,88,196 // vaddps %ymm12,%ymm0,%ymm0 - .byte 196,98,125,24,37,203,48,0,0 // vbroadcastss 0x30cb(%rip),%ymm12 # 5eec <_sk_callback_avx+0x28c> + .byte 196,98,125,24,37,179,54,0,0 // vbroadcastss 0x36b3(%rip),%ymm12 # 64d4 <_sk_callback_avx+0x28a> .byte 197,156,94,192 // vdivps %ymm0,%ymm12,%ymm0 .byte 197,164,92,192 // vsubps %ymm0,%ymm11,%ymm0 .byte 197,172,89,192 // vmulps %ymm0,%ymm10,%ymm0 .byte 196,99,125,8,208,1 // vroundps $0x1,%ymm0,%ymm10 .byte 196,65,124,92,210 // vsubps %ymm10,%ymm0,%ymm10 - .byte 196,98,125,24,29,175,48,0,0 // vbroadcastss 0x30af(%rip),%ymm11 # 5ef0 <_sk_callback_avx+0x290> + .byte 196,98,125,24,29,151,54,0,0 // vbroadcastss 0x3697(%rip),%ymm11 # 64d8 <_sk_callback_avx+0x28e> .byte 196,193,124,88,195 // vaddps %ymm11,%ymm0,%ymm0 - .byte 196,98,125,24,29,165,48,0,0 // vbroadcastss 0x30a5(%rip),%ymm11 # 5ef4 <_sk_callback_avx+0x294> + .byte 196,98,125,24,29,141,54,0,0 // vbroadcastss 0x368d(%rip),%ymm11 # 64dc <_sk_callback_avx+0x292> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,124,92,195 // vsubps %ymm11,%ymm0,%ymm0 - .byte 196,98,125,24,29,150,48,0,0 // vbroadcastss 0x3096(%rip),%ymm11 # 5ef8 <_sk_callback_avx+0x298> + .byte 196,98,125,24,29,126,54,0,0 // vbroadcastss 0x367e(%rip),%ymm11 # 64e0 <_sk_callback_avx+0x296> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,140,48,0,0 // vbroadcastss 0x308c(%rip),%ymm11 # 5efc <_sk_callback_avx+0x29c> + .byte 196,98,125,24,29,116,54,0,0 // vbroadcastss 0x3674(%rip),%ymm11 # 64e4 <_sk_callback_avx+0x29a> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,124,88,194 // vaddps %ymm10,%ymm0,%ymm0 - .byte 196,98,125,24,21,125,48,0,0 // vbroadcastss 0x307d(%rip),%ymm10 # 5f00 <_sk_callback_avx+0x2a0> + .byte 196,98,125,24,21,101,54,0,0 // vbroadcastss 0x3665(%rip),%ymm10 # 64e8 <_sk_callback_avx+0x29e> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -16432,7 +16706,7 @@ _sk_parametric_r_avx: .byte 196,195,125,74,193,128 // vblendvps %ymm8,%ymm9,%ymm0,%ymm0 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,124,95,192 // vmaxps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,84,48,0,0 // vbroadcastss 0x3054(%rip),%ymm8 # 5f04 <_sk_callback_avx+0x2a4> + .byte 196,98,125,24,5,60,54,0,0 // vbroadcastss 0x363c(%rip),%ymm8 # 64ec <_sk_callback_avx+0x2a2> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -16454,36 +16728,36 @@ _sk_parametric_g_avx: .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,217 // vcvtdq2ps %ymm1,%ymm11 - .byte 196,98,125,24,37,5,48,0,0 // vbroadcastss 0x3005(%rip),%ymm12 # 5f08 <_sk_callback_avx+0x2a8> + .byte 196,98,125,24,37,237,53,0,0 // vbroadcastss 0x35ed(%rip),%ymm12 # 64f0 <_sk_callback_avx+0x2a6> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,251,47,0,0 // vbroadcastss 0x2ffb(%rip),%ymm12 # 5f0c <_sk_callback_avx+0x2ac> + .byte 196,98,125,24,37,227,53,0,0 // vbroadcastss 0x35e3(%rip),%ymm12 # 64f4 <_sk_callback_avx+0x2aa> .byte 196,193,116,84,204 // vandps %ymm12,%ymm1,%ymm1 - .byte 196,98,125,24,37,241,47,0,0 // vbroadcastss 0x2ff1(%rip),%ymm12 # 5f10 <_sk_callback_avx+0x2b0> + .byte 196,98,125,24,37,217,53,0,0 // vbroadcastss 0x35d9(%rip),%ymm12 # 64f8 <_sk_callback_avx+0x2ae> .byte 196,193,116,86,204 // vorps %ymm12,%ymm1,%ymm1 - .byte 196,98,125,24,37,231,47,0,0 // vbroadcastss 0x2fe7(%rip),%ymm12 # 5f14 <_sk_callback_avx+0x2b4> + .byte 196,98,125,24,37,207,53,0,0 // vbroadcastss 0x35cf(%rip),%ymm12 # 64fc <_sk_callback_avx+0x2b2> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,221,47,0,0 // vbroadcastss 0x2fdd(%rip),%ymm12 # 5f18 <_sk_callback_avx+0x2b8> + .byte 196,98,125,24,37,197,53,0,0 // vbroadcastss 0x35c5(%rip),%ymm12 # 6500 <_sk_callback_avx+0x2b6> .byte 196,65,116,89,228 // vmulps %ymm12,%ymm1,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,206,47,0,0 // vbroadcastss 0x2fce(%rip),%ymm12 # 5f1c <_sk_callback_avx+0x2bc> + .byte 196,98,125,24,37,182,53,0,0 // vbroadcastss 0x35b6(%rip),%ymm12 # 6504 <_sk_callback_avx+0x2ba> .byte 196,193,116,88,204 // vaddps %ymm12,%ymm1,%ymm1 - .byte 196,98,125,24,37,196,47,0,0 // vbroadcastss 0x2fc4(%rip),%ymm12 # 5f20 <_sk_callback_avx+0x2c0> + .byte 196,98,125,24,37,172,53,0,0 // vbroadcastss 0x35ac(%rip),%ymm12 # 6508 <_sk_callback_avx+0x2be> .byte 197,156,94,201 // vdivps %ymm1,%ymm12,%ymm1 .byte 197,164,92,201 // vsubps %ymm1,%ymm11,%ymm1 .byte 197,172,89,201 // vmulps %ymm1,%ymm10,%ymm1 .byte 196,99,125,8,209,1 // vroundps $0x1,%ymm1,%ymm10 .byte 196,65,116,92,210 // vsubps %ymm10,%ymm1,%ymm10 - .byte 196,98,125,24,29,168,47,0,0 // vbroadcastss 0x2fa8(%rip),%ymm11 # 5f24 <_sk_callback_avx+0x2c4> + .byte 196,98,125,24,29,144,53,0,0 // vbroadcastss 0x3590(%rip),%ymm11 # 650c <_sk_callback_avx+0x2c2> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,158,47,0,0 // vbroadcastss 0x2f9e(%rip),%ymm11 # 5f28 <_sk_callback_avx+0x2c8> + .byte 196,98,125,24,29,134,53,0,0 // vbroadcastss 0x3586(%rip),%ymm11 # 6510 <_sk_callback_avx+0x2c6> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,116,92,203 // vsubps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,143,47,0,0 // vbroadcastss 0x2f8f(%rip),%ymm11 # 5f2c <_sk_callback_avx+0x2cc> + .byte 196,98,125,24,29,119,53,0,0 // vbroadcastss 0x3577(%rip),%ymm11 # 6514 <_sk_callback_avx+0x2ca> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,133,47,0,0 // vbroadcastss 0x2f85(%rip),%ymm11 # 5f30 <_sk_callback_avx+0x2d0> + .byte 196,98,125,24,29,109,53,0,0 // vbroadcastss 0x356d(%rip),%ymm11 # 6518 <_sk_callback_avx+0x2ce> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,116,88,202 // vaddps %ymm10,%ymm1,%ymm1 - .byte 196,98,125,24,21,118,47,0,0 // vbroadcastss 0x2f76(%rip),%ymm10 # 5f34 <_sk_callback_avx+0x2d4> + .byte 196,98,125,24,21,94,53,0,0 // vbroadcastss 0x355e(%rip),%ymm10 # 651c <_sk_callback_avx+0x2d2> .byte 196,193,116,89,202 // vmulps %ymm10,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -16491,7 +16765,7 @@ _sk_parametric_g_avx: .byte 196,195,117,74,201,128 // vblendvps %ymm8,%ymm9,%ymm1,%ymm1 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,116,95,200 // vmaxps %ymm8,%ymm1,%ymm1 - .byte 196,98,125,24,5,77,47,0,0 // vbroadcastss 0x2f4d(%rip),%ymm8 # 5f38 <_sk_callback_avx+0x2d8> + .byte 196,98,125,24,5,53,53,0,0 // vbroadcastss 0x3535(%rip),%ymm8 # 6520 <_sk_callback_avx+0x2d6> .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -16513,36 +16787,36 @@ _sk_parametric_b_avx: .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,218 // vcvtdq2ps %ymm2,%ymm11 - .byte 196,98,125,24,37,254,46,0,0 // vbroadcastss 0x2efe(%rip),%ymm12 # 5f3c <_sk_callback_avx+0x2dc> + .byte 196,98,125,24,37,230,52,0,0 // vbroadcastss 0x34e6(%rip),%ymm12 # 6524 <_sk_callback_avx+0x2da> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,244,46,0,0 // vbroadcastss 0x2ef4(%rip),%ymm12 # 5f40 <_sk_callback_avx+0x2e0> + .byte 196,98,125,24,37,220,52,0,0 // vbroadcastss 0x34dc(%rip),%ymm12 # 6528 <_sk_callback_avx+0x2de> .byte 196,193,108,84,212 // vandps %ymm12,%ymm2,%ymm2 - .byte 196,98,125,24,37,234,46,0,0 // vbroadcastss 0x2eea(%rip),%ymm12 # 5f44 <_sk_callback_avx+0x2e4> + .byte 196,98,125,24,37,210,52,0,0 // vbroadcastss 0x34d2(%rip),%ymm12 # 652c <_sk_callback_avx+0x2e2> .byte 196,193,108,86,212 // vorps %ymm12,%ymm2,%ymm2 - .byte 196,98,125,24,37,224,46,0,0 // vbroadcastss 0x2ee0(%rip),%ymm12 # 5f48 <_sk_callback_avx+0x2e8> + .byte 196,98,125,24,37,200,52,0,0 // vbroadcastss 0x34c8(%rip),%ymm12 # 6530 <_sk_callback_avx+0x2e6> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,214,46,0,0 // vbroadcastss 0x2ed6(%rip),%ymm12 # 5f4c <_sk_callback_avx+0x2ec> + .byte 196,98,125,24,37,190,52,0,0 // vbroadcastss 0x34be(%rip),%ymm12 # 6534 <_sk_callback_avx+0x2ea> .byte 196,65,108,89,228 // vmulps %ymm12,%ymm2,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,199,46,0,0 // vbroadcastss 0x2ec7(%rip),%ymm12 # 5f50 <_sk_callback_avx+0x2f0> + .byte 196,98,125,24,37,175,52,0,0 // vbroadcastss 0x34af(%rip),%ymm12 # 6538 <_sk_callback_avx+0x2ee> .byte 196,193,108,88,212 // vaddps %ymm12,%ymm2,%ymm2 - .byte 196,98,125,24,37,189,46,0,0 // vbroadcastss 0x2ebd(%rip),%ymm12 # 5f54 <_sk_callback_avx+0x2f4> + .byte 196,98,125,24,37,165,52,0,0 // vbroadcastss 0x34a5(%rip),%ymm12 # 653c <_sk_callback_avx+0x2f2> .byte 197,156,94,210 // vdivps %ymm2,%ymm12,%ymm2 .byte 197,164,92,210 // vsubps %ymm2,%ymm11,%ymm2 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 196,99,125,8,210,1 // vroundps $0x1,%ymm2,%ymm10 .byte 196,65,108,92,210 // vsubps %ymm10,%ymm2,%ymm10 - .byte 196,98,125,24,29,161,46,0,0 // vbroadcastss 0x2ea1(%rip),%ymm11 # 5f58 <_sk_callback_avx+0x2f8> + .byte 196,98,125,24,29,137,52,0,0 // vbroadcastss 0x3489(%rip),%ymm11 # 6540 <_sk_callback_avx+0x2f6> .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 - .byte 196,98,125,24,29,151,46,0,0 // vbroadcastss 0x2e97(%rip),%ymm11 # 5f5c <_sk_callback_avx+0x2fc> + .byte 196,98,125,24,29,127,52,0,0 // vbroadcastss 0x347f(%rip),%ymm11 # 6544 <_sk_callback_avx+0x2fa> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,108,92,211 // vsubps %ymm11,%ymm2,%ymm2 - .byte 196,98,125,24,29,136,46,0,0 // vbroadcastss 0x2e88(%rip),%ymm11 # 5f60 <_sk_callback_avx+0x300> + .byte 196,98,125,24,29,112,52,0,0 // vbroadcastss 0x3470(%rip),%ymm11 # 6548 <_sk_callback_avx+0x2fe> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,126,46,0,0 // vbroadcastss 0x2e7e(%rip),%ymm11 # 5f64 <_sk_callback_avx+0x304> + .byte 196,98,125,24,29,102,52,0,0 // vbroadcastss 0x3466(%rip),%ymm11 # 654c <_sk_callback_avx+0x302> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,108,88,210 // vaddps %ymm10,%ymm2,%ymm2 - .byte 196,98,125,24,21,111,46,0,0 // vbroadcastss 0x2e6f(%rip),%ymm10 # 5f68 <_sk_callback_avx+0x308> + .byte 196,98,125,24,21,87,52,0,0 // vbroadcastss 0x3457(%rip),%ymm10 # 6550 <_sk_callback_avx+0x306> .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 197,253,91,210 // vcvtps2dq %ymm2,%ymm2 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -16550,7 +16824,7 @@ _sk_parametric_b_avx: .byte 196,195,109,74,209,128 // vblendvps %ymm8,%ymm9,%ymm2,%ymm2 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,108,95,208 // vmaxps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,70,46,0,0 // vbroadcastss 0x2e46(%rip),%ymm8 # 5f6c <_sk_callback_avx+0x30c> + .byte 196,98,125,24,5,46,52,0,0 // vbroadcastss 0x342e(%rip),%ymm8 # 6554 <_sk_callback_avx+0x30a> .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -16572,36 +16846,36 @@ _sk_parametric_a_avx: .byte 196,193,100,88,219 // vaddps %ymm11,%ymm3,%ymm3 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,219 // vcvtdq2ps %ymm3,%ymm11 - .byte 196,98,125,24,37,247,45,0,0 // vbroadcastss 0x2df7(%rip),%ymm12 # 5f70 <_sk_callback_avx+0x310> + .byte 196,98,125,24,37,223,51,0,0 // vbroadcastss 0x33df(%rip),%ymm12 # 6558 <_sk_callback_avx+0x30e> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,237,45,0,0 // vbroadcastss 0x2ded(%rip),%ymm12 # 5f74 <_sk_callback_avx+0x314> + .byte 196,98,125,24,37,213,51,0,0 // vbroadcastss 0x33d5(%rip),%ymm12 # 655c <_sk_callback_avx+0x312> .byte 196,193,100,84,220 // vandps %ymm12,%ymm3,%ymm3 - .byte 196,98,125,24,37,227,45,0,0 // vbroadcastss 0x2de3(%rip),%ymm12 # 5f78 <_sk_callback_avx+0x318> + .byte 196,98,125,24,37,203,51,0,0 // vbroadcastss 0x33cb(%rip),%ymm12 # 6560 <_sk_callback_avx+0x316> .byte 196,193,100,86,220 // vorps %ymm12,%ymm3,%ymm3 - .byte 196,98,125,24,37,217,45,0,0 // vbroadcastss 0x2dd9(%rip),%ymm12 # 5f7c <_sk_callback_avx+0x31c> + .byte 196,98,125,24,37,193,51,0,0 // vbroadcastss 0x33c1(%rip),%ymm12 # 6564 <_sk_callback_avx+0x31a> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,207,45,0,0 // vbroadcastss 0x2dcf(%rip),%ymm12 # 5f80 <_sk_callback_avx+0x320> + .byte 196,98,125,24,37,183,51,0,0 // vbroadcastss 0x33b7(%rip),%ymm12 # 6568 <_sk_callback_avx+0x31e> .byte 196,65,100,89,228 // vmulps %ymm12,%ymm3,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,192,45,0,0 // vbroadcastss 0x2dc0(%rip),%ymm12 # 5f84 <_sk_callback_avx+0x324> + .byte 196,98,125,24,37,168,51,0,0 // vbroadcastss 0x33a8(%rip),%ymm12 # 656c <_sk_callback_avx+0x322> .byte 196,193,100,88,220 // vaddps %ymm12,%ymm3,%ymm3 - .byte 196,98,125,24,37,182,45,0,0 // vbroadcastss 0x2db6(%rip),%ymm12 # 5f88 <_sk_callback_avx+0x328> + .byte 196,98,125,24,37,158,51,0,0 // vbroadcastss 0x339e(%rip),%ymm12 # 6570 <_sk_callback_avx+0x326> .byte 197,156,94,219 // vdivps %ymm3,%ymm12,%ymm3 .byte 197,164,92,219 // vsubps %ymm3,%ymm11,%ymm3 .byte 197,172,89,219 // vmulps %ymm3,%ymm10,%ymm3 .byte 196,99,125,8,211,1 // vroundps $0x1,%ymm3,%ymm10 .byte 196,65,100,92,210 // vsubps %ymm10,%ymm3,%ymm10 - .byte 196,98,125,24,29,154,45,0,0 // vbroadcastss 0x2d9a(%rip),%ymm11 # 5f8c <_sk_callback_avx+0x32c> + .byte 196,98,125,24,29,130,51,0,0 // vbroadcastss 0x3382(%rip),%ymm11 # 6574 <_sk_callback_avx+0x32a> .byte 196,193,100,88,219 // vaddps %ymm11,%ymm3,%ymm3 - .byte 196,98,125,24,29,144,45,0,0 // vbroadcastss 0x2d90(%rip),%ymm11 # 5f90 <_sk_callback_avx+0x330> + .byte 196,98,125,24,29,120,51,0,0 // vbroadcastss 0x3378(%rip),%ymm11 # 6578 <_sk_callback_avx+0x32e> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,100,92,219 // vsubps %ymm11,%ymm3,%ymm3 - .byte 196,98,125,24,29,129,45,0,0 // vbroadcastss 0x2d81(%rip),%ymm11 # 5f94 <_sk_callback_avx+0x334> + .byte 196,98,125,24,29,105,51,0,0 // vbroadcastss 0x3369(%rip),%ymm11 # 657c <_sk_callback_avx+0x332> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,119,45,0,0 // vbroadcastss 0x2d77(%rip),%ymm11 # 5f98 <_sk_callback_avx+0x338> + .byte 196,98,125,24,29,95,51,0,0 // vbroadcastss 0x335f(%rip),%ymm11 # 6580 <_sk_callback_avx+0x336> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,100,88,218 // vaddps %ymm10,%ymm3,%ymm3 - .byte 196,98,125,24,21,104,45,0,0 // vbroadcastss 0x2d68(%rip),%ymm10 # 5f9c <_sk_callback_avx+0x33c> + .byte 196,98,125,24,21,80,51,0,0 // vbroadcastss 0x3350(%rip),%ymm10 # 6584 <_sk_callback_avx+0x33a> .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 197,253,91,219 // vcvtps2dq %ymm3,%ymm3 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -16609,7 +16883,7 @@ _sk_parametric_a_avx: .byte 196,195,101,74,217,128 // vblendvps %ymm8,%ymm9,%ymm3,%ymm3 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,100,95,216 // vmaxps %ymm8,%ymm3,%ymm3 - .byte 196,98,125,24,5,63,45,0,0 // vbroadcastss 0x2d3f(%rip),%ymm8 # 5fa0 <_sk_callback_avx+0x340> + .byte 196,98,125,24,5,39,51,0,0 // vbroadcastss 0x3327(%rip),%ymm8 # 6588 <_sk_callback_avx+0x33e> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -16618,31 +16892,31 @@ HIDDEN _sk_lab_to_xyz_avx .globl _sk_lab_to_xyz_avx FUNCTION(_sk_lab_to_xyz_avx) _sk_lab_to_xyz_avx: - .byte 196,98,125,24,5,49,45,0,0 // vbroadcastss 0x2d31(%rip),%ymm8 # 5fa4 <_sk_callback_avx+0x344> + .byte 196,98,125,24,5,25,51,0,0 // vbroadcastss 0x3319(%rip),%ymm8 # 658c <_sk_callback_avx+0x342> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,39,45,0,0 // vbroadcastss 0x2d27(%rip),%ymm8 # 5fa8 <_sk_callback_avx+0x348> + .byte 196,98,125,24,5,15,51,0,0 // vbroadcastss 0x330f(%rip),%ymm8 # 6590 <_sk_callback_avx+0x346> .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,98,125,24,13,29,45,0,0 // vbroadcastss 0x2d1d(%rip),%ymm9 # 5fac <_sk_callback_avx+0x34c> + .byte 196,98,125,24,13,5,51,0,0 // vbroadcastss 0x3305(%rip),%ymm9 # 6594 <_sk_callback_avx+0x34a> .byte 196,193,116,88,201 // vaddps %ymm9,%ymm1,%ymm1 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 196,193,108,88,209 // vaddps %ymm9,%ymm2,%ymm2 - .byte 196,98,125,24,5,9,45,0,0 // vbroadcastss 0x2d09(%rip),%ymm8 # 5fb0 <_sk_callback_avx+0x350> + .byte 196,98,125,24,5,241,50,0,0 // vbroadcastss 0x32f1(%rip),%ymm8 # 6598 <_sk_callback_avx+0x34e> .byte 196,193,124,88,192 // vaddps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,255,44,0,0 // vbroadcastss 0x2cff(%rip),%ymm8 # 5fb4 <_sk_callback_avx+0x354> + .byte 196,98,125,24,5,231,50,0,0 // vbroadcastss 0x32e7(%rip),%ymm8 # 659c <_sk_callback_avx+0x352> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,245,44,0,0 // vbroadcastss 0x2cf5(%rip),%ymm8 # 5fb8 <_sk_callback_avx+0x358> + .byte 196,98,125,24,5,221,50,0,0 // vbroadcastss 0x32dd(%rip),%ymm8 # 65a0 <_sk_callback_avx+0x356> .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 197,252,88,201 // vaddps %ymm1,%ymm0,%ymm1 - .byte 196,98,125,24,5,231,44,0,0 // vbroadcastss 0x2ce7(%rip),%ymm8 # 5fbc <_sk_callback_avx+0x35c> + .byte 196,98,125,24,5,207,50,0,0 // vbroadcastss 0x32cf(%rip),%ymm8 # 65a4 <_sk_callback_avx+0x35a> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,252,92,210 // vsubps %ymm2,%ymm0,%ymm2 .byte 197,116,89,193 // vmulps %ymm1,%ymm1,%ymm8 .byte 196,65,116,89,192 // vmulps %ymm8,%ymm1,%ymm8 - .byte 196,98,125,24,13,208,44,0,0 // vbroadcastss 0x2cd0(%rip),%ymm9 # 5fc0 <_sk_callback_avx+0x360> + .byte 196,98,125,24,13,184,50,0,0 // vbroadcastss 0x32b8(%rip),%ymm9 # 65a8 <_sk_callback_avx+0x35e> .byte 196,65,52,194,208,1 // vcmpltps %ymm8,%ymm9,%ymm10 - .byte 196,98,125,24,29,197,44,0,0 // vbroadcastss 0x2cc5(%rip),%ymm11 # 5fc4 <_sk_callback_avx+0x364> + .byte 196,98,125,24,29,173,50,0,0 // vbroadcastss 0x32ad(%rip),%ymm11 # 65ac <_sk_callback_avx+0x362> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,37,187,44,0,0 // vbroadcastss 0x2cbb(%rip),%ymm12 # 5fc8 <_sk_callback_avx+0x368> + .byte 196,98,125,24,37,163,50,0,0 // vbroadcastss 0x32a3(%rip),%ymm12 # 65b0 <_sk_callback_avx+0x366> .byte 196,193,116,89,204 // vmulps %ymm12,%ymm1,%ymm1 .byte 196,67,117,74,192,160 // vblendvps %ymm10,%ymm8,%ymm1,%ymm8 .byte 197,252,89,200 // vmulps %ymm0,%ymm0,%ymm1 @@ -16657,9 +16931,9 @@ _sk_lab_to_xyz_avx: .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 .byte 196,193,108,89,212 // vmulps %ymm12,%ymm2,%ymm2 .byte 196,227,109,74,208,144 // vblendvps %ymm9,%ymm0,%ymm2,%ymm2 - .byte 196,226,125,24,5,113,44,0,0 // vbroadcastss 0x2c71(%rip),%ymm0 # 5fcc <_sk_callback_avx+0x36c> + .byte 196,226,125,24,5,89,50,0,0 // vbroadcastss 0x3259(%rip),%ymm0 # 65b4 <_sk_callback_avx+0x36a> .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 - .byte 196,98,125,24,5,104,44,0,0 // vbroadcastss 0x2c68(%rip),%ymm8 # 5fd0 <_sk_callback_avx+0x370> + .byte 196,98,125,24,5,80,50,0,0 // vbroadcastss 0x3250(%rip),%ymm8 # 65b8 <_sk_callback_avx+0x36e> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -16680,7 +16954,7 @@ _sk_load_a8_avx: .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,117,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,44,44,0,0 // vbroadcastss 0x2c2c(%rip),%ymm1 # 5fd4 <_sk_callback_avx+0x374> + .byte 196,226,125,24,13,20,50,0,0 // vbroadcastss 0x3214(%rip),%ymm1 # 65bc <_sk_callback_avx+0x372> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -16749,7 +17023,7 @@ _sk_gather_a8_avx: .byte 196,226,121,49,201 // vpmovzxbd %xmm1,%xmm1 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,33,43,0,0 // vbroadcastss 0x2b21(%rip),%ymm1 # 5fd8 <_sk_callback_avx+0x378> + .byte 196,226,125,24,13,9,49,0,0 // vbroadcastss 0x3109(%rip),%ymm1 # 65c0 <_sk_callback_avx+0x376> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -16767,7 +17041,7 @@ FUNCTION(_sk_store_a8_avx) _sk_store_a8_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,252,42,0,0 // vbroadcastss 0x2afc(%rip),%ymm8 # 5fdc <_sk_callback_avx+0x37c> + .byte 196,98,125,24,5,228,48,0,0 // vbroadcastss 0x30e4(%rip),%ymm8 # 65c4 <_sk_callback_avx+0x37a> .byte 196,65,100,89,192 // vmulps %ymm8,%ymm3,%ymm8 .byte 196,65,125,91,192 // vcvtps2dq %ymm8,%ymm8 .byte 196,67,125,25,193,1 // vextractf128 $0x1,%ymm8,%xmm9 @@ -16837,10 +17111,10 @@ _sk_load_g8_avx: .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,117,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,33,42,0,0 // vbroadcastss 0x2a21(%rip),%ymm1 # 5fe0 <_sk_callback_avx+0x380> + .byte 196,226,125,24,13,9,48,0,0 // vbroadcastss 0x3009(%rip),%ymm1 # 65c8 <_sk_callback_avx+0x37e> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,22,42,0,0 // vbroadcastss 0x2a16(%rip),%ymm3 # 5fe4 <_sk_callback_avx+0x384> + .byte 196,226,125,24,29,254,47,0,0 // vbroadcastss 0x2ffe(%rip),%ymm3 # 65cc <_sk_callback_avx+0x382> .byte 76,137,193 // mov %r8,%rcx .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 @@ -16906,10 +17180,10 @@ _sk_gather_g8_avx: .byte 196,226,121,49,201 // vpmovzxbd %xmm1,%xmm1 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,21,41,0,0 // vbroadcastss 0x2915(%rip),%ymm1 # 5fe8 <_sk_callback_avx+0x388> + .byte 196,226,125,24,13,253,46,0,0 // vbroadcastss 0x2efd(%rip),%ymm1 # 65d0 <_sk_callback_avx+0x386> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,10,41,0,0 // vbroadcastss 0x290a(%rip),%ymm3 # 5fec <_sk_callback_avx+0x38c> + .byte 196,226,125,24,29,242,46,0,0 // vbroadcastss 0x2ef2(%rip),%ymm3 # 65d4 <_sk_callback_avx+0x38a> .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 .byte 91 // pop %rbx @@ -16989,10 +17263,10 @@ _sk_gather_i8_avx: .byte 196,163,121,34,4,163,2 // vpinsrd $0x2,(%rbx,%r12,4),%xmm0,%xmm0 .byte 196,163,121,34,28,19,3 // vpinsrd $0x3,(%rbx,%r10,1),%xmm0,%xmm3 .byte 196,227,61,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - .byte 197,124,40,21,146,41,0,0 // vmovaps 0x2992(%rip),%ymm10 # 61c0 <_sk_callback_avx+0x560> + .byte 197,124,40,21,114,47,0,0 // vmovaps 0x2f72(%rip),%ymm10 # 67a0 <_sk_callback_avx+0x556> .byte 196,193,124,84,194 // vandps %ymm10,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,176,39,0,0 // vbroadcastss 0x27b0(%rip),%ymm9 # 5ff0 <_sk_callback_avx+0x390> + .byte 196,98,125,24,13,152,45,0,0 // vbroadcastss 0x2d98(%rip),%ymm9 # 65d8 <_sk_callback_avx+0x38e> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,113,114,208,8 // vpsrld $0x8,%xmm8,%xmm1 .byte 197,233,114,211,8 // vpsrld $0x8,%xmm3,%xmm2 @@ -17032,23 +17306,23 @@ _sk_load_565_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,209,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - .byte 196,226,125,24,5,26,39,0,0 // vbroadcastss 0x271a(%rip),%ymm0 # 5ff4 <_sk_callback_avx+0x394> + .byte 196,226,125,24,5,2,45,0,0 // vbroadcastss 0x2d02(%rip),%ymm0 # 65dc <_sk_callback_avx+0x392> .byte 197,236,84,192 // vandps %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,13,39,0,0 // vbroadcastss 0x270d(%rip),%ymm1 # 5ff8 <_sk_callback_avx+0x398> + .byte 196,226,125,24,13,245,44,0,0 // vbroadcastss 0x2cf5(%rip),%ymm1 # 65e0 <_sk_callback_avx+0x396> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,4,39,0,0 // vbroadcastss 0x2704(%rip),%ymm1 # 5ffc <_sk_callback_avx+0x39c> + .byte 196,226,125,24,13,236,44,0,0 // vbroadcastss 0x2cec(%rip),%ymm1 # 65e4 <_sk_callback_avx+0x39a> .byte 197,236,84,201 // vandps %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,247,38,0,0 // vbroadcastss 0x26f7(%rip),%ymm3 # 6000 <_sk_callback_avx+0x3a0> + .byte 196,226,125,24,29,223,44,0,0 // vbroadcastss 0x2cdf(%rip),%ymm3 # 65e8 <_sk_callback_avx+0x39e> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,24,29,238,38,0,0 // vbroadcastss 0x26ee(%rip),%ymm3 # 6004 <_sk_callback_avx+0x3a4> + .byte 196,226,125,24,29,214,44,0,0 // vbroadcastss 0x2cd6(%rip),%ymm3 # 65ec <_sk_callback_avx+0x3a2> .byte 197,236,84,211 // vandps %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,225,38,0,0 // vbroadcastss 0x26e1(%rip),%ymm3 # 6008 <_sk_callback_avx+0x3a8> + .byte 196,226,125,24,29,201,44,0,0 // vbroadcastss 0x2cc9(%rip),%ymm3 # 65f0 <_sk_callback_avx+0x3a6> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,214,38,0,0 // vbroadcastss 0x26d6(%rip),%ymm3 # 600c <_sk_callback_avx+0x3ac> + .byte 196,226,125,24,29,190,44,0,0 // vbroadcastss 0x2cbe(%rip),%ymm3 # 65f4 <_sk_callback_avx+0x3aa> .byte 255,224 // jmpq *%rax .byte 65,137,200 // mov %ecx,%r8d .byte 65,128,224,7 // and $0x7,%r8b @@ -17147,23 +17421,23 @@ _sk_gather_565_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,209,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - .byte 196,226,125,24,5,118,37,0,0 // vbroadcastss 0x2576(%rip),%ymm0 # 6010 <_sk_callback_avx+0x3b0> + .byte 196,226,125,24,5,94,43,0,0 // vbroadcastss 0x2b5e(%rip),%ymm0 # 65f8 <_sk_callback_avx+0x3ae> .byte 197,236,84,192 // vandps %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,105,37,0,0 // vbroadcastss 0x2569(%rip),%ymm1 # 6014 <_sk_callback_avx+0x3b4> + .byte 196,226,125,24,13,81,43,0,0 // vbroadcastss 0x2b51(%rip),%ymm1 # 65fc <_sk_callback_avx+0x3b2> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,96,37,0,0 // vbroadcastss 0x2560(%rip),%ymm1 # 6018 <_sk_callback_avx+0x3b8> + .byte 196,226,125,24,13,72,43,0,0 // vbroadcastss 0x2b48(%rip),%ymm1 # 6600 <_sk_callback_avx+0x3b6> .byte 197,236,84,201 // vandps %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,83,37,0,0 // vbroadcastss 0x2553(%rip),%ymm3 # 601c <_sk_callback_avx+0x3bc> + .byte 196,226,125,24,29,59,43,0,0 // vbroadcastss 0x2b3b(%rip),%ymm3 # 6604 <_sk_callback_avx+0x3ba> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,24,29,74,37,0,0 // vbroadcastss 0x254a(%rip),%ymm3 # 6020 <_sk_callback_avx+0x3c0> + .byte 196,226,125,24,29,50,43,0,0 // vbroadcastss 0x2b32(%rip),%ymm3 # 6608 <_sk_callback_avx+0x3be> .byte 197,236,84,211 // vandps %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,61,37,0,0 // vbroadcastss 0x253d(%rip),%ymm3 # 6024 <_sk_callback_avx+0x3c4> + .byte 196,226,125,24,29,37,43,0,0 // vbroadcastss 0x2b25(%rip),%ymm3 # 660c <_sk_callback_avx+0x3c2> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,50,37,0,0 // vbroadcastss 0x2532(%rip),%ymm3 # 6028 <_sk_callback_avx+0x3c8> + .byte 196,226,125,24,29,26,43,0,0 // vbroadcastss 0x2b1a(%rip),%ymm3 # 6610 <_sk_callback_avx+0x3c6> .byte 91 // pop %rbx .byte 65,92 // pop %r12 .byte 65,94 // pop %r14 @@ -17177,14 +17451,14 @@ FUNCTION(_sk_store_565_avx) _sk_store_565_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,30,37,0,0 // vbroadcastss 0x251e(%rip),%ymm8 # 602c <_sk_callback_avx+0x3cc> + .byte 196,98,125,24,5,6,43,0,0 // vbroadcastss 0x2b06(%rip),%ymm8 # 6614 <_sk_callback_avx+0x3ca> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,41,114,241,11 // vpslld $0xb,%xmm9,%xmm10 .byte 196,67,125,25,201,1 // vextractf128 $0x1,%ymm9,%xmm9 .byte 196,193,49,114,241,11 // vpslld $0xb,%xmm9,%xmm9 .byte 196,67,45,24,201,1 // vinsertf128 $0x1,%xmm9,%ymm10,%ymm9 - .byte 196,98,125,24,21,247,36,0,0 // vbroadcastss 0x24f7(%rip),%ymm10 # 6030 <_sk_callback_avx+0x3d0> + .byte 196,98,125,24,21,223,42,0,0 // vbroadcastss 0x2adf(%rip),%ymm10 # 6618 <_sk_callback_avx+0x3ce> .byte 196,65,116,89,210 // vmulps %ymm10,%ymm1,%ymm10 .byte 196,65,125,91,210 // vcvtps2dq %ymm10,%ymm10 .byte 196,193,33,114,242,5 // vpslld $0x5,%xmm10,%xmm11 @@ -17258,25 +17532,25 @@ _sk_load_4444_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - .byte 196,226,125,24,5,0,36,0,0 // vbroadcastss 0x2400(%rip),%ymm0 # 6034 <_sk_callback_avx+0x3d4> + .byte 196,226,125,24,5,232,41,0,0 // vbroadcastss 0x29e8(%rip),%ymm0 # 661c <_sk_callback_avx+0x3d2> .byte 197,228,84,192 // vandps %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,243,35,0,0 // vbroadcastss 0x23f3(%rip),%ymm1 # 6038 <_sk_callback_avx+0x3d8> + .byte 196,226,125,24,13,219,41,0,0 // vbroadcastss 0x29db(%rip),%ymm1 # 6620 <_sk_callback_avx+0x3d6> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,234,35,0,0 // vbroadcastss 0x23ea(%rip),%ymm1 # 603c <_sk_callback_avx+0x3dc> + .byte 196,226,125,24,13,210,41,0,0 // vbroadcastss 0x29d2(%rip),%ymm1 # 6624 <_sk_callback_avx+0x3da> .byte 197,228,84,201 // vandps %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,221,35,0,0 // vbroadcastss 0x23dd(%rip),%ymm2 # 6040 <_sk_callback_avx+0x3e0> + .byte 196,226,125,24,21,197,41,0,0 // vbroadcastss 0x29c5(%rip),%ymm2 # 6628 <_sk_callback_avx+0x3de> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,21,212,35,0,0 // vbroadcastss 0x23d4(%rip),%ymm2 # 6044 <_sk_callback_avx+0x3e4> + .byte 196,226,125,24,21,188,41,0,0 // vbroadcastss 0x29bc(%rip),%ymm2 # 662c <_sk_callback_avx+0x3e2> .byte 197,228,84,210 // vandps %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,199,35,0,0 // vbroadcastss 0x23c7(%rip),%ymm8 # 6048 <_sk_callback_avx+0x3e8> + .byte 196,98,125,24,5,175,41,0,0 // vbroadcastss 0x29af(%rip),%ymm8 # 6630 <_sk_callback_avx+0x3e6> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,189,35,0,0 // vbroadcastss 0x23bd(%rip),%ymm8 # 604c <_sk_callback_avx+0x3ec> + .byte 196,98,125,24,5,165,41,0,0 // vbroadcastss 0x29a5(%rip),%ymm8 # 6634 <_sk_callback_avx+0x3ea> .byte 196,193,100,84,216 // vandps %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,175,35,0,0 // vbroadcastss 0x23af(%rip),%ymm8 # 6050 <_sk_callback_avx+0x3f0> + .byte 196,98,125,24,5,151,41,0,0 // vbroadcastss 0x2997(%rip),%ymm8 # 6638 <_sk_callback_avx+0x3ee> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -17378,25 +17652,25 @@ _sk_gather_4444_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - .byte 196,226,125,24,5,70,34,0,0 // vbroadcastss 0x2246(%rip),%ymm0 # 6054 <_sk_callback_avx+0x3f4> + .byte 196,226,125,24,5,46,40,0,0 // vbroadcastss 0x282e(%rip),%ymm0 # 663c <_sk_callback_avx+0x3f2> .byte 197,228,84,192 // vandps %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,57,34,0,0 // vbroadcastss 0x2239(%rip),%ymm1 # 6058 <_sk_callback_avx+0x3f8> + .byte 196,226,125,24,13,33,40,0,0 // vbroadcastss 0x2821(%rip),%ymm1 # 6640 <_sk_callback_avx+0x3f6> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,48,34,0,0 // vbroadcastss 0x2230(%rip),%ymm1 # 605c <_sk_callback_avx+0x3fc> + .byte 196,226,125,24,13,24,40,0,0 // vbroadcastss 0x2818(%rip),%ymm1 # 6644 <_sk_callback_avx+0x3fa> .byte 197,228,84,201 // vandps %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,35,34,0,0 // vbroadcastss 0x2223(%rip),%ymm2 # 6060 <_sk_callback_avx+0x400> + .byte 196,226,125,24,21,11,40,0,0 // vbroadcastss 0x280b(%rip),%ymm2 # 6648 <_sk_callback_avx+0x3fe> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,21,26,34,0,0 // vbroadcastss 0x221a(%rip),%ymm2 # 6064 <_sk_callback_avx+0x404> + .byte 196,226,125,24,21,2,40,0,0 // vbroadcastss 0x2802(%rip),%ymm2 # 664c <_sk_callback_avx+0x402> .byte 197,228,84,210 // vandps %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,13,34,0,0 // vbroadcastss 0x220d(%rip),%ymm8 # 6068 <_sk_callback_avx+0x408> + .byte 196,98,125,24,5,245,39,0,0 // vbroadcastss 0x27f5(%rip),%ymm8 # 6650 <_sk_callback_avx+0x406> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,3,34,0,0 // vbroadcastss 0x2203(%rip),%ymm8 # 606c <_sk_callback_avx+0x40c> + .byte 196,98,125,24,5,235,39,0,0 // vbroadcastss 0x27eb(%rip),%ymm8 # 6654 <_sk_callback_avx+0x40a> .byte 196,193,100,84,216 // vandps %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,245,33,0,0 // vbroadcastss 0x21f5(%rip),%ymm8 # 6070 <_sk_callback_avx+0x410> + .byte 196,98,125,24,5,221,39,0,0 // vbroadcastss 0x27dd(%rip),%ymm8 # 6658 <_sk_callback_avx+0x40e> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -17412,7 +17686,7 @@ FUNCTION(_sk_store_4444_avx) _sk_store_4444_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,218,33,0,0 // vbroadcastss 0x21da(%rip),%ymm8 # 6074 <_sk_callback_avx+0x414> + .byte 196,98,125,24,5,194,39,0,0 // vbroadcastss 0x27c2(%rip),%ymm8 # 665c <_sk_callback_avx+0x412> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,41,114,241,12 // vpslld $0xc,%xmm9,%xmm10 @@ -17493,10 +17767,10 @@ _sk_load_8888_avx: .byte 72,133,201 // test %rcx,%rcx .byte 15,133,135,0,0,0 // jne 4041 <_sk_load_8888_avx+0x95> .byte 196,65,124,16,12,186 // vmovups (%r10,%rdi,4),%ymm9 - .byte 197,124,40,21,24,34,0,0 // vmovaps 0x2218(%rip),%ymm10 # 61e0 <_sk_callback_avx+0x580> + .byte 197,124,40,21,248,39,0,0 // vmovaps 0x27f8(%rip),%ymm10 # 67c0 <_sk_callback_avx+0x576> .byte 196,193,52,84,194 // vandps %ymm10,%ymm9,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,158,32,0,0 // vbroadcastss 0x209e(%rip),%ymm8 # 6078 <_sk_callback_avx+0x418> + .byte 196,98,125,24,5,134,38,0,0 // vbroadcastss 0x2686(%rip),%ymm8 # 6660 <_sk_callback_avx+0x416> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 196,193,113,114,209,8 // vpsrld $0x8,%xmm9,%xmm1 .byte 196,99,125,25,203,1 // vextractf128 $0x1,%ymm9,%xmm3 @@ -17611,10 +17885,10 @@ _sk_gather_8888_avx: .byte 196,131,121,34,4,152,2 // vpinsrd $0x2,(%r8,%r11,4),%xmm0,%xmm0 .byte 196,131,121,34,28,144,3 // vpinsrd $0x3,(%r8,%r10,4),%xmm0,%xmm3 .byte 196,227,61,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - .byte 197,124,40,21,66,32,0,0 // vmovaps 0x2042(%rip),%ymm10 # 6200 <_sk_callback_avx+0x5a0> + .byte 197,124,40,21,34,38,0,0 // vmovaps 0x2622(%rip),%ymm10 # 67e0 <_sk_callback_avx+0x596> .byte 196,193,124,84,194 // vandps %ymm10,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,172,30,0,0 // vbroadcastss 0x1eac(%rip),%ymm9 # 607c <_sk_callback_avx+0x41c> + .byte 196,98,125,24,13,148,36,0,0 // vbroadcastss 0x2494(%rip),%ymm9 # 6664 <_sk_callback_avx+0x41a> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,113,114,208,8 // vpsrld $0x8,%xmm8,%xmm1 .byte 197,233,114,211,8 // vpsrld $0x8,%xmm3,%xmm2 @@ -17646,7 +17920,7 @@ FUNCTION(_sk_store_8888_avx) _sk_store_8888_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,58,30,0,0 // vbroadcastss 0x1e3a(%rip),%ymm8 # 6080 <_sk_callback_avx+0x420> + .byte 196,98,125,24,5,34,36,0,0 // vbroadcastss 0x2422(%rip),%ymm8 # 6668 <_sk_callback_avx+0x41e> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,65,116,89,208 // vmulps %ymm8,%ymm1,%ymm10 @@ -17751,13 +18025,13 @@ _sk_load_f16_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 - .byte 196,98,125,24,37,161,28,0,0 // vbroadcastss 0x1ca1(%rip),%ymm12 # 6084 <_sk_callback_avx+0x424> + .byte 196,98,125,24,37,137,34,0,0 // vbroadcastss 0x2289(%rip),%ymm12 # 666c <_sk_callback_avx+0x422> .byte 196,193,124,84,204 // vandps %ymm12,%ymm0,%ymm1 .byte 197,252,87,193 // vxorps %ymm1,%ymm0,%ymm0 .byte 196,195,125,25,198,1 // vextractf128 $0x1,%ymm0,%xmm14 - .byte 196,98,121,24,29,141,28,0,0 // vbroadcastss 0x1c8d(%rip),%xmm11 # 6088 <_sk_callback_avx+0x428> + .byte 196,98,121,24,29,117,34,0,0 // vbroadcastss 0x2275(%rip),%xmm11 # 6670 <_sk_callback_avx+0x426> .byte 196,193,8,87,219 // vxorps %xmm11,%xmm14,%xmm3 - .byte 196,98,121,24,45,131,28,0,0 // vbroadcastss 0x1c83(%rip),%xmm13 # 608c <_sk_callback_avx+0x42c> + .byte 196,98,121,24,45,107,34,0,0 // vbroadcastss 0x226b(%rip),%xmm13 # 6674 <_sk_callback_avx+0x42a> .byte 197,145,102,219 // vpcmpgtd %xmm3,%xmm13,%xmm3 .byte 196,65,120,87,211 // vxorps %xmm11,%xmm0,%xmm10 .byte 196,65,17,102,210 // vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -17771,7 +18045,7 @@ _sk_load_f16_avx: .byte 196,227,125,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 .byte 197,252,86,193 // vorps %ymm1,%ymm0,%ymm0 .byte 196,227,125,25,193,1 // vextractf128 $0x1,%ymm0,%xmm1 - .byte 196,226,121,24,29,57,28,0,0 // vbroadcastss 0x1c39(%rip),%xmm3 # 6090 <_sk_callback_avx+0x430> + .byte 196,226,121,24,29,33,34,0,0 // vbroadcastss 0x2221(%rip),%xmm3 # 6678 <_sk_callback_avx+0x42e> .byte 197,241,254,203 // vpaddd %xmm3,%xmm1,%xmm1 .byte 197,249,254,195 // vpaddd %xmm3,%xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 @@ -17950,13 +18224,13 @@ _sk_gather_f16_avx: .byte 197,249,105,210 // vpunpckhwd %xmm2,%xmm0,%xmm2 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,194,1 // vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 - .byte 196,98,125,24,37,253,24,0,0 // vbroadcastss 0x18fd(%rip),%ymm12 # 6094 <_sk_callback_avx+0x434> + .byte 196,98,125,24,37,229,30,0,0 // vbroadcastss 0x1ee5(%rip),%ymm12 # 667c <_sk_callback_avx+0x432> .byte 196,193,124,84,212 // vandps %ymm12,%ymm0,%ymm2 .byte 197,252,87,194 // vxorps %ymm2,%ymm0,%ymm0 .byte 196,195,125,25,198,1 // vextractf128 $0x1,%ymm0,%xmm14 - .byte 196,98,121,24,29,233,24,0,0 // vbroadcastss 0x18e9(%rip),%xmm11 # 6098 <_sk_callback_avx+0x438> + .byte 196,98,121,24,29,209,30,0,0 // vbroadcastss 0x1ed1(%rip),%xmm11 # 6680 <_sk_callback_avx+0x436> .byte 196,193,8,87,219 // vxorps %xmm11,%xmm14,%xmm3 - .byte 196,98,121,24,45,223,24,0,0 // vbroadcastss 0x18df(%rip),%xmm13 # 609c <_sk_callback_avx+0x43c> + .byte 196,98,121,24,45,199,30,0,0 // vbroadcastss 0x1ec7(%rip),%xmm13 # 6684 <_sk_callback_avx+0x43a> .byte 197,145,102,219 // vpcmpgtd %xmm3,%xmm13,%xmm3 .byte 196,65,120,87,211 // vxorps %xmm11,%xmm0,%xmm10 .byte 196,65,17,102,210 // vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -17970,7 +18244,7 @@ _sk_gather_f16_avx: .byte 196,227,125,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 .byte 197,252,86,194 // vorps %ymm2,%ymm0,%ymm0 .byte 196,227,125,25,194,1 // vextractf128 $0x1,%ymm0,%xmm2 - .byte 196,226,121,24,29,149,24,0,0 // vbroadcastss 0x1895(%rip),%xmm3 # 60a0 <_sk_callback_avx+0x440> + .byte 196,226,121,24,29,125,30,0,0 // vbroadcastss 0x1e7d(%rip),%xmm3 # 6688 <_sk_callback_avx+0x43e> .byte 197,233,254,211 // vpaddd %xmm3,%xmm2,%xmm2 .byte 197,249,254,195 // vpaddd %xmm3,%xmm0,%xmm0 .byte 196,227,125,24,194,1 // vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 @@ -18074,12 +18348,12 @@ _sk_store_f16_avx: .byte 197,252,17,52,36 // vmovups %ymm6,(%rsp) .byte 197,252,17,108,36,224 // vmovups %ymm5,-0x20(%rsp) .byte 197,252,17,100,36,192 // vmovups %ymm4,-0x40(%rsp) - .byte 196,98,125,24,13,174,22,0,0 // vbroadcastss 0x16ae(%rip),%ymm9 # 60a4 <_sk_callback_avx+0x444> + .byte 196,98,125,24,13,150,28,0,0 // vbroadcastss 0x1c96(%rip),%ymm9 # 668c <_sk_callback_avx+0x442> .byte 196,65,124,84,209 // vandps %ymm9,%ymm0,%ymm10 .byte 197,252,17,68,36,128 // vmovups %ymm0,-0x80(%rsp) .byte 196,65,124,87,218 // vxorps %ymm10,%ymm0,%ymm11 .byte 196,67,125,25,220,1 // vextractf128 $0x1,%ymm11,%xmm12 - .byte 196,98,121,24,5,147,22,0,0 // vbroadcastss 0x1693(%rip),%xmm8 # 60a8 <_sk_callback_avx+0x448> + .byte 196,98,121,24,5,123,28,0,0 // vbroadcastss 0x1c7b(%rip),%xmm8 # 6690 <_sk_callback_avx+0x446> .byte 196,65,57,102,236 // vpcmpgtd %xmm12,%xmm8,%xmm13 .byte 196,65,57,102,243 // vpcmpgtd %xmm11,%xmm8,%xmm14 .byte 196,67,13,24,237,1 // vinsertf128 $0x1,%xmm13,%ymm14,%ymm13 @@ -18089,7 +18363,7 @@ _sk_store_f16_avx: .byte 196,67,13,24,242,1 // vinsertf128 $0x1,%xmm10,%ymm14,%ymm14 .byte 196,193,33,114,211,13 // vpsrld $0xd,%xmm11,%xmm11 .byte 196,193,25,114,212,13 // vpsrld $0xd,%xmm12,%xmm12 - .byte 196,98,125,24,21,90,22,0,0 // vbroadcastss 0x165a(%rip),%ymm10 # 60ac <_sk_callback_avx+0x44c> + .byte 196,98,125,24,21,66,28,0,0 // vbroadcastss 0x1c42(%rip),%ymm10 # 6694 <_sk_callback_avx+0x44a> .byte 196,65,12,86,242 // vorps %ymm10,%ymm14,%ymm14 .byte 196,67,125,25,247,1 // vextractf128 $0x1,%ymm14,%xmm15 .byte 196,65,1,254,228 // vpaddd %xmm12,%xmm15,%xmm12 @@ -18234,7 +18508,7 @@ _sk_load_u16_be_avx: .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,29,178,19,0,0 // vbroadcastss 0x13b2(%rip),%ymm11 # 60b0 <_sk_callback_avx+0x450> + .byte 196,98,125,24,29,154,25,0,0 // vbroadcastss 0x199a(%rip),%ymm11 # 6698 <_sk_callback_avx+0x44e> .byte 196,193,124,89,195 // vmulps %ymm11,%ymm0,%ymm0 .byte 197,177,109,202 // vpunpckhqdq %xmm2,%xmm9,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -18327,7 +18601,7 @@ _sk_load_rgb_u16_be_avx: .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,29,18,18,0,0 // vbroadcastss 0x1212(%rip),%ymm11 # 60b4 <_sk_callback_avx+0x454> + .byte 196,98,125,24,29,250,23,0,0 // vbroadcastss 0x17fa(%rip),%ymm11 # 669c <_sk_callback_avx+0x452> .byte 196,193,124,89,195 // vmulps %ymm11,%ymm0,%ymm0 .byte 197,185,109,202 // vpunpckhqdq %xmm2,%xmm8,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -18348,7 +18622,7 @@ _sk_load_rgb_u16_be_avx: .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,211 // vmulps %ymm11,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,175,17,0,0 // vbroadcastss 0x11af(%rip),%ymm3 # 60b8 <_sk_callback_avx+0x458> + .byte 196,226,125,24,29,151,23,0,0 // vbroadcastss 0x1797(%rip),%ymm3 # 66a0 <_sk_callback_avx+0x456> .byte 255,224 // jmpq *%rax .byte 196,193,121,110,4,64 // vmovd (%r8,%rax,2),%xmm0 .byte 196,193,121,196,68,64,4,2 // vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 @@ -18391,7 +18665,7 @@ _sk_store_u16_be_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,189,0,0,0,0 // lea 0x0(,%rdi,4),%rax - .byte 196,98,125,24,5,236,16,0,0 // vbroadcastss 0x10ec(%rip),%ymm8 # 60bc <_sk_callback_avx+0x45c> + .byte 196,98,125,24,5,212,22,0,0 // vbroadcastss 0x16d4(%rip),%ymm8 # 66a4 <_sk_callback_avx+0x45a> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,67,125,25,202,1 // vextractf128 $0x1,%ymm9,%xmm10 @@ -18657,12 +18931,12 @@ HIDDEN _sk_luminance_to_alpha_avx .globl _sk_luminance_to_alpha_avx FUNCTION(_sk_luminance_to_alpha_avx) _sk_luminance_to_alpha_avx: - .byte 196,226,125,24,29,19,13,0,0 // vbroadcastss 0xd13(%rip),%ymm3 # 60c0 <_sk_callback_avx+0x460> + .byte 196,226,125,24,29,251,18,0,0 // vbroadcastss 0x12fb(%rip),%ymm3 # 66a8 <_sk_callback_avx+0x45e> .byte 197,252,89,195 // vmulps %ymm3,%ymm0,%ymm0 - .byte 196,226,125,24,29,10,13,0,0 // vbroadcastss 0xd0a(%rip),%ymm3 # 60c4 <_sk_callback_avx+0x464> + .byte 196,226,125,24,29,242,18,0,0 // vbroadcastss 0x12f2(%rip),%ymm3 # 66ac <_sk_callback_avx+0x462> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 .byte 197,252,88,193 // vaddps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,253,12,0,0 // vbroadcastss 0xcfd(%rip),%ymm1 # 60c8 <_sk_callback_avx+0x468> + .byte 196,226,125,24,13,229,18,0,0 // vbroadcastss 0x12e5(%rip),%ymm1 # 66b0 <_sk_callback_avx+0x466> .byte 197,236,89,201 // vmulps %ymm1,%ymm2,%ymm1 .byte 197,252,88,217 // vaddps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -18829,121 +19103,409 @@ _sk_matrix_perspective_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax +HIDDEN _sk_evenly_spaced_gradient_avx +.globl _sk_evenly_spaced_gradient_avx +FUNCTION(_sk_evenly_spaced_gradient_avx) +_sk_evenly_spaced_gradient_avx: + .byte 85 // push %rbp + .byte 65,87 // push %r15 + .byte 65,86 // push %r14 + .byte 65,85 // push %r13 + .byte 65,84 // push %r12 + .byte 83 // push %rbx + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 72,139,24 // mov (%rax),%rbx + .byte 72,139,104,8 // mov 0x8(%rax),%rbp + .byte 72,255,203 // dec %rbx + .byte 120,7 // js 5688 <_sk_evenly_spaced_gradient_avx+0x1f> + .byte 196,225,242,42,203 // vcvtsi2ss %rbx,%xmm1,%xmm1 + .byte 235,21 // jmp 569d <_sk_evenly_spaced_gradient_avx+0x34> + .byte 73,137,216 // mov %rbx,%r8 + .byte 73,209,232 // shr %r8 + .byte 131,227,1 // and $0x1,%ebx + .byte 76,9,195 // or %r8,%rbx + .byte 196,225,242,42,203 // vcvtsi2ss %rbx,%xmm1,%xmm1 + .byte 197,242,88,201 // vaddss %xmm1,%xmm1,%xmm1 + .byte 196,227,121,4,201,0 // vpermilps $0x0,%xmm1,%xmm1 + .byte 196,227,117,24,201,1 // vinsertf128 $0x1,%xmm1,%ymm1,%ymm1 + .byte 197,244,89,200 // vmulps %ymm0,%ymm1,%ymm1 + .byte 197,254,91,201 // vcvttps2dq %ymm1,%ymm1 + .byte 196,195,249,22,200,1 // vpextrq $0x1,%xmm1,%r8 + .byte 69,137,193 // mov %r8d,%r9d + .byte 73,193,232,32 // shr $0x20,%r8 + .byte 196,193,249,126,202 // vmovq %xmm1,%r10 + .byte 69,137,211 // mov %r10d,%r11d + .byte 73,193,234,32 // shr $0x20,%r10 + .byte 196,227,125,25,201,1 // vextractf128 $0x1,%ymm1,%xmm1 + .byte 196,195,249,22,207,1 // vpextrq $0x1,%xmm1,%r15 + .byte 69,137,254 // mov %r15d,%r14d + .byte 73,193,239,32 // shr $0x20,%r15 + .byte 196,193,249,126,205 // vmovq %xmm1,%r13 + .byte 69,137,236 // mov %r13d,%r12d + .byte 73,193,237,32 // shr $0x20,%r13 + .byte 196,161,122,16,76,165,0 // vmovss 0x0(%rbp,%r12,4),%xmm1 + .byte 196,163,113,33,76,173,0,16 // vinsertps $0x10,0x0(%rbp,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,84,181,0 // vmovss 0x0(%rbp,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,84,189,0 // vmovss 0x0(%rbp,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,84,157,0 // vmovss 0x0(%rbp,%r11,4),%xmm2 + .byte 196,163,105,33,84,149,0,16 // vinsertps $0x10,0x0(%rbp,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,92,141,0 // vmovss 0x0(%rbp,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,92,133,0 // vmovss 0x0(%rbp,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm8 + .byte 72,139,88,40 // mov 0x28(%rax),%rbx + .byte 196,161,122,16,20,163 // vmovss (%rbx,%r12,4),%xmm2 + .byte 196,163,105,33,20,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,179 // vmovss (%rbx,%r14,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,187 // vmovss (%rbx,%r15,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,155 // vmovss (%rbx,%r11,4),%xmm3 + .byte 196,163,97,33,28,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm3,%xmm3 + .byte 196,161,122,16,12,139 // vmovss (%rbx,%r9,4),%xmm1 + .byte 196,227,97,33,201,32 // vinsertps $0x20,%xmm1,%xmm3,%xmm1 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,113,33,203,48 // vinsertps $0x30,%xmm3,%xmm1,%xmm1 + .byte 196,99,117,24,226,1 // vinsertf128 $0x1,%xmm2,%ymm1,%ymm12 + .byte 72,139,88,16 // mov 0x10(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,28,179 // vmovss (%rbx,%r14,4),%xmm3 + .byte 196,227,113,33,203,32 // vinsertps $0x20,%xmm3,%xmm1,%xmm1 + .byte 196,161,122,16,28,187 // vmovss (%rbx,%r15,4),%xmm3 + .byte 196,227,113,33,203,48 // vinsertps $0x30,%xmm3,%xmm1,%xmm1 + .byte 196,161,122,16,28,155 // vmovss (%rbx,%r11,4),%xmm3 + .byte 196,163,97,33,28,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm3,%xmm3 + .byte 196,161,122,16,20,139 // vmovss (%rbx,%r9,4),%xmm2 + .byte 196,227,97,33,210,32 // vinsertps $0x20,%xmm2,%xmm3,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,233,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm13 + .byte 72,139,88,48 // mov 0x30(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,201,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm9 + .byte 72,139,88,24 // mov 0x18(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,209,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm10 + .byte 72,139,88,56 // mov 0x38(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm11 + .byte 72,139,88,32 // mov 0x20(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,241,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm14 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 196,161,122,16,12,160 // vmovss (%rax,%r12,4),%xmm1 + .byte 196,163,113,33,12,168,16 // vinsertps $0x10,(%rax,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,176 // vmovss (%rax,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,184 // vmovss (%rax,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,152 // vmovss (%rax,%r11,4),%xmm2 + .byte 196,163,105,33,20,144,16 // vinsertps $0x10,(%rax,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,136 // vmovss (%rax,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,128 // vmovss (%rax,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,227,109,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm3 + .byte 197,188,89,200 // vmulps %ymm0,%ymm8,%ymm1 + .byte 196,65,116,88,196 // vaddps %ymm12,%ymm1,%ymm8 + .byte 197,148,89,200 // vmulps %ymm0,%ymm13,%ymm1 + .byte 196,193,116,88,201 // vaddps %ymm9,%ymm1,%ymm1 + .byte 197,172,89,208 // vmulps %ymm0,%ymm10,%ymm2 + .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 + .byte 197,140,89,192 // vmulps %ymm0,%ymm14,%ymm0 + .byte 197,252,88,219 // vaddps %ymm3,%ymm0,%ymm3 + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 + .byte 91 // pop %rbx + .byte 65,92 // pop %r12 + .byte 65,93 // pop %r13 + .byte 65,94 // pop %r14 + .byte 65,95 // pop %r15 + .byte 93 // pop %rbp + .byte 255,224 // jmpq *%rax + HIDDEN _sk_gradient_avx .globl _sk_gradient_avx FUNCTION(_sk_gradient_avx) _sk_gradient_avx: + .byte 85 // push %rbp + .byte 65,87 // push %r15 + .byte 65,86 // push %r14 + .byte 65,85 // push %r13 + .byte 65,84 // push %r12 + .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,64,16 // vbroadcastss 0x10(%rax),%ymm8 - .byte 196,226,125,24,72,20 // vbroadcastss 0x14(%rax),%ymm1 - .byte 196,226,125,24,80,24 // vbroadcastss 0x18(%rax),%ymm2 - .byte 196,226,125,24,88,28 // vbroadcastss 0x1c(%rax),%ymm3 .byte 76,139,0 // mov (%rax),%r8 - .byte 77,133,192 // test %r8,%r8 - .byte 15,132,146,0,0,0 // je 5721 <_sk_gradient_avx+0xb8> - .byte 72,139,64,8 // mov 0x8(%rax),%rax - .byte 72,131,192,32 // add $0x20,%rax - .byte 196,65,28,87,228 // vxorps %ymm12,%ymm12,%ymm12 - .byte 196,65,52,87,201 // vxorps %ymm9,%ymm9,%ymm9 - .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 - .byte 196,65,36,87,219 // vxorps %ymm11,%ymm11,%ymm11 - .byte 196,98,125,24,104,224 // vbroadcastss -0x20(%rax),%ymm13 - .byte 196,65,124,194,237,1 // vcmpltps %ymm13,%ymm0,%ymm13 - .byte 196,98,125,24,112,228 // vbroadcastss -0x1c(%rax),%ymm14 - .byte 196,67,13,74,228,208 // vblendvps %ymm13,%ymm12,%ymm14,%ymm12 - .byte 196,98,125,24,112,232 // vbroadcastss -0x18(%rax),%ymm14 - .byte 196,67,13,74,219,208 // vblendvps %ymm13,%ymm11,%ymm14,%ymm11 - .byte 196,98,125,24,112,236 // vbroadcastss -0x14(%rax),%ymm14 - .byte 196,67,13,74,210,208 // vblendvps %ymm13,%ymm10,%ymm14,%ymm10 - .byte 196,98,125,24,112,240 // vbroadcastss -0x10(%rax),%ymm14 - .byte 196,67,13,74,201,208 // vblendvps %ymm13,%ymm9,%ymm14,%ymm9 - .byte 196,98,125,24,112,244 // vbroadcastss -0xc(%rax),%ymm14 - .byte 196,67,13,74,192,208 // vblendvps %ymm13,%ymm8,%ymm14,%ymm8 - .byte 196,98,125,24,112,248 // vbroadcastss -0x8(%rax),%ymm14 - .byte 196,227,13,74,201,208 // vblendvps %ymm13,%ymm1,%ymm14,%ymm1 - .byte 196,98,125,24,112,252 // vbroadcastss -0x4(%rax),%ymm14 - .byte 196,227,13,74,210,208 // vblendvps %ymm13,%ymm2,%ymm14,%ymm2 - .byte 196,98,125,24,48 // vbroadcastss (%rax),%ymm14 - .byte 196,227,13,74,219,208 // vblendvps %ymm13,%ymm3,%ymm14,%ymm3 - .byte 72,131,192,36 // add $0x24,%rax + .byte 197,244,87,201 // vxorps %ymm1,%ymm1,%ymm1 + .byte 73,131,248,2 // cmp $0x2,%r8 + .byte 114,80 // jb 5a2b <_sk_gradient_avx+0x69> + .byte 72,139,88,72 // mov 0x48(%rax),%rbx .byte 73,255,200 // dec %r8 - .byte 117,140 // jne 56ab <_sk_gradient_avx+0x42> - .byte 235,20 // jmp 5735 <_sk_gradient_avx+0xcc> - .byte 196,65,36,87,219 // vxorps %ymm11,%ymm11,%ymm11 - .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 + .byte 72,131,195,4 // add $0x4,%rbx .byte 196,65,52,87,201 // vxorps %ymm9,%ymm9,%ymm9 - .byte 196,65,28,87,228 // vxorps %ymm12,%ymm12,%ymm12 - .byte 197,28,89,224 // vmulps %ymm0,%ymm12,%ymm12 - .byte 196,65,60,88,196 // vaddps %ymm12,%ymm8,%ymm8 - .byte 197,36,89,216 // vmulps %ymm0,%ymm11,%ymm11 - .byte 197,164,88,201 // vaddps %ymm1,%ymm11,%ymm1 - .byte 197,44,89,208 // vmulps %ymm0,%ymm10,%ymm10 - .byte 197,172,88,210 // vaddps %ymm2,%ymm10,%ymm2 - .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 - .byte 197,252,88,219 // vaddps %ymm3,%ymm0,%ymm3 - .byte 72,173 // lods %ds:(%rsi),%rax - .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 - .byte 255,224 // jmpq *%rax - -HIDDEN _sk_evenly_spaced_2_stop_gradient_avx -.globl _sk_evenly_spaced_2_stop_gradient_avx -FUNCTION(_sk_evenly_spaced_2_stop_gradient_avx) -_sk_evenly_spaced_2_stop_gradient_avx: - .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,8 // vbroadcastss (%rax),%ymm1 - .byte 196,226,125,24,80,16 // vbroadcastss 0x10(%rax),%ymm2 - .byte 197,244,89,200 // vmulps %ymm0,%ymm1,%ymm1 - .byte 197,116,88,194 // vaddps %ymm2,%ymm1,%ymm8 - .byte 196,226,125,24,72,4 // vbroadcastss 0x4(%rax),%ymm1 - .byte 196,226,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm2 - .byte 197,244,89,200 // vmulps %ymm0,%ymm1,%ymm1 - .byte 197,244,88,202 // vaddps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,80,8 // vbroadcastss 0x8(%rax),%ymm2 - .byte 196,226,125,24,88,24 // vbroadcastss 0x18(%rax),%ymm3 - .byte 197,236,89,208 // vmulps %ymm0,%ymm2,%ymm2 - .byte 197,236,88,211 // vaddps %ymm3,%ymm2,%ymm2 - .byte 196,226,125,24,88,12 // vbroadcastss 0xc(%rax),%ymm3 - .byte 196,98,125,24,72,28 // vbroadcastss 0x1c(%rax),%ymm9 - .byte 197,228,89,192 // vmulps %ymm0,%ymm3,%ymm0 - .byte 196,193,124,88,217 // vaddps %ymm9,%ymm0,%ymm3 - .byte 72,173 // lods %ds:(%rsi),%rax - .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 - .byte 255,224 // jmpq *%rax - -HIDDEN _sk_xy_to_unit_angle_avx -.globl _sk_xy_to_unit_angle_avx -FUNCTION(_sk_xy_to_unit_angle_avx) -_sk_xy_to_unit_angle_avx: - .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 - .byte 197,60,92,200 // vsubps %ymm0,%ymm8,%ymm9 - .byte 197,52,84,200 // vandps %ymm0,%ymm9,%ymm9 - .byte 197,60,92,209 // vsubps %ymm1,%ymm8,%ymm10 - .byte 197,44,84,209 // vandps %ymm1,%ymm10,%ymm10 - .byte 196,65,52,93,218 // vminps %ymm10,%ymm9,%ymm11 - .byte 196,65,52,95,226 // vmaxps %ymm10,%ymm9,%ymm12 - .byte 196,65,36,94,220 // vdivps %ymm12,%ymm11,%ymm11 + .byte 196,98,125,24,21,192,12,0,0 // vbroadcastss 0xcc0(%rip),%ymm10 # 66b4 <_sk_callback_avx+0x46a> + .byte 197,244,87,201 // vxorps %ymm1,%ymm1,%ymm1 + .byte 196,98,125,24,3 // vbroadcastss (%rbx),%ymm8 + .byte 197,60,194,192,2 // vcmpleps %ymm0,%ymm8,%ymm8 + .byte 196,67,53,74,194,128 // vblendvps %ymm8,%ymm10,%ymm9,%ymm8 + .byte 196,99,125,25,194,1 // vextractf128 $0x1,%ymm8,%xmm2 + .byte 196,227,125,25,203,1 // vextractf128 $0x1,%ymm1,%xmm3 + .byte 197,233,254,211 // vpaddd %xmm3,%xmm2,%xmm2 + .byte 197,185,254,201 // vpaddd %xmm1,%xmm8,%xmm1 + .byte 196,227,117,24,202,1 // vinsertf128 $0x1,%xmm2,%ymm1,%ymm1 + .byte 72,131,195,4 // add $0x4,%rbx + .byte 73,255,200 // dec %r8 + .byte 117,205 // jne 59f8 <_sk_gradient_avx+0x36> + .byte 196,195,249,22,200,1 // vpextrq $0x1,%xmm1,%r8 + .byte 69,137,193 // mov %r8d,%r9d + .byte 73,193,232,32 // shr $0x20,%r8 + .byte 196,193,249,126,202 // vmovq %xmm1,%r10 + .byte 69,137,211 // mov %r10d,%r11d + .byte 73,193,234,32 // shr $0x20,%r10 + .byte 196,227,125,25,201,1 // vextractf128 $0x1,%ymm1,%xmm1 + .byte 196,195,249,22,207,1 // vpextrq $0x1,%xmm1,%r15 + .byte 69,137,254 // mov %r15d,%r14d + .byte 73,193,239,32 // shr $0x20,%r15 + .byte 196,193,249,126,205 // vmovq %xmm1,%r13 + .byte 69,137,236 // mov %r13d,%r12d + .byte 73,193,237,32 // shr $0x20,%r13 + .byte 72,139,104,8 // mov 0x8(%rax),%rbp + .byte 72,139,88,16 // mov 0x10(%rax),%rbx + .byte 196,161,122,16,76,165,0 // vmovss 0x0(%rbp,%r12,4),%xmm1 + .byte 196,163,113,33,76,173,0,16 // vinsertps $0x10,0x0(%rbp,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,84,181,0 // vmovss 0x0(%rbp,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,84,189,0 // vmovss 0x0(%rbp,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,84,157,0 // vmovss 0x0(%rbp,%r11,4),%xmm2 + .byte 196,163,105,33,84,149,0,16 // vinsertps $0x10,0x0(%rbp,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,92,141,0 // vmovss 0x0(%rbp,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,92,133,0 // vmovss 0x0(%rbp,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm8 + .byte 72,139,104,40 // mov 0x28(%rax),%rbp + .byte 196,161,122,16,84,165,0 // vmovss 0x0(%rbp,%r12,4),%xmm2 + .byte 196,163,105,33,84,173,0,16 // vinsertps $0x10,0x0(%rbp,%r13,4),%xmm2,%xmm2 + .byte 196,161,122,16,92,181,0 // vmovss 0x0(%rbp,%r14,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,92,189,0 // vmovss 0x0(%rbp,%r15,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,92,157,0 // vmovss 0x0(%rbp,%r11,4),%xmm3 + .byte 196,163,97,33,92,149,0,16 // vinsertps $0x10,0x0(%rbp,%r10,4),%xmm3,%xmm3 + .byte 196,161,122,16,76,141,0 // vmovss 0x0(%rbp,%r9,4),%xmm1 + .byte 196,227,97,33,201,32 // vinsertps $0x20,%xmm1,%xmm3,%xmm1 + .byte 196,161,122,16,92,133,0 // vmovss 0x0(%rbp,%r8,4),%xmm3 + .byte 196,227,113,33,203,48 // vinsertps $0x30,%xmm3,%xmm1,%xmm1 + .byte 196,99,117,24,226,1 // vinsertf128 $0x1,%xmm2,%ymm1,%ymm12 + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,28,179 // vmovss (%rbx,%r14,4),%xmm3 + .byte 196,227,113,33,203,32 // vinsertps $0x20,%xmm3,%xmm1,%xmm1 + .byte 196,161,122,16,28,187 // vmovss (%rbx,%r15,4),%xmm3 + .byte 196,227,113,33,203,48 // vinsertps $0x30,%xmm3,%xmm1,%xmm1 + .byte 196,161,122,16,28,155 // vmovss (%rbx,%r11,4),%xmm3 + .byte 196,163,97,33,28,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm3,%xmm3 + .byte 196,161,122,16,20,139 // vmovss (%rbx,%r9,4),%xmm2 + .byte 196,227,97,33,210,32 // vinsertps $0x20,%xmm2,%xmm3,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,233,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm13 + .byte 72,139,88,48 // mov 0x30(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,201,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm9 + .byte 72,139,88,24 // mov 0x18(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,209,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm10 + .byte 72,139,88,56 // mov 0x38(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm11 + .byte 72,139,88,32 // mov 0x20(%rax),%rbx + .byte 196,161,122,16,12,163 // vmovss (%rbx,%r12,4),%xmm1 + .byte 196,163,113,33,12,171,16 // vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,179 // vmovss (%rbx,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,187 // vmovss (%rbx,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,155 // vmovss (%rbx,%r11,4),%xmm2 + .byte 196,163,105,33,20,147,16 // vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,139 // vmovss (%rbx,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,131 // vmovss (%rbx,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,99,109,24,241,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm14 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 196,161,122,16,12,160 // vmovss (%rax,%r12,4),%xmm1 + .byte 196,163,113,33,12,168,16 // vinsertps $0x10,(%rax,%r13,4),%xmm1,%xmm1 + .byte 196,161,122,16,20,176 // vmovss (%rax,%r14,4),%xmm2 + .byte 196,227,113,33,202,32 // vinsertps $0x20,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,184 // vmovss (%rax,%r15,4),%xmm2 + .byte 196,227,113,33,202,48 // vinsertps $0x30,%xmm2,%xmm1,%xmm1 + .byte 196,161,122,16,20,152 // vmovss (%rax,%r11,4),%xmm2 + .byte 196,163,105,33,20,144,16 // vinsertps $0x10,(%rax,%r10,4),%xmm2,%xmm2 + .byte 196,161,122,16,28,136 // vmovss (%rax,%r9,4),%xmm3 + .byte 196,227,105,33,211,32 // vinsertps $0x20,%xmm3,%xmm2,%xmm2 + .byte 196,161,122,16,28,128 // vmovss (%rax,%r8,4),%xmm3 + .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 + .byte 196,227,109,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm2,%ymm3 + .byte 197,188,89,200 // vmulps %ymm0,%ymm8,%ymm1 + .byte 196,65,116,88,196 // vaddps %ymm12,%ymm1,%ymm8 + .byte 197,148,89,200 // vmulps %ymm0,%ymm13,%ymm1 + .byte 196,193,116,88,201 // vaddps %ymm9,%ymm1,%ymm1 + .byte 197,172,89,208 // vmulps %ymm0,%ymm10,%ymm2 + .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 + .byte 197,140,89,192 // vmulps %ymm0,%ymm14,%ymm0 + .byte 197,252,88,219 // vaddps %ymm3,%ymm0,%ymm3 + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 + .byte 91 // pop %rbx + .byte 65,92 // pop %r12 + .byte 65,93 // pop %r13 + .byte 65,94 // pop %r14 + .byte 65,95 // pop %r15 + .byte 93 // pop %rbp + .byte 255,224 // jmpq *%rax + +HIDDEN _sk_evenly_spaced_2_stop_gradient_avx +.globl _sk_evenly_spaced_2_stop_gradient_avx +FUNCTION(_sk_evenly_spaced_2_stop_gradient_avx) +_sk_evenly_spaced_2_stop_gradient_avx: + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 196,226,125,24,8 // vbroadcastss (%rax),%ymm1 + .byte 196,226,125,24,80,16 // vbroadcastss 0x10(%rax),%ymm2 + .byte 197,244,89,200 // vmulps %ymm0,%ymm1,%ymm1 + .byte 197,116,88,194 // vaddps %ymm2,%ymm1,%ymm8 + .byte 196,226,125,24,72,4 // vbroadcastss 0x4(%rax),%ymm1 + .byte 196,226,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm2 + .byte 197,244,89,200 // vmulps %ymm0,%ymm1,%ymm1 + .byte 197,244,88,202 // vaddps %ymm2,%ymm1,%ymm1 + .byte 196,226,125,24,80,8 // vbroadcastss 0x8(%rax),%ymm2 + .byte 196,226,125,24,88,24 // vbroadcastss 0x18(%rax),%ymm3 + .byte 197,236,89,208 // vmulps %ymm0,%ymm2,%ymm2 + .byte 197,236,88,211 // vaddps %ymm3,%ymm2,%ymm2 + .byte 196,226,125,24,88,12 // vbroadcastss 0xc(%rax),%ymm3 + .byte 196,98,125,24,72,28 // vbroadcastss 0x1c(%rax),%ymm9 + .byte 197,228,89,192 // vmulps %ymm0,%ymm3,%ymm0 + .byte 196,193,124,88,217 // vaddps %ymm9,%ymm0,%ymm3 + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 197,124,41,192 // vmovaps %ymm8,%ymm0 + .byte 255,224 // jmpq *%rax + +HIDDEN _sk_xy_to_unit_angle_avx +.globl _sk_xy_to_unit_angle_avx +FUNCTION(_sk_xy_to_unit_angle_avx) +_sk_xy_to_unit_angle_avx: + .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 + .byte 197,60,92,200 // vsubps %ymm0,%ymm8,%ymm9 + .byte 197,52,84,200 // vandps %ymm0,%ymm9,%ymm9 + .byte 197,60,92,209 // vsubps %ymm1,%ymm8,%ymm10 + .byte 197,44,84,209 // vandps %ymm1,%ymm10,%ymm10 + .byte 196,65,52,93,218 // vminps %ymm10,%ymm9,%ymm11 + .byte 196,65,52,95,226 // vmaxps %ymm10,%ymm9,%ymm12 + .byte 196,65,36,94,220 // vdivps %ymm12,%ymm11,%ymm11 .byte 196,65,36,89,227 // vmulps %ymm11,%ymm11,%ymm12 - .byte 196,98,125,24,45,226,8,0,0 // vbroadcastss 0x8e2(%rip),%ymm13 # 60cc <_sk_callback_avx+0x46c> + .byte 196,98,125,24,45,228,8,0,0 // vbroadcastss 0x8e4(%rip),%ymm13 # 66b8 <_sk_callback_avx+0x46e> .byte 196,65,28,89,237 // vmulps %ymm13,%ymm12,%ymm13 - .byte 196,98,125,24,53,216,8,0,0 // vbroadcastss 0x8d8(%rip),%ymm14 # 60d0 <_sk_callback_avx+0x470> + .byte 196,98,125,24,53,218,8,0,0 // vbroadcastss 0x8da(%rip),%ymm14 # 66bc <_sk_callback_avx+0x472> .byte 196,65,20,88,238 // vaddps %ymm14,%ymm13,%ymm13 .byte 196,65,28,89,237 // vmulps %ymm13,%ymm12,%ymm13 - .byte 196,98,125,24,53,201,8,0,0 // vbroadcastss 0x8c9(%rip),%ymm14 # 60d4 <_sk_callback_avx+0x474> + .byte 196,98,125,24,53,203,8,0,0 // vbroadcastss 0x8cb(%rip),%ymm14 # 66c0 <_sk_callback_avx+0x476> .byte 196,65,20,88,238 // vaddps %ymm14,%ymm13,%ymm13 .byte 196,65,28,89,229 // vmulps %ymm13,%ymm12,%ymm12 - .byte 196,98,125,24,45,186,8,0,0 // vbroadcastss 0x8ba(%rip),%ymm13 # 60d8 <_sk_callback_avx+0x478> + .byte 196,98,125,24,45,188,8,0,0 // vbroadcastss 0x8bc(%rip),%ymm13 # 66c4 <_sk_callback_avx+0x47a> .byte 196,65,28,88,229 // vaddps %ymm13,%ymm12,%ymm12 .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 .byte 196,65,52,194,202,1 // vcmpltps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,24,21,165,8,0,0 // vbroadcastss 0x8a5(%rip),%ymm10 # 60dc <_sk_callback_avx+0x47c> + .byte 196,98,125,24,21,167,8,0,0 // vbroadcastss 0x8a7(%rip),%ymm10 # 66c8 <_sk_callback_avx+0x47e> .byte 196,65,44,92,211 // vsubps %ymm11,%ymm10,%ymm10 .byte 196,67,37,74,202,144 // vblendvps %ymm9,%ymm10,%ymm11,%ymm9 .byte 196,193,124,194,192,1 // vcmpltps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,21,143,8,0,0 // vbroadcastss 0x88f(%rip),%ymm10 # 60e0 <_sk_callback_avx+0x480> + .byte 196,98,125,24,21,145,8,0,0 // vbroadcastss 0x891(%rip),%ymm10 # 66cc <_sk_callback_avx+0x482> .byte 196,65,44,92,209 // vsubps %ymm9,%ymm10,%ymm10 .byte 196,195,53,74,194,0 // vblendvps %ymm0,%ymm10,%ymm9,%ymm0 .byte 196,65,116,194,200,1 // vcmpltps %ymm8,%ymm1,%ymm9 - .byte 196,98,125,24,21,121,8,0,0 // vbroadcastss 0x879(%rip),%ymm10 # 60e4 <_sk_callback_avx+0x484> + .byte 196,98,125,24,21,123,8,0,0 // vbroadcastss 0x87b(%rip),%ymm10 # 66d0 <_sk_callback_avx+0x486> .byte 197,44,92,208 // vsubps %ymm0,%ymm10,%ymm10 .byte 196,195,125,74,194,144 // vblendvps %ymm9,%ymm10,%ymm0,%ymm0 .byte 196,65,124,194,200,3 // vcmpunordps %ymm8,%ymm0,%ymm9 @@ -18968,7 +19530,7 @@ HIDDEN _sk_save_xy_avx FUNCTION(_sk_save_xy_avx) _sk_save_xy_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,63,8,0,0 // vbroadcastss 0x83f(%rip),%ymm8 # 60e8 <_sk_callback_avx+0x488> + .byte 196,98,125,24,5,65,8,0,0 // vbroadcastss 0x841(%rip),%ymm8 # 66d4 <_sk_callback_avx+0x48a> .byte 196,65,124,88,200 // vaddps %ymm8,%ymm0,%ymm9 .byte 196,67,125,8,209,1 // vroundps $0x1,%ymm9,%ymm10 .byte 196,65,52,92,202 // vsubps %ymm10,%ymm9,%ymm9 @@ -19005,9 +19567,9 @@ HIDDEN _sk_bilinear_nx_avx FUNCTION(_sk_bilinear_nx_avx) _sk_bilinear_nx_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,203,7,0,0 // vbroadcastss 0x7cb(%rip),%ymm0 # 60ec <_sk_callback_avx+0x48c> + .byte 196,226,125,24,5,205,7,0,0 // vbroadcastss 0x7cd(%rip),%ymm0 # 66d8 <_sk_callback_avx+0x48e> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,194,7,0,0 // vbroadcastss 0x7c2(%rip),%ymm8 # 60f0 <_sk_callback_avx+0x490> + .byte 196,98,125,24,5,196,7,0,0 // vbroadcastss 0x7c4(%rip),%ymm8 # 66dc <_sk_callback_avx+0x492> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -19018,7 +19580,7 @@ HIDDEN _sk_bilinear_px_avx FUNCTION(_sk_bilinear_px_avx) _sk_bilinear_px_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,170,7,0,0 // vbroadcastss 0x7aa(%rip),%ymm0 # 60f4 <_sk_callback_avx+0x494> + .byte 196,226,125,24,5,172,7,0,0 // vbroadcastss 0x7ac(%rip),%ymm0 # 66e0 <_sk_callback_avx+0x496> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -19030,9 +19592,9 @@ HIDDEN _sk_bilinear_ny_avx FUNCTION(_sk_bilinear_ny_avx) _sk_bilinear_ny_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,142,7,0,0 // vbroadcastss 0x78e(%rip),%ymm1 # 60f8 <_sk_callback_avx+0x498> + .byte 196,226,125,24,13,144,7,0,0 // vbroadcastss 0x790(%rip),%ymm1 # 66e4 <_sk_callback_avx+0x49a> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,132,7,0,0 // vbroadcastss 0x784(%rip),%ymm8 # 60fc <_sk_callback_avx+0x49c> + .byte 196,98,125,24,5,134,7,0,0 // vbroadcastss 0x786(%rip),%ymm8 # 66e8 <_sk_callback_avx+0x49e> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -19043,7 +19605,7 @@ HIDDEN _sk_bilinear_py_avx FUNCTION(_sk_bilinear_py_avx) _sk_bilinear_py_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,108,7,0,0 // vbroadcastss 0x76c(%rip),%ymm1 # 6100 <_sk_callback_avx+0x4a0> + .byte 196,226,125,24,13,110,7,0,0 // vbroadcastss 0x76e(%rip),%ymm1 # 66ec <_sk_callback_avx+0x4a2> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -19055,14 +19617,14 @@ HIDDEN _sk_bicubic_n3x_avx FUNCTION(_sk_bicubic_n3x_avx) _sk_bicubic_n3x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,79,7,0,0 // vbroadcastss 0x74f(%rip),%ymm0 # 6104 <_sk_callback_avx+0x4a4> + .byte 196,226,125,24,5,81,7,0,0 // vbroadcastss 0x751(%rip),%ymm0 # 66f0 <_sk_callback_avx+0x4a6> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,70,7,0,0 // vbroadcastss 0x746(%rip),%ymm8 # 6108 <_sk_callback_avx+0x4a8> + .byte 196,98,125,24,5,72,7,0,0 // vbroadcastss 0x748(%rip),%ymm8 # 66f4 <_sk_callback_avx+0x4aa> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,55,7,0,0 // vbroadcastss 0x737(%rip),%ymm10 # 610c <_sk_callback_avx+0x4ac> + .byte 196,98,125,24,21,57,7,0,0 // vbroadcastss 0x739(%rip),%ymm10 # 66f8 <_sk_callback_avx+0x4ae> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,45,7,0,0 // vbroadcastss 0x72d(%rip),%ymm10 # 6110 <_sk_callback_avx+0x4b0> + .byte 196,98,125,24,21,47,7,0,0 // vbroadcastss 0x72f(%rip),%ymm10 # 66fc <_sk_callback_avx+0x4b2> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -19074,19 +19636,19 @@ HIDDEN _sk_bicubic_n1x_avx FUNCTION(_sk_bicubic_n1x_avx) _sk_bicubic_n1x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,16,7,0,0 // vbroadcastss 0x710(%rip),%ymm0 # 6114 <_sk_callback_avx+0x4b4> + .byte 196,226,125,24,5,18,7,0,0 // vbroadcastss 0x712(%rip),%ymm0 # 6700 <_sk_callback_avx+0x4b6> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,7,7,0,0 // vbroadcastss 0x707(%rip),%ymm8 # 6118 <_sk_callback_avx+0x4b8> + .byte 196,98,125,24,5,9,7,0,0 // vbroadcastss 0x709(%rip),%ymm8 # 6704 <_sk_callback_avx+0x4ba> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,253,6,0,0 // vbroadcastss 0x6fd(%rip),%ymm9 # 611c <_sk_callback_avx+0x4bc> + .byte 196,98,125,24,13,255,6,0,0 // vbroadcastss 0x6ff(%rip),%ymm9 # 6708 <_sk_callback_avx+0x4be> .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,243,6,0,0 // vbroadcastss 0x6f3(%rip),%ymm10 # 6120 <_sk_callback_avx+0x4c0> + .byte 196,98,125,24,21,245,6,0,0 // vbroadcastss 0x6f5(%rip),%ymm10 # 670c <_sk_callback_avx+0x4c2> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,228,6,0,0 // vbroadcastss 0x6e4(%rip),%ymm10 # 6124 <_sk_callback_avx+0x4c4> + .byte 196,98,125,24,21,230,6,0,0 // vbroadcastss 0x6e6(%rip),%ymm10 # 6710 <_sk_callback_avx+0x4c6> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,213,6,0,0 // vbroadcastss 0x6d5(%rip),%ymm9 # 6128 <_sk_callback_avx+0x4c8> + .byte 196,98,125,24,13,215,6,0,0 // vbroadcastss 0x6d7(%rip),%ymm9 # 6714 <_sk_callback_avx+0x4ca> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -19097,17 +19659,17 @@ HIDDEN _sk_bicubic_p1x_avx FUNCTION(_sk_bicubic_p1x_avx) _sk_bicubic_p1x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,189,6,0,0 // vbroadcastss 0x6bd(%rip),%ymm8 # 612c <_sk_callback_avx+0x4cc> + .byte 196,98,125,24,5,191,6,0,0 // vbroadcastss 0x6bf(%rip),%ymm8 # 6718 <_sk_callback_avx+0x4ce> .byte 197,188,88,0 // vaddps (%rax),%ymm8,%ymm0 .byte 197,124,16,72,64 // vmovups 0x40(%rax),%ymm9 - .byte 196,98,125,24,21,175,6,0,0 // vbroadcastss 0x6af(%rip),%ymm10 # 6130 <_sk_callback_avx+0x4d0> + .byte 196,98,125,24,21,177,6,0,0 // vbroadcastss 0x6b1(%rip),%ymm10 # 671c <_sk_callback_avx+0x4d2> .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 - .byte 196,98,125,24,29,165,6,0,0 // vbroadcastss 0x6a5(%rip),%ymm11 # 6134 <_sk_callback_avx+0x4d4> + .byte 196,98,125,24,29,167,6,0,0 // vbroadcastss 0x6a7(%rip),%ymm11 # 6720 <_sk_callback_avx+0x4d6> .byte 196,65,44,88,211 // vaddps %ymm11,%ymm10,%ymm10 .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 .byte 196,65,44,88,192 // vaddps %ymm8,%ymm10,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 - .byte 196,98,125,24,13,140,6,0,0 // vbroadcastss 0x68c(%rip),%ymm9 # 6138 <_sk_callback_avx+0x4d8> + .byte 196,98,125,24,13,142,6,0,0 // vbroadcastss 0x68e(%rip),%ymm9 # 6724 <_sk_callback_avx+0x4da> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -19118,13 +19680,13 @@ HIDDEN _sk_bicubic_p3x_avx FUNCTION(_sk_bicubic_p3x_avx) _sk_bicubic_p3x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,116,6,0,0 // vbroadcastss 0x674(%rip),%ymm0 # 613c <_sk_callback_avx+0x4dc> + .byte 196,226,125,24,5,118,6,0,0 // vbroadcastss 0x676(%rip),%ymm0 # 6728 <_sk_callback_avx+0x4de> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,97,6,0,0 // vbroadcastss 0x661(%rip),%ymm10 # 6140 <_sk_callback_avx+0x4e0> + .byte 196,98,125,24,21,99,6,0,0 // vbroadcastss 0x663(%rip),%ymm10 # 672c <_sk_callback_avx+0x4e2> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,87,6,0,0 // vbroadcastss 0x657(%rip),%ymm10 # 6144 <_sk_callback_avx+0x4e4> + .byte 196,98,125,24,21,89,6,0,0 // vbroadcastss 0x659(%rip),%ymm10 # 6730 <_sk_callback_avx+0x4e6> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -19136,14 +19698,14 @@ HIDDEN _sk_bicubic_n3y_avx FUNCTION(_sk_bicubic_n3y_avx) _sk_bicubic_n3y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,58,6,0,0 // vbroadcastss 0x63a(%rip),%ymm1 # 6148 <_sk_callback_avx+0x4e8> + .byte 196,226,125,24,13,60,6,0,0 // vbroadcastss 0x63c(%rip),%ymm1 # 6734 <_sk_callback_avx+0x4ea> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,48,6,0,0 // vbroadcastss 0x630(%rip),%ymm8 # 614c <_sk_callback_avx+0x4ec> + .byte 196,98,125,24,5,50,6,0,0 // vbroadcastss 0x632(%rip),%ymm8 # 6738 <_sk_callback_avx+0x4ee> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,33,6,0,0 // vbroadcastss 0x621(%rip),%ymm10 # 6150 <_sk_callback_avx+0x4f0> + .byte 196,98,125,24,21,35,6,0,0 // vbroadcastss 0x623(%rip),%ymm10 # 673c <_sk_callback_avx+0x4f2> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,23,6,0,0 // vbroadcastss 0x617(%rip),%ymm10 # 6154 <_sk_callback_avx+0x4f4> + .byte 196,98,125,24,21,25,6,0,0 // vbroadcastss 0x619(%rip),%ymm10 # 6740 <_sk_callback_avx+0x4f6> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -19155,19 +19717,19 @@ HIDDEN _sk_bicubic_n1y_avx FUNCTION(_sk_bicubic_n1y_avx) _sk_bicubic_n1y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,250,5,0,0 // vbroadcastss 0x5fa(%rip),%ymm1 # 6158 <_sk_callback_avx+0x4f8> + .byte 196,226,125,24,13,252,5,0,0 // vbroadcastss 0x5fc(%rip),%ymm1 # 6744 <_sk_callback_avx+0x4fa> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,240,5,0,0 // vbroadcastss 0x5f0(%rip),%ymm8 # 615c <_sk_callback_avx+0x4fc> + .byte 196,98,125,24,5,242,5,0,0 // vbroadcastss 0x5f2(%rip),%ymm8 # 6748 <_sk_callback_avx+0x4fe> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,230,5,0,0 // vbroadcastss 0x5e6(%rip),%ymm9 # 6160 <_sk_callback_avx+0x500> + .byte 196,98,125,24,13,232,5,0,0 // vbroadcastss 0x5e8(%rip),%ymm9 # 674c <_sk_callback_avx+0x502> .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,220,5,0,0 // vbroadcastss 0x5dc(%rip),%ymm10 # 6164 <_sk_callback_avx+0x504> + .byte 196,98,125,24,21,222,5,0,0 // vbroadcastss 0x5de(%rip),%ymm10 # 6750 <_sk_callback_avx+0x506> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,205,5,0,0 // vbroadcastss 0x5cd(%rip),%ymm10 # 6168 <_sk_callback_avx+0x508> + .byte 196,98,125,24,21,207,5,0,0 // vbroadcastss 0x5cf(%rip),%ymm10 # 6754 <_sk_callback_avx+0x50a> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,190,5,0,0 // vbroadcastss 0x5be(%rip),%ymm9 # 616c <_sk_callback_avx+0x50c> + .byte 196,98,125,24,13,192,5,0,0 // vbroadcastss 0x5c0(%rip),%ymm9 # 6758 <_sk_callback_avx+0x50e> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -19178,17 +19740,17 @@ HIDDEN _sk_bicubic_p1y_avx FUNCTION(_sk_bicubic_p1y_avx) _sk_bicubic_p1y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,166,5,0,0 // vbroadcastss 0x5a6(%rip),%ymm8 # 6170 <_sk_callback_avx+0x510> + .byte 196,98,125,24,5,168,5,0,0 // vbroadcastss 0x5a8(%rip),%ymm8 # 675c <_sk_callback_avx+0x512> .byte 197,188,88,72,32 // vaddps 0x20(%rax),%ymm8,%ymm1 .byte 197,124,16,72,96 // vmovups 0x60(%rax),%ymm9 - .byte 196,98,125,24,21,151,5,0,0 // vbroadcastss 0x597(%rip),%ymm10 # 6174 <_sk_callback_avx+0x514> + .byte 196,98,125,24,21,153,5,0,0 // vbroadcastss 0x599(%rip),%ymm10 # 6760 <_sk_callback_avx+0x516> .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 - .byte 196,98,125,24,29,141,5,0,0 // vbroadcastss 0x58d(%rip),%ymm11 # 6178 <_sk_callback_avx+0x518> + .byte 196,98,125,24,29,143,5,0,0 // vbroadcastss 0x58f(%rip),%ymm11 # 6764 <_sk_callback_avx+0x51a> .byte 196,65,44,88,211 // vaddps %ymm11,%ymm10,%ymm10 .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 .byte 196,65,44,88,192 // vaddps %ymm8,%ymm10,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 - .byte 196,98,125,24,13,116,5,0,0 // vbroadcastss 0x574(%rip),%ymm9 # 617c <_sk_callback_avx+0x51c> + .byte 196,98,125,24,13,118,5,0,0 // vbroadcastss 0x576(%rip),%ymm9 # 6768 <_sk_callback_avx+0x51e> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -19199,13 +19761,13 @@ HIDDEN _sk_bicubic_p3y_avx FUNCTION(_sk_bicubic_p3y_avx) _sk_bicubic_p3y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,92,5,0,0 // vbroadcastss 0x55c(%rip),%ymm1 # 6180 <_sk_callback_avx+0x520> + .byte 196,226,125,24,13,94,5,0,0 // vbroadcastss 0x55e(%rip),%ymm1 # 676c <_sk_callback_avx+0x522> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,72,5,0,0 // vbroadcastss 0x548(%rip),%ymm10 # 6184 <_sk_callback_avx+0x524> + .byte 196,98,125,24,21,74,5,0,0 // vbroadcastss 0x54a(%rip),%ymm10 # 6770 <_sk_callback_avx+0x526> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,62,5,0,0 // vbroadcastss 0x53e(%rip),%ymm10 # 6188 <_sk_callback_avx+0x528> + .byte 196,98,125,24,21,64,5,0,0 // vbroadcastss 0x540(%rip),%ymm10 # 6774 <_sk_callback_avx+0x52a> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -19329,25 +19891,25 @@ BALIGN4 .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 5e39 <.literal4+0xb1> + .byte 71,225,61 // rex.RXB loope 6421 <.literal4+0xb1> .byte 0,0 // add %al,(%rax) .byte 128,63,154 // cmpb $0x9a,(%rdi) .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 5e49 <.literal4+0xc1> + .byte 71,225,61 // rex.RXB loope 6431 <.literal4+0xc1> .byte 0,0 // add %al,(%rax) .byte 128,63,154 // cmpb $0x9a,(%rdi) .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 5e59 <.literal4+0xd1> + .byte 71,225,61 // rex.RXB loope 6441 <.literal4+0xd1> .byte 0,0 // add %al,(%rax) .byte 128,63,154 // cmpb $0x9a,(%rdi) .byte 153 // cltd .byte 153 // cltd .byte 62,61,10,23,63,174 // ds cmp $0xae3f170a,%eax - .byte 71,225,61 // rex.RXB loope 5e69 <.literal4+0xe1> + .byte 71,225,61 // rex.RXB loope 6451 <.literal4+0xe1> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -19397,7 +19959,7 @@ BALIGN4 .byte 190,129,128,128,59 // mov $0x3b808081,%esi .byte 129,128,128,59,0,248,0,0,8,33 // addl $0x21080000,-0x7ffc480(%rax) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 5eb5 <.literal4+0x12d> + .byte 224,7 // loopne 649d <.literal4+0x12d> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -19413,10 +19975,10 @@ BALIGN4 .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) .byte 0,52,255 // add %dh,(%rdi,%rdi,8) .byte 255 // (bad) - .byte 127,0 // jg 5edc <.literal4+0x154> + .byte 127,0 // jg 64c4 <.literal4+0x154> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5f55 <.literal4+0x1cd> + .byte 119,115 // ja 653d <.literal4+0x1cd> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -19430,10 +19992,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 5f10 <.literal4+0x188> + .byte 127,0 // jg 64f8 <.literal4+0x188> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5f89 <.literal4+0x201> + .byte 119,115 // ja 6571 <.literal4+0x201> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -19447,10 +20009,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 5f44 <.literal4+0x1bc> + .byte 127,0 // jg 652c <.literal4+0x1bc> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5fbd <.literal4+0x235> + .byte 119,115 // ja 65a5 <.literal4+0x235> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -19464,10 +20026,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 5f78 <.literal4+0x1f0> + .byte 127,0 // jg 6560 <.literal4+0x1f0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5ff1 <.literal4+0x269> + .byte 119,115 // ja 65d9 <.literal4+0x269> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -19480,7 +20042,7 @@ BALIGN4 .byte 0,75,0 // add %cl,0x0(%rbx) .byte 0,128,63,0,0,200 // add %al,-0x37ffffc1(%rax) .byte 66,0,0 // rex.X add %al,(%rax) - .byte 127,67 // jg 5fef <.literal4+0x267> + .byte 127,67 // jg 65d7 <.literal4+0x267> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -19492,10 +20054,10 @@ BALIGN4 .byte 190,80,128,3,62 // mov $0x3e038050,%esi .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 600f <.literal4+0x287> + .byte 118,63 // jbe 65f7 <.literal4+0x287> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 6023 <.literal4+0x29b> + .byte 127,67 // jg 660b <.literal4+0x29b> .byte 129,128,128,59,0,0,128,63,129,128 // addl $0x80813f80,0x3b80(%rax) .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,128,63,129,128,128 // add %al,-0x7f7f7ec1(%rax) @@ -19504,7 +20066,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 6005 <.literal4+0x27d> + .byte 224,7 // loopne 65ed <.literal4+0x27d> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -19516,7 +20078,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 6021 <.literal4+0x299> + .byte 224,7 // loopne 6609 <.literal4+0x299> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -19527,7 +20089,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 6076 <.literal4+0x2ee> + .byte 124,66 // jl 665e <.literal4+0x2ee> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 137,136,136,55,0,15 // mov %ecx,0xf003788(%rax) @@ -19545,9 +20107,9 @@ BALIGN4 .byte 137,136,136,59,15,0 // mov %ecx,0xf3b88(%rax) .byte 0,0 // add %al,(%rax) .byte 137,136,136,61,0,0 // mov %ecx,0x3d88(%rax) - .byte 112,65 // jo 60b9 <.literal4+0x331> + .byte 112,65 // jo 66a1 <.literal4+0x331> .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 60c7 <.literal4+0x33f> + .byte 127,67 // jg 66af <.literal4+0x33f> .byte 0,128,0,0,0,0 // add %al,0x0(%rax) .byte 0,128,0,4,0,128 // add %al,-0x7ffffc00(%rax) .byte 0,0 // add %al,(%rax) @@ -19563,7 +20125,7 @@ BALIGN4 .byte 0,128,55,0,0,128 // add %al,-0x7fffffc9(%rax) .byte 63 // (bad) .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 6107 <.literal4+0x37f> + .byte 127,71 // jg 66ef <.literal4+0x37f> .byte 208 // (bad) .byte 179,89 // mov $0x59,%bl .byte 62,89 // ds pop %rcx @@ -19571,9 +20133,12 @@ BALIGN4 .byte 55 // (bad) .byte 63 // (bad) .byte 152 // cwtl - .byte 221,147,61,111,43,231 // fstl -0x18d490c3(%rbx) - .byte 187,159,215,202,60 // mov $0x3ccad79f,%ebx - .byte 212 // (bad) + .byte 221,147,61,1,0,0 // fstl 0x13d(%rbx) + .byte 0,111,43 // add %ch,0x2b(%rdi) + .byte 231,187 // out %eax,$0xbb + .byte 159 // lahf + .byte 215 // xlat %ds:(%rbx) + .byte 202,60,212 // lret $0xd43c .byte 100,84 // fs push %rsp .byte 189,169,240,34,62 // mov $0x3e22f0a9,%ebp .byte 0,0 // add %al,(%rax) @@ -19790,7 +20355,7 @@ _sk_seed_shader_sse41: .byte 102,15,110,199 // movd %edi,%xmm0 .byte 102,15,112,192,0 // pshufd $0x0,%xmm0,%xmm0 .byte 15,91,200 // cvtdq2ps %xmm0,%xmm1 - .byte 15,40,21,52,68,0,0 // movaps 0x4434(%rip),%xmm2 # 44b0 <_sk_callback_sse41+0xe2> + .byte 15,40,21,116,70,0,0 // movaps 0x4674(%rip),%xmm2 # 46f0 <_sk_callback_sse41+0xe0> .byte 15,88,202 // addps %xmm2,%xmm1 .byte 15,16,2 // movups (%rdx),%xmm0 .byte 15,88,193 // addps %xmm1,%xmm0 @@ -19799,7 +20364,7 @@ _sk_seed_shader_sse41: .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 15,88,202 // addps %xmm2,%xmm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,21,35,68,0,0 // movaps 0x4423(%rip),%xmm2 # 44c0 <_sk_callback_sse41+0xf2> + .byte 15,40,21,99,70,0,0 // movaps 0x4663(%rip),%xmm2 # 4700 <_sk_callback_sse41+0xf0> .byte 15,87,219 // xorps %xmm3,%xmm3 .byte 15,87,228 // xorps %xmm4,%xmm4 .byte 15,87,237 // xorps %xmm5,%xmm5 @@ -19822,14 +20387,14 @@ _sk_dither_sse41: .byte 102,68,15,110,1 // movd (%rcx),%xmm8 .byte 102,69,15,112,192,0 // pshufd $0x0,%xmm8,%xmm8 .byte 102,69,15,239,193 // pxor %xmm9,%xmm8 - .byte 102,68,15,111,21,232,67,0,0 // movdqa 0x43e8(%rip),%xmm10 # 44d0 <_sk_callback_sse41+0x102> + .byte 102,68,15,111,21,40,70,0,0 // movdqa 0x4628(%rip),%xmm10 # 4710 <_sk_callback_sse41+0x100> .byte 102,69,15,111,216 // movdqa %xmm8,%xmm11 .byte 102,69,15,219,218 // pand %xmm10,%xmm11 .byte 102,65,15,114,243,5 // pslld $0x5,%xmm11 .byte 102,69,15,219,209 // pand %xmm9,%xmm10 .byte 102,65,15,114,242,4 // pslld $0x4,%xmm10 - .byte 102,68,15,111,37,212,67,0,0 // movdqa 0x43d4(%rip),%xmm12 # 44e0 <_sk_callback_sse41+0x112> - .byte 102,68,15,111,45,219,67,0,0 // movdqa 0x43db(%rip),%xmm13 # 44f0 <_sk_callback_sse41+0x122> + .byte 102,68,15,111,37,20,70,0,0 // movdqa 0x4614(%rip),%xmm12 # 4720 <_sk_callback_sse41+0x110> + .byte 102,68,15,111,45,27,70,0,0 // movdqa 0x461b(%rip),%xmm13 # 4730 <_sk_callback_sse41+0x120> .byte 102,69,15,111,240 // movdqa %xmm8,%xmm14 .byte 102,69,15,219,245 // pand %xmm13,%xmm14 .byte 102,65,15,114,246,2 // pslld $0x2,%xmm14 @@ -19845,8 +20410,8 @@ _sk_dither_sse41: .byte 102,69,15,235,245 // por %xmm13,%xmm14 .byte 102,69,15,235,240 // por %xmm8,%xmm14 .byte 69,15,91,198 // cvtdq2ps %xmm14,%xmm8 - .byte 68,15,89,5,150,67,0,0 // mulps 0x4396(%rip),%xmm8 # 4500 <_sk_callback_sse41+0x132> - .byte 68,15,88,5,158,67,0,0 // addps 0x439e(%rip),%xmm8 # 4510 <_sk_callback_sse41+0x142> + .byte 68,15,89,5,214,69,0,0 // mulps 0x45d6(%rip),%xmm8 # 4740 <_sk_callback_sse41+0x130> + .byte 68,15,88,5,222,69,0,0 // addps 0x45de(%rip),%xmm8 # 4750 <_sk_callback_sse41+0x140> .byte 243,68,15,16,72,8 // movss 0x8(%rax),%xmm9 .byte 69,15,198,201,0 // shufps $0x0,%xmm9,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 @@ -19912,7 +20477,7 @@ HIDDEN _sk_srcatop_sse41 FUNCTION(_sk_srcatop_sse41) _sk_srcatop_sse41: .byte 15,89,199 // mulps %xmm7,%xmm0 - .byte 68,15,40,5,33,67,0,0 // movaps 0x4321(%rip),%xmm8 # 4520 <_sk_callback_sse41+0x152> + .byte 68,15,40,5,97,69,0,0 // movaps 0x4561(%rip),%xmm8 # 4760 <_sk_callback_sse41+0x150> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -19937,7 +20502,7 @@ FUNCTION(_sk_dstatop_sse41) _sk_dstatop_sse41: .byte 68,15,40,195 // movaps %xmm3,%xmm8 .byte 68,15,89,196 // mulps %xmm4,%xmm8 - .byte 68,15,40,13,228,66,0,0 // movaps 0x42e4(%rip),%xmm9 # 4530 <_sk_callback_sse41+0x162> + .byte 68,15,40,13,36,69,0,0 // movaps 0x4524(%rip),%xmm9 # 4770 <_sk_callback_sse41+0x160> .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,88,192 // addps %xmm8,%xmm0 @@ -19984,7 +20549,7 @@ HIDDEN _sk_srcout_sse41 .globl _sk_srcout_sse41 FUNCTION(_sk_srcout_sse41) _sk_srcout_sse41: - .byte 68,15,40,5,136,66,0,0 // movaps 0x4288(%rip),%xmm8 # 4540 <_sk_callback_sse41+0x172> + .byte 68,15,40,5,200,68,0,0 // movaps 0x44c8(%rip),%xmm8 # 4780 <_sk_callback_sse41+0x170> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 @@ -19997,7 +20562,7 @@ HIDDEN _sk_dstout_sse41 .globl _sk_dstout_sse41 FUNCTION(_sk_dstout_sse41) _sk_dstout_sse41: - .byte 68,15,40,5,120,66,0,0 // movaps 0x4278(%rip),%xmm8 # 4550 <_sk_callback_sse41+0x182> + .byte 68,15,40,5,184,68,0,0 // movaps 0x44b8(%rip),%xmm8 # 4790 <_sk_callback_sse41+0x180> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 15,89,196 // mulps %xmm4,%xmm0 @@ -20014,7 +20579,7 @@ HIDDEN _sk_srcover_sse41 .globl _sk_srcover_sse41 FUNCTION(_sk_srcover_sse41) _sk_srcover_sse41: - .byte 68,15,40,5,91,66,0,0 // movaps 0x425b(%rip),%xmm8 # 4560 <_sk_callback_sse41+0x192> + .byte 68,15,40,5,155,68,0,0 // movaps 0x449b(%rip),%xmm8 # 47a0 <_sk_callback_sse41+0x190> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -20034,7 +20599,7 @@ HIDDEN _sk_dstover_sse41 .globl _sk_dstover_sse41 FUNCTION(_sk_dstover_sse41) _sk_dstover_sse41: - .byte 68,15,40,5,47,66,0,0 // movaps 0x422f(%rip),%xmm8 # 4570 <_sk_callback_sse41+0x1a2> + .byte 68,15,40,5,111,68,0,0 // movaps 0x446f(%rip),%xmm8 # 47b0 <_sk_callback_sse41+0x1a0> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -20062,7 +20627,7 @@ HIDDEN _sk_multiply_sse41 .globl _sk_multiply_sse41 FUNCTION(_sk_multiply_sse41) _sk_multiply_sse41: - .byte 68,15,40,5,3,66,0,0 // movaps 0x4203(%rip),%xmm8 # 4580 <_sk_callback_sse41+0x1b2> + .byte 68,15,40,5,67,68,0,0 // movaps 0x4443(%rip),%xmm8 # 47c0 <_sk_callback_sse41+0x1b0> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 69,15,40,209 // movaps %xmm9,%xmm10 @@ -20138,7 +20703,7 @@ HIDDEN _sk_xor__sse41 FUNCTION(_sk_xor__sse41) _sk_xor__sse41: .byte 68,15,40,195 // movaps %xmm3,%xmm8 - .byte 15,40,29,52,65,0,0 // movaps 0x4134(%rip),%xmm3 # 4590 <_sk_callback_sse41+0x1c2> + .byte 15,40,29,116,67,0,0 // movaps 0x4374(%rip),%xmm3 # 47d0 <_sk_callback_sse41+0x1c0> .byte 68,15,40,203 // movaps %xmm3,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 @@ -20186,7 +20751,7 @@ _sk_darken_sse41: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,95,209 // maxps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,159,64,0,0 // movaps 0x409f(%rip),%xmm2 # 45a0 <_sk_callback_sse41+0x1d2> + .byte 15,40,21,223,66,0,0 // movaps 0x42df(%rip),%xmm2 # 47e0 <_sk_callback_sse41+0x1d0> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -20220,7 +20785,7 @@ _sk_lighten_sse41: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,68,64,0,0 // movaps 0x4044(%rip),%xmm2 # 45b0 <_sk_callback_sse41+0x1e2> + .byte 15,40,21,132,66,0,0 // movaps 0x4284(%rip),%xmm2 # 47f0 <_sk_callback_sse41+0x1e0> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -20257,7 +20822,7 @@ _sk_difference_sse41: .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,222,63,0,0 // movaps 0x3fde(%rip),%xmm2 # 45c0 <_sk_callback_sse41+0x1f2> + .byte 15,40,21,30,66,0,0 // movaps 0x421e(%rip),%xmm2 # 4800 <_sk_callback_sse41+0x1f0> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -20284,7 +20849,7 @@ _sk_exclusion_sse41: .byte 15,89,214 // mulps %xmm6,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,202 // subps %xmm2,%xmm9 - .byte 15,40,13,159,63,0,0 // movaps 0x3f9f(%rip),%xmm1 # 45d0 <_sk_callback_sse41+0x202> + .byte 15,40,13,223,65,0,0 // movaps 0x41df(%rip),%xmm1 # 4810 <_sk_callback_sse41+0x200> .byte 15,92,203 // subps %xmm3,%xmm1 .byte 15,89,207 // mulps %xmm7,%xmm1 .byte 15,88,217 // addps %xmm1,%xmm3 @@ -20298,7 +20863,7 @@ HIDDEN _sk_colorburn_sse41 FUNCTION(_sk_colorburn_sse41) _sk_colorburn_sse41: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,40,21,142,63,0,0 // movaps 0x3f8e(%rip),%xmm10 # 45e0 <_sk_callback_sse41+0x212> + .byte 68,15,40,21,206,65,0,0 // movaps 0x41ce(%rip),%xmm10 # 4820 <_sk_callback_sse41+0x210> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 69,15,40,203 // movaps %xmm11,%xmm9 @@ -20380,7 +20945,7 @@ HIDDEN _sk_colordodge_sse41 FUNCTION(_sk_colordodge_sse41) _sk_colordodge_sse41: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,40,21,108,62,0,0 // movaps 0x3e6c(%rip),%xmm10 # 45f0 <_sk_callback_sse41+0x222> + .byte 68,15,40,21,172,64,0,0 // movaps 0x40ac(%rip),%xmm10 # 4830 <_sk_callback_sse41+0x220> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 69,15,40,227 // movaps %xmm11,%xmm12 @@ -20462,7 +21027,7 @@ _sk_hardlight_sse41: .byte 15,40,244 // movaps %xmm4,%xmm6 .byte 15,40,227 // movaps %xmm3,%xmm4 .byte 68,15,40,200 // movaps %xmm0,%xmm9 - .byte 68,15,40,21,69,61,0,0 // movaps 0x3d45(%rip),%xmm10 # 4600 <_sk_callback_sse41+0x232> + .byte 68,15,40,21,133,63,0,0 // movaps 0x3f85(%rip),%xmm10 # 4840 <_sk_callback_sse41+0x230> .byte 65,15,40,234 // movaps %xmm10,%xmm5 .byte 15,92,239 // subps %xmm7,%xmm5 .byte 15,40,197 // movaps %xmm5,%xmm0 @@ -20545,7 +21110,7 @@ FUNCTION(_sk_overlay_sse41) _sk_overlay_sse41: .byte 68,15,40,201 // movaps %xmm1,%xmm9 .byte 68,15,40,240 // movaps %xmm0,%xmm14 - .byte 68,15,40,21,42,60,0,0 // movaps 0x3c2a(%rip),%xmm10 # 4610 <_sk_callback_sse41+0x242> + .byte 68,15,40,21,106,62,0,0 // movaps 0x3e6a(%rip),%xmm10 # 4850 <_sk_callback_sse41+0x240> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 65,15,40,195 // movaps %xmm11,%xmm0 @@ -20630,7 +21195,7 @@ _sk_softlight_sse41: .byte 15,40,198 // movaps %xmm6,%xmm0 .byte 15,94,199 // divps %xmm7,%xmm0 .byte 65,15,84,193 // andps %xmm9,%xmm0 - .byte 15,40,13,1,59,0,0 // movaps 0x3b01(%rip),%xmm1 # 4620 <_sk_callback_sse41+0x252> + .byte 15,40,13,65,61,0,0 // movaps 0x3d41(%rip),%xmm1 # 4860 <_sk_callback_sse41+0x250> .byte 68,15,40,209 // movaps %xmm1,%xmm10 .byte 68,15,92,208 // subps %xmm0,%xmm10 .byte 68,15,40,240 // movaps %xmm0,%xmm14 @@ -20643,10 +21208,10 @@ _sk_softlight_sse41: .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 15,89,210 // mulps %xmm2,%xmm2 .byte 15,88,208 // addps %xmm0,%xmm2 - .byte 68,15,40,45,223,58,0,0 // movaps 0x3adf(%rip),%xmm13 # 4630 <_sk_callback_sse41+0x262> + .byte 68,15,40,45,31,61,0,0 // movaps 0x3d1f(%rip),%xmm13 # 4870 <_sk_callback_sse41+0x260> .byte 69,15,88,245 // addps %xmm13,%xmm14 .byte 68,15,89,242 // mulps %xmm2,%xmm14 - .byte 68,15,40,37,223,58,0,0 // movaps 0x3adf(%rip),%xmm12 # 4640 <_sk_callback_sse41+0x272> + .byte 68,15,40,37,31,61,0,0 // movaps 0x3d1f(%rip),%xmm12 # 4880 <_sk_callback_sse41+0x270> .byte 69,15,89,252 // mulps %xmm12,%xmm15 .byte 69,15,88,254 // addps %xmm14,%xmm15 .byte 15,40,198 // movaps %xmm6,%xmm0 @@ -20832,12 +21397,12 @@ _sk_hue_sse41: .byte 68,15,84,208 // andps %xmm0,%xmm10 .byte 15,84,200 // andps %xmm0,%xmm1 .byte 68,15,84,232 // andps %xmm0,%xmm13 - .byte 15,40,5,74,56,0,0 // movaps 0x384a(%rip),%xmm0 # 4650 <_sk_callback_sse41+0x282> + .byte 15,40,5,138,58,0,0 // movaps 0x3a8a(%rip),%xmm0 # 4890 <_sk_callback_sse41+0x280> .byte 68,15,89,224 // mulps %xmm0,%xmm12 - .byte 15,40,21,79,56,0,0 // movaps 0x384f(%rip),%xmm2 # 4660 <_sk_callback_sse41+0x292> + .byte 15,40,21,143,58,0,0 // movaps 0x3a8f(%rip),%xmm2 # 48a0 <_sk_callback_sse41+0x290> .byte 15,89,250 // mulps %xmm2,%xmm7 .byte 65,15,88,252 // addps %xmm12,%xmm7 - .byte 68,15,40,53,80,56,0,0 // movaps 0x3850(%rip),%xmm14 # 4670 <_sk_callback_sse41+0x2a2> + .byte 68,15,40,53,144,58,0,0 // movaps 0x3a90(%rip),%xmm14 # 48b0 <_sk_callback_sse41+0x2a0> .byte 68,15,40,252 // movaps %xmm4,%xmm15 .byte 69,15,89,254 // mulps %xmm14,%xmm15 .byte 68,15,88,255 // addps %xmm7,%xmm15 @@ -20920,7 +21485,7 @@ _sk_hue_sse41: .byte 65,15,88,214 // addps %xmm14,%xmm2 .byte 15,40,196 // movaps %xmm4,%xmm0 .byte 102,15,56,20,202 // blendvps %xmm0,%xmm2,%xmm1 - .byte 68,15,40,13,20,55,0,0 // movaps 0x3714(%rip),%xmm9 # 4680 <_sk_callback_sse41+0x2b2> + .byte 68,15,40,13,84,57,0,0 // movaps 0x3954(%rip),%xmm9 # 48c0 <_sk_callback_sse41+0x2b0> .byte 65,15,40,225 // movaps %xmm9,%xmm4 .byte 15,92,229 // subps %xmm5,%xmm4 .byte 15,40,68,36,200 // movaps -0x38(%rsp),%xmm0 @@ -21014,14 +21579,14 @@ _sk_saturation_sse41: .byte 68,15,84,215 // andps %xmm7,%xmm10 .byte 68,15,84,223 // andps %xmm7,%xmm11 .byte 68,15,84,199 // andps %xmm7,%xmm8 - .byte 15,40,21,206,53,0,0 // movaps 0x35ce(%rip),%xmm2 # 4690 <_sk_callback_sse41+0x2c2> + .byte 15,40,21,14,56,0,0 // movaps 0x380e(%rip),%xmm2 # 48d0 <_sk_callback_sse41+0x2c0> .byte 15,40,221 // movaps %xmm5,%xmm3 .byte 15,89,218 // mulps %xmm2,%xmm3 - .byte 15,40,13,209,53,0,0 // movaps 0x35d1(%rip),%xmm1 # 46a0 <_sk_callback_sse41+0x2d2> + .byte 15,40,13,17,56,0,0 // movaps 0x3811(%rip),%xmm1 # 48e0 <_sk_callback_sse41+0x2d0> .byte 15,40,254 // movaps %xmm6,%xmm7 .byte 15,89,249 // mulps %xmm1,%xmm7 .byte 15,88,251 // addps %xmm3,%xmm7 - .byte 68,15,40,45,208,53,0,0 // movaps 0x35d0(%rip),%xmm13 # 46b0 <_sk_callback_sse41+0x2e2> + .byte 68,15,40,45,16,56,0,0 // movaps 0x3810(%rip),%xmm13 # 48f0 <_sk_callback_sse41+0x2e0> .byte 69,15,89,245 // mulps %xmm13,%xmm14 .byte 68,15,88,247 // addps %xmm7,%xmm14 .byte 65,15,40,218 // movaps %xmm10,%xmm3 @@ -21102,7 +21667,7 @@ _sk_saturation_sse41: .byte 65,15,88,253 // addps %xmm13,%xmm7 .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 102,68,15,56,20,223 // blendvps %xmm0,%xmm7,%xmm11 - .byte 68,15,40,13,150,52,0,0 // movaps 0x3496(%rip),%xmm9 # 46c0 <_sk_callback_sse41+0x2f2> + .byte 68,15,40,13,214,54,0,0 // movaps 0x36d6(%rip),%xmm9 # 4900 <_sk_callback_sse41+0x2f0> .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 68,15,92,204 // subps %xmm4,%xmm9 .byte 15,40,124,36,168 // movaps -0x58(%rsp),%xmm7 @@ -21157,14 +21722,14 @@ _sk_color_sse41: .byte 15,40,231 // movaps %xmm7,%xmm4 .byte 68,15,89,244 // mulps %xmm4,%xmm14 .byte 15,89,204 // mulps %xmm4,%xmm1 - .byte 68,15,40,13,225,51,0,0 // movaps 0x33e1(%rip),%xmm9 # 46d0 <_sk_callback_sse41+0x302> + .byte 68,15,40,13,33,54,0,0 // movaps 0x3621(%rip),%xmm9 # 4910 <_sk_callback_sse41+0x300> .byte 65,15,40,250 // movaps %xmm10,%xmm7 .byte 65,15,89,249 // mulps %xmm9,%xmm7 - .byte 68,15,40,21,225,51,0,0 // movaps 0x33e1(%rip),%xmm10 # 46e0 <_sk_callback_sse41+0x312> + .byte 68,15,40,21,33,54,0,0 // movaps 0x3621(%rip),%xmm10 # 4920 <_sk_callback_sse41+0x310> .byte 65,15,40,219 // movaps %xmm11,%xmm3 .byte 65,15,89,218 // mulps %xmm10,%xmm3 .byte 15,88,223 // addps %xmm7,%xmm3 - .byte 68,15,40,29,222,51,0,0 // movaps 0x33de(%rip),%xmm11 # 46f0 <_sk_callback_sse41+0x322> + .byte 68,15,40,29,30,54,0,0 // movaps 0x361e(%rip),%xmm11 # 4930 <_sk_callback_sse41+0x320> .byte 69,15,40,236 // movaps %xmm12,%xmm13 .byte 69,15,89,235 // mulps %xmm11,%xmm13 .byte 68,15,88,235 // addps %xmm3,%xmm13 @@ -21249,7 +21814,7 @@ _sk_color_sse41: .byte 65,15,88,251 // addps %xmm11,%xmm7 .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 102,15,56,20,207 // blendvps %xmm0,%xmm7,%xmm1 - .byte 68,15,40,13,154,50,0,0 // movaps 0x329a(%rip),%xmm9 # 4700 <_sk_callback_sse41+0x332> + .byte 68,15,40,13,218,52,0,0 // movaps 0x34da(%rip),%xmm9 # 4940 <_sk_callback_sse41+0x330> .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 15,92,196 // subps %xmm4,%xmm0 .byte 68,15,89,192 // mulps %xmm0,%xmm8 @@ -21301,13 +21866,13 @@ _sk_luminosity_sse41: .byte 69,15,89,216 // mulps %xmm8,%xmm11 .byte 68,15,40,203 // movaps %xmm3,%xmm9 .byte 68,15,89,205 // mulps %xmm5,%xmm9 - .byte 68,15,40,5,242,49,0,0 // movaps 0x31f2(%rip),%xmm8 # 4710 <_sk_callback_sse41+0x342> + .byte 68,15,40,5,50,52,0,0 // movaps 0x3432(%rip),%xmm8 # 4950 <_sk_callback_sse41+0x340> .byte 65,15,89,192 // mulps %xmm8,%xmm0 - .byte 68,15,40,21,246,49,0,0 // movaps 0x31f6(%rip),%xmm10 # 4720 <_sk_callback_sse41+0x352> + .byte 68,15,40,21,54,52,0,0 // movaps 0x3436(%rip),%xmm10 # 4960 <_sk_callback_sse41+0x350> .byte 15,40,233 // movaps %xmm1,%xmm5 .byte 65,15,89,234 // mulps %xmm10,%xmm5 .byte 15,88,232 // addps %xmm0,%xmm5 - .byte 68,15,40,37,244,49,0,0 // movaps 0x31f4(%rip),%xmm12 # 4730 <_sk_callback_sse41+0x362> + .byte 68,15,40,37,52,52,0,0 // movaps 0x3434(%rip),%xmm12 # 4970 <_sk_callback_sse41+0x360> .byte 68,15,40,242 // movaps %xmm2,%xmm14 .byte 69,15,89,244 // mulps %xmm12,%xmm14 .byte 68,15,88,245 // addps %xmm5,%xmm14 @@ -21392,7 +21957,7 @@ _sk_luminosity_sse41: .byte 65,15,88,244 // addps %xmm12,%xmm6 .byte 65,15,40,195 // movaps %xmm11,%xmm0 .byte 102,68,15,56,20,206 // blendvps %xmm0,%xmm6,%xmm9 - .byte 15,40,5,170,48,0,0 // movaps 0x30aa(%rip),%xmm0 # 4740 <_sk_callback_sse41+0x372> + .byte 15,40,5,234,50,0,0 // movaps 0x32ea(%rip),%xmm0 # 4980 <_sk_callback_sse41+0x370> .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 15,92,215 // subps %xmm7,%xmm2 .byte 15,89,226 // mulps %xmm2,%xmm4 @@ -21441,7 +22006,7 @@ HIDDEN _sk_clamp_1_sse41 .globl _sk_clamp_1_sse41 FUNCTION(_sk_clamp_1_sse41) _sk_clamp_1_sse41: - .byte 68,15,40,5,45,48,0,0 // movaps 0x302d(%rip),%xmm8 # 4750 <_sk_callback_sse41+0x382> + .byte 68,15,40,5,109,50,0,0 // movaps 0x326d(%rip),%xmm8 # 4990 <_sk_callback_sse41+0x380> .byte 65,15,93,192 // minps %xmm8,%xmm0 .byte 65,15,93,200 // minps %xmm8,%xmm1 .byte 65,15,93,208 // minps %xmm8,%xmm2 @@ -21453,7 +22018,7 @@ HIDDEN _sk_clamp_a_sse41 .globl _sk_clamp_a_sse41 FUNCTION(_sk_clamp_a_sse41) _sk_clamp_a_sse41: - .byte 15,93,29,34,48,0,0 // minps 0x3022(%rip),%xmm3 # 4760 <_sk_callback_sse41+0x392> + .byte 15,93,29,98,50,0,0 // minps 0x3262(%rip),%xmm3 # 49a0 <_sk_callback_sse41+0x390> .byte 15,93,195 // minps %xmm3,%xmm0 .byte 15,93,203 // minps %xmm3,%xmm1 .byte 15,93,211 // minps %xmm3,%xmm2 @@ -21540,7 +22105,7 @@ HIDDEN _sk_unpremul_sse41 FUNCTION(_sk_unpremul_sse41) _sk_unpremul_sse41: .byte 69,15,87,192 // xorps %xmm8,%xmm8 - .byte 68,15,40,13,141,47,0,0 // movaps 0x2f8d(%rip),%xmm9 # 4770 <_sk_callback_sse41+0x3a2> + .byte 68,15,40,13,205,49,0,0 // movaps 0x31cd(%rip),%xmm9 # 49b0 <_sk_callback_sse41+0x3a0> .byte 68,15,94,203 // divps %xmm3,%xmm9 .byte 68,15,194,195,4 // cmpneqps %xmm3,%xmm8 .byte 69,15,84,193 // andps %xmm9,%xmm8 @@ -21554,20 +22119,20 @@ HIDDEN _sk_from_srgb_sse41 .globl _sk_from_srgb_sse41 FUNCTION(_sk_from_srgb_sse41) _sk_from_srgb_sse41: - .byte 68,15,40,29,120,47,0,0 // movaps 0x2f78(%rip),%xmm11 # 4780 <_sk_callback_sse41+0x3b2> + .byte 68,15,40,29,184,49,0,0 // movaps 0x31b8(%rip),%xmm11 # 49c0 <_sk_callback_sse41+0x3b0> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 .byte 68,15,40,208 // movaps %xmm0,%xmm10 .byte 69,15,89,210 // mulps %xmm10,%xmm10 - .byte 68,15,40,37,112,47,0,0 // movaps 0x2f70(%rip),%xmm12 # 4790 <_sk_callback_sse41+0x3c2> + .byte 68,15,40,37,176,49,0,0 // movaps 0x31b0(%rip),%xmm12 # 49d0 <_sk_callback_sse41+0x3c0> .byte 68,15,40,192 // movaps %xmm0,%xmm8 .byte 69,15,89,196 // mulps %xmm12,%xmm8 - .byte 68,15,40,45,112,47,0,0 // movaps 0x2f70(%rip),%xmm13 # 47a0 <_sk_callback_sse41+0x3d2> + .byte 68,15,40,45,176,49,0,0 // movaps 0x31b0(%rip),%xmm13 # 49e0 <_sk_callback_sse41+0x3d0> .byte 69,15,88,197 // addps %xmm13,%xmm8 .byte 69,15,89,194 // mulps %xmm10,%xmm8 - .byte 68,15,40,53,112,47,0,0 // movaps 0x2f70(%rip),%xmm14 # 47b0 <_sk_callback_sse41+0x3e2> + .byte 68,15,40,53,176,49,0,0 // movaps 0x31b0(%rip),%xmm14 # 49f0 <_sk_callback_sse41+0x3e0> .byte 69,15,88,198 // addps %xmm14,%xmm8 - .byte 68,15,40,61,116,47,0,0 // movaps 0x2f74(%rip),%xmm15 # 47c0 <_sk_callback_sse41+0x3f2> + .byte 68,15,40,61,180,49,0,0 // movaps 0x31b4(%rip),%xmm15 # 4a00 <_sk_callback_sse41+0x3f0> .byte 65,15,194,199,1 // cmpltps %xmm15,%xmm0 .byte 102,69,15,56,20,193 // blendvps %xmm0,%xmm9,%xmm8 .byte 68,15,40,209 // movaps %xmm1,%xmm10 @@ -21612,20 +22177,20 @@ _sk_to_srgb_sse41: .byte 68,15,82,192 // rsqrtps %xmm0,%xmm8 .byte 69,15,83,200 // rcpps %xmm8,%xmm9 .byte 69,15,82,208 // rsqrtps %xmm8,%xmm10 - .byte 68,15,40,29,228,46,0,0 // movaps 0x2ee4(%rip),%xmm11 # 47d0 <_sk_callback_sse41+0x402> + .byte 68,15,40,29,36,49,0,0 // movaps 0x3124(%rip),%xmm11 # 4a10 <_sk_callback_sse41+0x400> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 65,15,89,203 // mulps %xmm11,%xmm1 - .byte 68,15,40,37,229,46,0,0 // movaps 0x2ee5(%rip),%xmm12 # 47e0 <_sk_callback_sse41+0x412> + .byte 68,15,40,37,37,49,0,0 // movaps 0x3125(%rip),%xmm12 # 4a20 <_sk_callback_sse41+0x410> .byte 69,15,89,204 // mulps %xmm12,%xmm9 - .byte 68,15,40,45,233,46,0,0 // movaps 0x2ee9(%rip),%xmm13 # 47f0 <_sk_callback_sse41+0x422> + .byte 68,15,40,45,41,49,0,0 // movaps 0x3129(%rip),%xmm13 # 4a30 <_sk_callback_sse41+0x420> .byte 69,15,88,205 // addps %xmm13,%xmm9 - .byte 68,15,40,53,237,46,0,0 // movaps 0x2eed(%rip),%xmm14 # 4800 <_sk_callback_sse41+0x432> + .byte 68,15,40,53,45,49,0,0 // movaps 0x312d(%rip),%xmm14 # 4a40 <_sk_callback_sse41+0x430> .byte 69,15,89,214 // mulps %xmm14,%xmm10 .byte 69,15,88,209 // addps %xmm9,%xmm10 - .byte 68,15,40,5,237,46,0,0 // movaps 0x2eed(%rip),%xmm8 # 4810 <_sk_callback_sse41+0x442> + .byte 68,15,40,5,45,49,0,0 // movaps 0x312d(%rip),%xmm8 # 4a50 <_sk_callback_sse41+0x440> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,93,202 // minps %xmm10,%xmm9 - .byte 68,15,40,61,237,46,0,0 // movaps 0x2eed(%rip),%xmm15 # 4820 <_sk_callback_sse41+0x452> + .byte 68,15,40,61,45,49,0,0 // movaps 0x312d(%rip),%xmm15 # 4a60 <_sk_callback_sse41+0x450> .byte 65,15,194,199,1 // cmpltps %xmm15,%xmm0 .byte 102,68,15,56,20,201 // blendvps %xmm0,%xmm1,%xmm9 .byte 15,82,194 // rsqrtps %xmm2,%xmm0 @@ -21679,7 +22244,7 @@ _sk_rgb_to_hsl_sse41: .byte 68,15,93,226 // minps %xmm2,%xmm12 .byte 65,15,40,203 // movaps %xmm11,%xmm1 .byte 65,15,92,204 // subps %xmm12,%xmm1 - .byte 68,15,40,53,62,46,0,0 // movaps 0x2e3e(%rip),%xmm14 # 4830 <_sk_callback_sse41+0x462> + .byte 68,15,40,53,126,48,0,0 // movaps 0x307e(%rip),%xmm14 # 4a70 <_sk_callback_sse41+0x460> .byte 68,15,94,241 // divps %xmm1,%xmm14 .byte 69,15,40,211 // movaps %xmm11,%xmm10 .byte 69,15,194,208,0 // cmpeqps %xmm8,%xmm10 @@ -21688,27 +22253,27 @@ _sk_rgb_to_hsl_sse41: .byte 65,15,89,198 // mulps %xmm14,%xmm0 .byte 69,15,40,249 // movaps %xmm9,%xmm15 .byte 68,15,194,250,1 // cmpltps %xmm2,%xmm15 - .byte 68,15,84,61,37,46,0,0 // andps 0x2e25(%rip),%xmm15 # 4840 <_sk_callback_sse41+0x472> + .byte 68,15,84,61,101,48,0,0 // andps 0x3065(%rip),%xmm15 # 4a80 <_sk_callback_sse41+0x470> .byte 68,15,88,248 // addps %xmm0,%xmm15 .byte 65,15,40,195 // movaps %xmm11,%xmm0 .byte 65,15,194,193,0 // cmpeqps %xmm9,%xmm0 .byte 65,15,92,208 // subps %xmm8,%xmm2 .byte 65,15,89,214 // mulps %xmm14,%xmm2 - .byte 68,15,40,45,24,46,0,0 // movaps 0x2e18(%rip),%xmm13 # 4850 <_sk_callback_sse41+0x482> + .byte 68,15,40,45,88,48,0,0 // movaps 0x3058(%rip),%xmm13 # 4a90 <_sk_callback_sse41+0x480> .byte 65,15,88,213 // addps %xmm13,%xmm2 .byte 69,15,92,193 // subps %xmm9,%xmm8 .byte 69,15,89,198 // mulps %xmm14,%xmm8 - .byte 68,15,88,5,20,46,0,0 // addps 0x2e14(%rip),%xmm8 # 4860 <_sk_callback_sse41+0x492> + .byte 68,15,88,5,84,48,0,0 // addps 0x3054(%rip),%xmm8 # 4aa0 <_sk_callback_sse41+0x490> .byte 102,68,15,56,20,194 // blendvps %xmm0,%xmm2,%xmm8 .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 102,69,15,56,20,199 // blendvps %xmm0,%xmm15,%xmm8 - .byte 68,15,89,5,12,46,0,0 // mulps 0x2e0c(%rip),%xmm8 # 4870 <_sk_callback_sse41+0x4a2> + .byte 68,15,89,5,76,48,0,0 // mulps 0x304c(%rip),%xmm8 # 4ab0 <_sk_callback_sse41+0x4a0> .byte 69,15,40,203 // movaps %xmm11,%xmm9 .byte 69,15,194,204,4 // cmpneqps %xmm12,%xmm9 .byte 69,15,84,193 // andps %xmm9,%xmm8 .byte 69,15,92,235 // subps %xmm11,%xmm13 .byte 69,15,88,220 // addps %xmm12,%xmm11 - .byte 15,40,5,0,46,0,0 // movaps 0x2e00(%rip),%xmm0 # 4880 <_sk_callback_sse41+0x4b2> + .byte 15,40,5,64,48,0,0 // movaps 0x3040(%rip),%xmm0 # 4ac0 <_sk_callback_sse41+0x4b0> .byte 65,15,40,211 // movaps %xmm11,%xmm2 .byte 15,89,208 // mulps %xmm0,%xmm2 .byte 15,194,194,1 // cmpltps %xmm2,%xmm0 @@ -21730,7 +22295,7 @@ _sk_hsl_to_rgb_sse41: .byte 15,41,100,36,184 // movaps %xmm4,-0x48(%rsp) .byte 15,41,92,36,168 // movaps %xmm3,-0x58(%rsp) .byte 68,15,40,208 // movaps %xmm0,%xmm10 - .byte 68,15,40,13,198,45,0,0 // movaps 0x2dc6(%rip),%xmm9 # 4890 <_sk_callback_sse41+0x4c2> + .byte 68,15,40,13,6,48,0,0 // movaps 0x3006(%rip),%xmm9 # 4ad0 <_sk_callback_sse41+0x4c0> .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 15,194,194,2 // cmpleps %xmm2,%xmm0 .byte 15,40,217 // movaps %xmm1,%xmm3 @@ -21743,19 +22308,19 @@ _sk_hsl_to_rgb_sse41: .byte 15,41,84,36,152 // movaps %xmm2,-0x68(%rsp) .byte 69,15,88,192 // addps %xmm8,%xmm8 .byte 68,15,92,197 // subps %xmm5,%xmm8 - .byte 68,15,40,53,161,45,0,0 // movaps 0x2da1(%rip),%xmm14 # 48a0 <_sk_callback_sse41+0x4d2> + .byte 68,15,40,53,225,47,0,0 // movaps 0x2fe1(%rip),%xmm14 # 4ae0 <_sk_callback_sse41+0x4d0> .byte 69,15,88,242 // addps %xmm10,%xmm14 .byte 102,65,15,58,8,198,1 // roundps $0x1,%xmm14,%xmm0 .byte 68,15,92,240 // subps %xmm0,%xmm14 - .byte 68,15,40,29,154,45,0,0 // movaps 0x2d9a(%rip),%xmm11 # 48b0 <_sk_callback_sse41+0x4e2> + .byte 68,15,40,29,218,47,0,0 // movaps 0x2fda(%rip),%xmm11 # 4af0 <_sk_callback_sse41+0x4e0> .byte 65,15,40,195 // movaps %xmm11,%xmm0 .byte 65,15,194,198,2 // cmpleps %xmm14,%xmm0 .byte 15,40,245 // movaps %xmm5,%xmm6 .byte 65,15,92,240 // subps %xmm8,%xmm6 - .byte 15,40,61,147,45,0,0 // movaps 0x2d93(%rip),%xmm7 # 48c0 <_sk_callback_sse41+0x4f2> + .byte 15,40,61,211,47,0,0 // movaps 0x2fd3(%rip),%xmm7 # 4b00 <_sk_callback_sse41+0x4f0> .byte 69,15,40,238 // movaps %xmm14,%xmm13 .byte 68,15,89,239 // mulps %xmm7,%xmm13 - .byte 15,40,29,148,45,0,0 // movaps 0x2d94(%rip),%xmm3 # 48d0 <_sk_callback_sse41+0x502> + .byte 15,40,29,212,47,0,0 // movaps 0x2fd4(%rip),%xmm3 # 4b10 <_sk_callback_sse41+0x500> .byte 68,15,40,227 // movaps %xmm3,%xmm12 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 68,15,89,230 // mulps %xmm6,%xmm12 @@ -21765,7 +22330,7 @@ _sk_hsl_to_rgb_sse41: .byte 65,15,194,198,2 // cmpleps %xmm14,%xmm0 .byte 68,15,40,253 // movaps %xmm5,%xmm15 .byte 102,69,15,56,20,252 // blendvps %xmm0,%xmm12,%xmm15 - .byte 68,15,40,37,115,45,0,0 // movaps 0x2d73(%rip),%xmm12 # 48e0 <_sk_callback_sse41+0x512> + .byte 68,15,40,37,179,47,0,0 // movaps 0x2fb3(%rip),%xmm12 # 4b20 <_sk_callback_sse41+0x510> .byte 65,15,40,196 // movaps %xmm12,%xmm0 .byte 65,15,194,198,2 // cmpleps %xmm14,%xmm0 .byte 68,15,89,238 // mulps %xmm6,%xmm13 @@ -21799,7 +22364,7 @@ _sk_hsl_to_rgb_sse41: .byte 65,15,40,198 // movaps %xmm14,%xmm0 .byte 15,40,84,36,152 // movaps -0x68(%rsp),%xmm2 .byte 102,15,56,20,202 // blendvps %xmm0,%xmm2,%xmm1 - .byte 68,15,88,21,235,44,0,0 // addps 0x2ceb(%rip),%xmm10 # 48f0 <_sk_callback_sse41+0x522> + .byte 68,15,88,21,43,47,0,0 // addps 0x2f2b(%rip),%xmm10 # 4b30 <_sk_callback_sse41+0x520> .byte 102,65,15,58,8,194,1 // roundps $0x1,%xmm10,%xmm0 .byte 68,15,92,208 // subps %xmm0,%xmm10 .byte 69,15,194,218,2 // cmpleps %xmm10,%xmm11 @@ -21851,7 +22416,7 @@ _sk_scale_u8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,68,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,72,44,0,0 // mulps 0x2c48(%rip),%xmm8 # 4900 <_sk_callback_sse41+0x532> + .byte 68,15,89,5,136,46,0,0 // mulps 0x2e88(%rip),%xmm8 # 4b40 <_sk_callback_sse41+0x530> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 65,15,89,208 // mulps %xmm8,%xmm2 @@ -21889,7 +22454,7 @@ _sk_lerp_u8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,68,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,244,43,0,0 // mulps 0x2bf4(%rip),%xmm8 # 4910 <_sk_callback_sse41+0x542> + .byte 68,15,89,5,52,46,0,0 // mulps 0x2e34(%rip),%xmm8 # 4b50 <_sk_callback_sse41+0x540> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -21912,17 +22477,17 @@ _sk_lerp_565_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 102,68,15,56,51,20,120 // pmovzxwd (%rax,%rdi,2),%xmm10 - .byte 102,68,15,111,5,195,43,0,0 // movdqa 0x2bc3(%rip),%xmm8 # 4920 <_sk_callback_sse41+0x552> + .byte 102,68,15,111,5,3,46,0,0 // movdqa 0x2e03(%rip),%xmm8 # 4b60 <_sk_callback_sse41+0x550> .byte 102,69,15,219,194 // pand %xmm10,%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,194,43,0,0 // mulps 0x2bc2(%rip),%xmm8 # 4930 <_sk_callback_sse41+0x562> - .byte 102,68,15,111,13,201,43,0,0 // movdqa 0x2bc9(%rip),%xmm9 # 4940 <_sk_callback_sse41+0x572> + .byte 68,15,89,5,2,46,0,0 // mulps 0x2e02(%rip),%xmm8 # 4b70 <_sk_callback_sse41+0x560> + .byte 102,68,15,111,13,9,46,0,0 // movdqa 0x2e09(%rip),%xmm9 # 4b80 <_sk_callback_sse41+0x570> .byte 102,69,15,219,202 // pand %xmm10,%xmm9 .byte 69,15,91,201 // cvtdq2ps %xmm9,%xmm9 - .byte 68,15,89,13,200,43,0,0 // mulps 0x2bc8(%rip),%xmm9 # 4950 <_sk_callback_sse41+0x582> - .byte 102,68,15,219,21,207,43,0,0 // pand 0x2bcf(%rip),%xmm10 # 4960 <_sk_callback_sse41+0x592> + .byte 68,15,89,13,8,46,0,0 // mulps 0x2e08(%rip),%xmm9 # 4b90 <_sk_callback_sse41+0x580> + .byte 102,68,15,219,21,15,46,0,0 // pand 0x2e0f(%rip),%xmm10 # 4ba0 <_sk_callback_sse41+0x590> .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 - .byte 68,15,89,21,211,43,0,0 // mulps 0x2bd3(%rip),%xmm10 # 4970 <_sk_callback_sse41+0x5a2> + .byte 68,15,89,21,19,46,0,0 // mulps 0x2e13(%rip),%xmm10 # 4bb0 <_sk_callback_sse41+0x5a0> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -21953,7 +22518,7 @@ _sk_load_tables_sse41: .byte 76,139,0 // mov (%rax),%r8 .byte 76,139,72,8 // mov 0x8(%rax),%r9 .byte 243,69,15,111,4,184 // movdqu (%r8,%rdi,4),%xmm8 - .byte 102,15,111,5,132,43,0,0 // movdqa 0x2b84(%rip),%xmm0 # 4980 <_sk_callback_sse41+0x5b2> + .byte 102,15,111,5,196,45,0,0 // movdqa 0x2dc4(%rip),%xmm0 # 4bc0 <_sk_callback_sse41+0x5b0> .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,73,15,58,22,192,1 // pextrq $0x1,%xmm0,%r8 .byte 102,72,15,126,193 // movq %xmm0,%rcx @@ -21968,7 +22533,7 @@ _sk_load_tables_sse41: .byte 102,15,58,33,193,48 // insertps $0x30,%xmm1,%xmm0 .byte 76,139,64,16 // mov 0x10(%rax),%r8 .byte 102,65,15,111,200 // movdqa %xmm8,%xmm1 - .byte 102,15,56,0,13,63,43,0,0 // pshufb 0x2b3f(%rip),%xmm1 # 4990 <_sk_callback_sse41+0x5c2> + .byte 102,15,56,0,13,127,45,0,0 // pshufb 0x2d7f(%rip),%xmm1 # 4bd0 <_sk_callback_sse41+0x5c0> .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 .byte 102,72,15,126,201 // movq %xmm1,%rcx .byte 68,15,182,209 // movzbl %cl,%r10d @@ -21983,7 +22548,7 @@ _sk_load_tables_sse41: .byte 102,15,58,33,202,48 // insertps $0x30,%xmm2,%xmm1 .byte 76,139,64,24 // mov 0x18(%rax),%r8 .byte 102,65,15,111,208 // movdqa %xmm8,%xmm2 - .byte 102,15,56,0,21,251,42,0,0 // pshufb 0x2afb(%rip),%xmm2 # 49a0 <_sk_callback_sse41+0x5d2> + .byte 102,15,56,0,21,59,45,0,0 // pshufb 0x2d3b(%rip),%xmm2 # 4be0 <_sk_callback_sse41+0x5d0> .byte 102,72,15,58,22,209,1 // pextrq $0x1,%xmm2,%rcx .byte 102,72,15,126,208 // movq %xmm2,%rax .byte 68,15,182,200 // movzbl %al,%r9d @@ -21998,7 +22563,7 @@ _sk_load_tables_sse41: .byte 102,15,58,33,211,48 // insertps $0x30,%xmm3,%xmm2 .byte 102,65,15,114,208,24 // psrld $0x18,%xmm8 .byte 65,15,91,216 // cvtdq2ps %xmm8,%xmm3 - .byte 15,89,29,184,42,0,0 // mulps 0x2ab8(%rip),%xmm3 # 49b0 <_sk_callback_sse41+0x5e2> + .byte 15,89,29,248,44,0,0 // mulps 0x2cf8(%rip),%xmm3 # 4bf0 <_sk_callback_sse41+0x5e0> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -22017,7 +22582,7 @@ _sk_load_tables_u16_be_sse41: .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,97,200 // punpcklwd %xmm0,%xmm1 .byte 102,68,15,105,200 // punpckhwd %xmm0,%xmm9 - .byte 102,68,15,111,5,139,42,0,0 // movdqa 0x2a8b(%rip),%xmm8 # 49c0 <_sk_callback_sse41+0x5f2> + .byte 102,68,15,111,5,203,44,0,0 // movdqa 0x2ccb(%rip),%xmm8 # 4c00 <_sk_callback_sse41+0x5f0> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,15,56,51,192 // pmovzxwd %xmm0,%xmm0 @@ -22034,7 +22599,7 @@ _sk_load_tables_u16_be_sse41: .byte 243,67,15,16,20,8 // movss (%r8,%r9,1),%xmm2 .byte 102,15,58,33,194,48 // insertps $0x30,%xmm2,%xmm0 .byte 76,139,64,16 // mov 0x10(%rax),%r8 - .byte 102,15,56,0,13,62,42,0,0 // pshufb 0x2a3e(%rip),%xmm1 # 49d0 <_sk_callback_sse41+0x602> + .byte 102,15,56,0,13,126,44,0,0 // pshufb 0x2c7e(%rip),%xmm1 # 4c10 <_sk_callback_sse41+0x600> .byte 102,15,56,51,201 // pmovzxwd %xmm1,%xmm1 .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 .byte 102,72,15,126,201 // movq %xmm1,%rcx @@ -22070,7 +22635,7 @@ _sk_load_tables_u16_be_sse41: .byte 102,65,15,235,216 // por %xmm8,%xmm3 .byte 102,15,56,51,219 // pmovzxwd %xmm3,%xmm3 .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,140,41,0,0 // mulps 0x298c(%rip),%xmm3 # 49e0 <_sk_callback_sse41+0x612> + .byte 15,89,29,204,43,0,0 // mulps 0x2bcc(%rip),%xmm3 # 4c20 <_sk_callback_sse41+0x610> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -22092,7 +22657,7 @@ _sk_load_tables_rgb_u16_be_sse41: .byte 102,68,15,97,200 // punpcklwd %xmm0,%xmm9 .byte 102,15,111,202 // movdqa %xmm2,%xmm1 .byte 102,65,15,97,201 // punpcklwd %xmm9,%xmm1 - .byte 102,68,15,111,5,78,41,0,0 // movdqa 0x294e(%rip),%xmm8 # 49f0 <_sk_callback_sse41+0x622> + .byte 102,68,15,111,5,142,43,0,0 // movdqa 0x2b8e(%rip),%xmm8 # 4c30 <_sk_callback_sse41+0x620> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,15,56,51,192 // pmovzxwd %xmm0,%xmm0 @@ -22109,7 +22674,7 @@ _sk_load_tables_rgb_u16_be_sse41: .byte 243,67,15,16,28,8 // movss (%r8,%r9,1),%xmm3 .byte 102,15,58,33,195,48 // insertps $0x30,%xmm3,%xmm0 .byte 76,139,64,16 // mov 0x10(%rax),%r8 - .byte 102,15,56,0,13,1,41,0,0 // pshufb 0x2901(%rip),%xmm1 # 4a00 <_sk_callback_sse41+0x632> + .byte 102,15,56,0,13,65,43,0,0 // pshufb 0x2b41(%rip),%xmm1 # 4c40 <_sk_callback_sse41+0x630> .byte 102,15,56,51,201 // pmovzxwd %xmm1,%xmm1 .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 .byte 102,72,15,126,201 // movq %xmm1,%rcx @@ -22140,7 +22705,7 @@ _sk_load_tables_rgb_u16_be_sse41: .byte 243,65,15,16,28,8 // movss (%r8,%rcx,1),%xmm3 .byte 102,15,58,33,211,48 // insertps $0x30,%xmm3,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,108,40,0,0 // movaps 0x286c(%rip),%xmm3 # 4a10 <_sk_callback_sse41+0x642> + .byte 15,40,29,172,42,0,0 // movaps 0x2aac(%rip),%xmm3 # 4c50 <_sk_callback_sse41+0x640> .byte 255,224 // jmpq *%rax HIDDEN _sk_byte_tables_sse41 @@ -22150,7 +22715,7 @@ _sk_byte_tables_sse41: .byte 65,86 // push %r14 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,109,40,0,0 // movaps 0x286d(%rip),%xmm8 # 4a20 <_sk_callback_sse41+0x652> + .byte 68,15,40,5,173,42,0,0 // movaps 0x2aad(%rip),%xmm8 # 4c60 <_sk_callback_sse41+0x650> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,91,192 // cvtps2dq %xmm0,%xmm0 .byte 102,72,15,58,22,193,1 // pextrq $0x1,%xmm0,%rcx @@ -22169,7 +22734,7 @@ _sk_byte_tables_sse41: .byte 102,15,58,32,193,3 // pinsrb $0x3,%ecx,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,13,30,40,0,0 // movaps 0x281e(%rip),%xmm9 # 4a30 <_sk_callback_sse41+0x662> + .byte 68,15,40,13,94,42,0,0 // movaps 0x2a5e(%rip),%xmm9 # 4c70 <_sk_callback_sse41+0x660> .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -22260,7 +22825,7 @@ _sk_byte_tables_rgb_sse41: .byte 102,15,58,32,193,3 // pinsrb $0x3,%ecx,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,13,166,38,0,0 // movaps 0x26a6(%rip),%xmm9 # 4a40 <_sk_callback_sse41+0x672> + .byte 68,15,40,13,230,40,0,0 // movaps 0x28e6(%rip),%xmm9 # 4c80 <_sk_callback_sse41+0x670> .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -22437,31 +23002,31 @@ _sk_parametric_r_sse41: .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,194 // cvtdq2ps %xmm10,%xmm8 - .byte 68,15,89,5,253,35,0,0 // mulps 0x23fd(%rip),%xmm8 # 4a50 <_sk_callback_sse41+0x682> - .byte 68,15,84,21,5,36,0,0 // andps 0x2405(%rip),%xmm10 # 4a60 <_sk_callback_sse41+0x692> - .byte 68,15,86,21,13,36,0,0 // orps 0x240d(%rip),%xmm10 # 4a70 <_sk_callback_sse41+0x6a2> - .byte 68,15,88,5,21,36,0,0 // addps 0x2415(%rip),%xmm8 # 4a80 <_sk_callback_sse41+0x6b2> - .byte 68,15,40,37,29,36,0,0 // movaps 0x241d(%rip),%xmm12 # 4a90 <_sk_callback_sse41+0x6c2> + .byte 68,15,89,5,61,38,0,0 // mulps 0x263d(%rip),%xmm8 # 4c90 <_sk_callback_sse41+0x680> + .byte 68,15,84,21,69,38,0,0 // andps 0x2645(%rip),%xmm10 # 4ca0 <_sk_callback_sse41+0x690> + .byte 68,15,86,21,77,38,0,0 // orps 0x264d(%rip),%xmm10 # 4cb0 <_sk_callback_sse41+0x6a0> + .byte 68,15,88,5,85,38,0,0 // addps 0x2655(%rip),%xmm8 # 4cc0 <_sk_callback_sse41+0x6b0> + .byte 68,15,40,37,93,38,0,0 // movaps 0x265d(%rip),%xmm12 # 4cd0 <_sk_callback_sse41+0x6c0> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,196 // subps %xmm12,%xmm8 - .byte 68,15,88,21,29,36,0,0 // addps 0x241d(%rip),%xmm10 # 4aa0 <_sk_callback_sse41+0x6d2> - .byte 68,15,40,37,37,36,0,0 // movaps 0x2425(%rip),%xmm12 # 4ab0 <_sk_callback_sse41+0x6e2> + .byte 68,15,88,21,93,38,0,0 // addps 0x265d(%rip),%xmm10 # 4ce0 <_sk_callback_sse41+0x6d0> + .byte 68,15,40,37,101,38,0,0 // movaps 0x2665(%rip),%xmm12 # 4cf0 <_sk_callback_sse41+0x6e0> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,196 // subps %xmm12,%xmm8 .byte 69,15,89,195 // mulps %xmm11,%xmm8 .byte 102,69,15,58,8,208,1 // roundps $0x1,%xmm8,%xmm10 .byte 69,15,40,216 // movaps %xmm8,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,5,18,36,0,0 // addps 0x2412(%rip),%xmm8 # 4ac0 <_sk_callback_sse41+0x6f2> - .byte 68,15,40,21,26,36,0,0 // movaps 0x241a(%rip),%xmm10 # 4ad0 <_sk_callback_sse41+0x702> + .byte 68,15,88,5,82,38,0,0 // addps 0x2652(%rip),%xmm8 # 4d00 <_sk_callback_sse41+0x6f0> + .byte 68,15,40,21,90,38,0,0 // movaps 0x265a(%rip),%xmm10 # 4d10 <_sk_callback_sse41+0x700> .byte 69,15,89,211 // mulps %xmm11,%xmm10 .byte 69,15,92,194 // subps %xmm10,%xmm8 - .byte 68,15,40,21,26,36,0,0 // movaps 0x241a(%rip),%xmm10 # 4ae0 <_sk_callback_sse41+0x712> + .byte 68,15,40,21,90,38,0,0 // movaps 0x265a(%rip),%xmm10 # 4d20 <_sk_callback_sse41+0x710> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 68,15,40,29,30,36,0,0 // movaps 0x241e(%rip),%xmm11 # 4af0 <_sk_callback_sse41+0x722> + .byte 68,15,40,29,94,38,0,0 // movaps 0x265e(%rip),%xmm11 # 4d30 <_sk_callback_sse41+0x720> .byte 69,15,94,218 // divps %xmm10,%xmm11 .byte 69,15,88,216 // addps %xmm8,%xmm11 - .byte 68,15,89,29,30,36,0,0 // mulps 0x241e(%rip),%xmm11 # 4b00 <_sk_callback_sse41+0x732> + .byte 68,15,89,29,94,38,0,0 // mulps 0x265e(%rip),%xmm11 # 4d40 <_sk_callback_sse41+0x730> .byte 102,69,15,91,211 // cvtps2dq %xmm11,%xmm10 .byte 243,68,15,16,64,20 // movss 0x14(%rax),%xmm8 .byte 69,15,198,192,0 // shufps $0x0,%xmm8,%xmm8 @@ -22469,7 +23034,7 @@ _sk_parametric_r_sse41: .byte 102,69,15,56,20,193 // blendvps %xmm0,%xmm9,%xmm8 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 68,15,95,192 // maxps %xmm0,%xmm8 - .byte 68,15,93,5,5,36,0,0 // minps 0x2405(%rip),%xmm8 # 4b10 <_sk_callback_sse41+0x742> + .byte 68,15,93,5,69,38,0,0 // minps 0x2645(%rip),%xmm8 # 4d50 <_sk_callback_sse41+0x740> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -22499,31 +23064,31 @@ _sk_parametric_g_sse41: .byte 68,15,88,217 // addps %xmm1,%xmm11 .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 .byte 69,15,91,227 // cvtdq2ps %xmm11,%xmm12 - .byte 68,15,89,37,166,35,0,0 // mulps 0x23a6(%rip),%xmm12 # 4b20 <_sk_callback_sse41+0x752> - .byte 68,15,84,29,174,35,0,0 // andps 0x23ae(%rip),%xmm11 # 4b30 <_sk_callback_sse41+0x762> - .byte 68,15,86,29,182,35,0,0 // orps 0x23b6(%rip),%xmm11 # 4b40 <_sk_callback_sse41+0x772> - .byte 68,15,88,37,190,35,0,0 // addps 0x23be(%rip),%xmm12 # 4b50 <_sk_callback_sse41+0x782> - .byte 15,40,13,199,35,0,0 // movaps 0x23c7(%rip),%xmm1 # 4b60 <_sk_callback_sse41+0x792> + .byte 68,15,89,37,230,37,0,0 // mulps 0x25e6(%rip),%xmm12 # 4d60 <_sk_callback_sse41+0x750> + .byte 68,15,84,29,238,37,0,0 // andps 0x25ee(%rip),%xmm11 # 4d70 <_sk_callback_sse41+0x760> + .byte 68,15,86,29,246,37,0,0 // orps 0x25f6(%rip),%xmm11 # 4d80 <_sk_callback_sse41+0x770> + .byte 68,15,88,37,254,37,0,0 // addps 0x25fe(%rip),%xmm12 # 4d90 <_sk_callback_sse41+0x780> + .byte 15,40,13,7,38,0,0 // movaps 0x2607(%rip),%xmm1 # 4da0 <_sk_callback_sse41+0x790> .byte 65,15,89,203 // mulps %xmm11,%xmm1 .byte 68,15,92,225 // subps %xmm1,%xmm12 - .byte 68,15,88,29,199,35,0,0 // addps 0x23c7(%rip),%xmm11 # 4b70 <_sk_callback_sse41+0x7a2> - .byte 15,40,13,208,35,0,0 // movaps 0x23d0(%rip),%xmm1 # 4b80 <_sk_callback_sse41+0x7b2> + .byte 68,15,88,29,7,38,0,0 // addps 0x2607(%rip),%xmm11 # 4db0 <_sk_callback_sse41+0x7a0> + .byte 15,40,13,16,38,0,0 // movaps 0x2610(%rip),%xmm1 # 4dc0 <_sk_callback_sse41+0x7b0> .byte 65,15,94,203 // divps %xmm11,%xmm1 .byte 68,15,92,225 // subps %xmm1,%xmm12 .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 102,69,15,58,8,212,1 // roundps $0x1,%xmm12,%xmm10 .byte 69,15,40,220 // movaps %xmm12,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,37,189,35,0,0 // addps 0x23bd(%rip),%xmm12 # 4b90 <_sk_callback_sse41+0x7c2> - .byte 15,40,13,198,35,0,0 // movaps 0x23c6(%rip),%xmm1 # 4ba0 <_sk_callback_sse41+0x7d2> + .byte 68,15,88,37,253,37,0,0 // addps 0x25fd(%rip),%xmm12 # 4dd0 <_sk_callback_sse41+0x7c0> + .byte 15,40,13,6,38,0,0 // movaps 0x2606(%rip),%xmm1 # 4de0 <_sk_callback_sse41+0x7d0> .byte 65,15,89,203 // mulps %xmm11,%xmm1 .byte 68,15,92,225 // subps %xmm1,%xmm12 - .byte 68,15,40,21,198,35,0,0 // movaps 0x23c6(%rip),%xmm10 # 4bb0 <_sk_callback_sse41+0x7e2> + .byte 68,15,40,21,6,38,0,0 // movaps 0x2606(%rip),%xmm10 # 4df0 <_sk_callback_sse41+0x7e0> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 15,40,13,203,35,0,0 // movaps 0x23cb(%rip),%xmm1 # 4bc0 <_sk_callback_sse41+0x7f2> + .byte 15,40,13,11,38,0,0 // movaps 0x260b(%rip),%xmm1 # 4e00 <_sk_callback_sse41+0x7f0> .byte 65,15,94,202 // divps %xmm10,%xmm1 .byte 65,15,88,204 // addps %xmm12,%xmm1 - .byte 15,89,13,204,35,0,0 // mulps 0x23cc(%rip),%xmm1 # 4bd0 <_sk_callback_sse41+0x802> + .byte 15,89,13,12,38,0,0 // mulps 0x260c(%rip),%xmm1 # 4e10 <_sk_callback_sse41+0x800> .byte 102,68,15,91,209 // cvtps2dq %xmm1,%xmm10 .byte 243,15,16,72,20 // movss 0x14(%rax),%xmm1 .byte 15,198,201,0 // shufps $0x0,%xmm1,%xmm1 @@ -22531,7 +23096,7 @@ _sk_parametric_g_sse41: .byte 102,65,15,56,20,201 // blendvps %xmm0,%xmm9,%xmm1 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,95,200 // maxps %xmm0,%xmm1 - .byte 15,93,13,183,35,0,0 // minps 0x23b7(%rip),%xmm1 # 4be0 <_sk_callback_sse41+0x812> + .byte 15,93,13,247,37,0,0 // minps 0x25f7(%rip),%xmm1 # 4e20 <_sk_callback_sse41+0x810> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -22561,31 +23126,31 @@ _sk_parametric_b_sse41: .byte 68,15,88,218 // addps %xmm2,%xmm11 .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 .byte 69,15,91,227 // cvtdq2ps %xmm11,%xmm12 - .byte 68,15,89,37,88,35,0,0 // mulps 0x2358(%rip),%xmm12 # 4bf0 <_sk_callback_sse41+0x822> - .byte 68,15,84,29,96,35,0,0 // andps 0x2360(%rip),%xmm11 # 4c00 <_sk_callback_sse41+0x832> - .byte 68,15,86,29,104,35,0,0 // orps 0x2368(%rip),%xmm11 # 4c10 <_sk_callback_sse41+0x842> - .byte 68,15,88,37,112,35,0,0 // addps 0x2370(%rip),%xmm12 # 4c20 <_sk_callback_sse41+0x852> - .byte 15,40,21,121,35,0,0 // movaps 0x2379(%rip),%xmm2 # 4c30 <_sk_callback_sse41+0x862> + .byte 68,15,89,37,152,37,0,0 // mulps 0x2598(%rip),%xmm12 # 4e30 <_sk_callback_sse41+0x820> + .byte 68,15,84,29,160,37,0,0 // andps 0x25a0(%rip),%xmm11 # 4e40 <_sk_callback_sse41+0x830> + .byte 68,15,86,29,168,37,0,0 // orps 0x25a8(%rip),%xmm11 # 4e50 <_sk_callback_sse41+0x840> + .byte 68,15,88,37,176,37,0,0 // addps 0x25b0(%rip),%xmm12 # 4e60 <_sk_callback_sse41+0x850> + .byte 15,40,21,185,37,0,0 // movaps 0x25b9(%rip),%xmm2 # 4e70 <_sk_callback_sse41+0x860> .byte 65,15,89,211 // mulps %xmm11,%xmm2 .byte 68,15,92,226 // subps %xmm2,%xmm12 - .byte 68,15,88,29,121,35,0,0 // addps 0x2379(%rip),%xmm11 # 4c40 <_sk_callback_sse41+0x872> - .byte 15,40,21,130,35,0,0 // movaps 0x2382(%rip),%xmm2 # 4c50 <_sk_callback_sse41+0x882> + .byte 68,15,88,29,185,37,0,0 // addps 0x25b9(%rip),%xmm11 # 4e80 <_sk_callback_sse41+0x870> + .byte 15,40,21,194,37,0,0 // movaps 0x25c2(%rip),%xmm2 # 4e90 <_sk_callback_sse41+0x880> .byte 65,15,94,211 // divps %xmm11,%xmm2 .byte 68,15,92,226 // subps %xmm2,%xmm12 .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 102,69,15,58,8,212,1 // roundps $0x1,%xmm12,%xmm10 .byte 69,15,40,220 // movaps %xmm12,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,37,111,35,0,0 // addps 0x236f(%rip),%xmm12 # 4c60 <_sk_callback_sse41+0x892> - .byte 15,40,21,120,35,0,0 // movaps 0x2378(%rip),%xmm2 # 4c70 <_sk_callback_sse41+0x8a2> + .byte 68,15,88,37,175,37,0,0 // addps 0x25af(%rip),%xmm12 # 4ea0 <_sk_callback_sse41+0x890> + .byte 15,40,21,184,37,0,0 // movaps 0x25b8(%rip),%xmm2 # 4eb0 <_sk_callback_sse41+0x8a0> .byte 65,15,89,211 // mulps %xmm11,%xmm2 .byte 68,15,92,226 // subps %xmm2,%xmm12 - .byte 68,15,40,21,120,35,0,0 // movaps 0x2378(%rip),%xmm10 # 4c80 <_sk_callback_sse41+0x8b2> + .byte 68,15,40,21,184,37,0,0 // movaps 0x25b8(%rip),%xmm10 # 4ec0 <_sk_callback_sse41+0x8b0> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 15,40,21,125,35,0,0 // movaps 0x237d(%rip),%xmm2 # 4c90 <_sk_callback_sse41+0x8c2> + .byte 15,40,21,189,37,0,0 // movaps 0x25bd(%rip),%xmm2 # 4ed0 <_sk_callback_sse41+0x8c0> .byte 65,15,94,210 // divps %xmm10,%xmm2 .byte 65,15,88,212 // addps %xmm12,%xmm2 - .byte 15,89,21,126,35,0,0 // mulps 0x237e(%rip),%xmm2 # 4ca0 <_sk_callback_sse41+0x8d2> + .byte 15,89,21,190,37,0,0 // mulps 0x25be(%rip),%xmm2 # 4ee0 <_sk_callback_sse41+0x8d0> .byte 102,68,15,91,210 // cvtps2dq %xmm2,%xmm10 .byte 243,15,16,80,20 // movss 0x14(%rax),%xmm2 .byte 15,198,210,0 // shufps $0x0,%xmm2,%xmm2 @@ -22593,7 +23158,7 @@ _sk_parametric_b_sse41: .byte 102,65,15,56,20,209 // blendvps %xmm0,%xmm9,%xmm2 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,95,208 // maxps %xmm0,%xmm2 - .byte 15,93,21,105,35,0,0 // minps 0x2369(%rip),%xmm2 # 4cb0 <_sk_callback_sse41+0x8e2> + .byte 15,93,21,169,37,0,0 // minps 0x25a9(%rip),%xmm2 # 4ef0 <_sk_callback_sse41+0x8e0> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -22623,31 +23188,31 @@ _sk_parametric_a_sse41: .byte 68,15,88,219 // addps %xmm3,%xmm11 .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 .byte 69,15,91,227 // cvtdq2ps %xmm11,%xmm12 - .byte 68,15,89,37,10,35,0,0 // mulps 0x230a(%rip),%xmm12 # 4cc0 <_sk_callback_sse41+0x8f2> - .byte 68,15,84,29,18,35,0,0 // andps 0x2312(%rip),%xmm11 # 4cd0 <_sk_callback_sse41+0x902> - .byte 68,15,86,29,26,35,0,0 // orps 0x231a(%rip),%xmm11 # 4ce0 <_sk_callback_sse41+0x912> - .byte 68,15,88,37,34,35,0,0 // addps 0x2322(%rip),%xmm12 # 4cf0 <_sk_callback_sse41+0x922> - .byte 15,40,29,43,35,0,0 // movaps 0x232b(%rip),%xmm3 # 4d00 <_sk_callback_sse41+0x932> + .byte 68,15,89,37,74,37,0,0 // mulps 0x254a(%rip),%xmm12 # 4f00 <_sk_callback_sse41+0x8f0> + .byte 68,15,84,29,82,37,0,0 // andps 0x2552(%rip),%xmm11 # 4f10 <_sk_callback_sse41+0x900> + .byte 68,15,86,29,90,37,0,0 // orps 0x255a(%rip),%xmm11 # 4f20 <_sk_callback_sse41+0x910> + .byte 68,15,88,37,98,37,0,0 // addps 0x2562(%rip),%xmm12 # 4f30 <_sk_callback_sse41+0x920> + .byte 15,40,29,107,37,0,0 // movaps 0x256b(%rip),%xmm3 # 4f40 <_sk_callback_sse41+0x930> .byte 65,15,89,219 // mulps %xmm11,%xmm3 .byte 68,15,92,227 // subps %xmm3,%xmm12 - .byte 68,15,88,29,43,35,0,0 // addps 0x232b(%rip),%xmm11 # 4d10 <_sk_callback_sse41+0x942> - .byte 15,40,29,52,35,0,0 // movaps 0x2334(%rip),%xmm3 # 4d20 <_sk_callback_sse41+0x952> + .byte 68,15,88,29,107,37,0,0 // addps 0x256b(%rip),%xmm11 # 4f50 <_sk_callback_sse41+0x940> + .byte 15,40,29,116,37,0,0 // movaps 0x2574(%rip),%xmm3 # 4f60 <_sk_callback_sse41+0x950> .byte 65,15,94,219 // divps %xmm11,%xmm3 .byte 68,15,92,227 // subps %xmm3,%xmm12 .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 102,69,15,58,8,212,1 // roundps $0x1,%xmm12,%xmm10 .byte 69,15,40,220 // movaps %xmm12,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,37,33,35,0,0 // addps 0x2321(%rip),%xmm12 # 4d30 <_sk_callback_sse41+0x962> - .byte 15,40,29,42,35,0,0 // movaps 0x232a(%rip),%xmm3 # 4d40 <_sk_callback_sse41+0x972> + .byte 68,15,88,37,97,37,0,0 // addps 0x2561(%rip),%xmm12 # 4f70 <_sk_callback_sse41+0x960> + .byte 15,40,29,106,37,0,0 // movaps 0x256a(%rip),%xmm3 # 4f80 <_sk_callback_sse41+0x970> .byte 65,15,89,219 // mulps %xmm11,%xmm3 .byte 68,15,92,227 // subps %xmm3,%xmm12 - .byte 68,15,40,21,42,35,0,0 // movaps 0x232a(%rip),%xmm10 # 4d50 <_sk_callback_sse41+0x982> + .byte 68,15,40,21,106,37,0,0 // movaps 0x256a(%rip),%xmm10 # 4f90 <_sk_callback_sse41+0x980> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 15,40,29,47,35,0,0 // movaps 0x232f(%rip),%xmm3 # 4d60 <_sk_callback_sse41+0x992> + .byte 15,40,29,111,37,0,0 // movaps 0x256f(%rip),%xmm3 # 4fa0 <_sk_callback_sse41+0x990> .byte 65,15,94,218 // divps %xmm10,%xmm3 .byte 65,15,88,220 // addps %xmm12,%xmm3 - .byte 15,89,29,48,35,0,0 // mulps 0x2330(%rip),%xmm3 # 4d70 <_sk_callback_sse41+0x9a2> + .byte 15,89,29,112,37,0,0 // mulps 0x2570(%rip),%xmm3 # 4fb0 <_sk_callback_sse41+0x9a0> .byte 102,68,15,91,211 // cvtps2dq %xmm3,%xmm10 .byte 243,15,16,88,20 // movss 0x14(%rax),%xmm3 .byte 15,198,219,0 // shufps $0x0,%xmm3,%xmm3 @@ -22655,7 +23220,7 @@ _sk_parametric_a_sse41: .byte 102,65,15,56,20,217 // blendvps %xmm0,%xmm9,%xmm3 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,95,216 // maxps %xmm0,%xmm3 - .byte 15,93,29,27,35,0,0 // minps 0x231b(%rip),%xmm3 # 4d80 <_sk_callback_sse41+0x9b2> + .byte 15,93,29,91,37,0,0 // minps 0x255b(%rip),%xmm3 # 4fc0 <_sk_callback_sse41+0x9b0> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -22665,29 +23230,29 @@ HIDDEN _sk_lab_to_xyz_sse41 FUNCTION(_sk_lab_to_xyz_sse41) _sk_lab_to_xyz_sse41: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,89,5,23,35,0,0 // mulps 0x2317(%rip),%xmm8 # 4d90 <_sk_callback_sse41+0x9c2> - .byte 68,15,40,13,31,35,0,0 // movaps 0x231f(%rip),%xmm9 # 4da0 <_sk_callback_sse41+0x9d2> + .byte 68,15,89,5,87,37,0,0 // mulps 0x2557(%rip),%xmm8 # 4fd0 <_sk_callback_sse41+0x9c0> + .byte 68,15,40,13,95,37,0,0 // movaps 0x255f(%rip),%xmm9 # 4fe0 <_sk_callback_sse41+0x9d0> .byte 65,15,89,201 // mulps %xmm9,%xmm1 - .byte 15,40,5,36,35,0,0 // movaps 0x2324(%rip),%xmm0 # 4db0 <_sk_callback_sse41+0x9e2> + .byte 15,40,5,100,37,0,0 // movaps 0x2564(%rip),%xmm0 # 4ff0 <_sk_callback_sse41+0x9e0> .byte 15,88,200 // addps %xmm0,%xmm1 .byte 65,15,89,209 // mulps %xmm9,%xmm2 .byte 15,88,208 // addps %xmm0,%xmm2 - .byte 68,15,88,5,34,35,0,0 // addps 0x2322(%rip),%xmm8 # 4dc0 <_sk_callback_sse41+0x9f2> - .byte 68,15,89,5,42,35,0,0 // mulps 0x232a(%rip),%xmm8 # 4dd0 <_sk_callback_sse41+0xa02> - .byte 15,89,13,51,35,0,0 // mulps 0x2333(%rip),%xmm1 # 4de0 <_sk_callback_sse41+0xa12> + .byte 68,15,88,5,98,37,0,0 // addps 0x2562(%rip),%xmm8 # 5000 <_sk_callback_sse41+0x9f0> + .byte 68,15,89,5,106,37,0,0 // mulps 0x256a(%rip),%xmm8 # 5010 <_sk_callback_sse41+0xa00> + .byte 15,89,13,115,37,0,0 // mulps 0x2573(%rip),%xmm1 # 5020 <_sk_callback_sse41+0xa10> .byte 65,15,88,200 // addps %xmm8,%xmm1 - .byte 15,89,21,56,35,0,0 // mulps 0x2338(%rip),%xmm2 # 4df0 <_sk_callback_sse41+0xa22> + .byte 15,89,21,120,37,0,0 // mulps 0x2578(%rip),%xmm2 # 5030 <_sk_callback_sse41+0xa20> .byte 69,15,40,208 // movaps %xmm8,%xmm10 .byte 68,15,92,210 // subps %xmm2,%xmm10 .byte 68,15,40,217 // movaps %xmm1,%xmm11 .byte 69,15,89,219 // mulps %xmm11,%xmm11 .byte 68,15,89,217 // mulps %xmm1,%xmm11 - .byte 68,15,40,13,44,35,0,0 // movaps 0x232c(%rip),%xmm9 # 4e00 <_sk_callback_sse41+0xa32> + .byte 68,15,40,13,108,37,0,0 // movaps 0x256c(%rip),%xmm9 # 5040 <_sk_callback_sse41+0xa30> .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 65,15,194,195,1 // cmpltps %xmm11,%xmm0 - .byte 15,40,21,44,35,0,0 // movaps 0x232c(%rip),%xmm2 # 4e10 <_sk_callback_sse41+0xa42> + .byte 15,40,21,108,37,0,0 // movaps 0x256c(%rip),%xmm2 # 5050 <_sk_callback_sse41+0xa40> .byte 15,88,202 // addps %xmm2,%xmm1 - .byte 68,15,40,37,49,35,0,0 // movaps 0x2331(%rip),%xmm12 # 4e20 <_sk_callback_sse41+0xa52> + .byte 68,15,40,37,113,37,0,0 // movaps 0x2571(%rip),%xmm12 # 5060 <_sk_callback_sse41+0xa50> .byte 65,15,89,204 // mulps %xmm12,%xmm1 .byte 102,65,15,56,20,203 // blendvps %xmm0,%xmm11,%xmm1 .byte 69,15,40,216 // movaps %xmm8,%xmm11 @@ -22706,8 +23271,8 @@ _sk_lab_to_xyz_sse41: .byte 65,15,89,212 // mulps %xmm12,%xmm2 .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 102,65,15,56,20,211 // blendvps %xmm0,%xmm11,%xmm2 - .byte 15,89,13,234,34,0,0 // mulps 0x22ea(%rip),%xmm1 # 4e30 <_sk_callback_sse41+0xa62> - .byte 15,89,21,243,34,0,0 // mulps 0x22f3(%rip),%xmm2 # 4e40 <_sk_callback_sse41+0xa72> + .byte 15,89,13,42,37,0,0 // mulps 0x252a(%rip),%xmm1 # 5070 <_sk_callback_sse41+0xa60> + .byte 15,89,21,51,37,0,0 // mulps 0x2533(%rip),%xmm2 # 5080 <_sk_callback_sse41+0xa70> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,40,193 // movaps %xmm1,%xmm0 .byte 65,15,40,200 // movaps %xmm8,%xmm1 @@ -22721,7 +23286,7 @@ _sk_load_a8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,227,34,0,0 // mulps 0x22e3(%rip),%xmm3 # 4e50 <_sk_callback_sse41+0xa82> + .byte 15,89,29,35,37,0,0 // mulps 0x2523(%rip),%xmm3 # 5090 <_sk_callback_sse41+0xa80> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,87,201 // xorps %xmm1,%xmm1 @@ -22754,7 +23319,7 @@ _sk_gather_a8_sse41: .byte 102,15,58,32,192,3 // pinsrb $0x3,%eax,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,119,34,0,0 // mulps 0x2277(%rip),%xmm3 # 4e60 <_sk_callback_sse41+0xa92> + .byte 15,89,29,183,36,0,0 // mulps 0x24b7(%rip),%xmm3 # 50a0 <_sk_callback_sse41+0xa90> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 102,15,239,201 // pxor %xmm1,%xmm1 @@ -22767,7 +23332,7 @@ FUNCTION(_sk_store_a8_sse41) _sk_store_a8_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,107,34,0,0 // movaps 0x226b(%rip),%xmm8 # 4e70 <_sk_callback_sse41+0xaa2> + .byte 68,15,40,5,171,36,0,0 // movaps 0x24ab(%rip),%xmm8 # 50b0 <_sk_callback_sse41+0xaa0> .byte 68,15,89,195 // mulps %xmm3,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 .byte 102,69,15,56,43,192 // packusdw %xmm8,%xmm8 @@ -22784,9 +23349,9 @@ _sk_load_g8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,72,34,0,0 // mulps 0x2248(%rip),%xmm0 # 4e80 <_sk_callback_sse41+0xab2> + .byte 15,89,5,136,36,0,0 // mulps 0x2488(%rip),%xmm0 # 50c0 <_sk_callback_sse41+0xab0> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,79,34,0,0 // movaps 0x224f(%rip),%xmm3 # 4e90 <_sk_callback_sse41+0xac2> + .byte 15,40,29,143,36,0,0 // movaps 0x248f(%rip),%xmm3 # 50d0 <_sk_callback_sse41+0xac0> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -22817,9 +23382,9 @@ _sk_gather_g8_sse41: .byte 102,15,58,32,192,3 // pinsrb $0x3,%eax,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,232,33,0,0 // mulps 0x21e8(%rip),%xmm0 # 4ea0 <_sk_callback_sse41+0xad2> + .byte 15,89,5,40,36,0,0 // mulps 0x2428(%rip),%xmm0 # 50e0 <_sk_callback_sse41+0xad0> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,239,33,0,0 // movaps 0x21ef(%rip),%xmm3 # 4eb0 <_sk_callback_sse41+0xae2> + .byte 15,40,29,47,36,0,0 // movaps 0x242f(%rip),%xmm3 # 50f0 <_sk_callback_sse41+0xae0> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -22864,17 +23429,17 @@ _sk_gather_i8_sse41: .byte 102,15,58,34,28,8,1 // pinsrd $0x1,(%rax,%rcx,1),%xmm3 .byte 102,66,15,58,34,28,144,2 // pinsrd $0x2,(%rax,%r10,4),%xmm3 .byte 102,66,15,58,34,28,8,3 // pinsrd $0x3,(%rax,%r9,1),%xmm3 - .byte 102,15,111,5,70,33,0,0 // movdqa 0x2146(%rip),%xmm0 # 4ec0 <_sk_callback_sse41+0xaf2> + .byte 102,15,111,5,134,35,0,0 // movdqa 0x2386(%rip),%xmm0 # 5100 <_sk_callback_sse41+0xaf0> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,71,33,0,0 // movaps 0x2147(%rip),%xmm8 # 4ed0 <_sk_callback_sse41+0xb02> + .byte 68,15,40,5,135,35,0,0 // movaps 0x2387(%rip),%xmm8 # 5110 <_sk_callback_sse41+0xb00> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 - .byte 102,15,56,0,13,70,33,0,0 // pshufb 0x2146(%rip),%xmm1 # 4ee0 <_sk_callback_sse41+0xb12> + .byte 102,15,56,0,13,134,35,0,0 // pshufb 0x2386(%rip),%xmm1 # 5120 <_sk_callback_sse41+0xb10> .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,111,211 // movdqa %xmm3,%xmm2 - .byte 102,15,56,0,21,66,33,0,0 // pshufb 0x2142(%rip),%xmm2 # 4ef0 <_sk_callback_sse41+0xb22> + .byte 102,15,56,0,21,130,35,0,0 // pshufb 0x2382(%rip),%xmm2 # 5130 <_sk_callback_sse41+0xb20> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 102,15,114,211,24 // psrld $0x18,%xmm3 @@ -22890,19 +23455,19 @@ _sk_load_565_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,51,20,120 // pmovzxwd (%rax,%rdi,2),%xmm2 - .byte 102,15,111,5,40,33,0,0 // movdqa 0x2128(%rip),%xmm0 # 4f00 <_sk_callback_sse41+0xb32> + .byte 102,15,111,5,104,35,0,0 // movdqa 0x2368(%rip),%xmm0 # 5140 <_sk_callback_sse41+0xb30> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,42,33,0,0 // mulps 0x212a(%rip),%xmm0 # 4f10 <_sk_callback_sse41+0xb42> - .byte 102,15,111,13,50,33,0,0 // movdqa 0x2132(%rip),%xmm1 # 4f20 <_sk_callback_sse41+0xb52> + .byte 15,89,5,106,35,0,0 // mulps 0x236a(%rip),%xmm0 # 5150 <_sk_callback_sse41+0xb40> + .byte 102,15,111,13,114,35,0,0 // movdqa 0x2372(%rip),%xmm1 # 5160 <_sk_callback_sse41+0xb50> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,52,33,0,0 // mulps 0x2134(%rip),%xmm1 # 4f30 <_sk_callback_sse41+0xb62> - .byte 102,15,219,21,60,33,0,0 // pand 0x213c(%rip),%xmm2 # 4f40 <_sk_callback_sse41+0xb72> + .byte 15,89,13,116,35,0,0 // mulps 0x2374(%rip),%xmm1 # 5170 <_sk_callback_sse41+0xb60> + .byte 102,15,219,21,124,35,0,0 // pand 0x237c(%rip),%xmm2 # 5180 <_sk_callback_sse41+0xb70> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,66,33,0,0 // mulps 0x2142(%rip),%xmm2 # 4f50 <_sk_callback_sse41+0xb82> + .byte 15,89,21,130,35,0,0 // mulps 0x2382(%rip),%xmm2 # 5190 <_sk_callback_sse41+0xb80> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,73,33,0,0 // movaps 0x2149(%rip),%xmm3 # 4f60 <_sk_callback_sse41+0xb92> + .byte 15,40,29,137,35,0,0 // movaps 0x2389(%rip),%xmm3 # 51a0 <_sk_callback_sse41+0xb90> .byte 255,224 // jmpq *%rax HIDDEN _sk_gather_565_sse41 @@ -22930,19 +23495,19 @@ _sk_gather_565_sse41: .byte 65,15,183,4,65 // movzwl (%r9,%rax,2),%eax .byte 102,15,196,192,3 // pinsrw $0x3,%eax,%xmm0 .byte 102,15,56,51,208 // pmovzxwd %xmm0,%xmm2 - .byte 102,15,111,5,238,32,0,0 // movdqa 0x20ee(%rip),%xmm0 # 4f70 <_sk_callback_sse41+0xba2> + .byte 102,15,111,5,46,35,0,0 // movdqa 0x232e(%rip),%xmm0 # 51b0 <_sk_callback_sse41+0xba0> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,240,32,0,0 // mulps 0x20f0(%rip),%xmm0 # 4f80 <_sk_callback_sse41+0xbb2> - .byte 102,15,111,13,248,32,0,0 // movdqa 0x20f8(%rip),%xmm1 # 4f90 <_sk_callback_sse41+0xbc2> + .byte 15,89,5,48,35,0,0 // mulps 0x2330(%rip),%xmm0 # 51c0 <_sk_callback_sse41+0xbb0> + .byte 102,15,111,13,56,35,0,0 // movdqa 0x2338(%rip),%xmm1 # 51d0 <_sk_callback_sse41+0xbc0> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,250,32,0,0 // mulps 0x20fa(%rip),%xmm1 # 4fa0 <_sk_callback_sse41+0xbd2> - .byte 102,15,219,21,2,33,0,0 // pand 0x2102(%rip),%xmm2 # 4fb0 <_sk_callback_sse41+0xbe2> + .byte 15,89,13,58,35,0,0 // mulps 0x233a(%rip),%xmm1 # 51e0 <_sk_callback_sse41+0xbd0> + .byte 102,15,219,21,66,35,0,0 // pand 0x2342(%rip),%xmm2 # 51f0 <_sk_callback_sse41+0xbe0> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,8,33,0,0 // mulps 0x2108(%rip),%xmm2 # 4fc0 <_sk_callback_sse41+0xbf2> + .byte 15,89,21,72,35,0,0 // mulps 0x2348(%rip),%xmm2 # 5200 <_sk_callback_sse41+0xbf0> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,15,33,0,0 // movaps 0x210f(%rip),%xmm3 # 4fd0 <_sk_callback_sse41+0xc02> + .byte 15,40,29,79,35,0,0 // movaps 0x234f(%rip),%xmm3 # 5210 <_sk_callback_sse41+0xc00> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_565_sse41 @@ -22951,12 +23516,12 @@ FUNCTION(_sk_store_565_sse41) _sk_store_565_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,16,33,0,0 // movaps 0x2110(%rip),%xmm8 # 4fe0 <_sk_callback_sse41+0xc12> + .byte 68,15,40,5,80,35,0,0 // movaps 0x2350(%rip),%xmm8 # 5220 <_sk_callback_sse41+0xc10> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 .byte 102,65,15,114,241,11 // pslld $0xb,%xmm9 - .byte 68,15,40,21,5,33,0,0 // movaps 0x2105(%rip),%xmm10 # 4ff0 <_sk_callback_sse41+0xc22> + .byte 68,15,40,21,69,35,0,0 // movaps 0x2345(%rip),%xmm10 # 5230 <_sk_callback_sse41+0xc20> .byte 68,15,89,209 // mulps %xmm1,%xmm10 .byte 102,69,15,91,210 // cvtps2dq %xmm10,%xmm10 .byte 102,65,15,114,242,5 // pslld $0x5,%xmm10 @@ -22976,21 +23541,21 @@ _sk_load_4444_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,51,28,120 // pmovzxwd (%rax,%rdi,2),%xmm3 - .byte 102,15,111,5,208,32,0,0 // movdqa 0x20d0(%rip),%xmm0 # 5000 <_sk_callback_sse41+0xc32> + .byte 102,15,111,5,16,35,0,0 // movdqa 0x2310(%rip),%xmm0 # 5240 <_sk_callback_sse41+0xc30> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,210,32,0,0 // mulps 0x20d2(%rip),%xmm0 # 5010 <_sk_callback_sse41+0xc42> - .byte 102,15,111,13,218,32,0,0 // movdqa 0x20da(%rip),%xmm1 # 5020 <_sk_callback_sse41+0xc52> + .byte 15,89,5,18,35,0,0 // mulps 0x2312(%rip),%xmm0 # 5250 <_sk_callback_sse41+0xc40> + .byte 102,15,111,13,26,35,0,0 // movdqa 0x231a(%rip),%xmm1 # 5260 <_sk_callback_sse41+0xc50> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,220,32,0,0 // mulps 0x20dc(%rip),%xmm1 # 5030 <_sk_callback_sse41+0xc62> - .byte 102,15,111,21,228,32,0,0 // movdqa 0x20e4(%rip),%xmm2 # 5040 <_sk_callback_sse41+0xc72> + .byte 15,89,13,28,35,0,0 // mulps 0x231c(%rip),%xmm1 # 5270 <_sk_callback_sse41+0xc60> + .byte 102,15,111,21,36,35,0,0 // movdqa 0x2324(%rip),%xmm2 # 5280 <_sk_callback_sse41+0xc70> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,230,32,0,0 // mulps 0x20e6(%rip),%xmm2 # 5050 <_sk_callback_sse41+0xc82> - .byte 102,15,219,29,238,32,0,0 // pand 0x20ee(%rip),%xmm3 # 5060 <_sk_callback_sse41+0xc92> + .byte 15,89,21,38,35,0,0 // mulps 0x2326(%rip),%xmm2 # 5290 <_sk_callback_sse41+0xc80> + .byte 102,15,219,29,46,35,0,0 // pand 0x232e(%rip),%xmm3 # 52a0 <_sk_callback_sse41+0xc90> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,244,32,0,0 // mulps 0x20f4(%rip),%xmm3 # 5070 <_sk_callback_sse41+0xca2> + .byte 15,89,29,52,35,0,0 // mulps 0x2334(%rip),%xmm3 # 52b0 <_sk_callback_sse41+0xca0> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -23019,21 +23584,21 @@ _sk_gather_4444_sse41: .byte 65,15,183,4,65 // movzwl (%r9,%rax,2),%eax .byte 102,15,196,192,3 // pinsrw $0x3,%eax,%xmm0 .byte 102,15,56,51,216 // pmovzxwd %xmm0,%xmm3 - .byte 102,15,111,5,151,32,0,0 // movdqa 0x2097(%rip),%xmm0 # 5080 <_sk_callback_sse41+0xcb2> + .byte 102,15,111,5,215,34,0,0 // movdqa 0x22d7(%rip),%xmm0 # 52c0 <_sk_callback_sse41+0xcb0> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,153,32,0,0 // mulps 0x2099(%rip),%xmm0 # 5090 <_sk_callback_sse41+0xcc2> - .byte 102,15,111,13,161,32,0,0 // movdqa 0x20a1(%rip),%xmm1 # 50a0 <_sk_callback_sse41+0xcd2> + .byte 15,89,5,217,34,0,0 // mulps 0x22d9(%rip),%xmm0 # 52d0 <_sk_callback_sse41+0xcc0> + .byte 102,15,111,13,225,34,0,0 // movdqa 0x22e1(%rip),%xmm1 # 52e0 <_sk_callback_sse41+0xcd0> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,163,32,0,0 // mulps 0x20a3(%rip),%xmm1 # 50b0 <_sk_callback_sse41+0xce2> - .byte 102,15,111,21,171,32,0,0 // movdqa 0x20ab(%rip),%xmm2 # 50c0 <_sk_callback_sse41+0xcf2> + .byte 15,89,13,227,34,0,0 // mulps 0x22e3(%rip),%xmm1 # 52f0 <_sk_callback_sse41+0xce0> + .byte 102,15,111,21,235,34,0,0 // movdqa 0x22eb(%rip),%xmm2 # 5300 <_sk_callback_sse41+0xcf0> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,173,32,0,0 // mulps 0x20ad(%rip),%xmm2 # 50d0 <_sk_callback_sse41+0xd02> - .byte 102,15,219,29,181,32,0,0 // pand 0x20b5(%rip),%xmm3 # 50e0 <_sk_callback_sse41+0xd12> + .byte 15,89,21,237,34,0,0 // mulps 0x22ed(%rip),%xmm2 # 5310 <_sk_callback_sse41+0xd00> + .byte 102,15,219,29,245,34,0,0 // pand 0x22f5(%rip),%xmm3 # 5320 <_sk_callback_sse41+0xd10> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,187,32,0,0 // mulps 0x20bb(%rip),%xmm3 # 50f0 <_sk_callback_sse41+0xd22> + .byte 15,89,29,251,34,0,0 // mulps 0x22fb(%rip),%xmm3 # 5330 <_sk_callback_sse41+0xd20> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -23043,7 +23608,7 @@ FUNCTION(_sk_store_4444_sse41) _sk_store_4444_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,186,32,0,0 // movaps 0x20ba(%rip),%xmm8 # 5100 <_sk_callback_sse41+0xd32> + .byte 68,15,40,5,250,34,0,0 // movaps 0x22fa(%rip),%xmm8 # 5340 <_sk_callback_sse41+0xd30> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -23073,17 +23638,17 @@ _sk_load_8888_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 15,16,28,184 // movups (%rax,%rdi,4),%xmm3 - .byte 15,40,5,89,32,0,0 // movaps 0x2059(%rip),%xmm0 # 5110 <_sk_callback_sse41+0xd42> + .byte 15,40,5,153,34,0,0 // movaps 0x2299(%rip),%xmm0 # 5350 <_sk_callback_sse41+0xd40> .byte 15,84,195 // andps %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,91,32,0,0 // movaps 0x205b(%rip),%xmm8 # 5120 <_sk_callback_sse41+0xd52> + .byte 68,15,40,5,155,34,0,0 // movaps 0x229b(%rip),%xmm8 # 5360 <_sk_callback_sse41+0xd50> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,40,203 // movaps %xmm3,%xmm1 - .byte 102,15,56,0,13,91,32,0,0 // pshufb 0x205b(%rip),%xmm1 # 5130 <_sk_callback_sse41+0xd62> + .byte 102,15,56,0,13,155,34,0,0 // pshufb 0x229b(%rip),%xmm1 # 5370 <_sk_callback_sse41+0xd60> .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 15,40,211 // movaps %xmm3,%xmm2 - .byte 102,15,56,0,21,88,32,0,0 // pshufb 0x2058(%rip),%xmm2 # 5140 <_sk_callback_sse41+0xd72> + .byte 102,15,56,0,21,152,34,0,0 // pshufb 0x2298(%rip),%xmm2 # 5380 <_sk_callback_sse41+0xd70> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 102,15,114,211,24 // psrld $0x18,%xmm3 @@ -23114,17 +23679,17 @@ _sk_gather_8888_sse41: .byte 102,65,15,58,34,28,129,1 // pinsrd $0x1,(%r9,%rax,4),%xmm3 .byte 102,67,15,58,34,28,145,2 // pinsrd $0x2,(%r9,%r10,4),%xmm3 .byte 102,65,15,58,34,28,137,3 // pinsrd $0x3,(%r9,%rcx,4),%xmm3 - .byte 102,15,111,5,241,31,0,0 // movdqa 0x1ff1(%rip),%xmm0 # 5150 <_sk_callback_sse41+0xd82> + .byte 102,15,111,5,49,34,0,0 // movdqa 0x2231(%rip),%xmm0 # 5390 <_sk_callback_sse41+0xd80> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,242,31,0,0 // movaps 0x1ff2(%rip),%xmm8 # 5160 <_sk_callback_sse41+0xd92> + .byte 68,15,40,5,50,34,0,0 // movaps 0x2232(%rip),%xmm8 # 53a0 <_sk_callback_sse41+0xd90> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 - .byte 102,15,56,0,13,241,31,0,0 // pshufb 0x1ff1(%rip),%xmm1 # 5170 <_sk_callback_sse41+0xda2> + .byte 102,15,56,0,13,49,34,0,0 // pshufb 0x2231(%rip),%xmm1 # 53b0 <_sk_callback_sse41+0xda0> .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,111,211 // movdqa %xmm3,%xmm2 - .byte 102,15,56,0,21,237,31,0,0 // pshufb 0x1fed(%rip),%xmm2 # 5180 <_sk_callback_sse41+0xdb2> + .byte 102,15,56,0,21,45,34,0,0 // pshufb 0x222d(%rip),%xmm2 # 53c0 <_sk_callback_sse41+0xdb0> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 102,15,114,211,24 // psrld $0x18,%xmm3 @@ -23139,7 +23704,7 @@ FUNCTION(_sk_store_8888_sse41) _sk_store_8888_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,217,31,0,0 // movaps 0x1fd9(%rip),%xmm8 # 5190 <_sk_callback_sse41+0xdc2> + .byte 68,15,40,5,25,34,0,0 // movaps 0x2219(%rip),%xmm8 # 53d0 <_sk_callback_sse41+0xdc0> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -23176,18 +23741,18 @@ _sk_load_f16_sse41: .byte 102,68,15,97,216 // punpcklwd %xmm0,%xmm11 .byte 102,68,15,105,200 // punpckhwd %xmm0,%xmm9 .byte 102,65,15,56,51,203 // pmovzxwd %xmm11,%xmm1 - .byte 102,68,15,111,5,82,31,0,0 // movdqa 0x1f52(%rip),%xmm8 # 51a0 <_sk_callback_sse41+0xdd2> + .byte 102,68,15,111,5,146,33,0,0 // movdqa 0x2192(%rip),%xmm8 # 53e0 <_sk_callback_sse41+0xdd0> .byte 102,15,111,209 // movdqa %xmm1,%xmm2 .byte 102,65,15,219,208 // pand %xmm8,%xmm2 .byte 102,15,239,202 // pxor %xmm2,%xmm1 - .byte 102,15,111,29,77,31,0,0 // movdqa 0x1f4d(%rip),%xmm3 # 51b0 <_sk_callback_sse41+0xde2> + .byte 102,15,111,29,141,33,0,0 // movdqa 0x218d(%rip),%xmm3 # 53f0 <_sk_callback_sse41+0xde0> .byte 102,15,114,242,16 // pslld $0x10,%xmm2 .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,15,56,63,195 // pmaxud %xmm3,%xmm0 .byte 102,15,118,193 // pcmpeqd %xmm1,%xmm0 .byte 102,15,114,241,13 // pslld $0xd,%xmm1 .byte 102,15,235,202 // por %xmm2,%xmm1 - .byte 102,68,15,111,21,57,31,0,0 // movdqa 0x1f39(%rip),%xmm10 # 51c0 <_sk_callback_sse41+0xdf2> + .byte 102,68,15,111,21,121,33,0,0 // movdqa 0x2179(%rip),%xmm10 # 5400 <_sk_callback_sse41+0xdf0> .byte 102,65,15,254,202 // paddd %xmm10,%xmm1 .byte 102,15,219,193 // pand %xmm1,%xmm0 .byte 102,65,15,115,219,8 // psrldq $0x8,%xmm11 @@ -23260,18 +23825,18 @@ _sk_gather_f16_sse41: .byte 102,68,15,97,218 // punpcklwd %xmm2,%xmm11 .byte 102,68,15,105,202 // punpckhwd %xmm2,%xmm9 .byte 102,65,15,56,51,203 // pmovzxwd %xmm11,%xmm1 - .byte 102,68,15,111,5,247,29,0,0 // movdqa 0x1df7(%rip),%xmm8 # 51d0 <_sk_callback_sse41+0xe02> + .byte 102,68,15,111,5,55,32,0,0 // movdqa 0x2037(%rip),%xmm8 # 5410 <_sk_callback_sse41+0xe00> .byte 102,15,111,209 // movdqa %xmm1,%xmm2 .byte 102,65,15,219,208 // pand %xmm8,%xmm2 .byte 102,15,239,202 // pxor %xmm2,%xmm1 - .byte 102,15,111,29,242,29,0,0 // movdqa 0x1df2(%rip),%xmm3 # 51e0 <_sk_callback_sse41+0xe12> + .byte 102,15,111,29,50,32,0,0 // movdqa 0x2032(%rip),%xmm3 # 5420 <_sk_callback_sse41+0xe10> .byte 102,15,114,242,16 // pslld $0x10,%xmm2 .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,15,56,63,195 // pmaxud %xmm3,%xmm0 .byte 102,15,118,193 // pcmpeqd %xmm1,%xmm0 .byte 102,15,114,241,13 // pslld $0xd,%xmm1 .byte 102,15,235,202 // por %xmm2,%xmm1 - .byte 102,68,15,111,21,222,29,0,0 // movdqa 0x1dde(%rip),%xmm10 # 51f0 <_sk_callback_sse41+0xe22> + .byte 102,68,15,111,21,30,32,0,0 // movdqa 0x201e(%rip),%xmm10 # 5430 <_sk_callback_sse41+0xe20> .byte 102,65,15,254,202 // paddd %xmm10,%xmm1 .byte 102,15,219,193 // pand %xmm1,%xmm0 .byte 102,65,15,115,219,8 // psrldq $0x8,%xmm11 @@ -23319,17 +23884,17 @@ FUNCTION(_sk_store_f16_sse41) _sk_store_f16_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 102,68,15,111,21,20,29,0,0 // movdqa 0x1d14(%rip),%xmm10 # 5200 <_sk_callback_sse41+0xe32> + .byte 102,68,15,111,21,84,31,0,0 // movdqa 0x1f54(%rip),%xmm10 # 5440 <_sk_callback_sse41+0xe30> .byte 102,68,15,111,224 // movdqa %xmm0,%xmm12 .byte 102,68,15,111,232 // movdqa %xmm0,%xmm13 .byte 102,69,15,219,234 // pand %xmm10,%xmm13 .byte 102,69,15,239,229 // pxor %xmm13,%xmm12 - .byte 102,68,15,111,13,7,29,0,0 // movdqa 0x1d07(%rip),%xmm9 # 5210 <_sk_callback_sse41+0xe42> + .byte 102,68,15,111,13,71,31,0,0 // movdqa 0x1f47(%rip),%xmm9 # 5450 <_sk_callback_sse41+0xe40> .byte 102,65,15,114,213,16 // psrld $0x10,%xmm13 .byte 102,69,15,111,193 // movdqa %xmm9,%xmm8 .byte 102,69,15,102,196 // pcmpgtd %xmm12,%xmm8 .byte 102,65,15,114,212,13 // psrld $0xd,%xmm12 - .byte 102,68,15,111,29,248,28,0,0 // movdqa 0x1cf8(%rip),%xmm11 # 5220 <_sk_callback_sse41+0xe52> + .byte 102,68,15,111,29,56,31,0,0 // movdqa 0x1f38(%rip),%xmm11 # 5460 <_sk_callback_sse41+0xe50> .byte 102,69,15,235,235 // por %xmm11,%xmm13 .byte 102,69,15,254,236 // paddd %xmm12,%xmm13 .byte 102,69,15,223,197 // pandn %xmm13,%xmm8 @@ -23399,7 +23964,7 @@ _sk_load_u16_be_sse41: .byte 102,15,235,200 // por %xmm0,%xmm1 .byte 102,15,56,51,193 // pmovzxwd %xmm1,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,199,27,0,0 // movaps 0x1bc7(%rip),%xmm8 # 5230 <_sk_callback_sse41+0xe62> + .byte 68,15,40,5,7,30,0,0 // movaps 0x1e07(%rip),%xmm8 # 5470 <_sk_callback_sse41+0xe60> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -23451,7 +24016,7 @@ _sk_load_rgb_u16_be_sse41: .byte 102,15,235,193 // por %xmm1,%xmm0 .byte 102,15,56,51,192 // pmovzxwd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,8,27,0,0 // movaps 0x1b08(%rip),%xmm8 # 5240 <_sk_callback_sse41+0xe72> + .byte 68,15,40,5,72,29,0,0 // movaps 0x1d48(%rip),%xmm8 # 5480 <_sk_callback_sse41+0xe70> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -23468,7 +24033,7 @@ _sk_load_rgb_u16_be_sse41: .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,207,26,0,0 // movaps 0x1acf(%rip),%xmm3 # 5250 <_sk_callback_sse41+0xe82> + .byte 15,40,29,15,29,0,0 // movaps 0x1d0f(%rip),%xmm3 # 5490 <_sk_callback_sse41+0xe80> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_u16_be_sse41 @@ -23477,7 +24042,7 @@ FUNCTION(_sk_store_u16_be_sse41) _sk_store_u16_be_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,13,208,26,0,0 // movaps 0x1ad0(%rip),%xmm9 # 5260 <_sk_callback_sse41+0xe92> + .byte 68,15,40,13,16,29,0,0 // movaps 0x1d10(%rip),%xmm9 # 54a0 <_sk_callback_sse41+0xe90> .byte 68,15,40,192 // movaps %xmm0,%xmm8 .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 @@ -23688,10 +24253,10 @@ HIDDEN _sk_luminance_to_alpha_sse41 FUNCTION(_sk_luminance_to_alpha_sse41) _sk_luminance_to_alpha_sse41: .byte 15,40,218 // movaps %xmm2,%xmm3 - .byte 15,89,5,44,24,0,0 // mulps 0x182c(%rip),%xmm0 # 5270 <_sk_callback_sse41+0xea2> - .byte 15,89,13,53,24,0,0 // mulps 0x1835(%rip),%xmm1 # 5280 <_sk_callback_sse41+0xeb2> + .byte 15,89,5,108,26,0,0 // mulps 0x1a6c(%rip),%xmm0 # 54b0 <_sk_callback_sse41+0xea0> + .byte 15,89,13,117,26,0,0 // mulps 0x1a75(%rip),%xmm1 # 54c0 <_sk_callback_sse41+0xeb0> .byte 15,88,200 // addps %xmm0,%xmm1 - .byte 15,89,29,59,24,0,0 // mulps 0x183b(%rip),%xmm3 # 5290 <_sk_callback_sse41+0xec2> + .byte 15,89,29,123,26,0,0 // mulps 0x1a7b(%rip),%xmm3 # 54d0 <_sk_callback_sse41+0xec0> .byte 15,88,217 // addps %xmm1,%xmm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 @@ -23909,91 +24474,197 @@ _sk_matrix_perspective_sse41: .byte 65,15,40,201 // movaps %xmm9,%xmm1 .byte 255,224 // jmpq *%rax +HIDDEN _sk_evenly_spaced_gradient_sse41 +.globl _sk_evenly_spaced_gradient_sse41 +FUNCTION(_sk_evenly_spaced_gradient_sse41) +_sk_evenly_spaced_gradient_sse41: + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 72,139,8 // mov (%rax),%rcx + .byte 76,139,88,8 // mov 0x8(%rax),%r11 + .byte 72,255,201 // dec %rcx + .byte 120,7 // js 3dd4 <_sk_evenly_spaced_gradient_sse41+0x15> + .byte 243,72,15,42,201 // cvtsi2ss %rcx,%xmm1 + .byte 235,21 // jmp 3de9 <_sk_evenly_spaced_gradient_sse41+0x2a> + .byte 73,137,200 // mov %rcx,%r8 + .byte 73,209,232 // shr %r8 + .byte 131,225,1 // and $0x1,%ecx + .byte 76,9,193 // or %r8,%rcx + .byte 243,72,15,42,201 // cvtsi2ss %rcx,%xmm1 + .byte 243,15,88,201 // addss %xmm1,%xmm1 + .byte 15,198,201,0 // shufps $0x0,%xmm1,%xmm1 + .byte 15,89,200 // mulps %xmm0,%xmm1 + .byte 243,15,91,201 // cvttps2dq %xmm1,%xmm1 + .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 + .byte 69,137,200 // mov %r9d,%r8d + .byte 73,193,233,32 // shr $0x20,%r9 + .byte 102,72,15,126,201 // movq %xmm1,%rcx + .byte 65,137,202 // mov %ecx,%r10d + .byte 72,193,233,32 // shr $0x20,%rcx + .byte 243,71,15,16,4,147 // movss (%r11,%r10,4),%xmm8 + .byte 102,69,15,58,33,4,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm8 + .byte 243,67,15,16,12,131 // movss (%r11,%r8,4),%xmm1 + .byte 102,68,15,58,33,193,32 // insertps $0x20,%xmm1,%xmm8 + .byte 243,67,15,16,12,139 // movss (%r11,%r9,4),%xmm1 + .byte 102,68,15,58,33,193,48 // insertps $0x30,%xmm1,%xmm8 + .byte 76,139,88,40 // mov 0x28(%rax),%r11 + .byte 243,71,15,16,12,147 // movss (%r11,%r10,4),%xmm9 + .byte 102,69,15,58,33,12,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm9 + .byte 243,67,15,16,12,131 // movss (%r11,%r8,4),%xmm1 + .byte 102,68,15,58,33,201,32 // insertps $0x20,%xmm1,%xmm9 + .byte 243,67,15,16,12,139 // movss (%r11,%r9,4),%xmm1 + .byte 102,68,15,58,33,201,48 // insertps $0x30,%xmm1,%xmm9 + .byte 76,139,88,16 // mov 0x10(%rax),%r11 + .byte 243,67,15,16,12,147 // movss (%r11,%r10,4),%xmm1 + .byte 102,65,15,58,33,12,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm1 + .byte 243,67,15,16,20,131 // movss (%r11,%r8,4),%xmm2 + .byte 102,15,58,33,202,32 // insertps $0x20,%xmm2,%xmm1 + .byte 243,67,15,16,20,139 // movss (%r11,%r9,4),%xmm2 + .byte 102,15,58,33,202,48 // insertps $0x30,%xmm2,%xmm1 + .byte 76,139,88,48 // mov 0x30(%rax),%r11 + .byte 243,71,15,16,20,147 // movss (%r11,%r10,4),%xmm10 + .byte 102,69,15,58,33,20,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm10 + .byte 243,67,15,16,20,131 // movss (%r11,%r8,4),%xmm2 + .byte 102,68,15,58,33,210,32 // insertps $0x20,%xmm2,%xmm10 + .byte 243,67,15,16,20,139 // movss (%r11,%r9,4),%xmm2 + .byte 102,68,15,58,33,210,48 // insertps $0x30,%xmm2,%xmm10 + .byte 76,139,88,24 // mov 0x18(%rax),%r11 + .byte 243,67,15,16,20,147 // movss (%r11,%r10,4),%xmm2 + .byte 102,65,15,58,33,20,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm2 + .byte 243,67,15,16,28,131 // movss (%r11,%r8,4),%xmm3 + .byte 102,15,58,33,211,32 // insertps $0x20,%xmm3,%xmm2 + .byte 243,67,15,16,28,139 // movss (%r11,%r9,4),%xmm3 + .byte 102,15,58,33,211,48 // insertps $0x30,%xmm3,%xmm2 + .byte 76,139,88,56 // mov 0x38(%rax),%r11 + .byte 243,71,15,16,28,147 // movss (%r11,%r10,4),%xmm11 + .byte 102,69,15,58,33,28,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm11 + .byte 243,67,15,16,28,131 // movss (%r11,%r8,4),%xmm3 + .byte 102,68,15,58,33,219,32 // insertps $0x20,%xmm3,%xmm11 + .byte 243,67,15,16,28,139 // movss (%r11,%r9,4),%xmm3 + .byte 102,68,15,58,33,219,48 // insertps $0x30,%xmm3,%xmm11 + .byte 76,139,88,32 // mov 0x20(%rax),%r11 + .byte 243,67,15,16,28,147 // movss (%r11,%r10,4),%xmm3 + .byte 102,65,15,58,33,28,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm3 + .byte 243,71,15,16,36,131 // movss (%r11,%r8,4),%xmm12 + .byte 102,65,15,58,33,220,32 // insertps $0x20,%xmm12,%xmm3 + .byte 243,71,15,16,36,139 // movss (%r11,%r9,4),%xmm12 + .byte 102,65,15,58,33,220,48 // insertps $0x30,%xmm12,%xmm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 243,70,15,16,36,144 // movss (%rax,%r10,4),%xmm12 + .byte 102,68,15,58,33,36,136,16 // insertps $0x10,(%rax,%rcx,4),%xmm12 + .byte 243,70,15,16,44,128 // movss (%rax,%r8,4),%xmm13 + .byte 102,69,15,58,33,229,32 // insertps $0x20,%xmm13,%xmm12 + .byte 243,70,15,16,44,136 // movss (%rax,%r9,4),%xmm13 + .byte 102,69,15,58,33,229,48 // insertps $0x30,%xmm13,%xmm12 + .byte 68,15,89,192 // mulps %xmm0,%xmm8 + .byte 69,15,88,193 // addps %xmm9,%xmm8 + .byte 15,89,200 // mulps %xmm0,%xmm1 + .byte 65,15,88,202 // addps %xmm10,%xmm1 + .byte 15,89,208 // mulps %xmm0,%xmm2 + .byte 65,15,88,211 // addps %xmm11,%xmm2 + .byte 15,89,216 // mulps %xmm0,%xmm3 + .byte 65,15,88,220 // addps %xmm12,%xmm3 + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 65,15,40,192 // movaps %xmm8,%xmm0 + .byte 255,224 // jmpq *%rax + HIDDEN _sk_gradient_sse41 .globl _sk_gradient_sse41 FUNCTION(_sk_gradient_sse41) _sk_gradient_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 243,68,15,16,80,16 // movss 0x10(%rax),%xmm10 - .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 - .byte 243,68,15,16,88,20 // movss 0x14(%rax),%xmm11 - .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 - .byte 243,68,15,16,96,24 // movss 0x18(%rax),%xmm12 - .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 - .byte 243,68,15,16,104,28 // movss 0x1c(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 72,139,8 // mov (%rax),%rcx - .byte 72,133,201 // test %rcx,%rcx - .byte 15,132,254,0,0,0 // je 3ef7 <_sk_gradient_sse41+0x138> - .byte 15,41,100,36,168 // movaps %xmm4,-0x58(%rsp) - .byte 15,41,108,36,184 // movaps %xmm5,-0x48(%rsp) - .byte 15,41,116,36,200 // movaps %xmm6,-0x38(%rsp) - .byte 15,41,124,36,216 // movaps %xmm7,-0x28(%rsp) - .byte 72,139,64,8 // mov 0x8(%rax),%rax - .byte 72,131,192,32 // add $0x20,%rax - .byte 69,15,87,201 // xorps %xmm9,%xmm9 - .byte 15,87,219 // xorps %xmm3,%xmm3 - .byte 15,87,210 // xorps %xmm2,%xmm2 - .byte 15,87,201 // xorps %xmm1,%xmm1 - .byte 15,40,233 // movaps %xmm1,%xmm5 - .byte 15,40,242 // movaps %xmm2,%xmm6 - .byte 15,40,251 // movaps %xmm3,%xmm7 - .byte 69,15,40,194 // movaps %xmm10,%xmm8 - .byte 69,15,40,243 // movaps %xmm11,%xmm14 - .byte 69,15,40,252 // movaps %xmm12,%xmm15 - .byte 68,15,41,108,36,232 // movaps %xmm13,-0x18(%rsp) - .byte 65,15,40,201 // movaps %xmm9,%xmm1 - .byte 243,15,16,80,224 // movss -0x20(%rax),%xmm2 - .byte 243,68,15,16,72,228 // movss -0x1c(%rax),%xmm9 - .byte 15,198,210,0 // shufps $0x0,%xmm2,%xmm2 - .byte 15,40,224 // movaps %xmm0,%xmm4 - .byte 15,194,194,1 // cmpltps %xmm2,%xmm0 - .byte 69,15,198,201,0 // shufps $0x0,%xmm9,%xmm9 - .byte 102,68,15,56,20,201 // blendvps %xmm0,%xmm1,%xmm9 - .byte 243,15,16,72,232 // movss -0x18(%rax),%xmm1 - .byte 15,198,201,0 // shufps $0x0,%xmm1,%xmm1 - .byte 102,15,56,20,205 // blendvps %xmm0,%xmm5,%xmm1 - .byte 243,15,16,80,236 // movss -0x14(%rax),%xmm2 - .byte 15,198,210,0 // shufps $0x0,%xmm2,%xmm2 - .byte 102,15,56,20,214 // blendvps %xmm0,%xmm6,%xmm2 - .byte 243,15,16,88,240 // movss -0x10(%rax),%xmm3 + .byte 76,139,0 // mov (%rax),%r8 + .byte 102,15,239,201 // pxor %xmm1,%xmm1 + .byte 73,131,248,2 // cmp $0x2,%r8 + .byte 114,50 // jb 3fcc <_sk_gradient_sse41+0x41> + .byte 72,139,72,72 // mov 0x48(%rax),%rcx + .byte 73,255,200 // dec %r8 + .byte 72,131,193,4 // add $0x4,%rcx + .byte 102,15,239,201 // pxor %xmm1,%xmm1 + .byte 15,40,21,48,21,0,0 // movaps 0x1530(%rip),%xmm2 # 54e0 <_sk_callback_sse41+0xed0> + .byte 243,15,16,25 // movss (%rcx),%xmm3 .byte 15,198,219,0 // shufps $0x0,%xmm3,%xmm3 - .byte 102,15,56,20,223 // blendvps %xmm0,%xmm7,%xmm3 - .byte 243,68,15,16,80,244 // movss -0xc(%rax),%xmm10 - .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 - .byte 102,69,15,56,20,208 // blendvps %xmm0,%xmm8,%xmm10 - .byte 243,68,15,16,88,248 // movss -0x8(%rax),%xmm11 - .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 - .byte 102,69,15,56,20,222 // blendvps %xmm0,%xmm14,%xmm11 - .byte 243,68,15,16,96,252 // movss -0x4(%rax),%xmm12 - .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 - .byte 102,69,15,56,20,231 // blendvps %xmm0,%xmm15,%xmm12 - .byte 243,68,15,16,40 // movss (%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 102,68,15,56,20,108,36,232 // blendvps %xmm0,-0x18(%rsp),%xmm13 - .byte 15,40,196 // movaps %xmm4,%xmm0 - .byte 72,131,192,36 // add $0x24,%rax - .byte 72,255,201 // dec %rcx - .byte 15,133,65,255,255,255 // jne 3e22 <_sk_gradient_sse41+0x63> - .byte 15,40,124,36,216 // movaps -0x28(%rsp),%xmm7 - .byte 15,40,116,36,200 // movaps -0x38(%rsp),%xmm6 - .byte 15,40,108,36,184 // movaps -0x48(%rsp),%xmm5 - .byte 15,40,100,36,168 // movaps -0x58(%rsp),%xmm4 - .byte 235,13 // jmp 3f04 <_sk_gradient_sse41+0x145> - .byte 15,87,201 // xorps %xmm1,%xmm1 - .byte 15,87,210 // xorps %xmm2,%xmm2 - .byte 15,87,219 // xorps %xmm3,%xmm3 - .byte 69,15,87,201 // xorps %xmm9,%xmm9 - .byte 68,15,89,200 // mulps %xmm0,%xmm9 - .byte 69,15,88,202 // addps %xmm10,%xmm9 + .byte 15,194,216,2 // cmpleps %xmm0,%xmm3 + .byte 15,84,218 // andps %xmm2,%xmm3 + .byte 102,15,254,203 // paddd %xmm3,%xmm1 + .byte 72,131,193,4 // add $0x4,%rcx + .byte 73,255,200 // dec %r8 + .byte 117,228 // jne 3fb0 <_sk_gradient_sse41+0x25> + .byte 65,86 // push %r14 + .byte 83 // push %rbx + .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 + .byte 69,137,200 // mov %r9d,%r8d + .byte 73,193,233,32 // shr $0x20,%r9 + .byte 102,72,15,126,201 // movq %xmm1,%rcx + .byte 65,137,202 // mov %ecx,%r10d + .byte 72,193,233,32 // shr $0x20,%rcx + .byte 76,139,88,8 // mov 0x8(%rax),%r11 + .byte 76,139,112,16 // mov 0x10(%rax),%r14 + .byte 243,71,15,16,4,147 // movss (%r11,%r10,4),%xmm8 + .byte 102,69,15,58,33,4,139,16 // insertps $0x10,(%r11,%rcx,4),%xmm8 + .byte 243,67,15,16,12,131 // movss (%r11,%r8,4),%xmm1 + .byte 102,68,15,58,33,193,32 // insertps $0x20,%xmm1,%xmm8 + .byte 243,67,15,16,12,139 // movss (%r11,%r9,4),%xmm1 + .byte 102,68,15,58,33,193,48 // insertps $0x30,%xmm1,%xmm8 + .byte 72,139,88,40 // mov 0x28(%rax),%rbx + .byte 243,70,15,16,12,147 // movss (%rbx,%r10,4),%xmm9 + .byte 102,68,15,58,33,12,139,16 // insertps $0x10,(%rbx,%rcx,4),%xmm9 + .byte 243,66,15,16,12,131 // movss (%rbx,%r8,4),%xmm1 + .byte 102,68,15,58,33,201,32 // insertps $0x20,%xmm1,%xmm9 + .byte 243,66,15,16,12,139 // movss (%rbx,%r9,4),%xmm1 + .byte 102,68,15,58,33,201,48 // insertps $0x30,%xmm1,%xmm9 + .byte 243,67,15,16,12,150 // movss (%r14,%r10,4),%xmm1 + .byte 102,65,15,58,33,12,142,16 // insertps $0x10,(%r14,%rcx,4),%xmm1 + .byte 243,67,15,16,20,134 // movss (%r14,%r8,4),%xmm2 + .byte 102,15,58,33,202,32 // insertps $0x20,%xmm2,%xmm1 + .byte 243,67,15,16,20,142 // movss (%r14,%r9,4),%xmm2 + .byte 102,15,58,33,202,48 // insertps $0x30,%xmm2,%xmm1 + .byte 72,139,88,48 // mov 0x30(%rax),%rbx + .byte 243,70,15,16,20,147 // movss (%rbx,%r10,4),%xmm10 + .byte 102,68,15,58,33,20,139,16 // insertps $0x10,(%rbx,%rcx,4),%xmm10 + .byte 243,66,15,16,20,131 // movss (%rbx,%r8,4),%xmm2 + .byte 102,68,15,58,33,210,32 // insertps $0x20,%xmm2,%xmm10 + .byte 243,66,15,16,20,139 // movss (%rbx,%r9,4),%xmm2 + .byte 102,68,15,58,33,210,48 // insertps $0x30,%xmm2,%xmm10 + .byte 72,139,88,24 // mov 0x18(%rax),%rbx + .byte 243,66,15,16,20,147 // movss (%rbx,%r10,4),%xmm2 + .byte 102,15,58,33,20,139,16 // insertps $0x10,(%rbx,%rcx,4),%xmm2 + .byte 243,66,15,16,28,131 // movss (%rbx,%r8,4),%xmm3 + .byte 102,15,58,33,211,32 // insertps $0x20,%xmm3,%xmm2 + .byte 243,66,15,16,28,139 // movss (%rbx,%r9,4),%xmm3 + .byte 102,15,58,33,211,48 // insertps $0x30,%xmm3,%xmm2 + .byte 72,139,88,56 // mov 0x38(%rax),%rbx + .byte 243,70,15,16,28,147 // movss (%rbx,%r10,4),%xmm11 + .byte 102,68,15,58,33,28,139,16 // insertps $0x10,(%rbx,%rcx,4),%xmm11 + .byte 243,66,15,16,28,131 // movss (%rbx,%r8,4),%xmm3 + .byte 102,68,15,58,33,219,32 // insertps $0x20,%xmm3,%xmm11 + .byte 243,66,15,16,28,139 // movss (%rbx,%r9,4),%xmm3 + .byte 102,68,15,58,33,219,48 // insertps $0x30,%xmm3,%xmm11 + .byte 72,139,88,32 // mov 0x20(%rax),%rbx + .byte 243,66,15,16,28,147 // movss (%rbx,%r10,4),%xmm3 + .byte 102,15,58,33,28,139,16 // insertps $0x10,(%rbx,%rcx,4),%xmm3 + .byte 243,70,15,16,36,131 // movss (%rbx,%r8,4),%xmm12 + .byte 102,65,15,58,33,220,32 // insertps $0x20,%xmm12,%xmm3 + .byte 243,70,15,16,36,139 // movss (%rbx,%r9,4),%xmm12 + .byte 102,65,15,58,33,220,48 // insertps $0x30,%xmm12,%xmm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 243,70,15,16,36,144 // movss (%rax,%r10,4),%xmm12 + .byte 102,68,15,58,33,36,136,16 // insertps $0x10,(%rax,%rcx,4),%xmm12 + .byte 243,70,15,16,44,128 // movss (%rax,%r8,4),%xmm13 + .byte 102,69,15,58,33,229,32 // insertps $0x20,%xmm13,%xmm12 + .byte 243,70,15,16,44,136 // movss (%rax,%r9,4),%xmm13 + .byte 102,69,15,58,33,229,48 // insertps $0x30,%xmm13,%xmm12 + .byte 68,15,89,192 // mulps %xmm0,%xmm8 + .byte 69,15,88,193 // addps %xmm9,%xmm8 .byte 15,89,200 // mulps %xmm0,%xmm1 - .byte 65,15,88,203 // addps %xmm11,%xmm1 + .byte 65,15,88,202 // addps %xmm10,%xmm1 .byte 15,89,208 // mulps %xmm0,%xmm2 - .byte 65,15,88,212 // addps %xmm12,%xmm2 + .byte 65,15,88,211 // addps %xmm11,%xmm2 .byte 15,89,216 // mulps %xmm0,%xmm3 - .byte 65,15,88,221 // addps %xmm13,%xmm3 + .byte 65,15,88,220 // addps %xmm12,%xmm3 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 65,15,40,193 // movaps %xmm9,%xmm0 + .byte 65,15,40,192 // movaps %xmm8,%xmm0 + .byte 91 // pop %rbx + .byte 65,94 // pop %r14 .byte 255,224 // jmpq *%rax HIDDEN _sk_evenly_spaced_2_stop_gradient_sse41 @@ -24048,26 +24719,26 @@ _sk_xy_to_unit_angle_sse41: .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,40,236 // movaps %xmm12,%xmm13 .byte 69,15,89,237 // mulps %xmm13,%xmm13 - .byte 68,15,40,21,196,18,0,0 // movaps 0x12c4(%rip),%xmm10 # 52a0 <_sk_callback_sse41+0xed2> + .byte 68,15,40,21,210,18,0,0 // movaps 0x12d2(%rip),%xmm10 # 54f0 <_sk_callback_sse41+0xee0> .byte 69,15,89,213 // mulps %xmm13,%xmm10 - .byte 68,15,88,21,200,18,0,0 // addps 0x12c8(%rip),%xmm10 # 52b0 <_sk_callback_sse41+0xee2> + .byte 68,15,88,21,214,18,0,0 // addps 0x12d6(%rip),%xmm10 # 5500 <_sk_callback_sse41+0xef0> .byte 69,15,89,213 // mulps %xmm13,%xmm10 - .byte 68,15,88,21,204,18,0,0 // addps 0x12cc(%rip),%xmm10 # 52c0 <_sk_callback_sse41+0xef2> + .byte 68,15,88,21,218,18,0,0 // addps 0x12da(%rip),%xmm10 # 5510 <_sk_callback_sse41+0xf00> .byte 69,15,89,213 // mulps %xmm13,%xmm10 - .byte 68,15,88,21,208,18,0,0 // addps 0x12d0(%rip),%xmm10 # 52d0 <_sk_callback_sse41+0xf02> + .byte 68,15,88,21,222,18,0,0 // addps 0x12de(%rip),%xmm10 # 5520 <_sk_callback_sse41+0xf10> .byte 69,15,89,212 // mulps %xmm12,%xmm10 .byte 65,15,194,195,1 // cmpltps %xmm11,%xmm0 - .byte 68,15,40,29,207,18,0,0 // movaps 0x12cf(%rip),%xmm11 # 52e0 <_sk_callback_sse41+0xf12> + .byte 68,15,40,29,221,18,0,0 // movaps 0x12dd(%rip),%xmm11 # 5530 <_sk_callback_sse41+0xf20> .byte 69,15,92,218 // subps %xmm10,%xmm11 .byte 102,69,15,56,20,211 // blendvps %xmm0,%xmm11,%xmm10 .byte 69,15,194,200,1 // cmpltps %xmm8,%xmm9 - .byte 68,15,40,29,200,18,0,0 // movaps 0x12c8(%rip),%xmm11 # 52f0 <_sk_callback_sse41+0xf22> + .byte 68,15,40,29,214,18,0,0 // movaps 0x12d6(%rip),%xmm11 # 5540 <_sk_callback_sse41+0xf30> .byte 69,15,92,218 // subps %xmm10,%xmm11 .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 102,69,15,56,20,211 // blendvps %xmm0,%xmm11,%xmm10 .byte 15,40,193 // movaps %xmm1,%xmm0 .byte 65,15,194,192,1 // cmpltps %xmm8,%xmm0 - .byte 68,15,40,13,186,18,0,0 // movaps 0x12ba(%rip),%xmm9 # 5300 <_sk_callback_sse41+0xf32> + .byte 68,15,40,13,200,18,0,0 // movaps 0x12c8(%rip),%xmm9 # 5550 <_sk_callback_sse41+0xf40> .byte 69,15,92,202 // subps %xmm10,%xmm9 .byte 102,69,15,56,20,209 // blendvps %xmm0,%xmm9,%xmm10 .byte 69,15,194,194,7 // cmpordps %xmm10,%xmm8 @@ -24094,7 +24765,7 @@ HIDDEN _sk_save_xy_sse41 FUNCTION(_sk_save_xy_sse41) _sk_save_xy_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,139,18,0,0 // movaps 0x128b(%rip),%xmm8 # 5310 <_sk_callback_sse41+0xf42> + .byte 68,15,40,5,153,18,0,0 // movaps 0x1299(%rip),%xmm8 # 5560 <_sk_callback_sse41+0xf50> .byte 15,17,0 // movups %xmm0,(%rax) .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,88,200 // addps %xmm8,%xmm9 @@ -24138,8 +24809,8 @@ _sk_bilinear_nx_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,13,18,0,0 // addps 0x120d(%rip),%xmm0 # 5320 <_sk_callback_sse41+0xf52> - .byte 68,15,40,13,21,18,0,0 // movaps 0x1215(%rip),%xmm9 # 5330 <_sk_callback_sse41+0xf62> + .byte 15,88,5,27,18,0,0 // addps 0x121b(%rip),%xmm0 # 5570 <_sk_callback_sse41+0xf60> + .byte 68,15,40,13,35,18,0,0 // movaps 0x1223(%rip),%xmm9 # 5580 <_sk_callback_sse41+0xf70> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -24152,7 +24823,7 @@ _sk_bilinear_px_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,4,18,0,0 // addps 0x1204(%rip),%xmm0 # 5340 <_sk_callback_sse41+0xf72> + .byte 15,88,5,18,18,0,0 // addps 0x1212(%rip),%xmm0 # 5590 <_sk_callback_sse41+0xf80> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24164,8 +24835,8 @@ _sk_bilinear_ny_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,246,17,0,0 // addps 0x11f6(%rip),%xmm1 # 5350 <_sk_callback_sse41+0xf82> - .byte 68,15,40,13,254,17,0,0 // movaps 0x11fe(%rip),%xmm9 # 5360 <_sk_callback_sse41+0xf92> + .byte 15,88,13,4,18,0,0 // addps 0x1204(%rip),%xmm1 # 55a0 <_sk_callback_sse41+0xf90> + .byte 68,15,40,13,12,18,0,0 // movaps 0x120c(%rip),%xmm9 # 55b0 <_sk_callback_sse41+0xfa0> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -24178,7 +24849,7 @@ _sk_bilinear_py_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,236,17,0,0 // addps 0x11ec(%rip),%xmm1 # 5370 <_sk_callback_sse41+0xfa2> + .byte 15,88,13,250,17,0,0 // addps 0x11fa(%rip),%xmm1 # 55c0 <_sk_callback_sse41+0xfb0> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24190,13 +24861,13 @@ _sk_bicubic_n3x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,223,17,0,0 // addps 0x11df(%rip),%xmm0 # 5380 <_sk_callback_sse41+0xfb2> - .byte 68,15,40,13,231,17,0,0 // movaps 0x11e7(%rip),%xmm9 # 5390 <_sk_callback_sse41+0xfc2> + .byte 15,88,5,237,17,0,0 // addps 0x11ed(%rip),%xmm0 # 55d0 <_sk_callback_sse41+0xfc0> + .byte 68,15,40,13,245,17,0,0 // movaps 0x11f5(%rip),%xmm9 # 55e0 <_sk_callback_sse41+0xfd0> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,227,17,0,0 // mulps 0x11e3(%rip),%xmm9 # 53a0 <_sk_callback_sse41+0xfd2> - .byte 68,15,88,13,235,17,0,0 // addps 0x11eb(%rip),%xmm9 # 53b0 <_sk_callback_sse41+0xfe2> + .byte 68,15,89,13,241,17,0,0 // mulps 0x11f1(%rip),%xmm9 # 55f0 <_sk_callback_sse41+0xfe0> + .byte 68,15,88,13,249,17,0,0 // addps 0x11f9(%rip),%xmm9 # 5600 <_sk_callback_sse41+0xff0> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -24209,16 +24880,16 @@ _sk_bicubic_n1x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,218,17,0,0 // addps 0x11da(%rip),%xmm0 # 53c0 <_sk_callback_sse41+0xff2> - .byte 68,15,40,13,226,17,0,0 // movaps 0x11e2(%rip),%xmm9 # 53d0 <_sk_callback_sse41+0x1002> + .byte 15,88,5,232,17,0,0 // addps 0x11e8(%rip),%xmm0 # 5610 <_sk_callback_sse41+0x1000> + .byte 68,15,40,13,240,17,0,0 // movaps 0x11f0(%rip),%xmm9 # 5620 <_sk_callback_sse41+0x1010> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,230,17,0,0 // movaps 0x11e6(%rip),%xmm8 # 53e0 <_sk_callback_sse41+0x1012> + .byte 68,15,40,5,244,17,0,0 // movaps 0x11f4(%rip),%xmm8 # 5630 <_sk_callback_sse41+0x1020> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,234,17,0,0 // addps 0x11ea(%rip),%xmm8 # 53f0 <_sk_callback_sse41+0x1022> + .byte 68,15,88,5,248,17,0,0 // addps 0x11f8(%rip),%xmm8 # 5640 <_sk_callback_sse41+0x1030> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,238,17,0,0 // addps 0x11ee(%rip),%xmm8 # 5400 <_sk_callback_sse41+0x1032> + .byte 68,15,88,5,252,17,0,0 // addps 0x11fc(%rip),%xmm8 # 5650 <_sk_callback_sse41+0x1040> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,242,17,0,0 // addps 0x11f2(%rip),%xmm8 # 5410 <_sk_callback_sse41+0x1042> + .byte 68,15,88,5,0,18,0,0 // addps 0x1200(%rip),%xmm8 # 5660 <_sk_callback_sse41+0x1050> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24228,17 +24899,17 @@ HIDDEN _sk_bicubic_p1x_sse41 FUNCTION(_sk_bicubic_p1x_sse41) _sk_bicubic_p1x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,236,17,0,0 // movaps 0x11ec(%rip),%xmm8 # 5420 <_sk_callback_sse41+0x1052> + .byte 68,15,40,5,250,17,0,0 // movaps 0x11fa(%rip),%xmm8 # 5670 <_sk_callback_sse41+0x1060> .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,72,64 // movups 0x40(%rax),%xmm9 .byte 65,15,88,192 // addps %xmm8,%xmm0 - .byte 68,15,40,21,232,17,0,0 // movaps 0x11e8(%rip),%xmm10 # 5430 <_sk_callback_sse41+0x1062> + .byte 68,15,40,21,246,17,0,0 // movaps 0x11f6(%rip),%xmm10 # 5680 <_sk_callback_sse41+0x1070> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,236,17,0,0 // addps 0x11ec(%rip),%xmm10 # 5440 <_sk_callback_sse41+0x1072> + .byte 68,15,88,21,250,17,0,0 // addps 0x11fa(%rip),%xmm10 # 5690 <_sk_callback_sse41+0x1080> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,232,17,0,0 // addps 0x11e8(%rip),%xmm10 # 5450 <_sk_callback_sse41+0x1082> + .byte 68,15,88,21,246,17,0,0 // addps 0x11f6(%rip),%xmm10 # 56a0 <_sk_callback_sse41+0x1090> .byte 68,15,17,144,128,0,0,0 // movups %xmm10,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24250,11 +24921,11 @@ _sk_bicubic_p3x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,219,17,0,0 // addps 0x11db(%rip),%xmm0 # 5460 <_sk_callback_sse41+0x1092> + .byte 15,88,5,233,17,0,0 // addps 0x11e9(%rip),%xmm0 # 56b0 <_sk_callback_sse41+0x10a0> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,219,17,0,0 // mulps 0x11db(%rip),%xmm8 # 5470 <_sk_callback_sse41+0x10a2> - .byte 68,15,88,5,227,17,0,0 // addps 0x11e3(%rip),%xmm8 # 5480 <_sk_callback_sse41+0x10b2> + .byte 68,15,89,5,233,17,0,0 // mulps 0x11e9(%rip),%xmm8 # 56c0 <_sk_callback_sse41+0x10b0> + .byte 68,15,88,5,241,17,0,0 // addps 0x11f1(%rip),%xmm8 # 56d0 <_sk_callback_sse41+0x10c0> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -24267,13 +24938,13 @@ _sk_bicubic_n3y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,209,17,0,0 // addps 0x11d1(%rip),%xmm1 # 5490 <_sk_callback_sse41+0x10c2> - .byte 68,15,40,13,217,17,0,0 // movaps 0x11d9(%rip),%xmm9 # 54a0 <_sk_callback_sse41+0x10d2> + .byte 15,88,13,223,17,0,0 // addps 0x11df(%rip),%xmm1 # 56e0 <_sk_callback_sse41+0x10d0> + .byte 68,15,40,13,231,17,0,0 // movaps 0x11e7(%rip),%xmm9 # 56f0 <_sk_callback_sse41+0x10e0> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,213,17,0,0 // mulps 0x11d5(%rip),%xmm9 # 54b0 <_sk_callback_sse41+0x10e2> - .byte 68,15,88,13,221,17,0,0 // addps 0x11dd(%rip),%xmm9 # 54c0 <_sk_callback_sse41+0x10f2> + .byte 68,15,89,13,227,17,0,0 // mulps 0x11e3(%rip),%xmm9 # 5700 <_sk_callback_sse41+0x10f0> + .byte 68,15,88,13,235,17,0,0 // addps 0x11eb(%rip),%xmm9 # 5710 <_sk_callback_sse41+0x1100> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -24286,16 +24957,16 @@ _sk_bicubic_n1y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,203,17,0,0 // addps 0x11cb(%rip),%xmm1 # 54d0 <_sk_callback_sse41+0x1102> - .byte 68,15,40,13,211,17,0,0 // movaps 0x11d3(%rip),%xmm9 # 54e0 <_sk_callback_sse41+0x1112> + .byte 15,88,13,217,17,0,0 // addps 0x11d9(%rip),%xmm1 # 5720 <_sk_callback_sse41+0x1110> + .byte 68,15,40,13,225,17,0,0 // movaps 0x11e1(%rip),%xmm9 # 5730 <_sk_callback_sse41+0x1120> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,215,17,0,0 // movaps 0x11d7(%rip),%xmm8 # 54f0 <_sk_callback_sse41+0x1122> + .byte 68,15,40,5,229,17,0,0 // movaps 0x11e5(%rip),%xmm8 # 5740 <_sk_callback_sse41+0x1130> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,219,17,0,0 // addps 0x11db(%rip),%xmm8 # 5500 <_sk_callback_sse41+0x1132> + .byte 68,15,88,5,233,17,0,0 // addps 0x11e9(%rip),%xmm8 # 5750 <_sk_callback_sse41+0x1140> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,223,17,0,0 // addps 0x11df(%rip),%xmm8 # 5510 <_sk_callback_sse41+0x1142> + .byte 68,15,88,5,237,17,0,0 // addps 0x11ed(%rip),%xmm8 # 5760 <_sk_callback_sse41+0x1150> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,227,17,0,0 // addps 0x11e3(%rip),%xmm8 # 5520 <_sk_callback_sse41+0x1152> + .byte 68,15,88,5,241,17,0,0 // addps 0x11f1(%rip),%xmm8 # 5770 <_sk_callback_sse41+0x1160> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24305,17 +24976,17 @@ HIDDEN _sk_bicubic_p1y_sse41 FUNCTION(_sk_bicubic_p1y_sse41) _sk_bicubic_p1y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,221,17,0,0 // movaps 0x11dd(%rip),%xmm8 # 5530 <_sk_callback_sse41+0x1162> + .byte 68,15,40,5,235,17,0,0 // movaps 0x11eb(%rip),%xmm8 # 5780 <_sk_callback_sse41+0x1170> .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,72,96 // movups 0x60(%rax),%xmm9 .byte 65,15,88,200 // addps %xmm8,%xmm1 - .byte 68,15,40,21,216,17,0,0 // movaps 0x11d8(%rip),%xmm10 # 5540 <_sk_callback_sse41+0x1172> + .byte 68,15,40,21,230,17,0,0 // movaps 0x11e6(%rip),%xmm10 # 5790 <_sk_callback_sse41+0x1180> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,220,17,0,0 // addps 0x11dc(%rip),%xmm10 # 5550 <_sk_callback_sse41+0x1182> + .byte 68,15,88,21,234,17,0,0 // addps 0x11ea(%rip),%xmm10 # 57a0 <_sk_callback_sse41+0x1190> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,216,17,0,0 // addps 0x11d8(%rip),%xmm10 # 5560 <_sk_callback_sse41+0x1192> + .byte 68,15,88,21,230,17,0,0 // addps 0x11e6(%rip),%xmm10 # 57b0 <_sk_callback_sse41+0x11a0> .byte 68,15,17,144,160,0,0,0 // movups %xmm10,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24327,11 +24998,11 @@ _sk_bicubic_p3y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,202,17,0,0 // addps 0x11ca(%rip),%xmm1 # 5570 <_sk_callback_sse41+0x11a2> + .byte 15,88,13,216,17,0,0 // addps 0x11d8(%rip),%xmm1 # 57c0 <_sk_callback_sse41+0x11b0> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,202,17,0,0 // mulps 0x11ca(%rip),%xmm8 # 5580 <_sk_callback_sse41+0x11b2> - .byte 68,15,88,5,210,17,0,0 // addps 0x11d2(%rip),%xmm8 # 5590 <_sk_callback_sse41+0x11c2> + .byte 68,15,89,5,216,17,0,0 // mulps 0x11d8(%rip),%xmm8 # 57d0 <_sk_callback_sse41+0x11c0> + .byte 68,15,88,5,224,17,0,0 // addps 0x11e0(%rip),%xmm8 # 57e0 <_sk_callback_sse41+0x11d0> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -24550,11 +25221,11 @@ BALIGN16 .byte 128,191,0,0,128,191,0 // cmpb $0x0,-0x40800000(%rdi) .byte 0,224 // add %ah,%al .byte 64,0,0 // add %al,(%rax) - .byte 224,64 // loopne 4688 <.literal16+0x1d8> + .byte 224,64 // loopne 48c8 <.literal16+0x1d8> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 468c <.literal16+0x1dc> + .byte 224,64 // loopne 48cc <.literal16+0x1dc> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 4690 <.literal16+0x1e0> + .byte 224,64 // loopne 48d0 <.literal16+0x1e0> .byte 154 // (bad) .byte 153 // cltd .byte 153 // cltd @@ -24574,13 +25245,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46b1 <.literal16+0x201> + .byte 71,225,61 // rex.RXB loope 48f1 <.literal16+0x201> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46b5 <.literal16+0x205> + .byte 71,225,61 // rex.RXB loope 48f5 <.literal16+0x205> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46b9 <.literal16+0x209> + .byte 71,225,61 // rex.RXB loope 48f9 <.literal16+0x209> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46bd <.literal16+0x20d> + .byte 71,225,61 // rex.RXB loope 48fd <.literal16+0x20d> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -24605,13 +25276,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46f1 <.literal16+0x241> + .byte 71,225,61 // rex.RXB loope 4931 <.literal16+0x241> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46f5 <.literal16+0x245> + .byte 71,225,61 // rex.RXB loope 4935 <.literal16+0x245> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46f9 <.literal16+0x249> + .byte 71,225,61 // rex.RXB loope 4939 <.literal16+0x249> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 46fd <.literal16+0x24d> + .byte 71,225,61 // rex.RXB loope 493d <.literal16+0x24d> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -24636,13 +25307,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4731 <.literal16+0x281> + .byte 71,225,61 // rex.RXB loope 4971 <.literal16+0x281> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4735 <.literal16+0x285> + .byte 71,225,61 // rex.RXB loope 4975 <.literal16+0x285> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4739 <.literal16+0x289> + .byte 71,225,61 // rex.RXB loope 4979 <.literal16+0x289> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 473d <.literal16+0x28d> + .byte 71,225,61 // rex.RXB loope 497d <.literal16+0x28d> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -24667,13 +25338,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4771 <.literal16+0x2c1> + .byte 71,225,61 // rex.RXB loope 49b1 <.literal16+0x2c1> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4775 <.literal16+0x2c5> + .byte 71,225,61 // rex.RXB loope 49b5 <.literal16+0x2c5> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4779 <.literal16+0x2c9> + .byte 71,225,61 // rex.RXB loope 49b9 <.literal16+0x2c9> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 477d <.literal16+0x2cd> + .byte 71,225,61 // rex.RXB loope 49bd <.literal16+0x2cd> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -24897,13 +25568,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4949 <.literal16+0x499> + .byte 224,7 // loopne 4b89 <.literal16+0x499> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 494d <.literal16+0x49d> + .byte 224,7 // loopne 4b8d <.literal16+0x49d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4951 <.literal16+0x4a1> + .byte 224,7 // loopne 4b91 <.literal16+0x4a1> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4955 <.literal16+0x4a5> + .byte 224,7 // loopne 4b95 <.literal16+0x4a5> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -24937,10 +25608,10 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004998 <_sk_callback_sse41+0xa0005ca> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004bd8 <_sk_callback_sse41+0xa0005c8> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 30049a0 <_sk_callback_sse41+0x30005d2> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004be0 <_sk_callback_sse41+0x30005d0> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -24995,11 +25666,11 @@ BALIGN16 .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4a6b <.literal16+0x5bb> + .byte 127,67 // jg 4cab <.literal16+0x5bb> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4a6f <.literal16+0x5bf> + .byte 127,67 // jg 4caf <.literal16+0x5bf> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4a73 <.literal16+0x5c3> + .byte 127,67 // jg 4cb3 <.literal16+0x5c3> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,129,128,128,59 // addb $0x3b,-0x7f7f7ec5(%rax) @@ -25014,16 +25685,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4a64 <.literal16+0x5b4> + .byte 127,0 // jg 4ca4 <.literal16+0x5b4> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4a68 <.literal16+0x5b8> + .byte 127,0 // jg 4ca8 <.literal16+0x5b8> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4a6c <.literal16+0x5bc> + .byte 127,0 // jg 4cac <.literal16+0x5bc> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4a70 <.literal16+0x5c0> + .byte 127,0 // jg 4cb0 <.literal16+0x5c0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -25032,7 +25703,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4af5 <.literal16+0x645> + .byte 119,115 // ja 4d35 <.literal16+0x645> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -25043,7 +25714,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4a59 <.literal16+0x5a9> + .byte 117,191 // jne 4c99 <.literal16+0x5a9> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -25055,7 +25726,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a38a9a <_sk_callback_sse41+0xffffffffe9a346cc> + .byte 233,220,63,163,233 // jmpq ffffffffe9a38cda <_sk_callback_sse41+0xffffffffe9a346ca> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -25110,16 +25781,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4b34 <.literal16+0x684> + .byte 127,0 // jg 4d74 <.literal16+0x684> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4b38 <.literal16+0x688> + .byte 127,0 // jg 4d78 <.literal16+0x688> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4b3c <.literal16+0x68c> + .byte 127,0 // jg 4d7c <.literal16+0x68c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4b40 <.literal16+0x690> + .byte 127,0 // jg 4d80 <.literal16+0x690> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -25128,7 +25799,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4bc5 <.literal16+0x715> + .byte 119,115 // ja 4e05 <.literal16+0x715> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -25139,7 +25810,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4b29 <.literal16+0x679> + .byte 117,191 // jne 4d69 <.literal16+0x679> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -25151,7 +25822,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a38b6a <_sk_callback_sse41+0xffffffffe9a3479c> + .byte 233,220,63,163,233 // jmpq ffffffffe9a38daa <_sk_callback_sse41+0xffffffffe9a3479a> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -25206,16 +25877,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4c04 <.literal16+0x754> + .byte 127,0 // jg 4e44 <.literal16+0x754> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4c08 <.literal16+0x758> + .byte 127,0 // jg 4e48 <.literal16+0x758> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4c0c <.literal16+0x75c> + .byte 127,0 // jg 4e4c <.literal16+0x75c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4c10 <.literal16+0x760> + .byte 127,0 // jg 4e50 <.literal16+0x760> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -25224,7 +25895,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4c95 <.literal16+0x7e5> + .byte 119,115 // ja 4ed5 <.literal16+0x7e5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -25235,7 +25906,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4bf9 <.literal16+0x749> + .byte 117,191 // jne 4e39 <.literal16+0x749> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -25247,7 +25918,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a38c3a <_sk_callback_sse41+0xffffffffe9a3486c> + .byte 233,220,63,163,233 // jmpq ffffffffe9a38e7a <_sk_callback_sse41+0xffffffffe9a3486a> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -25302,16 +25973,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4cd4 <.literal16+0x824> + .byte 127,0 // jg 4f14 <.literal16+0x824> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4cd8 <.literal16+0x828> + .byte 127,0 // jg 4f18 <.literal16+0x828> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4cdc <.literal16+0x82c> + .byte 127,0 // jg 4f1c <.literal16+0x82c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4ce0 <.literal16+0x830> + .byte 127,0 // jg 4f20 <.literal16+0x830> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -25320,7 +25991,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4d65 <.literal16+0x8b5> + .byte 119,115 // ja 4fa5 <.literal16+0x8b5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -25331,7 +26002,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4cc9 <.literal16+0x819> + .byte 117,191 // jne 4f09 <.literal16+0x819> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -25343,7 +26014,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a38d0a <_sk_callback_sse41+0xffffffffe9a3493c> + .byte 233,220,63,163,233 // jmpq ffffffffe9a38f4a <_sk_callback_sse41+0xffffffffe9a3493a> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -25394,13 +26065,13 @@ BALIGN16 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 - .byte 127,67 // jg 4de7 <.literal16+0x937> + .byte 127,67 // jg 5027 <.literal16+0x937> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4deb <.literal16+0x93b> + .byte 127,67 // jg 502b <.literal16+0x93b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4def <.literal16+0x93f> + .byte 127,67 // jg 502f <.literal16+0x93f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4df3 <.literal16+0x943> + .byte 127,67 // jg 5033 <.literal16+0x943> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -25447,16 +26118,16 @@ BALIGN16 .byte 128,3,62 // addb $0x3e,(%rbx) .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4e73 <.literal16+0x9c3> + .byte 118,63 // jbe 50b3 <.literal16+0x9c3> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4e77 <.literal16+0x9c7> + .byte 118,63 // jbe 50b7 <.literal16+0x9c7> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4e7b <.literal16+0x9cb> + .byte 118,63 // jbe 50bb <.literal16+0x9cb> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4e7f <.literal16+0x9cf> + .byte 118,63 // jbe 50bf <.literal16+0x9cf> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) @@ -25468,11 +26139,11 @@ BALIGN16 .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4ebb <.literal16+0xa0b> + .byte 127,67 // jg 50fb <.literal16+0xa0b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4ebf <.literal16+0xa0f> + .byte 127,67 // jg 50ff <.literal16+0xa0f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4ec3 <.literal16+0xa13> + .byte 127,67 // jg 5103 <.literal16+0xa13> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,0,0,128,63 // addb $0x3f,-0x7fffffc5(%rax) @@ -25501,7 +26172,7 @@ BALIGN16 .byte 5,255,255,255,9 // add $0x9ffffff,%eax .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004ef0 <_sk_callback_sse41+0x3000b22> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3005130 <_sk_callback_sse41+0x3000b20> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -25530,13 +26201,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4f29 <.literal16+0xa79> + .byte 224,7 // loopne 5169 <.literal16+0xa79> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4f2d <.literal16+0xa7d> + .byte 224,7 // loopne 516d <.literal16+0xa7d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4f31 <.literal16+0xa81> + .byte 224,7 // loopne 5171 <.literal16+0xa81> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4f35 <.literal16+0xa85> + .byte 224,7 // loopne 5175 <.literal16+0xa85> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -25582,13 +26253,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4f99 <.literal16+0xae9> + .byte 224,7 // loopne 51d9 <.literal16+0xae9> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4f9d <.literal16+0xaed> + .byte 224,7 // loopne 51dd <.literal16+0xaed> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4fa1 <.literal16+0xaf1> + .byte 224,7 // loopne 51e1 <.literal16+0xaf1> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4fa5 <.literal16+0xaf5> + .byte 224,7 // loopne 51e5 <.literal16+0xaf5> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -25626,13 +26297,13 @@ BALIGN16 .byte 65,0,0 // add %al,(%r8) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 5036 <.literal16+0xb86> + .byte 124,66 // jl 5276 <.literal16+0xb86> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 503a <.literal16+0xb8a> + .byte 124,66 // jl 527a <.literal16+0xb8a> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 503e <.literal16+0xb8e> + .byte 124,66 // jl 527e <.literal16+0xb8e> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 5042 <.literal16+0xb92> + .byte 124,66 // jl 5282 <.literal16+0xb92> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 0,240 // add %dh,%al @@ -25722,13 +26393,13 @@ BALIGN16 .byte 136,136,61,137,136,136 // mov %cl,-0x777776c3(%rax) .byte 61,137,136,136,61 // cmp $0x3d888889,%eax .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 5145 <.literal16+0xc95> + .byte 112,65 // jo 5385 <.literal16+0xc95> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 5149 <.literal16+0xc99> + .byte 112,65 // jo 5389 <.literal16+0xc99> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 514d <.literal16+0xc9d> + .byte 112,65 // jo 538d <.literal16+0xc9d> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 5151 <.literal16+0xca1> + .byte 112,65 // jo 5391 <.literal16+0xca1> .byte 255,0 // incl (%rax) .byte 0,0 // add %al,(%rax) .byte 255,0 // incl (%rax) @@ -25743,7 +26414,7 @@ BALIGN16 .byte 5,255,255,255,9 // add $0x9ffffff,%eax .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3005140 <_sk_callback_sse41+0x3000d72> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3005380 <_sk_callback_sse41+0x3000d70> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -25770,7 +26441,7 @@ BALIGN16 .byte 5,255,255,255,9 // add $0x9ffffff,%eax .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3005180 <_sk_callback_sse41+0x3000db2> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 30053c0 <_sk_callback_sse41+0x3000db0> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -25785,11 +26456,11 @@ BALIGN16 .byte 255,0 // incl (%rax) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 51db <.literal16+0xd2b> + .byte 127,67 // jg 541b <.literal16+0xd2b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 51df <.literal16+0xd2f> + .byte 127,67 // jg 541f <.literal16+0xd2f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 51e3 <.literal16+0xd33> + .byte 127,67 // jg 5423 <.literal16+0xd33> .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) .byte 0,0 // add %al,(%rax) .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) @@ -25865,13 +26536,13 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 255 // (bad) - .byte 127,71 // jg 52ab <.literal16+0xdfb> + .byte 127,71 // jg 54eb <.literal16+0xdfb> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 52af <.literal16+0xdff> + .byte 127,71 // jg 54ef <.literal16+0xdff> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 52b3 <.literal16+0xe03> + .byte 127,71 // jg 54f3 <.literal16+0xe03> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 52b7 <.literal16+0xe07> + .byte 127,71 // jg 54f7 <.literal16+0xe07> .byte 208 // (bad) .byte 179,89 // mov $0x59,%bl .byte 62,208 // ds (bad) @@ -25900,19 +26571,27 @@ BALIGN16 .byte 221,147,61,152,221,147 // fstl -0x6c2267c3(%rbx) .byte 61,152,221,147,61 // cmp $0x3d93dd98,%eax .byte 152 // cwtl - .byte 221,147,61,111,43,231 // fstl -0x18d490c3(%rbx) - .byte 187,111,43,231,187 // mov $0xbbe72b6f,%ebx + .byte 221,147,61,1,0,0 // fstl 0x13d(%rbx) + .byte 0,1 // add %al,(%rcx) + .byte 0,0 // add %al,(%rax) + .byte 0,1 // add %al,(%rcx) + .byte 0,0 // add %al,(%rax) + .byte 0,1 // add %al,(%rcx) + .byte 0,0 // add %al,(%rax) + .byte 0,111,43 // add %ch,0x2b(%rdi) + .byte 231,187 // out %eax,$0xbb .byte 111 // outsl %ds:(%rsi),(%dx) .byte 43,231 // sub %edi,%esp .byte 187,111,43,231,187 // mov $0xbbe72b6f,%ebx + .byte 111 // outsl %ds:(%rsi),(%dx) + .byte 43,231 // sub %edi,%esp + .byte 187,159,215,202,60 // mov $0x3ccad79f,%ebx .byte 159 // lahf .byte 215 // xlat %ds:(%rbx) .byte 202,60,159 // lret $0x9f3c .byte 215 // xlat %ds:(%rbx) .byte 202,60,159 // lret $0x9f3c .byte 215 // xlat %ds:(%rbx) - .byte 202,60,159 // lret $0x9f3c - .byte 215 // xlat %ds:(%rbx) .byte 202,60,212 // lret $0xd43c .byte 100,84 // fs push %rsp .byte 189,212,100,84,189 // mov $0xbd5464d4,%ebp @@ -25997,11 +26676,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 53c2 <.literal16+0xf12> + .byte 62,114,28 // jb,pt 5612 <.literal16+0xf22> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 53c6 <.literal16+0xf16> + .byte 62,114,28 // jb,pt 5616 <.literal16+0xf26> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 53ca <.literal16+0xf1a> + .byte 62,114,28 // jb,pt 561a <.literal16+0xf2a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -26045,7 +26724,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e255 <_sk_callback_sse41+0x3d639e87> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e4a5 <_sk_callback_sse41+0x3d639e95> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -26071,7 +26750,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e295 <_sk_callback_sse41+0x3d639ec7> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e4e5 <_sk_callback_sse41+0x3d639ed5> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -26080,13 +26759,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 548e <.literal16+0xfde> + .byte 114,28 // jb 56de <.literal16+0xfee> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5492 <.literal16+0xfe2> + .byte 62,114,28 // jb,pt 56e2 <.literal16+0xff2> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5496 <.literal16+0xfe6> + .byte 62,114,28 // jb,pt 56e6 <.literal16+0xff6> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 549a <.literal16+0xfea> + .byte 62,114,28 // jb,pt 56ea <.literal16+0xffa> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -26107,11 +26786,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 54d2 <.literal16+0x1022> + .byte 62,114,28 // jb,pt 5722 <.literal16+0x1032> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 54d6 <.literal16+0x1026> + .byte 62,114,28 // jb,pt 5726 <.literal16+0x1036> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 54da <.literal16+0x102a> + .byte 62,114,28 // jb,pt 572a <.literal16+0x103a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -26155,7 +26834,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e365 <_sk_callback_sse41+0x3d639f97> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e5b5 <_sk_callback_sse41+0x3d639fa5> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -26181,7 +26860,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e3a5 <_sk_callback_sse41+0x3d639fd7> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e5f5 <_sk_callback_sse41+0x3d639fe5> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -26190,13 +26869,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 559e <.literal16+0x10ee> + .byte 114,28 // jb 57ee <.literal16+0x10fe> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 55a2 <_sk_callback_sse41+0x11d4> + .byte 62,114,28 // jb,pt 57f2 <_sk_callback_sse41+0x11e2> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 55a6 <_sk_callback_sse41+0x11d8> + .byte 62,114,28 // jb,pt 57f6 <_sk_callback_sse41+0x11e6> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 55aa <_sk_callback_sse41+0x11dc> + .byte 62,114,28 // jb,pt 57fa <_sk_callback_sse41+0x11ea> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -26266,7 +26945,7 @@ _sk_seed_shader_sse2: .byte 102,15,110,199 // movd %edi,%xmm0 .byte 102,15,112,192,0 // pshufd $0x0,%xmm0,%xmm0 .byte 15,91,200 // cvtdq2ps %xmm0,%xmm1 - .byte 15,40,21,244,72,0,0 // movaps 0x48f4(%rip),%xmm2 # 4970 <_sk_callback_sse2+0xdd> + .byte 15,40,21,228,74,0,0 // movaps 0x4ae4(%rip),%xmm2 # 4b60 <_sk_callback_sse2+0xdc> .byte 15,88,202 // addps %xmm2,%xmm1 .byte 15,16,2 // movups (%rdx),%xmm0 .byte 15,88,193 // addps %xmm1,%xmm0 @@ -26275,7 +26954,7 @@ _sk_seed_shader_sse2: .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 15,88,202 // addps %xmm2,%xmm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,21,227,72,0,0 // movaps 0x48e3(%rip),%xmm2 # 4980 <_sk_callback_sse2+0xed> + .byte 15,40,21,211,74,0,0 // movaps 0x4ad3(%rip),%xmm2 # 4b70 <_sk_callback_sse2+0xec> .byte 15,87,219 // xorps %xmm3,%xmm3 .byte 15,87,228 // xorps %xmm4,%xmm4 .byte 15,87,237 // xorps %xmm5,%xmm5 @@ -26298,14 +26977,14 @@ _sk_dither_sse2: .byte 102,68,15,110,1 // movd (%rcx),%xmm8 .byte 102,69,15,112,192,0 // pshufd $0x0,%xmm8,%xmm8 .byte 102,69,15,239,193 // pxor %xmm9,%xmm8 - .byte 102,68,15,111,21,168,72,0,0 // movdqa 0x48a8(%rip),%xmm10 # 4990 <_sk_callback_sse2+0xfd> + .byte 102,68,15,111,21,152,74,0,0 // movdqa 0x4a98(%rip),%xmm10 # 4b80 <_sk_callback_sse2+0xfc> .byte 102,69,15,111,216 // movdqa %xmm8,%xmm11 .byte 102,69,15,219,218 // pand %xmm10,%xmm11 .byte 102,65,15,114,243,5 // pslld $0x5,%xmm11 .byte 102,69,15,219,209 // pand %xmm9,%xmm10 .byte 102,65,15,114,242,4 // pslld $0x4,%xmm10 - .byte 102,68,15,111,37,148,72,0,0 // movdqa 0x4894(%rip),%xmm12 # 49a0 <_sk_callback_sse2+0x10d> - .byte 102,68,15,111,45,155,72,0,0 // movdqa 0x489b(%rip),%xmm13 # 49b0 <_sk_callback_sse2+0x11d> + .byte 102,68,15,111,37,132,74,0,0 // movdqa 0x4a84(%rip),%xmm12 # 4b90 <_sk_callback_sse2+0x10c> + .byte 102,68,15,111,45,139,74,0,0 // movdqa 0x4a8b(%rip),%xmm13 # 4ba0 <_sk_callback_sse2+0x11c> .byte 102,69,15,111,240 // movdqa %xmm8,%xmm14 .byte 102,69,15,219,245 // pand %xmm13,%xmm14 .byte 102,65,15,114,246,2 // pslld $0x2,%xmm14 @@ -26321,8 +27000,8 @@ _sk_dither_sse2: .byte 102,69,15,235,245 // por %xmm13,%xmm14 .byte 102,69,15,235,240 // por %xmm8,%xmm14 .byte 69,15,91,198 // cvtdq2ps %xmm14,%xmm8 - .byte 68,15,89,5,86,72,0,0 // mulps 0x4856(%rip),%xmm8 # 49c0 <_sk_callback_sse2+0x12d> - .byte 68,15,88,5,94,72,0,0 // addps 0x485e(%rip),%xmm8 # 49d0 <_sk_callback_sse2+0x13d> + .byte 68,15,89,5,70,74,0,0 // mulps 0x4a46(%rip),%xmm8 # 4bb0 <_sk_callback_sse2+0x12c> + .byte 68,15,88,5,78,74,0,0 // addps 0x4a4e(%rip),%xmm8 # 4bc0 <_sk_callback_sse2+0x13c> .byte 243,68,15,16,72,8 // movss 0x8(%rax),%xmm9 .byte 69,15,198,201,0 // shufps $0x0,%xmm9,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 @@ -26388,7 +27067,7 @@ HIDDEN _sk_srcatop_sse2 FUNCTION(_sk_srcatop_sse2) _sk_srcatop_sse2: .byte 15,89,199 // mulps %xmm7,%xmm0 - .byte 68,15,40,5,225,71,0,0 // movaps 0x47e1(%rip),%xmm8 # 49e0 <_sk_callback_sse2+0x14d> + .byte 68,15,40,5,209,73,0,0 // movaps 0x49d1(%rip),%xmm8 # 4bd0 <_sk_callback_sse2+0x14c> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -26413,7 +27092,7 @@ FUNCTION(_sk_dstatop_sse2) _sk_dstatop_sse2: .byte 68,15,40,195 // movaps %xmm3,%xmm8 .byte 68,15,89,196 // mulps %xmm4,%xmm8 - .byte 68,15,40,13,164,71,0,0 // movaps 0x47a4(%rip),%xmm9 # 49f0 <_sk_callback_sse2+0x15d> + .byte 68,15,40,13,148,73,0,0 // movaps 0x4994(%rip),%xmm9 # 4be0 <_sk_callback_sse2+0x15c> .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,88,192 // addps %xmm8,%xmm0 @@ -26460,7 +27139,7 @@ HIDDEN _sk_srcout_sse2 .globl _sk_srcout_sse2 FUNCTION(_sk_srcout_sse2) _sk_srcout_sse2: - .byte 68,15,40,5,72,71,0,0 // movaps 0x4748(%rip),%xmm8 # 4a00 <_sk_callback_sse2+0x16d> + .byte 68,15,40,5,56,73,0,0 // movaps 0x4938(%rip),%xmm8 # 4bf0 <_sk_callback_sse2+0x16c> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 @@ -26473,7 +27152,7 @@ HIDDEN _sk_dstout_sse2 .globl _sk_dstout_sse2 FUNCTION(_sk_dstout_sse2) _sk_dstout_sse2: - .byte 68,15,40,5,56,71,0,0 // movaps 0x4738(%rip),%xmm8 # 4a10 <_sk_callback_sse2+0x17d> + .byte 68,15,40,5,40,73,0,0 // movaps 0x4928(%rip),%xmm8 # 4c00 <_sk_callback_sse2+0x17c> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 15,89,196 // mulps %xmm4,%xmm0 @@ -26490,7 +27169,7 @@ HIDDEN _sk_srcover_sse2 .globl _sk_srcover_sse2 FUNCTION(_sk_srcover_sse2) _sk_srcover_sse2: - .byte 68,15,40,5,27,71,0,0 // movaps 0x471b(%rip),%xmm8 # 4a20 <_sk_callback_sse2+0x18d> + .byte 68,15,40,5,11,73,0,0 // movaps 0x490b(%rip),%xmm8 # 4c10 <_sk_callback_sse2+0x18c> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -26510,7 +27189,7 @@ HIDDEN _sk_dstover_sse2 .globl _sk_dstover_sse2 FUNCTION(_sk_dstover_sse2) _sk_dstover_sse2: - .byte 68,15,40,5,239,70,0,0 // movaps 0x46ef(%rip),%xmm8 # 4a30 <_sk_callback_sse2+0x19d> + .byte 68,15,40,5,223,72,0,0 // movaps 0x48df(%rip),%xmm8 # 4c20 <_sk_callback_sse2+0x19c> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -26538,7 +27217,7 @@ HIDDEN _sk_multiply_sse2 .globl _sk_multiply_sse2 FUNCTION(_sk_multiply_sse2) _sk_multiply_sse2: - .byte 68,15,40,5,195,70,0,0 // movaps 0x46c3(%rip),%xmm8 # 4a40 <_sk_callback_sse2+0x1ad> + .byte 68,15,40,5,179,72,0,0 // movaps 0x48b3(%rip),%xmm8 # 4c30 <_sk_callback_sse2+0x1ac> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 69,15,40,209 // movaps %xmm9,%xmm10 @@ -26614,7 +27293,7 @@ HIDDEN _sk_xor__sse2 FUNCTION(_sk_xor__sse2) _sk_xor__sse2: .byte 68,15,40,195 // movaps %xmm3,%xmm8 - .byte 15,40,29,244,69,0,0 // movaps 0x45f4(%rip),%xmm3 # 4a50 <_sk_callback_sse2+0x1bd> + .byte 15,40,29,228,71,0,0 // movaps 0x47e4(%rip),%xmm3 # 4c40 <_sk_callback_sse2+0x1bc> .byte 68,15,40,203 // movaps %xmm3,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 @@ -26662,7 +27341,7 @@ _sk_darken_sse2: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,95,209 // maxps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,95,69,0,0 // movaps 0x455f(%rip),%xmm2 # 4a60 <_sk_callback_sse2+0x1cd> + .byte 15,40,21,79,71,0,0 // movaps 0x474f(%rip),%xmm2 # 4c50 <_sk_callback_sse2+0x1cc> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -26696,7 +27375,7 @@ _sk_lighten_sse2: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,4,69,0,0 // movaps 0x4504(%rip),%xmm2 # 4a70 <_sk_callback_sse2+0x1dd> + .byte 15,40,21,244,70,0,0 // movaps 0x46f4(%rip),%xmm2 # 4c60 <_sk_callback_sse2+0x1dc> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -26733,7 +27412,7 @@ _sk_difference_sse2: .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,158,68,0,0 // movaps 0x449e(%rip),%xmm2 # 4a80 <_sk_callback_sse2+0x1ed> + .byte 15,40,21,142,70,0,0 // movaps 0x468e(%rip),%xmm2 # 4c70 <_sk_callback_sse2+0x1ec> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -26760,7 +27439,7 @@ _sk_exclusion_sse2: .byte 15,89,214 // mulps %xmm6,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,202 // subps %xmm2,%xmm9 - .byte 15,40,13,95,68,0,0 // movaps 0x445f(%rip),%xmm1 # 4a90 <_sk_callback_sse2+0x1fd> + .byte 15,40,13,79,70,0,0 // movaps 0x464f(%rip),%xmm1 # 4c80 <_sk_callback_sse2+0x1fc> .byte 15,92,203 // subps %xmm3,%xmm1 .byte 15,89,207 // mulps %xmm7,%xmm1 .byte 15,88,217 // addps %xmm1,%xmm3 @@ -26774,7 +27453,7 @@ HIDDEN _sk_colorburn_sse2 FUNCTION(_sk_colorburn_sse2) _sk_colorburn_sse2: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,40,21,78,68,0,0 // movaps 0x444e(%rip),%xmm10 # 4aa0 <_sk_callback_sse2+0x20d> + .byte 68,15,40,21,62,70,0,0 // movaps 0x463e(%rip),%xmm10 # 4c90 <_sk_callback_sse2+0x20c> .byte 69,15,40,202 // movaps %xmm10,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 69,15,40,217 // movaps %xmm9,%xmm11 @@ -26868,7 +27547,7 @@ HIDDEN _sk_colordodge_sse2 FUNCTION(_sk_colordodge_sse2) _sk_colordodge_sse2: .byte 68,15,40,200 // movaps %xmm0,%xmm9 - .byte 68,15,40,21,4,67,0,0 // movaps 0x4304(%rip),%xmm10 # 4ab0 <_sk_callback_sse2+0x21d> + .byte 68,15,40,21,244,68,0,0 // movaps 0x44f4(%rip),%xmm10 # 4ca0 <_sk_callback_sse2+0x21c> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 69,15,40,227 // movaps %xmm11,%xmm12 @@ -26962,7 +27641,7 @@ _sk_hardlight_sse2: .byte 15,41,116,36,232 // movaps %xmm6,-0x18(%rsp) .byte 15,40,245 // movaps %xmm5,%xmm6 .byte 15,40,236 // movaps %xmm4,%xmm5 - .byte 68,15,40,29,185,65,0,0 // movaps 0x41b9(%rip),%xmm11 # 4ac0 <_sk_callback_sse2+0x22d> + .byte 68,15,40,29,169,67,0,0 // movaps 0x43a9(%rip),%xmm11 # 4cb0 <_sk_callback_sse2+0x22c> .byte 69,15,40,211 // movaps %xmm11,%xmm10 .byte 68,15,92,215 // subps %xmm7,%xmm10 .byte 69,15,40,194 // movaps %xmm10,%xmm8 @@ -27050,7 +27729,7 @@ FUNCTION(_sk_overlay_sse2) _sk_overlay_sse2: .byte 68,15,40,193 // movaps %xmm1,%xmm8 .byte 68,15,40,232 // movaps %xmm0,%xmm13 - .byte 68,15,40,13,135,64,0,0 // movaps 0x4087(%rip),%xmm9 # 4ad0 <_sk_callback_sse2+0x23d> + .byte 68,15,40,13,119,66,0,0 // movaps 0x4277(%rip),%xmm9 # 4cc0 <_sk_callback_sse2+0x23c> .byte 69,15,40,209 // movaps %xmm9,%xmm10 .byte 68,15,92,215 // subps %xmm7,%xmm10 .byte 69,15,40,218 // movaps %xmm10,%xmm11 @@ -27141,7 +27820,7 @@ _sk_softlight_sse2: .byte 68,15,40,213 // movaps %xmm5,%xmm10 .byte 68,15,94,215 // divps %xmm7,%xmm10 .byte 69,15,84,212 // andps %xmm12,%xmm10 - .byte 68,15,40,13,68,63,0,0 // movaps 0x3f44(%rip),%xmm9 # 4ae0 <_sk_callback_sse2+0x24d> + .byte 68,15,40,13,52,65,0,0 // movaps 0x4134(%rip),%xmm9 # 4cd0 <_sk_callback_sse2+0x24c> .byte 69,15,40,249 // movaps %xmm9,%xmm15 .byte 69,15,92,250 // subps %xmm10,%xmm15 .byte 69,15,40,218 // movaps %xmm10,%xmm11 @@ -27154,10 +27833,10 @@ _sk_softlight_sse2: .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 15,89,192 // mulps %xmm0,%xmm0 .byte 65,15,88,194 // addps %xmm10,%xmm0 - .byte 68,15,40,53,30,63,0,0 // movaps 0x3f1e(%rip),%xmm14 # 4af0 <_sk_callback_sse2+0x25d> + .byte 68,15,40,53,14,65,0,0 // movaps 0x410e(%rip),%xmm14 # 4ce0 <_sk_callback_sse2+0x25c> .byte 69,15,88,222 // addps %xmm14,%xmm11 .byte 68,15,89,216 // mulps %xmm0,%xmm11 - .byte 68,15,40,21,30,63,0,0 // movaps 0x3f1e(%rip),%xmm10 # 4b00 <_sk_callback_sse2+0x26d> + .byte 68,15,40,21,14,65,0,0 // movaps 0x410e(%rip),%xmm10 # 4cf0 <_sk_callback_sse2+0x26c> .byte 69,15,89,234 // mulps %xmm10,%xmm13 .byte 69,15,88,235 // addps %xmm11,%xmm13 .byte 15,88,228 // addps %xmm4,%xmm4 @@ -27302,7 +27981,7 @@ _sk_hue_sse2: .byte 68,15,40,209 // movaps %xmm1,%xmm10 .byte 68,15,40,225 // movaps %xmm1,%xmm12 .byte 68,15,89,211 // mulps %xmm3,%xmm10 - .byte 68,15,40,5,97,61,0,0 // movaps 0x3d61(%rip),%xmm8 # 4b40 <_sk_callback_sse2+0x2ad> + .byte 68,15,40,5,81,63,0,0 // movaps 0x3f51(%rip),%xmm8 # 4d30 <_sk_callback_sse2+0x2ac> .byte 69,15,40,216 // movaps %xmm8,%xmm11 .byte 15,40,207 // movaps %xmm7,%xmm1 .byte 68,15,92,217 // subps %xmm1,%xmm11 @@ -27348,12 +28027,12 @@ _sk_hue_sse2: .byte 69,15,84,206 // andps %xmm14,%xmm9 .byte 69,15,84,214 // andps %xmm14,%xmm10 .byte 65,15,84,214 // andps %xmm14,%xmm2 - .byte 68,15,40,61,117,60,0,0 // movaps 0x3c75(%rip),%xmm15 # 4b10 <_sk_callback_sse2+0x27d> + .byte 68,15,40,61,101,62,0,0 // movaps 0x3e65(%rip),%xmm15 # 4d00 <_sk_callback_sse2+0x27c> .byte 65,15,89,231 // mulps %xmm15,%xmm4 - .byte 15,40,5,122,60,0,0 // movaps 0x3c7a(%rip),%xmm0 # 4b20 <_sk_callback_sse2+0x28d> + .byte 15,40,5,106,62,0,0 // movaps 0x3e6a(%rip),%xmm0 # 4d10 <_sk_callback_sse2+0x28c> .byte 15,89,240 // mulps %xmm0,%xmm6 .byte 15,88,244 // addps %xmm4,%xmm6 - .byte 68,15,40,53,124,60,0,0 // movaps 0x3c7c(%rip),%xmm14 # 4b30 <_sk_callback_sse2+0x29d> + .byte 68,15,40,53,108,62,0,0 // movaps 0x3e6c(%rip),%xmm14 # 4d20 <_sk_callback_sse2+0x29c> .byte 68,15,40,239 // movaps %xmm7,%xmm13 .byte 69,15,89,238 // mulps %xmm14,%xmm13 .byte 68,15,88,238 // addps %xmm6,%xmm13 @@ -27530,14 +28209,14 @@ _sk_saturation_sse2: .byte 68,15,84,211 // andps %xmm3,%xmm10 .byte 68,15,84,203 // andps %xmm3,%xmm9 .byte 15,84,195 // andps %xmm3,%xmm0 - .byte 68,15,40,5,17,58,0,0 // movaps 0x3a11(%rip),%xmm8 # 4b50 <_sk_callback_sse2+0x2bd> + .byte 68,15,40,5,1,60,0,0 // movaps 0x3c01(%rip),%xmm8 # 4d40 <_sk_callback_sse2+0x2bc> .byte 15,40,214 // movaps %xmm6,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 - .byte 15,40,13,19,58,0,0 // movaps 0x3a13(%rip),%xmm1 # 4b60 <_sk_callback_sse2+0x2cd> + .byte 15,40,13,3,60,0,0 // movaps 0x3c03(%rip),%xmm1 # 4d50 <_sk_callback_sse2+0x2cc> .byte 15,40,221 // movaps %xmm5,%xmm3 .byte 15,89,217 // mulps %xmm1,%xmm3 .byte 15,88,218 // addps %xmm2,%xmm3 - .byte 68,15,40,37,18,58,0,0 // movaps 0x3a12(%rip),%xmm12 # 4b70 <_sk_callback_sse2+0x2dd> + .byte 68,15,40,37,2,60,0,0 // movaps 0x3c02(%rip),%xmm12 # 4d60 <_sk_callback_sse2+0x2dc> .byte 69,15,89,236 // mulps %xmm12,%xmm13 .byte 68,15,88,235 // addps %xmm3,%xmm13 .byte 65,15,40,210 // movaps %xmm10,%xmm2 @@ -27582,7 +28261,7 @@ _sk_saturation_sse2: .byte 15,40,223 // movaps %xmm7,%xmm3 .byte 15,40,236 // movaps %xmm4,%xmm5 .byte 15,89,221 // mulps %xmm5,%xmm3 - .byte 68,15,40,5,119,57,0,0 // movaps 0x3977(%rip),%xmm8 # 4b80 <_sk_callback_sse2+0x2ed> + .byte 68,15,40,5,103,59,0,0 // movaps 0x3b67(%rip),%xmm8 # 4d70 <_sk_callback_sse2+0x2ec> .byte 65,15,40,224 // movaps %xmm8,%xmm4 .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 15,88,253 // addps %xmm5,%xmm7 @@ -27683,14 +28362,14 @@ _sk_color_sse2: .byte 68,15,40,213 // movaps %xmm5,%xmm10 .byte 69,15,89,208 // mulps %xmm8,%xmm10 .byte 65,15,40,208 // movaps %xmm8,%xmm2 - .byte 68,15,40,45,21,56,0,0 // movaps 0x3815(%rip),%xmm13 # 4b90 <_sk_callback_sse2+0x2fd> + .byte 68,15,40,45,5,58,0,0 // movaps 0x3a05(%rip),%xmm13 # 4d80 <_sk_callback_sse2+0x2fc> .byte 68,15,40,198 // movaps %xmm6,%xmm8 .byte 69,15,89,197 // mulps %xmm13,%xmm8 - .byte 68,15,40,53,21,56,0,0 // movaps 0x3815(%rip),%xmm14 # 4ba0 <_sk_callback_sse2+0x30d> + .byte 68,15,40,53,5,58,0,0 // movaps 0x3a05(%rip),%xmm14 # 4d90 <_sk_callback_sse2+0x30c> .byte 65,15,40,195 // movaps %xmm11,%xmm0 .byte 65,15,89,198 // mulps %xmm14,%xmm0 .byte 65,15,88,192 // addps %xmm8,%xmm0 - .byte 68,15,40,29,17,56,0,0 // movaps 0x3811(%rip),%xmm11 # 4bb0 <_sk_callback_sse2+0x31d> + .byte 68,15,40,29,1,58,0,0 // movaps 0x3a01(%rip),%xmm11 # 4da0 <_sk_callback_sse2+0x31c> .byte 69,15,89,227 // mulps %xmm11,%xmm12 .byte 68,15,88,224 // addps %xmm0,%xmm12 .byte 65,15,40,193 // movaps %xmm9,%xmm0 @@ -27698,7 +28377,7 @@ _sk_color_sse2: .byte 69,15,40,250 // movaps %xmm10,%xmm15 .byte 69,15,89,254 // mulps %xmm14,%xmm15 .byte 68,15,88,248 // addps %xmm0,%xmm15 - .byte 68,15,40,5,253,55,0,0 // movaps 0x37fd(%rip),%xmm8 # 4bc0 <_sk_callback_sse2+0x32d> + .byte 68,15,40,5,237,57,0,0 // movaps 0x39ed(%rip),%xmm8 # 4db0 <_sk_callback_sse2+0x32c> .byte 65,15,40,224 // movaps %xmm8,%xmm4 .byte 15,92,226 // subps %xmm2,%xmm4 .byte 15,89,252 // mulps %xmm4,%xmm7 @@ -27834,15 +28513,15 @@ _sk_luminosity_sse2: .byte 68,15,40,205 // movaps %xmm5,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 .byte 15,89,222 // mulps %xmm6,%xmm3 - .byte 68,15,40,37,20,54,0,0 // movaps 0x3614(%rip),%xmm12 # 4bd0 <_sk_callback_sse2+0x33d> + .byte 68,15,40,37,4,56,0,0 // movaps 0x3804(%rip),%xmm12 # 4dc0 <_sk_callback_sse2+0x33c> .byte 68,15,40,199 // movaps %xmm7,%xmm8 .byte 69,15,89,196 // mulps %xmm12,%xmm8 - .byte 68,15,40,45,20,54,0,0 // movaps 0x3614(%rip),%xmm13 # 4be0 <_sk_callback_sse2+0x34d> + .byte 68,15,40,45,4,56,0,0 // movaps 0x3804(%rip),%xmm13 # 4dd0 <_sk_callback_sse2+0x34c> .byte 68,15,40,241 // movaps %xmm1,%xmm14 .byte 69,15,89,245 // mulps %xmm13,%xmm14 .byte 69,15,88,240 // addps %xmm8,%xmm14 - .byte 68,15,40,29,16,54,0,0 // movaps 0x3610(%rip),%xmm11 # 4bf0 <_sk_callback_sse2+0x35d> - .byte 68,15,40,5,24,54,0,0 // movaps 0x3618(%rip),%xmm8 # 4c00 <_sk_callback_sse2+0x36d> + .byte 68,15,40,29,0,56,0,0 // movaps 0x3800(%rip),%xmm11 # 4de0 <_sk_callback_sse2+0x35c> + .byte 68,15,40,5,8,56,0,0 // movaps 0x3808(%rip),%xmm8 # 4df0 <_sk_callback_sse2+0x36c> .byte 69,15,40,248 // movaps %xmm8,%xmm15 .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 68,15,92,248 // subps %xmm0,%xmm15 @@ -27987,7 +28666,7 @@ HIDDEN _sk_clamp_1_sse2 .globl _sk_clamp_1_sse2 FUNCTION(_sk_clamp_1_sse2) _sk_clamp_1_sse2: - .byte 68,15,40,5,33,52,0,0 // movaps 0x3421(%rip),%xmm8 # 4c10 <_sk_callback_sse2+0x37d> + .byte 68,15,40,5,17,54,0,0 // movaps 0x3611(%rip),%xmm8 # 4e00 <_sk_callback_sse2+0x37c> .byte 65,15,93,192 // minps %xmm8,%xmm0 .byte 65,15,93,200 // minps %xmm8,%xmm1 .byte 65,15,93,208 // minps %xmm8,%xmm2 @@ -27999,7 +28678,7 @@ HIDDEN _sk_clamp_a_sse2 .globl _sk_clamp_a_sse2 FUNCTION(_sk_clamp_a_sse2) _sk_clamp_a_sse2: - .byte 15,93,29,22,52,0,0 // minps 0x3416(%rip),%xmm3 # 4c20 <_sk_callback_sse2+0x38d> + .byte 15,93,29,6,54,0,0 // minps 0x3606(%rip),%xmm3 # 4e10 <_sk_callback_sse2+0x38c> .byte 15,93,195 // minps %xmm3,%xmm0 .byte 15,93,203 // minps %xmm3,%xmm1 .byte 15,93,211 // minps %xmm3,%xmm2 @@ -28086,7 +28765,7 @@ HIDDEN _sk_unpremul_sse2 FUNCTION(_sk_unpremul_sse2) _sk_unpremul_sse2: .byte 69,15,87,192 // xorps %xmm8,%xmm8 - .byte 68,15,40,13,129,51,0,0 // movaps 0x3381(%rip),%xmm9 # 4c30 <_sk_callback_sse2+0x39d> + .byte 68,15,40,13,113,53,0,0 // movaps 0x3571(%rip),%xmm9 # 4e20 <_sk_callback_sse2+0x39c> .byte 68,15,94,203 // divps %xmm3,%xmm9 .byte 68,15,194,195,4 // cmpneqps %xmm3,%xmm8 .byte 69,15,84,193 // andps %xmm9,%xmm8 @@ -28100,20 +28779,20 @@ HIDDEN _sk_from_srgb_sse2 .globl _sk_from_srgb_sse2 FUNCTION(_sk_from_srgb_sse2) _sk_from_srgb_sse2: - .byte 68,15,40,5,108,51,0,0 // movaps 0x336c(%rip),%xmm8 # 4c40 <_sk_callback_sse2+0x3ad> + .byte 68,15,40,5,92,53,0,0 // movaps 0x355c(%rip),%xmm8 # 4e30 <_sk_callback_sse2+0x3ac> .byte 68,15,40,232 // movaps %xmm0,%xmm13 .byte 69,15,89,232 // mulps %xmm8,%xmm13 .byte 68,15,40,216 // movaps %xmm0,%xmm11 .byte 69,15,89,219 // mulps %xmm11,%xmm11 - .byte 68,15,40,13,100,51,0,0 // movaps 0x3364(%rip),%xmm9 # 4c50 <_sk_callback_sse2+0x3bd> + .byte 68,15,40,13,84,53,0,0 // movaps 0x3554(%rip),%xmm9 # 4e40 <_sk_callback_sse2+0x3bc> .byte 68,15,40,240 // movaps %xmm0,%xmm14 .byte 69,15,89,241 // mulps %xmm9,%xmm14 - .byte 68,15,40,21,100,51,0,0 // movaps 0x3364(%rip),%xmm10 # 4c60 <_sk_callback_sse2+0x3cd> + .byte 68,15,40,21,84,53,0,0 // movaps 0x3554(%rip),%xmm10 # 4e50 <_sk_callback_sse2+0x3cc> .byte 69,15,88,242 // addps %xmm10,%xmm14 .byte 69,15,89,243 // mulps %xmm11,%xmm14 - .byte 68,15,40,29,100,51,0,0 // movaps 0x3364(%rip),%xmm11 # 4c70 <_sk_callback_sse2+0x3dd> + .byte 68,15,40,29,84,53,0,0 // movaps 0x3554(%rip),%xmm11 # 4e60 <_sk_callback_sse2+0x3dc> .byte 69,15,88,243 // addps %xmm11,%xmm14 - .byte 68,15,40,37,104,51,0,0 // movaps 0x3368(%rip),%xmm12 # 4c80 <_sk_callback_sse2+0x3ed> + .byte 68,15,40,37,88,53,0,0 // movaps 0x3558(%rip),%xmm12 # 4e70 <_sk_callback_sse2+0x3ec> .byte 65,15,194,196,1 // cmpltps %xmm12,%xmm0 .byte 68,15,84,232 // andps %xmm0,%xmm13 .byte 65,15,85,198 // andnps %xmm14,%xmm0 @@ -28152,20 +28831,20 @@ _sk_to_srgb_sse2: .byte 68,15,82,192 // rsqrtps %xmm0,%xmm8 .byte 69,15,83,200 // rcpps %xmm8,%xmm9 .byte 69,15,82,232 // rsqrtps %xmm8,%xmm13 - .byte 68,15,40,5,237,50,0,0 // movaps 0x32ed(%rip),%xmm8 # 4c90 <_sk_callback_sse2+0x3fd> + .byte 68,15,40,5,221,52,0,0 // movaps 0x34dd(%rip),%xmm8 # 4e80 <_sk_callback_sse2+0x3fc> .byte 68,15,40,240 // movaps %xmm0,%xmm14 .byte 69,15,89,240 // mulps %xmm8,%xmm14 - .byte 68,15,40,21,237,50,0,0 // movaps 0x32ed(%rip),%xmm10 # 4ca0 <_sk_callback_sse2+0x40d> + .byte 68,15,40,21,221,52,0,0 // movaps 0x34dd(%rip),%xmm10 # 4e90 <_sk_callback_sse2+0x40c> .byte 69,15,89,202 // mulps %xmm10,%xmm9 - .byte 68,15,40,29,241,50,0,0 // movaps 0x32f1(%rip),%xmm11 # 4cb0 <_sk_callback_sse2+0x41d> + .byte 68,15,40,29,225,52,0,0 // movaps 0x34e1(%rip),%xmm11 # 4ea0 <_sk_callback_sse2+0x41c> .byte 69,15,88,203 // addps %xmm11,%xmm9 - .byte 68,15,40,37,245,50,0,0 // movaps 0x32f5(%rip),%xmm12 # 4cc0 <_sk_callback_sse2+0x42d> + .byte 68,15,40,37,229,52,0,0 // movaps 0x34e5(%rip),%xmm12 # 4eb0 <_sk_callback_sse2+0x42c> .byte 69,15,89,236 // mulps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,40,13,245,50,0,0 // movaps 0x32f5(%rip),%xmm9 # 4cd0 <_sk_callback_sse2+0x43d> + .byte 68,15,40,13,229,52,0,0 // movaps 0x34e5(%rip),%xmm9 # 4ec0 <_sk_callback_sse2+0x43c> .byte 69,15,40,249 // movaps %xmm9,%xmm15 .byte 69,15,93,253 // minps %xmm13,%xmm15 - .byte 68,15,40,45,245,50,0,0 // movaps 0x32f5(%rip),%xmm13 # 4ce0 <_sk_callback_sse2+0x44d> + .byte 68,15,40,45,229,52,0,0 // movaps 0x34e5(%rip),%xmm13 # 4ed0 <_sk_callback_sse2+0x44c> .byte 65,15,194,197,1 // cmpltps %xmm13,%xmm0 .byte 68,15,84,240 // andps %xmm0,%xmm14 .byte 65,15,85,199 // andnps %xmm15,%xmm0 @@ -28215,7 +28894,7 @@ _sk_rgb_to_hsl_sse2: .byte 68,15,93,218 // minps %xmm2,%xmm11 .byte 65,15,40,202 // movaps %xmm10,%xmm1 .byte 65,15,92,203 // subps %xmm11,%xmm1 - .byte 68,15,40,45,78,50,0,0 // movaps 0x324e(%rip),%xmm13 # 4cf0 <_sk_callback_sse2+0x45d> + .byte 68,15,40,45,62,52,0,0 // movaps 0x343e(%rip),%xmm13 # 4ee0 <_sk_callback_sse2+0x45c> .byte 68,15,94,233 // divps %xmm1,%xmm13 .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 65,15,194,192,0 // cmpeqps %xmm8,%xmm0 @@ -28224,30 +28903,30 @@ _sk_rgb_to_hsl_sse2: .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,40,241 // movaps %xmm9,%xmm14 .byte 68,15,194,242,1 // cmpltps %xmm2,%xmm14 - .byte 68,15,84,53,52,50,0,0 // andps 0x3234(%rip),%xmm14 # 4d00 <_sk_callback_sse2+0x46d> + .byte 68,15,84,53,36,52,0,0 // andps 0x3424(%rip),%xmm14 # 4ef0 <_sk_callback_sse2+0x46c> .byte 69,15,88,244 // addps %xmm12,%xmm14 .byte 69,15,40,250 // movaps %xmm10,%xmm15 .byte 69,15,194,249,0 // cmpeqps %xmm9,%xmm15 .byte 65,15,92,208 // subps %xmm8,%xmm2 .byte 65,15,89,213 // mulps %xmm13,%xmm2 - .byte 68,15,40,37,39,50,0,0 // movaps 0x3227(%rip),%xmm12 # 4d10 <_sk_callback_sse2+0x47d> + .byte 68,15,40,37,23,52,0,0 // movaps 0x3417(%rip),%xmm12 # 4f00 <_sk_callback_sse2+0x47c> .byte 65,15,88,212 // addps %xmm12,%xmm2 .byte 69,15,92,193 // subps %xmm9,%xmm8 .byte 69,15,89,197 // mulps %xmm13,%xmm8 - .byte 68,15,88,5,35,50,0,0 // addps 0x3223(%rip),%xmm8 # 4d20 <_sk_callback_sse2+0x48d> + .byte 68,15,88,5,19,52,0,0 // addps 0x3413(%rip),%xmm8 # 4f10 <_sk_callback_sse2+0x48c> .byte 65,15,84,215 // andps %xmm15,%xmm2 .byte 69,15,85,248 // andnps %xmm8,%xmm15 .byte 68,15,86,250 // orps %xmm2,%xmm15 .byte 68,15,84,240 // andps %xmm0,%xmm14 .byte 65,15,85,199 // andnps %xmm15,%xmm0 .byte 65,15,86,198 // orps %xmm14,%xmm0 - .byte 15,89,5,20,50,0,0 // mulps 0x3214(%rip),%xmm0 # 4d30 <_sk_callback_sse2+0x49d> + .byte 15,89,5,4,52,0,0 // mulps 0x3404(%rip),%xmm0 # 4f20 <_sk_callback_sse2+0x49c> .byte 69,15,40,194 // movaps %xmm10,%xmm8 .byte 69,15,194,195,4 // cmpneqps %xmm11,%xmm8 .byte 65,15,84,192 // andps %xmm8,%xmm0 .byte 69,15,92,226 // subps %xmm10,%xmm12 .byte 69,15,88,211 // addps %xmm11,%xmm10 - .byte 68,15,40,13,7,50,0,0 // movaps 0x3207(%rip),%xmm9 # 4d40 <_sk_callback_sse2+0x4ad> + .byte 68,15,40,13,247,51,0,0 // movaps 0x33f7(%rip),%xmm9 # 4f30 <_sk_callback_sse2+0x4ac> .byte 65,15,40,210 // movaps %xmm10,%xmm2 .byte 65,15,89,209 // mulps %xmm9,%xmm2 .byte 68,15,194,202,1 // cmpltps %xmm2,%xmm9 @@ -28271,7 +28950,7 @@ _sk_hsl_to_rgb_sse2: .byte 15,41,92,36,168 // movaps %xmm3,-0x58(%rsp) .byte 68,15,40,218 // movaps %xmm2,%xmm11 .byte 15,40,240 // movaps %xmm0,%xmm6 - .byte 68,15,40,13,198,49,0,0 // movaps 0x31c6(%rip),%xmm9 # 4d50 <_sk_callback_sse2+0x4bd> + .byte 68,15,40,13,182,51,0,0 // movaps 0x33b6(%rip),%xmm9 # 4f40 <_sk_callback_sse2+0x4bc> .byte 69,15,40,209 // movaps %xmm9,%xmm10 .byte 69,15,194,211,2 // cmpleps %xmm11,%xmm10 .byte 15,40,193 // movaps %xmm1,%xmm0 @@ -28288,28 +28967,28 @@ _sk_hsl_to_rgb_sse2: .byte 69,15,88,211 // addps %xmm11,%xmm10 .byte 69,15,88,219 // addps %xmm11,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 15,40,5,143,49,0,0 // movaps 0x318f(%rip),%xmm0 # 4d60 <_sk_callback_sse2+0x4cd> + .byte 15,40,5,127,51,0,0 // movaps 0x337f(%rip),%xmm0 # 4f50 <_sk_callback_sse2+0x4cc> .byte 15,88,198 // addps %xmm6,%xmm0 .byte 243,15,91,200 // cvttps2dq %xmm0,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 15,40,216 // movaps %xmm0,%xmm3 .byte 15,194,217,1 // cmpltps %xmm1,%xmm3 - .byte 15,84,29,135,49,0,0 // andps 0x3187(%rip),%xmm3 # 4d70 <_sk_callback_sse2+0x4dd> + .byte 15,84,29,119,51,0,0 // andps 0x3377(%rip),%xmm3 # 4f60 <_sk_callback_sse2+0x4dc> .byte 15,92,203 // subps %xmm3,%xmm1 .byte 15,92,193 // subps %xmm1,%xmm0 - .byte 68,15,40,45,137,49,0,0 // movaps 0x3189(%rip),%xmm13 # 4d80 <_sk_callback_sse2+0x4ed> + .byte 68,15,40,45,121,51,0,0 // movaps 0x3379(%rip),%xmm13 # 4f70 <_sk_callback_sse2+0x4ec> .byte 69,15,40,197 // movaps %xmm13,%xmm8 .byte 68,15,194,192,2 // cmpleps %xmm0,%xmm8 .byte 69,15,40,242 // movaps %xmm10,%xmm14 .byte 69,15,92,243 // subps %xmm11,%xmm14 .byte 65,15,40,217 // movaps %xmm9,%xmm3 .byte 15,194,216,2 // cmpleps %xmm0,%xmm3 - .byte 15,40,21,153,49,0,0 // movaps 0x3199(%rip),%xmm2 # 4db0 <_sk_callback_sse2+0x51d> + .byte 15,40,21,137,51,0,0 // movaps 0x3389(%rip),%xmm2 # 4fa0 <_sk_callback_sse2+0x51c> .byte 68,15,40,250 // movaps %xmm2,%xmm15 .byte 68,15,194,248,2 // cmpleps %xmm0,%xmm15 - .byte 15,40,13,105,49,0,0 // movaps 0x3169(%rip),%xmm1 # 4d90 <_sk_callback_sse2+0x4fd> + .byte 15,40,13,89,51,0,0 // movaps 0x3359(%rip),%xmm1 # 4f80 <_sk_callback_sse2+0x4fc> .byte 15,89,193 // mulps %xmm1,%xmm0 - .byte 15,40,45,111,49,0,0 // movaps 0x316f(%rip),%xmm5 # 4da0 <_sk_callback_sse2+0x50d> + .byte 15,40,45,95,51,0,0 // movaps 0x335f(%rip),%xmm5 # 4f90 <_sk_callback_sse2+0x50c> .byte 15,40,229 // movaps %xmm5,%xmm4 .byte 15,92,224 // subps %xmm0,%xmm4 .byte 65,15,89,230 // mulps %xmm14,%xmm4 @@ -28332,7 +29011,7 @@ _sk_hsl_to_rgb_sse2: .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 .byte 15,40,222 // movaps %xmm6,%xmm3 .byte 15,194,216,1 // cmpltps %xmm0,%xmm3 - .byte 15,84,29,228,48,0,0 // andps 0x30e4(%rip),%xmm3 # 4d70 <_sk_callback_sse2+0x4dd> + .byte 15,84,29,212,50,0,0 // andps 0x32d4(%rip),%xmm3 # 4f60 <_sk_callback_sse2+0x4dc> .byte 15,92,195 // subps %xmm3,%xmm0 .byte 68,15,40,230 // movaps %xmm6,%xmm12 .byte 68,15,92,224 // subps %xmm0,%xmm12 @@ -28362,12 +29041,12 @@ _sk_hsl_to_rgb_sse2: .byte 15,40,124,36,136 // movaps -0x78(%rsp),%xmm7 .byte 15,40,231 // movaps %xmm7,%xmm4 .byte 15,85,227 // andnps %xmm3,%xmm4 - .byte 15,88,53,188,48,0,0 // addps 0x30bc(%rip),%xmm6 # 4dc0 <_sk_callback_sse2+0x52d> + .byte 15,88,53,172,50,0,0 // addps 0x32ac(%rip),%xmm6 # 4fb0 <_sk_callback_sse2+0x52c> .byte 243,15,91,198 // cvttps2dq %xmm6,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 .byte 15,40,222 // movaps %xmm6,%xmm3 .byte 15,194,216,1 // cmpltps %xmm0,%xmm3 - .byte 15,84,29,87,48,0,0 // andps 0x3057(%rip),%xmm3 # 4d70 <_sk_callback_sse2+0x4dd> + .byte 15,84,29,71,50,0,0 // andps 0x3247(%rip),%xmm3 # 4f60 <_sk_callback_sse2+0x4dc> .byte 15,92,195 // subps %xmm3,%xmm0 .byte 15,92,240 // subps %xmm0,%xmm6 .byte 15,89,206 // mulps %xmm6,%xmm1 @@ -28431,7 +29110,7 @@ _sk_scale_u8_sse2: .byte 102,69,15,96,193 // punpcklbw %xmm9,%xmm8 .byte 102,69,15,97,193 // punpcklwd %xmm9,%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,229,47,0,0 // mulps 0x2fe5(%rip),%xmm8 # 4dd0 <_sk_callback_sse2+0x53d> + .byte 68,15,89,5,213,49,0,0 // mulps 0x31d5(%rip),%xmm8 # 4fc0 <_sk_callback_sse2+0x53c> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 65,15,89,208 // mulps %xmm8,%xmm2 @@ -28472,7 +29151,7 @@ _sk_lerp_u8_sse2: .byte 102,69,15,96,193 // punpcklbw %xmm9,%xmm8 .byte 102,69,15,97,193 // punpcklwd %xmm9,%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,131,47,0,0 // mulps 0x2f83(%rip),%xmm8 # 4de0 <_sk_callback_sse2+0x54d> + .byte 68,15,89,5,115,49,0,0 // mulps 0x3173(%rip),%xmm8 # 4fd0 <_sk_callback_sse2+0x54c> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -28497,17 +29176,17 @@ _sk_lerp_565_sse2: .byte 243,68,15,126,20,120 // movq (%rax,%rdi,2),%xmm10 .byte 102,69,15,239,192 // pxor %xmm8,%xmm8 .byte 102,69,15,97,208 // punpcklwd %xmm8,%xmm10 - .byte 102,68,15,111,5,73,47,0,0 // movdqa 0x2f49(%rip),%xmm8 # 4df0 <_sk_callback_sse2+0x55d> + .byte 102,68,15,111,5,57,49,0,0 // movdqa 0x3139(%rip),%xmm8 # 4fe0 <_sk_callback_sse2+0x55c> .byte 102,69,15,219,194 // pand %xmm10,%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,72,47,0,0 // mulps 0x2f48(%rip),%xmm8 # 4e00 <_sk_callback_sse2+0x56d> - .byte 102,68,15,111,13,79,47,0,0 // movdqa 0x2f4f(%rip),%xmm9 # 4e10 <_sk_callback_sse2+0x57d> + .byte 68,15,89,5,56,49,0,0 // mulps 0x3138(%rip),%xmm8 # 4ff0 <_sk_callback_sse2+0x56c> + .byte 102,68,15,111,13,63,49,0,0 // movdqa 0x313f(%rip),%xmm9 # 5000 <_sk_callback_sse2+0x57c> .byte 102,69,15,219,202 // pand %xmm10,%xmm9 .byte 69,15,91,201 // cvtdq2ps %xmm9,%xmm9 - .byte 68,15,89,13,78,47,0,0 // mulps 0x2f4e(%rip),%xmm9 # 4e20 <_sk_callback_sse2+0x58d> - .byte 102,68,15,219,21,85,47,0,0 // pand 0x2f55(%rip),%xmm10 # 4e30 <_sk_callback_sse2+0x59d> + .byte 68,15,89,13,62,49,0,0 // mulps 0x313e(%rip),%xmm9 # 5010 <_sk_callback_sse2+0x58c> + .byte 102,68,15,219,21,69,49,0,0 // pand 0x3145(%rip),%xmm10 # 5020 <_sk_callback_sse2+0x59c> .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 - .byte 68,15,89,21,89,47,0,0 // mulps 0x2f59(%rip),%xmm10 # 4e40 <_sk_callback_sse2+0x5ad> + .byte 68,15,89,21,73,49,0,0 // mulps 0x3149(%rip),%xmm10 # 5030 <_sk_callback_sse2+0x5ac> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -28538,7 +29217,7 @@ _sk_load_tables_sse2: .byte 76,139,0 // mov (%rax),%r8 .byte 76,139,72,8 // mov 0x8(%rax),%r9 .byte 243,69,15,111,12,184 // movdqu (%r8,%rdi,4),%xmm9 - .byte 102,68,15,111,5,9,47,0,0 // movdqa 0x2f09(%rip),%xmm8 # 4e50 <_sk_callback_sse2+0x5bd> + .byte 102,68,15,111,5,249,48,0,0 // movdqa 0x30f9(%rip),%xmm8 # 5040 <_sk_callback_sse2+0x5bc> .byte 102,65,15,111,193 // movdqa %xmm9,%xmm0 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,15,112,200,78 // pshufd $0x4e,%xmm0,%xmm1 @@ -28593,7 +29272,7 @@ _sk_load_tables_sse2: .byte 65,15,20,208 // unpcklps %xmm8,%xmm2 .byte 102,65,15,114,209,24 // psrld $0x18,%xmm9 .byte 65,15,91,217 // cvtdq2ps %xmm9,%xmm3 - .byte 15,89,29,22,46,0,0 // mulps 0x2e16(%rip),%xmm3 # 4e60 <_sk_callback_sse2+0x5cd> + .byte 15,89,29,6,48,0,0 // mulps 0x3006(%rip),%xmm3 # 5050 <_sk_callback_sse2+0x5cc> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -28612,7 +29291,7 @@ _sk_load_tables_u16_be_sse2: .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,97,200 // punpcklwd %xmm0,%xmm1 .byte 102,68,15,105,200 // punpckhwd %xmm0,%xmm9 - .byte 102,68,15,111,21,233,45,0,0 // movdqa 0x2de9(%rip),%xmm10 # 4e70 <_sk_callback_sse2+0x5dd> + .byte 102,68,15,111,21,217,47,0,0 // movdqa 0x2fd9(%rip),%xmm10 # 5060 <_sk_callback_sse2+0x5dc> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,194 // pand %xmm10,%xmm0 .byte 102,69,15,239,192 // pxor %xmm8,%xmm8 @@ -28673,7 +29352,7 @@ _sk_load_tables_u16_be_sse2: .byte 102,65,15,235,217 // por %xmm9,%xmm3 .byte 102,65,15,97,216 // punpcklwd %xmm8,%xmm3 .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,216,44,0,0 // mulps 0x2cd8(%rip),%xmm3 # 4e80 <_sk_callback_sse2+0x5ed> + .byte 15,89,29,200,46,0,0 // mulps 0x2ec8(%rip),%xmm3 # 5070 <_sk_callback_sse2+0x5ec> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -28695,7 +29374,7 @@ _sk_load_tables_rgb_u16_be_sse2: .byte 102,68,15,97,208 // punpcklwd %xmm0,%xmm10 .byte 102,65,15,111,195 // movdqa %xmm11,%xmm0 .byte 102,65,15,97,194 // punpcklwd %xmm10,%xmm0 - .byte 102,68,15,111,5,152,44,0,0 // movdqa 0x2c98(%rip),%xmm8 # 4e90 <_sk_callback_sse2+0x5fd> + .byte 102,68,15,111,5,136,46,0,0 // movdqa 0x2e88(%rip),%xmm8 # 5080 <_sk_callback_sse2+0x5fc> .byte 102,15,112,200,78 // pshufd $0x4e,%xmm0,%xmm1 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,69,15,239,201 // pxor %xmm9,%xmm9 @@ -28750,7 +29429,7 @@ _sk_load_tables_rgb_u16_be_sse2: .byte 15,20,211 // unpcklps %xmm3,%xmm2 .byte 65,15,20,208 // unpcklps %xmm8,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,167,43,0,0 // movaps 0x2ba7(%rip),%xmm3 # 4ea0 <_sk_callback_sse2+0x60d> + .byte 15,40,29,151,45,0,0 // movaps 0x2d97(%rip),%xmm3 # 5090 <_sk_callback_sse2+0x60c> .byte 255,224 // jmpq *%rax HIDDEN _sk_byte_tables_sse2 @@ -28760,7 +29439,7 @@ _sk_byte_tables_sse2: .byte 65,86 // push %r14 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,168,43,0,0 // movaps 0x2ba8(%rip),%xmm8 # 4eb0 <_sk_callback_sse2+0x61d> + .byte 68,15,40,5,152,45,0,0 // movaps 0x2d98(%rip),%xmm8 # 50a0 <_sk_callback_sse2+0x61c> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,91,192 // cvtps2dq %xmm0,%xmm0 .byte 102,72,15,126,193 // movq %xmm0,%rcx @@ -28787,7 +29466,7 @@ _sk_byte_tables_sse2: .byte 102,65,15,96,193 // punpcklbw %xmm9,%xmm0 .byte 102,65,15,97,193 // punpcklwd %xmm9,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,21,69,43,0,0 // movaps 0x2b45(%rip),%xmm10 # 4ec0 <_sk_callback_sse2+0x62d> + .byte 68,15,40,21,53,45,0,0 // movaps 0x2d35(%rip),%xmm10 # 50b0 <_sk_callback_sse2+0x62c> .byte 65,15,89,194 // mulps %xmm10,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -28903,7 +29582,7 @@ _sk_byte_tables_rgb_sse2: .byte 102,65,15,96,193 // punpcklbw %xmm9,%xmm0 .byte 102,65,15,97,193 // punpcklwd %xmm9,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,21,152,41,0,0 // movaps 0x2998(%rip),%xmm10 # 4ed0 <_sk_callback_sse2+0x63d> + .byte 68,15,40,21,136,43,0,0 // movaps 0x2b88(%rip),%xmm10 # 50c0 <_sk_callback_sse2+0x63c> .byte 65,15,89,194 // mulps %xmm10,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -29100,15 +29779,15 @@ _sk_parametric_r_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,215,38,0,0 // mulps 0x26d7(%rip),%xmm9 # 4ee0 <_sk_callback_sse2+0x64d> - .byte 68,15,84,21,223,38,0,0 // andps 0x26df(%rip),%xmm10 # 4ef0 <_sk_callback_sse2+0x65d> - .byte 68,15,86,21,231,38,0,0 // orps 0x26e7(%rip),%xmm10 # 4f00 <_sk_callback_sse2+0x66d> - .byte 68,15,88,13,239,38,0,0 // addps 0x26ef(%rip),%xmm9 # 4f10 <_sk_callback_sse2+0x67d> - .byte 68,15,40,37,247,38,0,0 // movaps 0x26f7(%rip),%xmm12 # 4f20 <_sk_callback_sse2+0x68d> + .byte 68,15,89,13,199,40,0,0 // mulps 0x28c7(%rip),%xmm9 # 50d0 <_sk_callback_sse2+0x64c> + .byte 68,15,84,21,207,40,0,0 // andps 0x28cf(%rip),%xmm10 # 50e0 <_sk_callback_sse2+0x65c> + .byte 68,15,86,21,215,40,0,0 // orps 0x28d7(%rip),%xmm10 # 50f0 <_sk_callback_sse2+0x66c> + .byte 68,15,88,13,223,40,0,0 // addps 0x28df(%rip),%xmm9 # 5100 <_sk_callback_sse2+0x67c> + .byte 68,15,40,37,231,40,0,0 // movaps 0x28e7(%rip),%xmm12 # 5110 <_sk_callback_sse2+0x68c> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,247,38,0,0 // addps 0x26f7(%rip),%xmm10 # 4f30 <_sk_callback_sse2+0x69d> - .byte 68,15,40,37,255,38,0,0 // movaps 0x26ff(%rip),%xmm12 # 4f40 <_sk_callback_sse2+0x6ad> + .byte 68,15,88,21,231,40,0,0 // addps 0x28e7(%rip),%xmm10 # 5120 <_sk_callback_sse2+0x69c> + .byte 68,15,40,37,239,40,0,0 // movaps 0x28ef(%rip),%xmm12 # 5130 <_sk_callback_sse2+0x6ac> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -29116,22 +29795,22 @@ _sk_parametric_r_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,233,38,0,0 // movaps 0x26e9(%rip),%xmm10 # 4f50 <_sk_callback_sse2+0x6bd> + .byte 68,15,40,21,217,40,0,0 // movaps 0x28d9(%rip),%xmm10 # 5140 <_sk_callback_sse2+0x6bc> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,221,38,0,0 // addps 0x26dd(%rip),%xmm9 # 4f60 <_sk_callback_sse2+0x6cd> - .byte 68,15,40,37,229,38,0,0 // movaps 0x26e5(%rip),%xmm12 # 4f70 <_sk_callback_sse2+0x6dd> + .byte 68,15,88,13,205,40,0,0 // addps 0x28cd(%rip),%xmm9 # 5150 <_sk_callback_sse2+0x6cc> + .byte 68,15,40,37,213,40,0,0 // movaps 0x28d5(%rip),%xmm12 # 5160 <_sk_callback_sse2+0x6dc> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,229,38,0,0 // movaps 0x26e5(%rip),%xmm12 # 4f80 <_sk_callback_sse2+0x6ed> + .byte 68,15,40,37,213,40,0,0 // movaps 0x28d5(%rip),%xmm12 # 5170 <_sk_callback_sse2+0x6ec> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,233,38,0,0 // movaps 0x26e9(%rip),%xmm13 # 4f90 <_sk_callback_sse2+0x6fd> + .byte 68,15,40,45,217,40,0,0 // movaps 0x28d9(%rip),%xmm13 # 5180 <_sk_callback_sse2+0x6fc> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,233,38,0,0 // mulps 0x26e9(%rip),%xmm13 # 4fa0 <_sk_callback_sse2+0x70d> + .byte 68,15,89,45,217,40,0,0 // mulps 0x28d9(%rip),%xmm13 # 5190 <_sk_callback_sse2+0x70c> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -29167,15 +29846,15 @@ _sk_parametric_g_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,105,38,0,0 // mulps 0x2669(%rip),%xmm9 # 4fb0 <_sk_callback_sse2+0x71d> - .byte 68,15,84,21,113,38,0,0 // andps 0x2671(%rip),%xmm10 # 4fc0 <_sk_callback_sse2+0x72d> - .byte 68,15,86,21,121,38,0,0 // orps 0x2679(%rip),%xmm10 # 4fd0 <_sk_callback_sse2+0x73d> - .byte 68,15,88,13,129,38,0,0 // addps 0x2681(%rip),%xmm9 # 4fe0 <_sk_callback_sse2+0x74d> - .byte 68,15,40,37,137,38,0,0 // movaps 0x2689(%rip),%xmm12 # 4ff0 <_sk_callback_sse2+0x75d> + .byte 68,15,89,13,89,40,0,0 // mulps 0x2859(%rip),%xmm9 # 51a0 <_sk_callback_sse2+0x71c> + .byte 68,15,84,21,97,40,0,0 // andps 0x2861(%rip),%xmm10 # 51b0 <_sk_callback_sse2+0x72c> + .byte 68,15,86,21,105,40,0,0 // orps 0x2869(%rip),%xmm10 # 51c0 <_sk_callback_sse2+0x73c> + .byte 68,15,88,13,113,40,0,0 // addps 0x2871(%rip),%xmm9 # 51d0 <_sk_callback_sse2+0x74c> + .byte 68,15,40,37,121,40,0,0 // movaps 0x2879(%rip),%xmm12 # 51e0 <_sk_callback_sse2+0x75c> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,137,38,0,0 // addps 0x2689(%rip),%xmm10 # 5000 <_sk_callback_sse2+0x76d> - .byte 68,15,40,37,145,38,0,0 // movaps 0x2691(%rip),%xmm12 # 5010 <_sk_callback_sse2+0x77d> + .byte 68,15,88,21,121,40,0,0 // addps 0x2879(%rip),%xmm10 # 51f0 <_sk_callback_sse2+0x76c> + .byte 68,15,40,37,129,40,0,0 // movaps 0x2881(%rip),%xmm12 # 5200 <_sk_callback_sse2+0x77c> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -29183,22 +29862,22 @@ _sk_parametric_g_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,123,38,0,0 // movaps 0x267b(%rip),%xmm10 # 5020 <_sk_callback_sse2+0x78d> + .byte 68,15,40,21,107,40,0,0 // movaps 0x286b(%rip),%xmm10 # 5210 <_sk_callback_sse2+0x78c> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,111,38,0,0 // addps 0x266f(%rip),%xmm9 # 5030 <_sk_callback_sse2+0x79d> - .byte 68,15,40,37,119,38,0,0 // movaps 0x2677(%rip),%xmm12 # 5040 <_sk_callback_sse2+0x7ad> + .byte 68,15,88,13,95,40,0,0 // addps 0x285f(%rip),%xmm9 # 5220 <_sk_callback_sse2+0x79c> + .byte 68,15,40,37,103,40,0,0 // movaps 0x2867(%rip),%xmm12 # 5230 <_sk_callback_sse2+0x7ac> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,119,38,0,0 // movaps 0x2677(%rip),%xmm12 # 5050 <_sk_callback_sse2+0x7bd> + .byte 68,15,40,37,103,40,0,0 // movaps 0x2867(%rip),%xmm12 # 5240 <_sk_callback_sse2+0x7bc> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,123,38,0,0 // movaps 0x267b(%rip),%xmm13 # 5060 <_sk_callback_sse2+0x7cd> + .byte 68,15,40,45,107,40,0,0 // movaps 0x286b(%rip),%xmm13 # 5250 <_sk_callback_sse2+0x7cc> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,123,38,0,0 // mulps 0x267b(%rip),%xmm13 # 5070 <_sk_callback_sse2+0x7dd> + .byte 68,15,89,45,107,40,0,0 // mulps 0x286b(%rip),%xmm13 # 5260 <_sk_callback_sse2+0x7dc> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -29234,15 +29913,15 @@ _sk_parametric_b_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,251,37,0,0 // mulps 0x25fb(%rip),%xmm9 # 5080 <_sk_callback_sse2+0x7ed> - .byte 68,15,84,21,3,38,0,0 // andps 0x2603(%rip),%xmm10 # 5090 <_sk_callback_sse2+0x7fd> - .byte 68,15,86,21,11,38,0,0 // orps 0x260b(%rip),%xmm10 # 50a0 <_sk_callback_sse2+0x80d> - .byte 68,15,88,13,19,38,0,0 // addps 0x2613(%rip),%xmm9 # 50b0 <_sk_callback_sse2+0x81d> - .byte 68,15,40,37,27,38,0,0 // movaps 0x261b(%rip),%xmm12 # 50c0 <_sk_callback_sse2+0x82d> + .byte 68,15,89,13,235,39,0,0 // mulps 0x27eb(%rip),%xmm9 # 5270 <_sk_callback_sse2+0x7ec> + .byte 68,15,84,21,243,39,0,0 // andps 0x27f3(%rip),%xmm10 # 5280 <_sk_callback_sse2+0x7fc> + .byte 68,15,86,21,251,39,0,0 // orps 0x27fb(%rip),%xmm10 # 5290 <_sk_callback_sse2+0x80c> + .byte 68,15,88,13,3,40,0,0 // addps 0x2803(%rip),%xmm9 # 52a0 <_sk_callback_sse2+0x81c> + .byte 68,15,40,37,11,40,0,0 // movaps 0x280b(%rip),%xmm12 # 52b0 <_sk_callback_sse2+0x82c> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,27,38,0,0 // addps 0x261b(%rip),%xmm10 # 50d0 <_sk_callback_sse2+0x83d> - .byte 68,15,40,37,35,38,0,0 // movaps 0x2623(%rip),%xmm12 # 50e0 <_sk_callback_sse2+0x84d> + .byte 68,15,88,21,11,40,0,0 // addps 0x280b(%rip),%xmm10 # 52c0 <_sk_callback_sse2+0x83c> + .byte 68,15,40,37,19,40,0,0 // movaps 0x2813(%rip),%xmm12 # 52d0 <_sk_callback_sse2+0x84c> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -29250,22 +29929,22 @@ _sk_parametric_b_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,13,38,0,0 // movaps 0x260d(%rip),%xmm10 # 50f0 <_sk_callback_sse2+0x85d> + .byte 68,15,40,21,253,39,0,0 // movaps 0x27fd(%rip),%xmm10 # 52e0 <_sk_callback_sse2+0x85c> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,1,38,0,0 // addps 0x2601(%rip),%xmm9 # 5100 <_sk_callback_sse2+0x86d> - .byte 68,15,40,37,9,38,0,0 // movaps 0x2609(%rip),%xmm12 # 5110 <_sk_callback_sse2+0x87d> + .byte 68,15,88,13,241,39,0,0 // addps 0x27f1(%rip),%xmm9 # 52f0 <_sk_callback_sse2+0x86c> + .byte 68,15,40,37,249,39,0,0 // movaps 0x27f9(%rip),%xmm12 # 5300 <_sk_callback_sse2+0x87c> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,9,38,0,0 // movaps 0x2609(%rip),%xmm12 # 5120 <_sk_callback_sse2+0x88d> + .byte 68,15,40,37,249,39,0,0 // movaps 0x27f9(%rip),%xmm12 # 5310 <_sk_callback_sse2+0x88c> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,13,38,0,0 // movaps 0x260d(%rip),%xmm13 # 5130 <_sk_callback_sse2+0x89d> + .byte 68,15,40,45,253,39,0,0 // movaps 0x27fd(%rip),%xmm13 # 5320 <_sk_callback_sse2+0x89c> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,13,38,0,0 // mulps 0x260d(%rip),%xmm13 # 5140 <_sk_callback_sse2+0x8ad> + .byte 68,15,89,45,253,39,0,0 // mulps 0x27fd(%rip),%xmm13 # 5330 <_sk_callback_sse2+0x8ac> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -29301,15 +29980,15 @@ _sk_parametric_a_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,141,37,0,0 // mulps 0x258d(%rip),%xmm9 # 5150 <_sk_callback_sse2+0x8bd> - .byte 68,15,84,21,149,37,0,0 // andps 0x2595(%rip),%xmm10 # 5160 <_sk_callback_sse2+0x8cd> - .byte 68,15,86,21,157,37,0,0 // orps 0x259d(%rip),%xmm10 # 5170 <_sk_callback_sse2+0x8dd> - .byte 68,15,88,13,165,37,0,0 // addps 0x25a5(%rip),%xmm9 # 5180 <_sk_callback_sse2+0x8ed> - .byte 68,15,40,37,173,37,0,0 // movaps 0x25ad(%rip),%xmm12 # 5190 <_sk_callback_sse2+0x8fd> + .byte 68,15,89,13,125,39,0,0 // mulps 0x277d(%rip),%xmm9 # 5340 <_sk_callback_sse2+0x8bc> + .byte 68,15,84,21,133,39,0,0 // andps 0x2785(%rip),%xmm10 # 5350 <_sk_callback_sse2+0x8cc> + .byte 68,15,86,21,141,39,0,0 // orps 0x278d(%rip),%xmm10 # 5360 <_sk_callback_sse2+0x8dc> + .byte 68,15,88,13,149,39,0,0 // addps 0x2795(%rip),%xmm9 # 5370 <_sk_callback_sse2+0x8ec> + .byte 68,15,40,37,157,39,0,0 // movaps 0x279d(%rip),%xmm12 # 5380 <_sk_callback_sse2+0x8fc> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,173,37,0,0 // addps 0x25ad(%rip),%xmm10 # 51a0 <_sk_callback_sse2+0x90d> - .byte 68,15,40,37,181,37,0,0 // movaps 0x25b5(%rip),%xmm12 # 51b0 <_sk_callback_sse2+0x91d> + .byte 68,15,88,21,157,39,0,0 // addps 0x279d(%rip),%xmm10 # 5390 <_sk_callback_sse2+0x90c> + .byte 68,15,40,37,165,39,0,0 // movaps 0x27a5(%rip),%xmm12 # 53a0 <_sk_callback_sse2+0x91c> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -29317,22 +29996,22 @@ _sk_parametric_a_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,159,37,0,0 // movaps 0x259f(%rip),%xmm10 # 51c0 <_sk_callback_sse2+0x92d> + .byte 68,15,40,21,143,39,0,0 // movaps 0x278f(%rip),%xmm10 # 53b0 <_sk_callback_sse2+0x92c> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,147,37,0,0 // addps 0x2593(%rip),%xmm9 # 51d0 <_sk_callback_sse2+0x93d> - .byte 68,15,40,37,155,37,0,0 // movaps 0x259b(%rip),%xmm12 # 51e0 <_sk_callback_sse2+0x94d> + .byte 68,15,88,13,131,39,0,0 // addps 0x2783(%rip),%xmm9 # 53c0 <_sk_callback_sse2+0x93c> + .byte 68,15,40,37,139,39,0,0 // movaps 0x278b(%rip),%xmm12 # 53d0 <_sk_callback_sse2+0x94c> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,155,37,0,0 // movaps 0x259b(%rip),%xmm12 # 51f0 <_sk_callback_sse2+0x95d> + .byte 68,15,40,37,139,39,0,0 // movaps 0x278b(%rip),%xmm12 # 53e0 <_sk_callback_sse2+0x95c> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,159,37,0,0 // movaps 0x259f(%rip),%xmm13 # 5200 <_sk_callback_sse2+0x96d> + .byte 68,15,40,45,143,39,0,0 // movaps 0x278f(%rip),%xmm13 # 53f0 <_sk_callback_sse2+0x96c> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,159,37,0,0 // mulps 0x259f(%rip),%xmm13 # 5210 <_sk_callback_sse2+0x97d> + .byte 68,15,89,45,143,39,0,0 // mulps 0x278f(%rip),%xmm13 # 5400 <_sk_callback_sse2+0x97c> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -29349,29 +30028,29 @@ HIDDEN _sk_lab_to_xyz_sse2 .globl _sk_lab_to_xyz_sse2 FUNCTION(_sk_lab_to_xyz_sse2) _sk_lab_to_xyz_sse2: - .byte 15,89,5,124,37,0,0 // mulps 0x257c(%rip),%xmm0 # 5220 <_sk_callback_sse2+0x98d> - .byte 68,15,40,5,132,37,0,0 // movaps 0x2584(%rip),%xmm8 # 5230 <_sk_callback_sse2+0x99d> + .byte 15,89,5,108,39,0,0 // mulps 0x276c(%rip),%xmm0 # 5410 <_sk_callback_sse2+0x98c> + .byte 68,15,40,5,116,39,0,0 // movaps 0x2774(%rip),%xmm8 # 5420 <_sk_callback_sse2+0x99c> .byte 65,15,89,200 // mulps %xmm8,%xmm1 - .byte 68,15,40,13,136,37,0,0 // movaps 0x2588(%rip),%xmm9 # 5240 <_sk_callback_sse2+0x9ad> + .byte 68,15,40,13,120,39,0,0 // movaps 0x2778(%rip),%xmm9 # 5430 <_sk_callback_sse2+0x9ac> .byte 65,15,88,201 // addps %xmm9,%xmm1 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 65,15,88,209 // addps %xmm9,%xmm2 - .byte 15,88,5,133,37,0,0 // addps 0x2585(%rip),%xmm0 # 5250 <_sk_callback_sse2+0x9bd> - .byte 15,89,5,142,37,0,0 // mulps 0x258e(%rip),%xmm0 # 5260 <_sk_callback_sse2+0x9cd> - .byte 15,89,13,151,37,0,0 // mulps 0x2597(%rip),%xmm1 # 5270 <_sk_callback_sse2+0x9dd> + .byte 15,88,5,117,39,0,0 // addps 0x2775(%rip),%xmm0 # 5440 <_sk_callback_sse2+0x9bc> + .byte 15,89,5,126,39,0,0 // mulps 0x277e(%rip),%xmm0 # 5450 <_sk_callback_sse2+0x9cc> + .byte 15,89,13,135,39,0,0 // mulps 0x2787(%rip),%xmm1 # 5460 <_sk_callback_sse2+0x9dc> .byte 15,88,200 // addps %xmm0,%xmm1 - .byte 15,89,21,157,37,0,0 // mulps 0x259d(%rip),%xmm2 # 5280 <_sk_callback_sse2+0x9ed> + .byte 15,89,21,141,39,0,0 // mulps 0x278d(%rip),%xmm2 # 5470 <_sk_callback_sse2+0x9ec> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 68,15,92,202 // subps %xmm2,%xmm9 .byte 68,15,40,225 // movaps %xmm1,%xmm12 .byte 69,15,89,228 // mulps %xmm12,%xmm12 .byte 68,15,89,225 // mulps %xmm1,%xmm12 - .byte 15,40,21,146,37,0,0 // movaps 0x2592(%rip),%xmm2 # 5290 <_sk_callback_sse2+0x9fd> + .byte 15,40,21,130,39,0,0 // movaps 0x2782(%rip),%xmm2 # 5480 <_sk_callback_sse2+0x9fc> .byte 68,15,40,194 // movaps %xmm2,%xmm8 .byte 69,15,194,196,1 // cmpltps %xmm12,%xmm8 - .byte 68,15,40,21,145,37,0,0 // movaps 0x2591(%rip),%xmm10 # 52a0 <_sk_callback_sse2+0xa0d> + .byte 68,15,40,21,129,39,0,0 // movaps 0x2781(%rip),%xmm10 # 5490 <_sk_callback_sse2+0xa0c> .byte 65,15,88,202 // addps %xmm10,%xmm1 - .byte 68,15,40,29,149,37,0,0 // movaps 0x2595(%rip),%xmm11 # 52b0 <_sk_callback_sse2+0xa1d> + .byte 68,15,40,29,133,39,0,0 // movaps 0x2785(%rip),%xmm11 # 54a0 <_sk_callback_sse2+0xa1c> .byte 65,15,89,203 // mulps %xmm11,%xmm1 .byte 69,15,84,224 // andps %xmm8,%xmm12 .byte 68,15,85,193 // andnps %xmm1,%xmm8 @@ -29395,8 +30074,8 @@ _sk_lab_to_xyz_sse2: .byte 15,84,194 // andps %xmm2,%xmm0 .byte 65,15,85,209 // andnps %xmm9,%xmm2 .byte 15,86,208 // orps %xmm0,%xmm2 - .byte 68,15,89,5,69,37,0,0 // mulps 0x2545(%rip),%xmm8 # 52c0 <_sk_callback_sse2+0xa2d> - .byte 15,89,21,78,37,0,0 // mulps 0x254e(%rip),%xmm2 # 52d0 <_sk_callback_sse2+0xa3d> + .byte 68,15,89,5,53,39,0,0 // mulps 0x2735(%rip),%xmm8 # 54b0 <_sk_callback_sse2+0xa2c> + .byte 15,89,21,62,39,0,0 // mulps 0x273e(%rip),%xmm2 # 54c0 <_sk_callback_sse2+0xa3c> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -29412,7 +30091,7 @@ _sk_load_a8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,54,37,0,0 // mulps 0x2536(%rip),%xmm3 # 52e0 <_sk_callback_sse2+0xa4d> + .byte 15,89,29,38,39,0,0 // mulps 0x2726(%rip),%xmm3 # 54d0 <_sk_callback_sse2+0xa4c> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 102,15,239,201 // pxor %xmm1,%xmm1 @@ -29457,7 +30136,7 @@ _sk_gather_a8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,165,36,0,0 // mulps 0x24a5(%rip),%xmm3 # 52f0 <_sk_callback_sse2+0xa5d> + .byte 15,89,29,149,38,0,0 // mulps 0x2695(%rip),%xmm3 # 54e0 <_sk_callback_sse2+0xa5c> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 102,15,239,201 // pxor %xmm1,%xmm1 @@ -29470,7 +30149,7 @@ FUNCTION(_sk_store_a8_sse2) _sk_store_a8_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,153,36,0,0 // movaps 0x2499(%rip),%xmm8 # 5300 <_sk_callback_sse2+0xa6d> + .byte 68,15,40,5,137,38,0,0 // movaps 0x2689(%rip),%xmm8 # 54f0 <_sk_callback_sse2+0xa6c> .byte 68,15,89,195 // mulps %xmm3,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 .byte 102,65,15,114,240,16 // pslld $0x10,%xmm8 @@ -29492,9 +30171,9 @@ _sk_load_g8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,96,36,0,0 // mulps 0x2460(%rip),%xmm0 # 5310 <_sk_callback_sse2+0xa7d> + .byte 15,89,5,80,38,0,0 // mulps 0x2650(%rip),%xmm0 # 5500 <_sk_callback_sse2+0xa7c> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,103,36,0,0 // movaps 0x2467(%rip),%xmm3 # 5320 <_sk_callback_sse2+0xa8d> + .byte 15,40,29,87,38,0,0 // movaps 0x2657(%rip),%xmm3 # 5510 <_sk_callback_sse2+0xa8c> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -29537,9 +30216,9 @@ _sk_gather_g8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,220,35,0,0 // mulps 0x23dc(%rip),%xmm0 # 5330 <_sk_callback_sse2+0xa9d> + .byte 15,89,5,204,37,0,0 // mulps 0x25cc(%rip),%xmm0 # 5520 <_sk_callback_sse2+0xa9c> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,227,35,0,0 // movaps 0x23e3(%rip),%xmm3 # 5340 <_sk_callback_sse2+0xaad> + .byte 15,40,29,211,37,0,0 // movaps 0x25d3(%rip),%xmm3 # 5530 <_sk_callback_sse2+0xaac> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -29602,11 +30281,11 @@ _sk_gather_i8_sse2: .byte 102,67,15,110,12,136 // movd (%r8,%r9,4),%xmm1 .byte 102,68,15,98,201 // punpckldq %xmm1,%xmm9 .byte 102,68,15,98,200 // punpckldq %xmm0,%xmm9 - .byte 102,15,111,21,2,35,0,0 // movdqa 0x2302(%rip),%xmm2 # 5350 <_sk_callback_sse2+0xabd> + .byte 102,15,111,21,242,36,0,0 // movdqa 0x24f2(%rip),%xmm2 # 5540 <_sk_callback_sse2+0xabc> .byte 102,65,15,111,193 // movdqa %xmm9,%xmm0 .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,254,34,0,0 // movaps 0x22fe(%rip),%xmm8 # 5360 <_sk_callback_sse2+0xacd> + .byte 68,15,40,5,238,36,0,0 // movaps 0x24ee(%rip),%xmm8 # 5550 <_sk_callback_sse2+0xacc> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,114,209,8 // psrld $0x8,%xmm1 @@ -29633,19 +30312,19 @@ _sk_load_565_sse2: .byte 243,15,126,20,120 // movq (%rax,%rdi,2),%xmm2 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,208 // punpcklwd %xmm0,%xmm2 - .byte 102,15,111,5,180,34,0,0 // movdqa 0x22b4(%rip),%xmm0 # 5370 <_sk_callback_sse2+0xadd> + .byte 102,15,111,5,164,36,0,0 // movdqa 0x24a4(%rip),%xmm0 # 5560 <_sk_callback_sse2+0xadc> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,182,34,0,0 // mulps 0x22b6(%rip),%xmm0 # 5380 <_sk_callback_sse2+0xaed> - .byte 102,15,111,13,190,34,0,0 // movdqa 0x22be(%rip),%xmm1 # 5390 <_sk_callback_sse2+0xafd> + .byte 15,89,5,166,36,0,0 // mulps 0x24a6(%rip),%xmm0 # 5570 <_sk_callback_sse2+0xaec> + .byte 102,15,111,13,174,36,0,0 // movdqa 0x24ae(%rip),%xmm1 # 5580 <_sk_callback_sse2+0xafc> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,192,34,0,0 // mulps 0x22c0(%rip),%xmm1 # 53a0 <_sk_callback_sse2+0xb0d> - .byte 102,15,219,21,200,34,0,0 // pand 0x22c8(%rip),%xmm2 # 53b0 <_sk_callback_sse2+0xb1d> + .byte 15,89,13,176,36,0,0 // mulps 0x24b0(%rip),%xmm1 # 5590 <_sk_callback_sse2+0xb0c> + .byte 102,15,219,21,184,36,0,0 // pand 0x24b8(%rip),%xmm2 # 55a0 <_sk_callback_sse2+0xb1c> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,206,34,0,0 // mulps 0x22ce(%rip),%xmm2 # 53c0 <_sk_callback_sse2+0xb2d> + .byte 15,89,21,190,36,0,0 // mulps 0x24be(%rip),%xmm2 # 55b0 <_sk_callback_sse2+0xb2c> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,213,34,0,0 // movaps 0x22d5(%rip),%xmm3 # 53d0 <_sk_callback_sse2+0xb3d> + .byte 15,40,29,197,36,0,0 // movaps 0x24c5(%rip),%xmm3 # 55c0 <_sk_callback_sse2+0xb3c> .byte 255,224 // jmpq *%rax HIDDEN _sk_gather_565_sse2 @@ -29680,19 +30359,19 @@ _sk_gather_565_sse2: .byte 102,15,196,208,3 // pinsrw $0x3,%eax,%xmm2 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,208 // punpcklwd %xmm0,%xmm2 - .byte 102,15,111,5,94,34,0,0 // movdqa 0x225e(%rip),%xmm0 # 53e0 <_sk_callback_sse2+0xb4d> + .byte 102,15,111,5,78,36,0,0 // movdqa 0x244e(%rip),%xmm0 # 55d0 <_sk_callback_sse2+0xb4c> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,96,34,0,0 // mulps 0x2260(%rip),%xmm0 # 53f0 <_sk_callback_sse2+0xb5d> - .byte 102,15,111,13,104,34,0,0 // movdqa 0x2268(%rip),%xmm1 # 5400 <_sk_callback_sse2+0xb6d> + .byte 15,89,5,80,36,0,0 // mulps 0x2450(%rip),%xmm0 # 55e0 <_sk_callback_sse2+0xb5c> + .byte 102,15,111,13,88,36,0,0 // movdqa 0x2458(%rip),%xmm1 # 55f0 <_sk_callback_sse2+0xb6c> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,106,34,0,0 // mulps 0x226a(%rip),%xmm1 # 5410 <_sk_callback_sse2+0xb7d> - .byte 102,15,219,21,114,34,0,0 // pand 0x2272(%rip),%xmm2 # 5420 <_sk_callback_sse2+0xb8d> + .byte 15,89,13,90,36,0,0 // mulps 0x245a(%rip),%xmm1 # 5600 <_sk_callback_sse2+0xb7c> + .byte 102,15,219,21,98,36,0,0 // pand 0x2462(%rip),%xmm2 # 5610 <_sk_callback_sse2+0xb8c> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,120,34,0,0 // mulps 0x2278(%rip),%xmm2 # 5430 <_sk_callback_sse2+0xb9d> + .byte 15,89,21,104,36,0,0 // mulps 0x2468(%rip),%xmm2 # 5620 <_sk_callback_sse2+0xb9c> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,127,34,0,0 // movaps 0x227f(%rip),%xmm3 # 5440 <_sk_callback_sse2+0xbad> + .byte 15,40,29,111,36,0,0 // movaps 0x246f(%rip),%xmm3 # 5630 <_sk_callback_sse2+0xbac> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_565_sse2 @@ -29701,12 +30380,12 @@ FUNCTION(_sk_store_565_sse2) _sk_store_565_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,128,34,0,0 // movaps 0x2280(%rip),%xmm8 # 5450 <_sk_callback_sse2+0xbbd> + .byte 68,15,40,5,112,36,0,0 // movaps 0x2470(%rip),%xmm8 # 5640 <_sk_callback_sse2+0xbbc> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 .byte 102,65,15,114,241,11 // pslld $0xb,%xmm9 - .byte 68,15,40,21,117,34,0,0 // movaps 0x2275(%rip),%xmm10 # 5460 <_sk_callback_sse2+0xbcd> + .byte 68,15,40,21,101,36,0,0 // movaps 0x2465(%rip),%xmm10 # 5650 <_sk_callback_sse2+0xbcc> .byte 68,15,89,209 // mulps %xmm1,%xmm10 .byte 102,69,15,91,210 // cvtps2dq %xmm10,%xmm10 .byte 102,65,15,114,242,5 // pslld $0x5,%xmm10 @@ -29730,21 +30409,21 @@ _sk_load_4444_sse2: .byte 243,15,126,28,120 // movq (%rax,%rdi,2),%xmm3 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,216 // punpcklwd %xmm0,%xmm3 - .byte 102,15,111,5,46,34,0,0 // movdqa 0x222e(%rip),%xmm0 # 5470 <_sk_callback_sse2+0xbdd> + .byte 102,15,111,5,30,36,0,0 // movdqa 0x241e(%rip),%xmm0 # 5660 <_sk_callback_sse2+0xbdc> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,48,34,0,0 // mulps 0x2230(%rip),%xmm0 # 5480 <_sk_callback_sse2+0xbed> - .byte 102,15,111,13,56,34,0,0 // movdqa 0x2238(%rip),%xmm1 # 5490 <_sk_callback_sse2+0xbfd> + .byte 15,89,5,32,36,0,0 // mulps 0x2420(%rip),%xmm0 # 5670 <_sk_callback_sse2+0xbec> + .byte 102,15,111,13,40,36,0,0 // movdqa 0x2428(%rip),%xmm1 # 5680 <_sk_callback_sse2+0xbfc> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,58,34,0,0 // mulps 0x223a(%rip),%xmm1 # 54a0 <_sk_callback_sse2+0xc0d> - .byte 102,15,111,21,66,34,0,0 // movdqa 0x2242(%rip),%xmm2 # 54b0 <_sk_callback_sse2+0xc1d> + .byte 15,89,13,42,36,0,0 // mulps 0x242a(%rip),%xmm1 # 5690 <_sk_callback_sse2+0xc0c> + .byte 102,15,111,21,50,36,0,0 // movdqa 0x2432(%rip),%xmm2 # 56a0 <_sk_callback_sse2+0xc1c> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,68,34,0,0 // mulps 0x2244(%rip),%xmm2 # 54c0 <_sk_callback_sse2+0xc2d> - .byte 102,15,219,29,76,34,0,0 // pand 0x224c(%rip),%xmm3 # 54d0 <_sk_callback_sse2+0xc3d> + .byte 15,89,21,52,36,0,0 // mulps 0x2434(%rip),%xmm2 # 56b0 <_sk_callback_sse2+0xc2c> + .byte 102,15,219,29,60,36,0,0 // pand 0x243c(%rip),%xmm3 # 56c0 <_sk_callback_sse2+0xc3c> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,82,34,0,0 // mulps 0x2252(%rip),%xmm3 # 54e0 <_sk_callback_sse2+0xc4d> + .byte 15,89,29,66,36,0,0 // mulps 0x2442(%rip),%xmm3 # 56d0 <_sk_callback_sse2+0xc4c> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -29780,21 +30459,21 @@ _sk_gather_4444_sse2: .byte 102,15,196,216,3 // pinsrw $0x3,%eax,%xmm3 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,216 // punpcklwd %xmm0,%xmm3 - .byte 102,15,111,5,217,33,0,0 // movdqa 0x21d9(%rip),%xmm0 # 54f0 <_sk_callback_sse2+0xc5d> + .byte 102,15,111,5,201,35,0,0 // movdqa 0x23c9(%rip),%xmm0 # 56e0 <_sk_callback_sse2+0xc5c> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,219,33,0,0 // mulps 0x21db(%rip),%xmm0 # 5500 <_sk_callback_sse2+0xc6d> - .byte 102,15,111,13,227,33,0,0 // movdqa 0x21e3(%rip),%xmm1 # 5510 <_sk_callback_sse2+0xc7d> + .byte 15,89,5,203,35,0,0 // mulps 0x23cb(%rip),%xmm0 # 56f0 <_sk_callback_sse2+0xc6c> + .byte 102,15,111,13,211,35,0,0 // movdqa 0x23d3(%rip),%xmm1 # 5700 <_sk_callback_sse2+0xc7c> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,229,33,0,0 // mulps 0x21e5(%rip),%xmm1 # 5520 <_sk_callback_sse2+0xc8d> - .byte 102,15,111,21,237,33,0,0 // movdqa 0x21ed(%rip),%xmm2 # 5530 <_sk_callback_sse2+0xc9d> + .byte 15,89,13,213,35,0,0 // mulps 0x23d5(%rip),%xmm1 # 5710 <_sk_callback_sse2+0xc8c> + .byte 102,15,111,21,221,35,0,0 // movdqa 0x23dd(%rip),%xmm2 # 5720 <_sk_callback_sse2+0xc9c> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,239,33,0,0 // mulps 0x21ef(%rip),%xmm2 # 5540 <_sk_callback_sse2+0xcad> - .byte 102,15,219,29,247,33,0,0 // pand 0x21f7(%rip),%xmm3 # 5550 <_sk_callback_sse2+0xcbd> + .byte 15,89,21,223,35,0,0 // mulps 0x23df(%rip),%xmm2 # 5730 <_sk_callback_sse2+0xcac> + .byte 102,15,219,29,231,35,0,0 // pand 0x23e7(%rip),%xmm3 # 5740 <_sk_callback_sse2+0xcbc> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,253,33,0,0 // mulps 0x21fd(%rip),%xmm3 # 5560 <_sk_callback_sse2+0xccd> + .byte 15,89,29,237,35,0,0 // mulps 0x23ed(%rip),%xmm3 # 5750 <_sk_callback_sse2+0xccc> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -29804,7 +30483,7 @@ FUNCTION(_sk_store_4444_sse2) _sk_store_4444_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,252,33,0,0 // movaps 0x21fc(%rip),%xmm8 # 5570 <_sk_callback_sse2+0xcdd> + .byte 68,15,40,5,236,35,0,0 // movaps 0x23ec(%rip),%xmm8 # 5760 <_sk_callback_sse2+0xcdc> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -29836,11 +30515,11 @@ _sk_load_8888_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 68,15,16,12,184 // movups (%rax,%rdi,4),%xmm9 - .byte 15,40,21,143,33,0,0 // movaps 0x218f(%rip),%xmm2 # 5580 <_sk_callback_sse2+0xced> + .byte 15,40,21,127,35,0,0 // movaps 0x237f(%rip),%xmm2 # 5770 <_sk_callback_sse2+0xcec> .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 15,84,194 // andps %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,141,33,0,0 // movaps 0x218d(%rip),%xmm8 # 5590 <_sk_callback_sse2+0xcfd> + .byte 68,15,40,5,125,35,0,0 // movaps 0x237d(%rip),%xmm8 # 5780 <_sk_callback_sse2+0xcfc> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,40,201 // movaps %xmm9,%xmm1 .byte 102,15,114,209,8 // psrld $0x8,%xmm1 @@ -29889,11 +30568,11 @@ _sk_gather_8888_sse2: .byte 102,67,15,110,12,129 // movd (%r9,%r8,4),%xmm1 .byte 102,68,15,98,201 // punpckldq %xmm1,%xmm9 .byte 102,68,15,98,200 // punpckldq %xmm0,%xmm9 - .byte 102,15,111,21,222,32,0,0 // movdqa 0x20de(%rip),%xmm2 # 55a0 <_sk_callback_sse2+0xd0d> + .byte 102,15,111,21,206,34,0,0 // movdqa 0x22ce(%rip),%xmm2 # 5790 <_sk_callback_sse2+0xd0c> .byte 102,65,15,111,193 // movdqa %xmm9,%xmm0 .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,218,32,0,0 // movaps 0x20da(%rip),%xmm8 # 55b0 <_sk_callback_sse2+0xd1d> + .byte 68,15,40,5,202,34,0,0 // movaps 0x22ca(%rip),%xmm8 # 57a0 <_sk_callback_sse2+0xd1c> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,114,209,8 // psrld $0x8,%xmm1 @@ -29917,7 +30596,7 @@ FUNCTION(_sk_store_8888_sse2) _sk_store_8888_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,157,32,0,0 // movaps 0x209d(%rip),%xmm8 # 55c0 <_sk_callback_sse2+0xd2d> + .byte 68,15,40,5,141,34,0,0 // movaps 0x228d(%rip),%xmm8 # 57b0 <_sk_callback_sse2+0xd2c> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -29956,7 +30635,7 @@ _sk_load_f16_sse2: .byte 102,69,15,239,210 // pxor %xmm10,%xmm10 .byte 102,65,15,111,206 // movdqa %xmm14,%xmm1 .byte 102,65,15,97,202 // punpcklwd %xmm10,%xmm1 - .byte 102,68,15,111,13,13,32,0,0 // movdqa 0x200d(%rip),%xmm9 # 55d0 <_sk_callback_sse2+0xd3d> + .byte 102,68,15,111,13,253,33,0,0 // movdqa 0x21fd(%rip),%xmm9 # 57c0 <_sk_callback_sse2+0xd3c> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,193 // pand %xmm9,%xmm0 .byte 102,15,239,200 // pxor %xmm0,%xmm1 @@ -29964,11 +30643,11 @@ _sk_load_f16_sse2: .byte 102,68,15,111,233 // movdqa %xmm1,%xmm13 .byte 102,65,15,114,245,13 // pslld $0xd,%xmm13 .byte 102,68,15,235,232 // por %xmm0,%xmm13 - .byte 102,68,15,111,29,242,31,0,0 // movdqa 0x1ff2(%rip),%xmm11 # 55e0 <_sk_callback_sse2+0xd4d> + .byte 102,68,15,111,29,226,33,0,0 // movdqa 0x21e2(%rip),%xmm11 # 57d0 <_sk_callback_sse2+0xd4c> .byte 102,69,15,254,235 // paddd %xmm11,%xmm13 - .byte 102,68,15,111,37,244,31,0,0 // movdqa 0x1ff4(%rip),%xmm12 # 55f0 <_sk_callback_sse2+0xd5d> + .byte 102,68,15,111,37,228,33,0,0 // movdqa 0x21e4(%rip),%xmm12 # 57e0 <_sk_callback_sse2+0xd5c> .byte 102,65,15,239,204 // pxor %xmm12,%xmm1 - .byte 102,15,111,29,247,31,0,0 // movdqa 0x1ff7(%rip),%xmm3 # 5600 <_sk_callback_sse2+0xd6d> + .byte 102,15,111,29,231,33,0,0 // movdqa 0x21e7(%rip),%xmm3 # 57f0 <_sk_callback_sse2+0xd6c> .byte 102,15,111,195 // movdqa %xmm3,%xmm0 .byte 102,15,102,193 // pcmpgtd %xmm1,%xmm0 .byte 102,65,15,223,197 // pandn %xmm13,%xmm0 @@ -30054,7 +30733,7 @@ _sk_gather_f16_sse2: .byte 102,69,15,239,210 // pxor %xmm10,%xmm10 .byte 102,65,15,111,206 // movdqa %xmm14,%xmm1 .byte 102,65,15,97,202 // punpcklwd %xmm10,%xmm1 - .byte 102,68,15,111,13,133,30,0,0 // movdqa 0x1e85(%rip),%xmm9 # 5610 <_sk_callback_sse2+0xd7d> + .byte 102,68,15,111,13,117,32,0,0 // movdqa 0x2075(%rip),%xmm9 # 5800 <_sk_callback_sse2+0xd7c> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,193 // pand %xmm9,%xmm0 .byte 102,15,239,200 // pxor %xmm0,%xmm1 @@ -30062,11 +30741,11 @@ _sk_gather_f16_sse2: .byte 102,68,15,111,233 // movdqa %xmm1,%xmm13 .byte 102,65,15,114,245,13 // pslld $0xd,%xmm13 .byte 102,68,15,235,232 // por %xmm0,%xmm13 - .byte 102,68,15,111,29,106,30,0,0 // movdqa 0x1e6a(%rip),%xmm11 # 5620 <_sk_callback_sse2+0xd8d> + .byte 102,68,15,111,29,90,32,0,0 // movdqa 0x205a(%rip),%xmm11 # 5810 <_sk_callback_sse2+0xd8c> .byte 102,69,15,254,235 // paddd %xmm11,%xmm13 - .byte 102,68,15,111,37,108,30,0,0 // movdqa 0x1e6c(%rip),%xmm12 # 5630 <_sk_callback_sse2+0xd9d> + .byte 102,68,15,111,37,92,32,0,0 // movdqa 0x205c(%rip),%xmm12 # 5820 <_sk_callback_sse2+0xd9c> .byte 102,65,15,239,204 // pxor %xmm12,%xmm1 - .byte 102,15,111,29,111,30,0,0 // movdqa 0x1e6f(%rip),%xmm3 # 5640 <_sk_callback_sse2+0xdad> + .byte 102,15,111,29,95,32,0,0 // movdqa 0x205f(%rip),%xmm3 # 5830 <_sk_callback_sse2+0xdac> .byte 102,15,111,195 // movdqa %xmm3,%xmm0 .byte 102,15,102,193 // pcmpgtd %xmm1,%xmm0 .byte 102,65,15,223,197 // pandn %xmm13,%xmm0 @@ -30119,17 +30798,17 @@ FUNCTION(_sk_store_f16_sse2) _sk_store_f16_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 102,68,15,111,21,151,29,0,0 // movdqa 0x1d97(%rip),%xmm10 # 5650 <_sk_callback_sse2+0xdbd> + .byte 102,68,15,111,21,135,31,0,0 // movdqa 0x1f87(%rip),%xmm10 # 5840 <_sk_callback_sse2+0xdbc> .byte 102,68,15,111,224 // movdqa %xmm0,%xmm12 .byte 102,68,15,111,232 // movdqa %xmm0,%xmm13 .byte 102,69,15,219,234 // pand %xmm10,%xmm13 .byte 102,69,15,239,229 // pxor %xmm13,%xmm12 - .byte 102,68,15,111,13,138,29,0,0 // movdqa 0x1d8a(%rip),%xmm9 # 5660 <_sk_callback_sse2+0xdcd> + .byte 102,68,15,111,13,122,31,0,0 // movdqa 0x1f7a(%rip),%xmm9 # 5850 <_sk_callback_sse2+0xdcc> .byte 102,65,15,114,213,16 // psrld $0x10,%xmm13 .byte 102,69,15,111,193 // movdqa %xmm9,%xmm8 .byte 102,69,15,102,196 // pcmpgtd %xmm12,%xmm8 .byte 102,65,15,114,212,13 // psrld $0xd,%xmm12 - .byte 102,68,15,111,29,123,29,0,0 // movdqa 0x1d7b(%rip),%xmm11 # 5670 <_sk_callback_sse2+0xddd> + .byte 102,68,15,111,29,107,31,0,0 // movdqa 0x1f6b(%rip),%xmm11 # 5860 <_sk_callback_sse2+0xddc> .byte 102,69,15,235,235 // por %xmm11,%xmm13 .byte 102,69,15,254,236 // paddd %xmm12,%xmm13 .byte 102,65,15,114,245,16 // pslld $0x10,%xmm13 @@ -30208,7 +30887,7 @@ _sk_load_u16_be_sse2: .byte 102,69,15,239,201 // pxor %xmm9,%xmm9 .byte 102,65,15,97,201 // punpcklwd %xmm9,%xmm1 .byte 15,91,193 // cvtdq2ps %xmm1,%xmm0 - .byte 68,15,40,5,25,28,0,0 // movaps 0x1c19(%rip),%xmm8 # 5680 <_sk_callback_sse2+0xded> + .byte 68,15,40,5,9,30,0,0 // movaps 0x1e09(%rip),%xmm8 # 5870 <_sk_callback_sse2+0xdec> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -30261,7 +30940,7 @@ _sk_load_rgb_u16_be_sse2: .byte 102,69,15,239,192 // pxor %xmm8,%xmm8 .byte 102,65,15,97,192 // punpcklwd %xmm8,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,13,85,27,0,0 // movaps 0x1b55(%rip),%xmm9 # 5690 <_sk_callback_sse2+0xdfd> + .byte 68,15,40,13,69,29,0,0 // movaps 0x1d45(%rip),%xmm9 # 5880 <_sk_callback_sse2+0xdfc> .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -30278,7 +30957,7 @@ _sk_load_rgb_u16_be_sse2: .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,209 // mulps %xmm9,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,28,27,0,0 // movaps 0x1b1c(%rip),%xmm3 # 56a0 <_sk_callback_sse2+0xe0d> + .byte 15,40,29,12,29,0,0 // movaps 0x1d0c(%rip),%xmm3 # 5890 <_sk_callback_sse2+0xe0c> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_u16_be_sse2 @@ -30287,7 +30966,7 @@ FUNCTION(_sk_store_u16_be_sse2) _sk_store_u16_be_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,13,29,27,0,0 // movaps 0x1b1d(%rip),%xmm9 # 56b0 <_sk_callback_sse2+0xe1d> + .byte 68,15,40,13,13,29,0,0 // movaps 0x1d0d(%rip),%xmm9 # 58a0 <_sk_callback_sse2+0xe1c> .byte 68,15,40,192 // movaps %xmm0,%xmm8 .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 @@ -30433,7 +31112,7 @@ _sk_repeat_x_sse2: .byte 243,69,15,91,209 // cvttps2dq %xmm9,%xmm10 .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 .byte 69,15,194,202,1 // cmpltps %xmm10,%xmm9 - .byte 68,15,84,13,29,25,0,0 // andps 0x191d(%rip),%xmm9 # 56c0 <_sk_callback_sse2+0xe2d> + .byte 68,15,84,13,13,27,0,0 // andps 0x1b0d(%rip),%xmm9 # 58b0 <_sk_callback_sse2+0xe2c> .byte 69,15,92,209 // subps %xmm9,%xmm10 .byte 69,15,89,208 // mulps %xmm8,%xmm10 .byte 65,15,92,194 // subps %xmm10,%xmm0 @@ -30453,7 +31132,7 @@ _sk_repeat_y_sse2: .byte 243,69,15,91,209 // cvttps2dq %xmm9,%xmm10 .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 .byte 69,15,194,202,1 // cmpltps %xmm10,%xmm9 - .byte 68,15,84,13,239,24,0,0 // andps 0x18ef(%rip),%xmm9 # 56d0 <_sk_callback_sse2+0xe3d> + .byte 68,15,84,13,223,26,0,0 // andps 0x1adf(%rip),%xmm9 # 58c0 <_sk_callback_sse2+0xe3c> .byte 69,15,92,209 // subps %xmm9,%xmm10 .byte 69,15,89,208 // mulps %xmm8,%xmm10 .byte 65,15,92,202 // subps %xmm10,%xmm1 @@ -30477,7 +31156,7 @@ _sk_mirror_x_sse2: .byte 243,69,15,91,218 // cvttps2dq %xmm10,%xmm11 .byte 69,15,91,219 // cvtdq2ps %xmm11,%xmm11 .byte 69,15,194,211,1 // cmpltps %xmm11,%xmm10 - .byte 68,15,84,21,175,24,0,0 // andps 0x18af(%rip),%xmm10 # 56e0 <_sk_callback_sse2+0xe4d> + .byte 68,15,84,21,159,26,0,0 // andps 0x1a9f(%rip),%xmm10 # 58d0 <_sk_callback_sse2+0xe4c> .byte 69,15,87,228 // xorps %xmm12,%xmm12 .byte 69,15,92,218 // subps %xmm10,%xmm11 .byte 69,15,89,216 // mulps %xmm8,%xmm11 @@ -30505,7 +31184,7 @@ _sk_mirror_y_sse2: .byte 243,69,15,91,218 // cvttps2dq %xmm10,%xmm11 .byte 69,15,91,219 // cvtdq2ps %xmm11,%xmm11 .byte 69,15,194,211,1 // cmpltps %xmm11,%xmm10 - .byte 68,15,84,21,95,24,0,0 // andps 0x185f(%rip),%xmm10 # 56f0 <_sk_callback_sse2+0xe5d> + .byte 68,15,84,21,79,26,0,0 // andps 0x1a4f(%rip),%xmm10 # 58e0 <_sk_callback_sse2+0xe5c> .byte 69,15,87,228 // xorps %xmm12,%xmm12 .byte 69,15,92,218 // subps %xmm10,%xmm11 .byte 69,15,89,216 // mulps %xmm8,%xmm11 @@ -30522,10 +31201,10 @@ HIDDEN _sk_luminance_to_alpha_sse2 FUNCTION(_sk_luminance_to_alpha_sse2) _sk_luminance_to_alpha_sse2: .byte 15,40,218 // movaps %xmm2,%xmm3 - .byte 15,89,5,65,24,0,0 // mulps 0x1841(%rip),%xmm0 # 5700 <_sk_callback_sse2+0xe6d> - .byte 15,89,13,74,24,0,0 // mulps 0x184a(%rip),%xmm1 # 5710 <_sk_callback_sse2+0xe7d> + .byte 15,89,5,49,26,0,0 // mulps 0x1a31(%rip),%xmm0 # 58f0 <_sk_callback_sse2+0xe6c> + .byte 15,89,13,58,26,0,0 // mulps 0x1a3a(%rip),%xmm1 # 5900 <_sk_callback_sse2+0xe7c> .byte 15,88,200 // addps %xmm0,%xmm1 - .byte 15,89,29,80,24,0,0 // mulps 0x1850(%rip),%xmm3 # 5720 <_sk_callback_sse2+0xe8d> + .byte 15,89,29,64,26,0,0 // mulps 0x1a40(%rip),%xmm3 # 5910 <_sk_callback_sse2+0xe8c> .byte 15,88,217 // addps %xmm1,%xmm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 @@ -30743,88 +31422,203 @@ _sk_matrix_perspective_sse2: .byte 65,15,40,201 // movaps %xmm9,%xmm1 .byte 255,224 // jmpq *%rax +HIDDEN _sk_evenly_spaced_gradient_sse2 +.globl _sk_evenly_spaced_gradient_sse2 +FUNCTION(_sk_evenly_spaced_gradient_sse2) +_sk_evenly_spaced_gradient_sse2: + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 72,139,8 // mov (%rax),%rcx + .byte 76,139,88,8 // mov 0x8(%rax),%r11 + .byte 72,255,201 // dec %rcx + .byte 120,7 // js 424f <_sk_evenly_spaced_gradient_sse2+0x15> + .byte 243,72,15,42,201 // cvtsi2ss %rcx,%xmm1 + .byte 235,21 // jmp 4264 <_sk_evenly_spaced_gradient_sse2+0x2a> + .byte 73,137,200 // mov %rcx,%r8 + .byte 73,209,232 // shr %r8 + .byte 131,225,1 // and $0x1,%ecx + .byte 76,9,193 // or %r8,%rcx + .byte 243,72,15,42,201 // cvtsi2ss %rcx,%xmm1 + .byte 243,15,88,201 // addss %xmm1,%xmm1 + .byte 15,198,201,0 // shufps $0x0,%xmm1,%xmm1 + .byte 15,89,200 // mulps %xmm0,%xmm1 + .byte 243,15,91,201 // cvttps2dq %xmm1,%xmm1 + .byte 102,15,112,209,78 // pshufd $0x4e,%xmm1,%xmm2 + .byte 102,73,15,126,210 // movq %xmm2,%r10 + .byte 69,137,208 // mov %r10d,%r8d + .byte 73,193,234,32 // shr $0x20,%r10 + .byte 102,72,15,126,201 // movq %xmm1,%rcx + .byte 65,137,201 // mov %ecx,%r9d + .byte 72,193,233,32 // shr $0x20,%rcx + .byte 243,65,15,16,12,139 // movss (%r11,%rcx,4),%xmm1 + .byte 243,67,15,16,20,147 // movss (%r11,%r10,4),%xmm2 + .byte 15,20,202 // unpcklps %xmm2,%xmm1 + .byte 243,71,15,16,4,139 // movss (%r11,%r9,4),%xmm8 + .byte 243,67,15,16,20,131 // movss (%r11,%r8,4),%xmm2 + .byte 68,15,20,194 // unpcklps %xmm2,%xmm8 + .byte 68,15,20,193 // unpcklps %xmm1,%xmm8 + .byte 76,139,88,40 // mov 0x28(%rax),%r11 + .byte 243,65,15,16,12,139 // movss (%r11,%rcx,4),%xmm1 + .byte 243,67,15,16,20,147 // movss (%r11,%r10,4),%xmm2 + .byte 15,20,202 // unpcklps %xmm2,%xmm1 + .byte 243,71,15,16,12,139 // movss (%r11,%r9,4),%xmm9 + .byte 243,67,15,16,20,131 // movss (%r11,%r8,4),%xmm2 + .byte 68,15,20,202 // unpcklps %xmm2,%xmm9 + .byte 68,15,20,201 // unpcklps %xmm1,%xmm9 + .byte 76,139,88,16 // mov 0x10(%rax),%r11 + .byte 243,65,15,16,20,139 // movss (%r11,%rcx,4),%xmm2 + .byte 243,67,15,16,12,147 // movss (%r11,%r10,4),%xmm1 + .byte 15,20,209 // unpcklps %xmm1,%xmm2 + .byte 243,67,15,16,12,139 // movss (%r11,%r9,4),%xmm1 + .byte 243,67,15,16,28,131 // movss (%r11,%r8,4),%xmm3 + .byte 15,20,203 // unpcklps %xmm3,%xmm1 + .byte 15,20,202 // unpcklps %xmm2,%xmm1 + .byte 76,139,88,48 // mov 0x30(%rax),%r11 + .byte 243,65,15,16,20,139 // movss (%r11,%rcx,4),%xmm2 + .byte 243,67,15,16,28,147 // movss (%r11,%r10,4),%xmm3 + .byte 15,20,211 // unpcklps %xmm3,%xmm2 + .byte 243,71,15,16,20,139 // movss (%r11,%r9,4),%xmm10 + .byte 243,67,15,16,28,131 // movss (%r11,%r8,4),%xmm3 + .byte 68,15,20,211 // unpcklps %xmm3,%xmm10 + .byte 68,15,20,210 // unpcklps %xmm2,%xmm10 + .byte 76,139,88,24 // mov 0x18(%rax),%r11 + .byte 243,69,15,16,28,139 // movss (%r11,%rcx,4),%xmm11 + .byte 243,67,15,16,20,147 // movss (%r11,%r10,4),%xmm2 + .byte 68,15,20,218 // unpcklps %xmm2,%xmm11 + .byte 243,67,15,16,20,139 // movss (%r11,%r9,4),%xmm2 + .byte 243,67,15,16,28,131 // movss (%r11,%r8,4),%xmm3 + .byte 15,20,211 // unpcklps %xmm3,%xmm2 + .byte 65,15,20,211 // unpcklps %xmm11,%xmm2 + .byte 76,139,88,56 // mov 0x38(%rax),%r11 + .byte 243,69,15,16,36,139 // movss (%r11,%rcx,4),%xmm12 + .byte 243,67,15,16,28,147 // movss (%r11,%r10,4),%xmm3 + .byte 68,15,20,227 // unpcklps %xmm3,%xmm12 + .byte 243,71,15,16,28,139 // movss (%r11,%r9,4),%xmm11 + .byte 243,67,15,16,28,131 // movss (%r11,%r8,4),%xmm3 + .byte 68,15,20,219 // unpcklps %xmm3,%xmm11 + .byte 69,15,20,220 // unpcklps %xmm12,%xmm11 + .byte 76,139,88,32 // mov 0x20(%rax),%r11 + .byte 243,69,15,16,36,139 // movss (%r11,%rcx,4),%xmm12 + .byte 243,67,15,16,28,147 // movss (%r11,%r10,4),%xmm3 + .byte 68,15,20,227 // unpcklps %xmm3,%xmm12 + .byte 243,67,15,16,28,139 // movss (%r11,%r9,4),%xmm3 + .byte 243,71,15,16,44,131 // movss (%r11,%r8,4),%xmm13 + .byte 65,15,20,221 // unpcklps %xmm13,%xmm3 + .byte 65,15,20,220 // unpcklps %xmm12,%xmm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 243,68,15,16,36,136 // movss (%rax,%rcx,4),%xmm12 + .byte 243,70,15,16,44,144 // movss (%rax,%r10,4),%xmm13 + .byte 69,15,20,229 // unpcklps %xmm13,%xmm12 + .byte 243,70,15,16,44,136 // movss (%rax,%r9,4),%xmm13 + .byte 243,70,15,16,52,128 // movss (%rax,%r8,4),%xmm14 + .byte 69,15,20,238 // unpcklps %xmm14,%xmm13 + .byte 69,15,20,236 // unpcklps %xmm12,%xmm13 + .byte 68,15,89,192 // mulps %xmm0,%xmm8 + .byte 69,15,88,193 // addps %xmm9,%xmm8 + .byte 15,89,200 // mulps %xmm0,%xmm1 + .byte 65,15,88,202 // addps %xmm10,%xmm1 + .byte 15,89,208 // mulps %xmm0,%xmm2 + .byte 65,15,88,211 // addps %xmm11,%xmm2 + .byte 15,89,216 // mulps %xmm0,%xmm3 + .byte 65,15,88,221 // addps %xmm13,%xmm3 + .byte 72,173 // lods %ds:(%rsi),%rax + .byte 65,15,40,192 // movaps %xmm8,%xmm0 + .byte 255,224 // jmpq *%rax + HIDDEN _sk_gradient_sse2 .globl _sk_gradient_sse2 FUNCTION(_sk_gradient_sse2) _sk_gradient_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 243,68,15,16,72,16 // movss 0x10(%rax),%xmm9 - .byte 69,15,198,201,0 // shufps $0x0,%xmm9,%xmm9 - .byte 243,68,15,16,80,20 // movss 0x14(%rax),%xmm10 - .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 - .byte 243,68,15,16,88,24 // movss 0x18(%rax),%xmm11 - .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 - .byte 243,68,15,16,96,28 // movss 0x1c(%rax),%xmm12 - .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 - .byte 72,139,8 // mov (%rax),%rcx - .byte 72,133,201 // test %rcx,%rcx - .byte 15,132,15,1,0,0 // je 4383 <_sk_gradient_sse2+0x149> - .byte 72,139,64,8 // mov 0x8(%rax),%rax - .byte 72,131,192,32 // add $0x20,%rax - .byte 69,15,87,192 // xorps %xmm8,%xmm8 - .byte 15,87,219 // xorps %xmm3,%xmm3 - .byte 15,87,210 // xorps %xmm2,%xmm2 - .byte 15,87,201 // xorps %xmm1,%xmm1 - .byte 243,68,15,16,112,224 // movss -0x20(%rax),%xmm14 - .byte 243,68,15,16,104,228 // movss -0x1c(%rax),%xmm13 - .byte 69,15,198,246,0 // shufps $0x0,%xmm14,%xmm14 - .byte 69,15,40,252 // movaps %xmm12,%xmm15 - .byte 68,15,40,224 // movaps %xmm0,%xmm12 - .byte 69,15,194,230,1 // cmpltps %xmm14,%xmm12 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 69,15,84,196 // andps %xmm12,%xmm8 - .byte 69,15,86,198 // orps %xmm14,%xmm8 - .byte 243,68,15,16,104,232 // movss -0x18(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 65,15,84,204 // andps %xmm12,%xmm1 - .byte 65,15,86,206 // orps %xmm14,%xmm1 - .byte 243,68,15,16,104,236 // movss -0x14(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 65,15,84,212 // andps %xmm12,%xmm2 - .byte 65,15,86,214 // orps %xmm14,%xmm2 - .byte 243,68,15,16,104,240 // movss -0x10(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 65,15,84,220 // andps %xmm12,%xmm3 - .byte 65,15,86,222 // orps %xmm14,%xmm3 - .byte 243,68,15,16,104,244 // movss -0xc(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 69,15,84,204 // andps %xmm12,%xmm9 - .byte 69,15,86,206 // orps %xmm14,%xmm9 - .byte 243,68,15,16,104,248 // movss -0x8(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 69,15,84,212 // andps %xmm12,%xmm10 - .byte 69,15,86,214 // orps %xmm14,%xmm10 - .byte 243,68,15,16,104,252 // movss -0x4(%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 69,15,85,245 // andnps %xmm13,%xmm14 - .byte 69,15,84,220 // andps %xmm12,%xmm11 - .byte 69,15,86,222 // orps %xmm14,%xmm11 - .byte 243,68,15,16,40 // movss (%rax),%xmm13 - .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 - .byte 69,15,84,252 // andps %xmm12,%xmm15 - .byte 69,15,85,229 // andnps %xmm13,%xmm12 - .byte 69,15,86,231 // orps %xmm15,%xmm12 - .byte 72,131,192,36 // add $0x24,%rax - .byte 72,255,201 // dec %rcx - .byte 15,133,8,255,255,255 // jne 4289 <_sk_gradient_sse2+0x4f> - .byte 235,13 // jmp 4390 <_sk_gradient_sse2+0x156> - .byte 15,87,201 // xorps %xmm1,%xmm1 - .byte 15,87,210 // xorps %xmm2,%xmm2 - .byte 15,87,219 // xorps %xmm3,%xmm3 - .byte 69,15,87,192 // xorps %xmm8,%xmm8 + .byte 76,139,0 // mov (%rax),%r8 + .byte 102,15,239,201 // pxor %xmm1,%xmm1 + .byte 73,131,248,2 // cmp $0x2,%r8 + .byte 114,50 // jb 4427 <_sk_gradient_sse2+0x41> + .byte 72,139,72,72 // mov 0x48(%rax),%rcx + .byte 73,255,200 // dec %r8 + .byte 72,131,193,4 // add $0x4,%rcx + .byte 102,15,239,201 // pxor %xmm1,%xmm1 + .byte 15,40,21,21,21,0,0 // movaps 0x1515(%rip),%xmm2 # 5920 <_sk_callback_sse2+0xe9c> + .byte 243,15,16,25 // movss (%rcx),%xmm3 + .byte 15,198,219,0 // shufps $0x0,%xmm3,%xmm3 + .byte 15,194,216,2 // cmpleps %xmm0,%xmm3 + .byte 15,84,218 // andps %xmm2,%xmm3 + .byte 102,15,254,203 // paddd %xmm3,%xmm1 + .byte 72,131,193,4 // add $0x4,%rcx + .byte 73,255,200 // dec %r8 + .byte 117,228 // jne 440b <_sk_gradient_sse2+0x25> + .byte 65,86 // push %r14 + .byte 83 // push %rbx + .byte 102,15,112,209,78 // pshufd $0x4e,%xmm1,%xmm2 + .byte 102,73,15,126,210 // movq %xmm2,%r10 + .byte 69,137,208 // mov %r10d,%r8d + .byte 73,193,234,32 // shr $0x20,%r10 + .byte 102,72,15,126,201 // movq %xmm1,%rcx + .byte 65,137,201 // mov %ecx,%r9d + .byte 72,193,233,32 // shr $0x20,%rcx + .byte 76,139,88,8 // mov 0x8(%rax),%r11 + .byte 76,139,112,16 // mov 0x10(%rax),%r14 + .byte 243,65,15,16,12,139 // movss (%r11,%rcx,4),%xmm1 + .byte 243,67,15,16,20,147 // movss (%r11,%r10,4),%xmm2 + .byte 15,20,202 // unpcklps %xmm2,%xmm1 + .byte 243,71,15,16,4,139 // movss (%r11,%r9,4),%xmm8 + .byte 243,67,15,16,20,131 // movss (%r11,%r8,4),%xmm2 + .byte 68,15,20,194 // unpcklps %xmm2,%xmm8 + .byte 68,15,20,193 // unpcklps %xmm1,%xmm8 + .byte 72,139,88,40 // mov 0x28(%rax),%rbx + .byte 243,15,16,12,139 // movss (%rbx,%rcx,4),%xmm1 + .byte 243,66,15,16,20,147 // movss (%rbx,%r10,4),%xmm2 + .byte 15,20,202 // unpcklps %xmm2,%xmm1 + .byte 243,70,15,16,12,139 // movss (%rbx,%r9,4),%xmm9 + .byte 243,66,15,16,20,131 // movss (%rbx,%r8,4),%xmm2 + .byte 68,15,20,202 // unpcklps %xmm2,%xmm9 + .byte 68,15,20,201 // unpcklps %xmm1,%xmm9 + .byte 243,65,15,16,20,142 // movss (%r14,%rcx,4),%xmm2 + .byte 243,67,15,16,12,150 // movss (%r14,%r10,4),%xmm1 + .byte 15,20,209 // unpcklps %xmm1,%xmm2 + .byte 243,67,15,16,12,142 // movss (%r14,%r9,4),%xmm1 + .byte 243,67,15,16,28,134 // movss (%r14,%r8,4),%xmm3 + .byte 15,20,203 // unpcklps %xmm3,%xmm1 + .byte 15,20,202 // unpcklps %xmm2,%xmm1 + .byte 72,139,88,48 // mov 0x30(%rax),%rbx + .byte 243,15,16,20,139 // movss (%rbx,%rcx,4),%xmm2 + .byte 243,66,15,16,28,147 // movss (%rbx,%r10,4),%xmm3 + .byte 15,20,211 // unpcklps %xmm3,%xmm2 + .byte 243,70,15,16,20,139 // movss (%rbx,%r9,4),%xmm10 + .byte 243,66,15,16,28,131 // movss (%rbx,%r8,4),%xmm3 + .byte 68,15,20,211 // unpcklps %xmm3,%xmm10 + .byte 68,15,20,210 // unpcklps %xmm2,%xmm10 + .byte 72,139,88,24 // mov 0x18(%rax),%rbx + .byte 243,68,15,16,28,139 // movss (%rbx,%rcx,4),%xmm11 + .byte 243,66,15,16,20,147 // movss (%rbx,%r10,4),%xmm2 + .byte 68,15,20,218 // unpcklps %xmm2,%xmm11 + .byte 243,66,15,16,20,139 // movss (%rbx,%r9,4),%xmm2 + .byte 243,66,15,16,28,131 // movss (%rbx,%r8,4),%xmm3 + .byte 15,20,211 // unpcklps %xmm3,%xmm2 + .byte 65,15,20,211 // unpcklps %xmm11,%xmm2 + .byte 72,139,88,56 // mov 0x38(%rax),%rbx + .byte 243,68,15,16,36,139 // movss (%rbx,%rcx,4),%xmm12 + .byte 243,66,15,16,28,147 // movss (%rbx,%r10,4),%xmm3 + .byte 68,15,20,227 // unpcklps %xmm3,%xmm12 + .byte 243,70,15,16,28,139 // movss (%rbx,%r9,4),%xmm11 + .byte 243,66,15,16,28,131 // movss (%rbx,%r8,4),%xmm3 + .byte 68,15,20,219 // unpcklps %xmm3,%xmm11 + .byte 69,15,20,220 // unpcklps %xmm12,%xmm11 + .byte 72,139,88,32 // mov 0x20(%rax),%rbx + .byte 243,68,15,16,36,139 // movss (%rbx,%rcx,4),%xmm12 + .byte 243,66,15,16,28,147 // movss (%rbx,%r10,4),%xmm3 + .byte 68,15,20,227 // unpcklps %xmm3,%xmm12 + .byte 243,66,15,16,28,139 // movss (%rbx,%r9,4),%xmm3 + .byte 243,70,15,16,44,131 // movss (%rbx,%r8,4),%xmm13 + .byte 65,15,20,221 // unpcklps %xmm13,%xmm3 + .byte 65,15,20,220 // unpcklps %xmm12,%xmm3 + .byte 72,139,64,64 // mov 0x40(%rax),%rax + .byte 243,68,15,16,36,136 // movss (%rax,%rcx,4),%xmm12 + .byte 243,70,15,16,44,144 // movss (%rax,%r10,4),%xmm13 + .byte 69,15,20,229 // unpcklps %xmm13,%xmm12 + .byte 243,70,15,16,44,136 // movss (%rax,%r9,4),%xmm13 + .byte 243,70,15,16,52,128 // movss (%rax,%r8,4),%xmm14 + .byte 69,15,20,238 // unpcklps %xmm14,%xmm13 + .byte 69,15,20,236 // unpcklps %xmm12,%xmm13 .byte 68,15,89,192 // mulps %xmm0,%xmm8 .byte 69,15,88,193 // addps %xmm9,%xmm8 .byte 15,89,200 // mulps %xmm0,%xmm1 @@ -30832,9 +31626,11 @@ _sk_gradient_sse2: .byte 15,89,208 // mulps %xmm0,%xmm2 .byte 65,15,88,211 // addps %xmm11,%xmm2 .byte 15,89,216 // mulps %xmm0,%xmm3 - .byte 65,15,88,220 // addps %xmm12,%xmm3 + .byte 65,15,88,221 // addps %xmm13,%xmm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 + .byte 91 // pop %rbx + .byte 65,94 // pop %r14 .byte 255,224 // jmpq *%rax HIDDEN _sk_evenly_spaced_2_stop_gradient_sse2 @@ -30889,29 +31685,29 @@ _sk_xy_to_unit_angle_sse2: .byte 69,15,94,220 // divps %xmm12,%xmm11 .byte 69,15,40,227 // movaps %xmm11,%xmm12 .byte 69,15,89,228 // mulps %xmm12,%xmm12 - .byte 68,15,40,45,200,18,0,0 // movaps 0x12c8(%rip),%xmm13 # 5730 <_sk_callback_sse2+0xe9d> + .byte 68,15,40,45,215,18,0,0 // movaps 0x12d7(%rip),%xmm13 # 5930 <_sk_callback_sse2+0xeac> .byte 69,15,89,236 // mulps %xmm12,%xmm13 - .byte 68,15,88,45,204,18,0,0 // addps 0x12cc(%rip),%xmm13 # 5740 <_sk_callback_sse2+0xead> + .byte 68,15,88,45,219,18,0,0 // addps 0x12db(%rip),%xmm13 # 5940 <_sk_callback_sse2+0xebc> .byte 69,15,89,236 // mulps %xmm12,%xmm13 - .byte 68,15,88,45,208,18,0,0 // addps 0x12d0(%rip),%xmm13 # 5750 <_sk_callback_sse2+0xebd> + .byte 68,15,88,45,223,18,0,0 // addps 0x12df(%rip),%xmm13 # 5950 <_sk_callback_sse2+0xecc> .byte 69,15,89,236 // mulps %xmm12,%xmm13 - .byte 68,15,88,45,212,18,0,0 // addps 0x12d4(%rip),%xmm13 # 5760 <_sk_callback_sse2+0xecd> + .byte 68,15,88,45,227,18,0,0 // addps 0x12e3(%rip),%xmm13 # 5960 <_sk_callback_sse2+0xedc> .byte 69,15,89,235 // mulps %xmm11,%xmm13 .byte 69,15,194,202,1 // cmpltps %xmm10,%xmm9 - .byte 68,15,40,21,211,18,0,0 // movaps 0x12d3(%rip),%xmm10 # 5770 <_sk_callback_sse2+0xedd> + .byte 68,15,40,21,226,18,0,0 // movaps 0x12e2(%rip),%xmm10 # 5970 <_sk_callback_sse2+0xeec> .byte 69,15,92,213 // subps %xmm13,%xmm10 .byte 69,15,84,209 // andps %xmm9,%xmm10 .byte 69,15,85,205 // andnps %xmm13,%xmm9 .byte 69,15,86,202 // orps %xmm10,%xmm9 .byte 68,15,194,192,1 // cmpltps %xmm0,%xmm8 - .byte 68,15,40,21,198,18,0,0 // movaps 0x12c6(%rip),%xmm10 # 5780 <_sk_callback_sse2+0xeed> + .byte 68,15,40,21,213,18,0,0 // movaps 0x12d5(%rip),%xmm10 # 5980 <_sk_callback_sse2+0xefc> .byte 69,15,92,209 // subps %xmm9,%xmm10 .byte 69,15,84,208 // andps %xmm8,%xmm10 .byte 69,15,85,193 // andnps %xmm9,%xmm8 .byte 69,15,86,194 // orps %xmm10,%xmm8 .byte 68,15,40,201 // movaps %xmm1,%xmm9 .byte 68,15,194,200,1 // cmpltps %xmm0,%xmm9 - .byte 68,15,40,21,181,18,0,0 // movaps 0x12b5(%rip),%xmm10 # 5790 <_sk_callback_sse2+0xefd> + .byte 68,15,40,21,196,18,0,0 // movaps 0x12c4(%rip),%xmm10 # 5990 <_sk_callback_sse2+0xf0c> .byte 69,15,92,208 // subps %xmm8,%xmm10 .byte 69,15,84,209 // andps %xmm9,%xmm10 .byte 69,15,85,200 // andnps %xmm8,%xmm9 @@ -30939,7 +31735,7 @@ HIDDEN _sk_save_xy_sse2 FUNCTION(_sk_save_xy_sse2) _sk_save_xy_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,132,18,0,0 // movaps 0x1284(%rip),%xmm8 # 57a0 <_sk_callback_sse2+0xf0d> + .byte 68,15,40,5,147,18,0,0 // movaps 0x1293(%rip),%xmm8 # 59a0 <_sk_callback_sse2+0xf1c> .byte 15,17,0 // movups %xmm0,(%rax) .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,88,200 // addps %xmm8,%xmm9 @@ -30947,7 +31743,7 @@ _sk_save_xy_sse2: .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 .byte 69,15,40,217 // movaps %xmm9,%xmm11 .byte 69,15,194,218,1 // cmpltps %xmm10,%xmm11 - .byte 68,15,40,37,111,18,0,0 // movaps 0x126f(%rip),%xmm12 # 57b0 <_sk_callback_sse2+0xf1d> + .byte 68,15,40,37,126,18,0,0 // movaps 0x127e(%rip),%xmm12 # 59b0 <_sk_callback_sse2+0xf2c> .byte 69,15,84,220 // andps %xmm12,%xmm11 .byte 69,15,92,211 // subps %xmm11,%xmm10 .byte 69,15,92,202 // subps %xmm10,%xmm9 @@ -30994,8 +31790,8 @@ _sk_bilinear_nx_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,232,17,0,0 // addps 0x11e8(%rip),%xmm0 # 57c0 <_sk_callback_sse2+0xf2d> - .byte 68,15,40,13,240,17,0,0 // movaps 0x11f0(%rip),%xmm9 # 57d0 <_sk_callback_sse2+0xf3d> + .byte 15,88,5,247,17,0,0 // addps 0x11f7(%rip),%xmm0 # 59c0 <_sk_callback_sse2+0xf3c> + .byte 68,15,40,13,255,17,0,0 // movaps 0x11ff(%rip),%xmm9 # 59d0 <_sk_callback_sse2+0xf4c> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -31008,7 +31804,7 @@ _sk_bilinear_px_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,223,17,0,0 // addps 0x11df(%rip),%xmm0 # 57e0 <_sk_callback_sse2+0xf4d> + .byte 15,88,5,238,17,0,0 // addps 0x11ee(%rip),%xmm0 # 59e0 <_sk_callback_sse2+0xf5c> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -31020,8 +31816,8 @@ _sk_bilinear_ny_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,209,17,0,0 // addps 0x11d1(%rip),%xmm1 # 57f0 <_sk_callback_sse2+0xf5d> - .byte 68,15,40,13,217,17,0,0 // movaps 0x11d9(%rip),%xmm9 # 5800 <_sk_callback_sse2+0xf6d> + .byte 15,88,13,224,17,0,0 // addps 0x11e0(%rip),%xmm1 # 59f0 <_sk_callback_sse2+0xf6c> + .byte 68,15,40,13,232,17,0,0 // movaps 0x11e8(%rip),%xmm9 # 5a00 <_sk_callback_sse2+0xf7c> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -31034,7 +31830,7 @@ _sk_bilinear_py_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,199,17,0,0 // addps 0x11c7(%rip),%xmm1 # 5810 <_sk_callback_sse2+0xf7d> + .byte 15,88,13,214,17,0,0 // addps 0x11d6(%rip),%xmm1 # 5a10 <_sk_callback_sse2+0xf8c> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -31046,13 +31842,13 @@ _sk_bicubic_n3x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,186,17,0,0 // addps 0x11ba(%rip),%xmm0 # 5820 <_sk_callback_sse2+0xf8d> - .byte 68,15,40,13,194,17,0,0 // movaps 0x11c2(%rip),%xmm9 # 5830 <_sk_callback_sse2+0xf9d> + .byte 15,88,5,201,17,0,0 // addps 0x11c9(%rip),%xmm0 # 5a20 <_sk_callback_sse2+0xf9c> + .byte 68,15,40,13,209,17,0,0 // movaps 0x11d1(%rip),%xmm9 # 5a30 <_sk_callback_sse2+0xfac> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,190,17,0,0 // mulps 0x11be(%rip),%xmm9 # 5840 <_sk_callback_sse2+0xfad> - .byte 68,15,88,13,198,17,0,0 // addps 0x11c6(%rip),%xmm9 # 5850 <_sk_callback_sse2+0xfbd> + .byte 68,15,89,13,205,17,0,0 // mulps 0x11cd(%rip),%xmm9 # 5a40 <_sk_callback_sse2+0xfbc> + .byte 68,15,88,13,213,17,0,0 // addps 0x11d5(%rip),%xmm9 # 5a50 <_sk_callback_sse2+0xfcc> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -31065,16 +31861,16 @@ _sk_bicubic_n1x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,181,17,0,0 // addps 0x11b5(%rip),%xmm0 # 5860 <_sk_callback_sse2+0xfcd> - .byte 68,15,40,13,189,17,0,0 // movaps 0x11bd(%rip),%xmm9 # 5870 <_sk_callback_sse2+0xfdd> + .byte 15,88,5,196,17,0,0 // addps 0x11c4(%rip),%xmm0 # 5a60 <_sk_callback_sse2+0xfdc> + .byte 68,15,40,13,204,17,0,0 // movaps 0x11cc(%rip),%xmm9 # 5a70 <_sk_callback_sse2+0xfec> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,193,17,0,0 // movaps 0x11c1(%rip),%xmm8 # 5880 <_sk_callback_sse2+0xfed> + .byte 68,15,40,5,208,17,0,0 // movaps 0x11d0(%rip),%xmm8 # 5a80 <_sk_callback_sse2+0xffc> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,197,17,0,0 // addps 0x11c5(%rip),%xmm8 # 5890 <_sk_callback_sse2+0xffd> + .byte 68,15,88,5,212,17,0,0 // addps 0x11d4(%rip),%xmm8 # 5a90 <_sk_callback_sse2+0x100c> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,201,17,0,0 // addps 0x11c9(%rip),%xmm8 # 58a0 <_sk_callback_sse2+0x100d> + .byte 68,15,88,5,216,17,0,0 // addps 0x11d8(%rip),%xmm8 # 5aa0 <_sk_callback_sse2+0x101c> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,205,17,0,0 // addps 0x11cd(%rip),%xmm8 # 58b0 <_sk_callback_sse2+0x101d> + .byte 68,15,88,5,220,17,0,0 // addps 0x11dc(%rip),%xmm8 # 5ab0 <_sk_callback_sse2+0x102c> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -31084,17 +31880,17 @@ HIDDEN _sk_bicubic_p1x_sse2 FUNCTION(_sk_bicubic_p1x_sse2) _sk_bicubic_p1x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,199,17,0,0 // movaps 0x11c7(%rip),%xmm8 # 58c0 <_sk_callback_sse2+0x102d> + .byte 68,15,40,5,214,17,0,0 // movaps 0x11d6(%rip),%xmm8 # 5ac0 <_sk_callback_sse2+0x103c> .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,72,64 // movups 0x40(%rax),%xmm9 .byte 65,15,88,192 // addps %xmm8,%xmm0 - .byte 68,15,40,21,195,17,0,0 // movaps 0x11c3(%rip),%xmm10 # 58d0 <_sk_callback_sse2+0x103d> + .byte 68,15,40,21,210,17,0,0 // movaps 0x11d2(%rip),%xmm10 # 5ad0 <_sk_callback_sse2+0x104c> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,199,17,0,0 // addps 0x11c7(%rip),%xmm10 # 58e0 <_sk_callback_sse2+0x104d> + .byte 68,15,88,21,214,17,0,0 // addps 0x11d6(%rip),%xmm10 # 5ae0 <_sk_callback_sse2+0x105c> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,195,17,0,0 // addps 0x11c3(%rip),%xmm10 # 58f0 <_sk_callback_sse2+0x105d> + .byte 68,15,88,21,210,17,0,0 // addps 0x11d2(%rip),%xmm10 # 5af0 <_sk_callback_sse2+0x106c> .byte 68,15,17,144,128,0,0,0 // movups %xmm10,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -31106,11 +31902,11 @@ _sk_bicubic_p3x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,182,17,0,0 // addps 0x11b6(%rip),%xmm0 # 5900 <_sk_callback_sse2+0x106d> + .byte 15,88,5,197,17,0,0 // addps 0x11c5(%rip),%xmm0 # 5b00 <_sk_callback_sse2+0x107c> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,182,17,0,0 // mulps 0x11b6(%rip),%xmm8 # 5910 <_sk_callback_sse2+0x107d> - .byte 68,15,88,5,190,17,0,0 // addps 0x11be(%rip),%xmm8 # 5920 <_sk_callback_sse2+0x108d> + .byte 68,15,89,5,197,17,0,0 // mulps 0x11c5(%rip),%xmm8 # 5b10 <_sk_callback_sse2+0x108c> + .byte 68,15,88,5,205,17,0,0 // addps 0x11cd(%rip),%xmm8 # 5b20 <_sk_callback_sse2+0x109c> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -31123,13 +31919,13 @@ _sk_bicubic_n3y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,172,17,0,0 // addps 0x11ac(%rip),%xmm1 # 5930 <_sk_callback_sse2+0x109d> - .byte 68,15,40,13,180,17,0,0 // movaps 0x11b4(%rip),%xmm9 # 5940 <_sk_callback_sse2+0x10ad> + .byte 15,88,13,187,17,0,0 // addps 0x11bb(%rip),%xmm1 # 5b30 <_sk_callback_sse2+0x10ac> + .byte 68,15,40,13,195,17,0,0 // movaps 0x11c3(%rip),%xmm9 # 5b40 <_sk_callback_sse2+0x10bc> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,176,17,0,0 // mulps 0x11b0(%rip),%xmm9 # 5950 <_sk_callback_sse2+0x10bd> - .byte 68,15,88,13,184,17,0,0 // addps 0x11b8(%rip),%xmm9 # 5960 <_sk_callback_sse2+0x10cd> + .byte 68,15,89,13,191,17,0,0 // mulps 0x11bf(%rip),%xmm9 # 5b50 <_sk_callback_sse2+0x10cc> + .byte 68,15,88,13,199,17,0,0 // addps 0x11c7(%rip),%xmm9 # 5b60 <_sk_callback_sse2+0x10dc> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -31142,16 +31938,16 @@ _sk_bicubic_n1y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,166,17,0,0 // addps 0x11a6(%rip),%xmm1 # 5970 <_sk_callback_sse2+0x10dd> - .byte 68,15,40,13,174,17,0,0 // movaps 0x11ae(%rip),%xmm9 # 5980 <_sk_callback_sse2+0x10ed> + .byte 15,88,13,181,17,0,0 // addps 0x11b5(%rip),%xmm1 # 5b70 <_sk_callback_sse2+0x10ec> + .byte 68,15,40,13,189,17,0,0 // movaps 0x11bd(%rip),%xmm9 # 5b80 <_sk_callback_sse2+0x10fc> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,178,17,0,0 // movaps 0x11b2(%rip),%xmm8 # 5990 <_sk_callback_sse2+0x10fd> + .byte 68,15,40,5,193,17,0,0 // movaps 0x11c1(%rip),%xmm8 # 5b90 <_sk_callback_sse2+0x110c> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,182,17,0,0 // addps 0x11b6(%rip),%xmm8 # 59a0 <_sk_callback_sse2+0x110d> + .byte 68,15,88,5,197,17,0,0 // addps 0x11c5(%rip),%xmm8 # 5ba0 <_sk_callback_sse2+0x111c> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,186,17,0,0 // addps 0x11ba(%rip),%xmm8 # 59b0 <_sk_callback_sse2+0x111d> + .byte 68,15,88,5,201,17,0,0 // addps 0x11c9(%rip),%xmm8 # 5bb0 <_sk_callback_sse2+0x112c> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,190,17,0,0 // addps 0x11be(%rip),%xmm8 # 59c0 <_sk_callback_sse2+0x112d> + .byte 68,15,88,5,205,17,0,0 // addps 0x11cd(%rip),%xmm8 # 5bc0 <_sk_callback_sse2+0x113c> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -31161,17 +31957,17 @@ HIDDEN _sk_bicubic_p1y_sse2 FUNCTION(_sk_bicubic_p1y_sse2) _sk_bicubic_p1y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,184,17,0,0 // movaps 0x11b8(%rip),%xmm8 # 59d0 <_sk_callback_sse2+0x113d> + .byte 68,15,40,5,199,17,0,0 // movaps 0x11c7(%rip),%xmm8 # 5bd0 <_sk_callback_sse2+0x114c> .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,72,96 // movups 0x60(%rax),%xmm9 .byte 65,15,88,200 // addps %xmm8,%xmm1 - .byte 68,15,40,21,179,17,0,0 // movaps 0x11b3(%rip),%xmm10 # 59e0 <_sk_callback_sse2+0x114d> + .byte 68,15,40,21,194,17,0,0 // movaps 0x11c2(%rip),%xmm10 # 5be0 <_sk_callback_sse2+0x115c> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,183,17,0,0 // addps 0x11b7(%rip),%xmm10 # 59f0 <_sk_callback_sse2+0x115d> + .byte 68,15,88,21,198,17,0,0 // addps 0x11c6(%rip),%xmm10 # 5bf0 <_sk_callback_sse2+0x116c> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,179,17,0,0 // addps 0x11b3(%rip),%xmm10 # 5a00 <_sk_callback_sse2+0x116d> + .byte 68,15,88,21,194,17,0,0 // addps 0x11c2(%rip),%xmm10 # 5c00 <_sk_callback_sse2+0x117c> .byte 68,15,17,144,160,0,0,0 // movups %xmm10,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -31183,11 +31979,11 @@ _sk_bicubic_p3y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,165,17,0,0 // addps 0x11a5(%rip),%xmm1 # 5a10 <_sk_callback_sse2+0x117d> + .byte 15,88,13,180,17,0,0 // addps 0x11b4(%rip),%xmm1 # 5c10 <_sk_callback_sse2+0x118c> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,165,17,0,0 // mulps 0x11a5(%rip),%xmm8 # 5a20 <_sk_callback_sse2+0x118d> - .byte 68,15,88,5,173,17,0,0 // addps 0x11ad(%rip),%xmm8 # 5a30 <_sk_callback_sse2+0x119d> + .byte 68,15,89,5,180,17,0,0 // mulps 0x11b4(%rip),%xmm8 # 5c20 <_sk_callback_sse2+0x119c> + .byte 68,15,88,5,188,17,0,0 // addps 0x11bc(%rip),%xmm8 # 5c30 <_sk_callback_sse2+0x11ac> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -31406,11 +32202,11 @@ BALIGN16 .byte 128,191,0,0,128,191,0 // cmpb $0x0,-0x40800000(%rdi) .byte 0,224 // add %ah,%al .byte 64,0,0 // add %al,(%rax) - .byte 224,64 // loopne 4b48 <.literal16+0x1d8> + .byte 224,64 // loopne 4d38 <.literal16+0x1d8> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 4b4c <.literal16+0x1dc> + .byte 224,64 // loopne 4d3c <.literal16+0x1dc> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 4b50 <.literal16+0x1e0> + .byte 224,64 // loopne 4d40 <.literal16+0x1e0> .byte 154 // (bad) .byte 153 // cltd .byte 153 // cltd @@ -31430,13 +32226,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4b71 <.literal16+0x201> + .byte 71,225,61 // rex.RXB loope 4d61 <.literal16+0x201> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4b75 <.literal16+0x205> + .byte 71,225,61 // rex.RXB loope 4d65 <.literal16+0x205> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4b79 <.literal16+0x209> + .byte 71,225,61 // rex.RXB loope 4d69 <.literal16+0x209> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4b7d <.literal16+0x20d> + .byte 71,225,61 // rex.RXB loope 4d6d <.literal16+0x20d> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -31461,13 +32257,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bb1 <.literal16+0x241> + .byte 71,225,61 // rex.RXB loope 4da1 <.literal16+0x241> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bb5 <.literal16+0x245> + .byte 71,225,61 // rex.RXB loope 4da5 <.literal16+0x245> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bb9 <.literal16+0x249> + .byte 71,225,61 // rex.RXB loope 4da9 <.literal16+0x249> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bbd <.literal16+0x24d> + .byte 71,225,61 // rex.RXB loope 4dad <.literal16+0x24d> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -31492,13 +32288,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bf1 <.literal16+0x281> + .byte 71,225,61 // rex.RXB loope 4de1 <.literal16+0x281> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bf5 <.literal16+0x285> + .byte 71,225,61 // rex.RXB loope 4de5 <.literal16+0x285> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bf9 <.literal16+0x289> + .byte 71,225,61 // rex.RXB loope 4de9 <.literal16+0x289> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4bfd <.literal16+0x28d> + .byte 71,225,61 // rex.RXB loope 4ded <.literal16+0x28d> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -31523,13 +32319,13 @@ BALIGN16 .byte 10,23 // or (%rdi),%dl .byte 63 // (bad) .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4c31 <.literal16+0x2c1> + .byte 71,225,61 // rex.RXB loope 4e21 <.literal16+0x2c1> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4c35 <.literal16+0x2c5> + .byte 71,225,61 // rex.RXB loope 4e25 <.literal16+0x2c5> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4c39 <.literal16+0x2c9> + .byte 71,225,61 // rex.RXB loope 4e29 <.literal16+0x2c9> .byte 174 // scas %es:(%rdi),%al - .byte 71,225,61 // rex.RXB loope 4c3d <.literal16+0x2cd> + .byte 71,225,61 // rex.RXB loope 4e2d <.literal16+0x2cd> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -31758,13 +32554,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4e19 <.literal16+0x4a9> + .byte 224,7 // loopne 5009 <.literal16+0x4a9> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4e1d <.literal16+0x4ad> + .byte 224,7 // loopne 500d <.literal16+0x4ad> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4e21 <.literal16+0x4b1> + .byte 224,7 // loopne 5011 <.literal16+0x4b1> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4e25 <.literal16+0x4b5> + .byte 224,7 // loopne 5015 <.literal16+0x4b5> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -31829,11 +32625,11 @@ BALIGN16 .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4efb <.literal16+0x58b> + .byte 127,67 // jg 50eb <.literal16+0x58b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4eff <.literal16+0x58f> + .byte 127,67 // jg 50ef <.literal16+0x58f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4f03 <.literal16+0x593> + .byte 127,67 // jg 50f3 <.literal16+0x593> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,129,128,128,59 // addb $0x3b,-0x7f7f7ec5(%rax) @@ -31848,16 +32644,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4ef4 <.literal16+0x584> + .byte 127,0 // jg 50e4 <.literal16+0x584> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4ef8 <.literal16+0x588> + .byte 127,0 // jg 50e8 <.literal16+0x588> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4efc <.literal16+0x58c> + .byte 127,0 // jg 50ec <.literal16+0x58c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4f00 <.literal16+0x590> + .byte 127,0 // jg 50f0 <.literal16+0x590> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -31866,7 +32662,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4f85 <.literal16+0x615> + .byte 119,115 // ja 5175 <.literal16+0x615> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -31877,7 +32673,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4ee9 <.literal16+0x579> + .byte 117,191 // jne 50d9 <.literal16+0x579> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -31889,7 +32685,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a38f2a <_sk_callback_sse2+0xffffffffe9a34697> + .byte 233,220,63,163,233 // jmpq ffffffffe9a3911a <_sk_callback_sse2+0xffffffffe9a34696> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -31943,16 +32739,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4fc4 <.literal16+0x654> + .byte 127,0 // jg 51b4 <.literal16+0x654> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4fc8 <.literal16+0x658> + .byte 127,0 // jg 51b8 <.literal16+0x658> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4fcc <.literal16+0x65c> + .byte 127,0 // jg 51bc <.literal16+0x65c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4fd0 <.literal16+0x660> + .byte 127,0 // jg 51c0 <.literal16+0x660> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -31961,7 +32757,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5055 <.literal16+0x6e5> + .byte 119,115 // ja 5245 <.literal16+0x6e5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -31972,7 +32768,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4fb9 <.literal16+0x649> + .byte 117,191 // jne 51a9 <.literal16+0x649> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -31984,7 +32780,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a38ffa <_sk_callback_sse2+0xffffffffe9a34767> + .byte 233,220,63,163,233 // jmpq ffffffffe9a391ea <_sk_callback_sse2+0xffffffffe9a34766> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -32038,16 +32834,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 5094 <.literal16+0x724> + .byte 127,0 // jg 5284 <.literal16+0x724> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 5098 <.literal16+0x728> + .byte 127,0 // jg 5288 <.literal16+0x728> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 509c <.literal16+0x72c> + .byte 127,0 // jg 528c <.literal16+0x72c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 50a0 <.literal16+0x730> + .byte 127,0 // jg 5290 <.literal16+0x730> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -32056,7 +32852,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5125 <.literal16+0x7b5> + .byte 119,115 // ja 5315 <.literal16+0x7b5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -32067,7 +32863,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 5089 <.literal16+0x719> + .byte 117,191 // jne 5279 <.literal16+0x719> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -32079,7 +32875,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a390ca <_sk_callback_sse2+0xffffffffe9a34837> + .byte 233,220,63,163,233 // jmpq ffffffffe9a392ba <_sk_callback_sse2+0xffffffffe9a34836> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -32133,16 +32929,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 5164 <.literal16+0x7f4> + .byte 127,0 // jg 5354 <.literal16+0x7f4> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 5168 <.literal16+0x7f8> + .byte 127,0 // jg 5358 <.literal16+0x7f8> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 516c <.literal16+0x7fc> + .byte 127,0 // jg 535c <.literal16+0x7fc> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 5170 <.literal16+0x800> + .byte 127,0 // jg 5360 <.literal16+0x800> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -32151,7 +32947,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 51f5 <.literal16+0x885> + .byte 119,115 // ja 53e5 <.literal16+0x885> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -32162,7 +32958,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 5159 <.literal16+0x7e9> + .byte 117,191 // jne 5349 <.literal16+0x7e9> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -32174,7 +32970,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a3919a <_sk_callback_sse2+0xffffffffe9a34907> + .byte 233,220,63,163,233 // jmpq ffffffffe9a3938a <_sk_callback_sse2+0xffffffffe9a34906> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -32224,13 +33020,13 @@ BALIGN16 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 - .byte 127,67 // jg 5277 <.literal16+0x907> + .byte 127,67 // jg 5467 <.literal16+0x907> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 527b <.literal16+0x90b> + .byte 127,67 // jg 546b <.literal16+0x90b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 527f <.literal16+0x90f> + .byte 127,67 // jg 546f <.literal16+0x90f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 5283 <.literal16+0x913> + .byte 127,67 // jg 5473 <.literal16+0x913> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -32277,16 +33073,16 @@ BALIGN16 .byte 128,3,62 // addb $0x3e,(%rbx) .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 5303 <.literal16+0x993> + .byte 118,63 // jbe 54f3 <.literal16+0x993> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 5307 <.literal16+0x997> + .byte 118,63 // jbe 54f7 <.literal16+0x997> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 530b <.literal16+0x99b> + .byte 118,63 // jbe 54fb <.literal16+0x99b> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 530f <.literal16+0x99f> + .byte 118,63 // jbe 54ff <.literal16+0x99f> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) @@ -32298,11 +33094,11 @@ BALIGN16 .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 534b <.literal16+0x9db> + .byte 127,67 // jg 553b <.literal16+0x9db> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 534f <.literal16+0x9df> + .byte 127,67 // jg 553f <.literal16+0x9df> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 5353 <.literal16+0x9e3> + .byte 127,67 // jg 5543 <.literal16+0x9e3> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,0,0,128,63 // addb $0x3f,-0x7fffffc5(%rax) @@ -32342,13 +33138,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 5399 <.literal16+0xa29> + .byte 224,7 // loopne 5589 <.literal16+0xa29> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 539d <.literal16+0xa2d> + .byte 224,7 // loopne 558d <.literal16+0xa2d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 53a1 <.literal16+0xa31> + .byte 224,7 // loopne 5591 <.literal16+0xa31> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 53a5 <.literal16+0xa35> + .byte 224,7 // loopne 5595 <.literal16+0xa35> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -32394,13 +33190,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 5409 <.literal16+0xa99> + .byte 224,7 // loopne 55f9 <.literal16+0xa99> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 540d <.literal16+0xa9d> + .byte 224,7 // loopne 55fd <.literal16+0xa9d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 5411 <.literal16+0xaa1> + .byte 224,7 // loopne 5601 <.literal16+0xaa1> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 5415 <.literal16+0xaa5> + .byte 224,7 // loopne 5605 <.literal16+0xaa5> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -32438,13 +33234,13 @@ BALIGN16 .byte 65,0,0 // add %al,(%r8) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 54a6 <.literal16+0xb36> + .byte 124,66 // jl 5696 <.literal16+0xb36> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 54aa <.literal16+0xb3a> + .byte 124,66 // jl 569a <.literal16+0xb3a> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 54ae <.literal16+0xb3e> + .byte 124,66 // jl 569e <.literal16+0xb3e> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 54b2 <.literal16+0xb42> + .byte 124,66 // jl 56a2 <.literal16+0xb42> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 0,240 // add %dh,%al @@ -32534,13 +33330,13 @@ BALIGN16 .byte 136,136,61,137,136,136 // mov %cl,-0x777776c3(%rax) .byte 61,137,136,136,61 // cmp $0x3d888889,%eax .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 55b5 <.literal16+0xc45> + .byte 112,65 // jo 57a5 <.literal16+0xc45> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 55b9 <.literal16+0xc49> + .byte 112,65 // jo 57a9 <.literal16+0xc49> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 55bd <.literal16+0xc4d> + .byte 112,65 // jo 57ad <.literal16+0xc4d> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 55c1 <.literal16+0xc51> + .byte 112,65 // jo 57b1 <.literal16+0xc51> .byte 255,0 // incl (%rax) .byte 0,0 // add %al,(%rax) .byte 255,0 // incl (%rax) @@ -32562,11 +33358,11 @@ BALIGN16 .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,0,0,127,67 // addb $0x43,0x7f00003b(%rax) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 560b <.literal16+0xc9b> + .byte 127,67 // jg 57fb <.literal16+0xc9b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 560f <.literal16+0xc9f> + .byte 127,67 // jg 57ff <.literal16+0xc9f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 5613 <.literal16+0xca3> + .byte 127,67 // jg 5803 <.literal16+0xca3> .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) .byte 0,0 // add %al,(%rax) .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) @@ -32642,13 +33438,13 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 255 // (bad) - .byte 127,71 // jg 56fb <.literal16+0xd8b> + .byte 127,71 // jg 58eb <.literal16+0xd8b> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 56ff <.literal16+0xd8f> + .byte 127,71 // jg 58ef <.literal16+0xd8f> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 5703 <.literal16+0xd93> + .byte 127,71 // jg 58f3 <.literal16+0xd93> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 5707 <.literal16+0xd97> + .byte 127,71 // jg 58f7 <.literal16+0xd97> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -32698,19 +33494,27 @@ BALIGN16 .byte 221,147,61,152,221,147 // fstl -0x6c2267c3(%rbx) .byte 61,152,221,147,61 // cmp $0x3d93dd98,%eax .byte 152 // cwtl - .byte 221,147,61,111,43,231 // fstl -0x18d490c3(%rbx) - .byte 187,111,43,231,187 // mov $0xbbe72b6f,%ebx + .byte 221,147,61,1,0,0 // fstl 0x13d(%rbx) + .byte 0,1 // add %al,(%rcx) + .byte 0,0 // add %al,(%rax) + .byte 0,1 // add %al,(%rcx) + .byte 0,0 // add %al,(%rax) + .byte 0,1 // add %al,(%rcx) + .byte 0,0 // add %al,(%rax) + .byte 0,111,43 // add %ch,0x2b(%rdi) + .byte 231,187 // out %eax,$0xbb .byte 111 // outsl %ds:(%rsi),(%dx) .byte 43,231 // sub %edi,%esp .byte 187,111,43,231,187 // mov $0xbbe72b6f,%ebx + .byte 111 // outsl %ds:(%rsi),(%dx) + .byte 43,231 // sub %edi,%esp + .byte 187,159,215,202,60 // mov $0x3ccad79f,%ebx .byte 159 // lahf .byte 215 // xlat %ds:(%rbx) .byte 202,60,159 // lret $0x9f3c .byte 215 // xlat %ds:(%rbx) .byte 202,60,159 // lret $0x9f3c .byte 215 // xlat %ds:(%rbx) - .byte 202,60,159 // lret $0x9f3c - .byte 215 // xlat %ds:(%rbx) .byte 202,60,212 // lret $0xd43c .byte 100,84 // fs push %rsp .byte 189,212,100,84,189 // mov $0xbd5464d4,%ebp @@ -32801,11 +33605,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 5862 <.literal16+0xef2> + .byte 62,114,28 // jb,pt 5a62 <.literal16+0xf02> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5866 <.literal16+0xef6> + .byte 62,114,28 // jb,pt 5a66 <.literal16+0xf06> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 586a <.literal16+0xefa> + .byte 62,114,28 // jb,pt 5a6a <.literal16+0xf0a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -32849,7 +33653,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e6f5 <_sk_callback_sse2+0x3d639e62> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e8f5 <_sk_callback_sse2+0x3d639e71> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -32875,7 +33679,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e735 <_sk_callback_sse2+0x3d639ea2> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e935 <_sk_callback_sse2+0x3d639eb1> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -32884,13 +33688,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 592e <.literal16+0xfbe> + .byte 114,28 // jb 5b2e <.literal16+0xfce> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5932 <.literal16+0xfc2> + .byte 62,114,28 // jb,pt 5b32 <.literal16+0xfd2> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5936 <.literal16+0xfc6> + .byte 62,114,28 // jb,pt 5b36 <.literal16+0xfd6> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 593a <.literal16+0xfca> + .byte 62,114,28 // jb,pt 5b3a <.literal16+0xfda> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -32911,11 +33715,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 5972 <.literal16+0x1002> + .byte 62,114,28 // jb,pt 5b72 <.literal16+0x1012> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5976 <.literal16+0x1006> + .byte 62,114,28 // jb,pt 5b76 <.literal16+0x1016> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 597a <.literal16+0x100a> + .byte 62,114,28 // jb,pt 5b7a <.literal16+0x101a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -32959,7 +33763,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e805 <_sk_callback_sse2+0x3d639f72> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63ea05 <_sk_callback_sse2+0x3d639f81> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -32985,7 +33789,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63e845 <_sk_callback_sse2+0x3d639fb2> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63ea45 <_sk_callback_sse2+0x3d639fc1> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -32994,13 +33798,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 5a3e <.literal16+0x10ce> + .byte 114,28 // jb 5c3e <.literal16+0x10de> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5a42 <_sk_callback_sse2+0x11af> + .byte 62,114,28 // jb,pt 5c42 <_sk_callback_sse2+0x11be> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5a46 <_sk_callback_sse2+0x11b3> + .byte 62,114,28 // jb,pt 5c46 <_sk_callback_sse2+0x11c2> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 5a4a <_sk_callback_sse2+0x11b7> + .byte 62,114,28 // jb,pt 5c4a <_sk_callback_sse2+0x11c6> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) diff --git a/src/jumper/SkJumper_generated_win.S b/src/jumper/SkJumper_generated_win.S index 10fea4b..d55a0a4 100644 --- a/src/jumper/SkJumper_generated_win.S +++ b/src/jumper/SkJumper_generated_win.S @@ -106,14 +106,14 @@ _sk_seed_shader_hsw LABEL PROC DB 197,249,110,199 ; vmovd %edi,%xmm0 DB 196,226,125,88,192 ; vpbroadcastd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,126,69,0,0 ; vbroadcastss 0x457e(%rip),%ymm1 # 46d8 <_sk_callback_hsw+0x11b> + DB 196,226,125,24,13,218,70,0,0 ; vbroadcastss 0x46da(%rip),%ymm1 # 4834 <_sk_callback_hsw+0x11c> DB 197,252,88,193 ; vaddps %ymm1,%ymm0,%ymm0 DB 197,252,88,2 ; vaddps (%rdx),%ymm0,%ymm0 DB 196,226,125,24,16 ; vbroadcastss (%rax),%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 197,236,88,201 ; vaddps %ymm1,%ymm2,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,21,98,69,0,0 ; vbroadcastss 0x4562(%rip),%ymm2 # 46dc <_sk_callback_hsw+0x11f> + DB 196,226,125,24,21,190,70,0,0 ; vbroadcastss 0x46be(%rip),%ymm2 # 4838 <_sk_callback_hsw+0x120> DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 DB 197,220,87,228 ; vxorps %ymm4,%ymm4,%ymm4 DB 197,212,87,237 ; vxorps %ymm5,%ymm5,%ymm5 @@ -132,13 +132,13 @@ _sk_dither_hsw LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 196,66,125,88,8 ; vpbroadcastd (%r8),%ymm9 DB 196,65,61,239,201 ; vpxor %ymm9,%ymm8,%ymm9 - DB 196,98,125,88,21,33,69,0,0 ; vpbroadcastd 0x4521(%rip),%ymm10 # 46e0 <_sk_callback_hsw+0x123> + DB 196,98,125,88,21,125,70,0,0 ; vpbroadcastd 0x467d(%rip),%ymm10 # 483c <_sk_callback_hsw+0x124> DB 196,65,53,219,218 ; vpand %ymm10,%ymm9,%ymm11 DB 196,193,37,114,243,5 ; vpslld $0x5,%ymm11,%ymm11 DB 196,65,61,219,210 ; vpand %ymm10,%ymm8,%ymm10 DB 196,193,45,114,242,4 ; vpslld $0x4,%ymm10,%ymm10 - DB 196,98,125,88,37,6,69,0,0 ; vpbroadcastd 0x4506(%rip),%ymm12 # 46e4 <_sk_callback_hsw+0x127> - DB 196,98,125,88,45,1,69,0,0 ; vpbroadcastd 0x4501(%rip),%ymm13 # 46e8 <_sk_callback_hsw+0x12b> + DB 196,98,125,88,37,98,70,0,0 ; vpbroadcastd 0x4662(%rip),%ymm12 # 4840 <_sk_callback_hsw+0x128> + DB 196,98,125,88,45,93,70,0,0 ; vpbroadcastd 0x465d(%rip),%ymm13 # 4844 <_sk_callback_hsw+0x12c> DB 196,65,53,219,245 ; vpand %ymm13,%ymm9,%ymm14 DB 196,193,13,114,246,2 ; vpslld $0x2,%ymm14,%ymm14 DB 196,65,61,219,237 ; vpand %ymm13,%ymm8,%ymm13 @@ -153,8 +153,8 @@ _sk_dither_hsw LABEL PROC DB 196,65,61,235,194 ; vpor %ymm10,%ymm8,%ymm8 DB 196,65,61,235,193 ; vpor %ymm9,%ymm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,179,68,0,0 ; vbroadcastss 0x44b3(%rip),%ymm9 # 46ec <_sk_callback_hsw+0x12f> - DB 196,98,125,24,21,174,68,0,0 ; vbroadcastss 0x44ae(%rip),%ymm10 # 46f0 <_sk_callback_hsw+0x133> + DB 196,98,125,24,13,15,70,0,0 ; vbroadcastss 0x460f(%rip),%ymm9 # 4848 <_sk_callback_hsw+0x130> + DB 196,98,125,24,21,10,70,0,0 ; vbroadcastss 0x460a(%rip),%ymm10 # 484c <_sk_callback_hsw+0x134> DB 196,66,61,184,209 ; vfmadd231ps %ymm9,%ymm8,%ymm10 DB 196,98,125,24,64,8 ; vbroadcastss 0x8(%rax),%ymm8 DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 @@ -206,7 +206,7 @@ _sk_clear_hsw LABEL PROC PUBLIC _sk_srcatop_hsw _sk_srcatop_hsw LABEL PROC DB 197,252,89,199 ; vmulps %ymm7,%ymm0,%ymm0 - DB 196,98,125,24,5,34,68,0,0 ; vbroadcastss 0x4422(%rip),%ymm8 # 46f4 <_sk_callback_hsw+0x137> + DB 196,98,125,24,5,126,69,0,0 ; vbroadcastss 0x457e(%rip),%ymm8 # 4850 <_sk_callback_hsw+0x138> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,226,61,184,196 ; vfmadd231ps %ymm4,%ymm8,%ymm0 DB 197,244,89,207 ; vmulps %ymm7,%ymm1,%ymm1 @@ -220,7 +220,7 @@ _sk_srcatop_hsw LABEL PROC PUBLIC _sk_dstatop_hsw _sk_dstatop_hsw LABEL PROC - DB 196,98,125,24,5,245,67,0,0 ; vbroadcastss 0x43f5(%rip),%ymm8 # 46f8 <_sk_callback_hsw+0x13b> + DB 196,98,125,24,5,81,69,0,0 ; vbroadcastss 0x4551(%rip),%ymm8 # 4854 <_sk_callback_hsw+0x13c> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 196,226,101,184,196 ; vfmadd231ps %ymm4,%ymm3,%ymm0 @@ -253,7 +253,7 @@ _sk_dstin_hsw LABEL PROC PUBLIC _sk_srcout_hsw _sk_srcout_hsw LABEL PROC - DB 196,98,125,24,5,156,67,0,0 ; vbroadcastss 0x439c(%rip),%ymm8 # 46fc <_sk_callback_hsw+0x13f> + DB 196,98,125,24,5,248,68,0,0 ; vbroadcastss 0x44f8(%rip),%ymm8 # 4858 <_sk_callback_hsw+0x140> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -264,7 +264,7 @@ _sk_srcout_hsw LABEL PROC PUBLIC _sk_dstout_hsw _sk_dstout_hsw LABEL PROC - DB 196,226,125,24,5,127,67,0,0 ; vbroadcastss 0x437f(%rip),%ymm0 # 4700 <_sk_callback_hsw+0x143> + DB 196,226,125,24,5,219,68,0,0 ; vbroadcastss 0x44db(%rip),%ymm0 # 485c <_sk_callback_hsw+0x144> DB 197,252,92,219 ; vsubps %ymm3,%ymm0,%ymm3 DB 197,228,89,196 ; vmulps %ymm4,%ymm3,%ymm0 DB 197,228,89,205 ; vmulps %ymm5,%ymm3,%ymm1 @@ -275,7 +275,7 @@ _sk_dstout_hsw LABEL PROC PUBLIC _sk_srcover_hsw _sk_srcover_hsw LABEL PROC - DB 196,98,125,24,5,98,67,0,0 ; vbroadcastss 0x4362(%rip),%ymm8 # 4704 <_sk_callback_hsw+0x147> + DB 196,98,125,24,5,190,68,0,0 ; vbroadcastss 0x44be(%rip),%ymm8 # 4860 <_sk_callback_hsw+0x148> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,93,184,192 ; vfmadd231ps %ymm8,%ymm4,%ymm0 DB 196,194,85,184,200 ; vfmadd231ps %ymm8,%ymm5,%ymm1 @@ -286,7 +286,7 @@ _sk_srcover_hsw LABEL PROC PUBLIC _sk_dstover_hsw _sk_dstover_hsw LABEL PROC - DB 196,98,125,24,5,65,67,0,0 ; vbroadcastss 0x4341(%rip),%ymm8 # 4708 <_sk_callback_hsw+0x14b> + DB 196,98,125,24,5,157,68,0,0 ; vbroadcastss 0x449d(%rip),%ymm8 # 4864 <_sk_callback_hsw+0x14c> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 196,226,61,168,196 ; vfmadd213ps %ymm4,%ymm8,%ymm0 DB 196,226,61,168,205 ; vfmadd213ps %ymm5,%ymm8,%ymm1 @@ -306,7 +306,7 @@ _sk_modulate_hsw LABEL PROC PUBLIC _sk_multiply_hsw _sk_multiply_hsw LABEL PROC - DB 196,98,125,24,5,12,67,0,0 ; vbroadcastss 0x430c(%rip),%ymm8 # 470c <_sk_callback_hsw+0x14f> + DB 196,98,125,24,5,104,68,0,0 ; vbroadcastss 0x4468(%rip),%ymm8 # 4868 <_sk_callback_hsw+0x150> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,208 ; vmulps %ymm0,%ymm9,%ymm10 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -348,7 +348,7 @@ _sk_screen_hsw LABEL PROC PUBLIC _sk_xor__hsw _sk_xor__hsw LABEL PROC - DB 196,98,125,24,5,135,66,0,0 ; vbroadcastss 0x4287(%rip),%ymm8 # 4710 <_sk_callback_hsw+0x153> + DB 196,98,125,24,5,227,67,0,0 ; vbroadcastss 0x43e3(%rip),%ymm8 # 486c <_sk_callback_hsw+0x154> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -380,7 +380,7 @@ _sk_darken_hsw LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,95,209 ; vmaxps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,15,66,0,0 ; vbroadcastss 0x420f(%rip),%ymm8 # 4714 <_sk_callback_hsw+0x157> + DB 196,98,125,24,5,107,67,0,0 ; vbroadcastss 0x436b(%rip),%ymm8 # 4870 <_sk_callback_hsw+0x158> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -403,7 +403,7 @@ _sk_lighten_hsw LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,190,65,0,0 ; vbroadcastss 0x41be(%rip),%ymm8 # 4718 <_sk_callback_hsw+0x15b> + DB 196,98,125,24,5,26,67,0,0 ; vbroadcastss 0x431a(%rip),%ymm8 # 4874 <_sk_callback_hsw+0x15c> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -429,7 +429,7 @@ _sk_difference_hsw LABEL PROC DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,97,65,0,0 ; vbroadcastss 0x4161(%rip),%ymm8 # 471c <_sk_callback_hsw+0x15f> + DB 196,98,125,24,5,189,66,0,0 ; vbroadcastss 0x42bd(%rip),%ymm8 # 4878 <_sk_callback_hsw+0x160> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -449,7 +449,7 @@ _sk_exclusion_hsw LABEL PROC DB 197,236,89,214 ; vmulps %ymm6,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,31,65,0,0 ; vbroadcastss 0x411f(%rip),%ymm8 # 4720 <_sk_callback_hsw+0x163> + DB 196,98,125,24,5,123,66,0,0 ; vbroadcastss 0x427b(%rip),%ymm8 # 487c <_sk_callback_hsw+0x164> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -457,7 +457,7 @@ _sk_exclusion_hsw LABEL PROC PUBLIC _sk_colorburn_hsw _sk_colorburn_hsw LABEL PROC - DB 196,98,125,24,5,13,65,0,0 ; vbroadcastss 0x410d(%rip),%ymm8 # 4724 <_sk_callback_hsw+0x167> + DB 196,98,125,24,5,105,66,0,0 ; vbroadcastss 0x4269(%rip),%ymm8 # 4880 <_sk_callback_hsw+0x168> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,216 ; vmulps %ymm0,%ymm9,%ymm11 DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 @@ -513,7 +513,7 @@ _sk_colorburn_hsw LABEL PROC PUBLIC _sk_colordodge_hsw _sk_colordodge_hsw LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 - DB 196,98,125,24,13,24,64,0,0 ; vbroadcastss 0x4018(%rip),%ymm9 # 4728 <_sk_callback_hsw+0x16b> + DB 196,98,125,24,13,116,65,0,0 ; vbroadcastss 0x4174(%rip),%ymm9 # 4884 <_sk_callback_hsw+0x16c> DB 197,52,92,215 ; vsubps %ymm7,%ymm9,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,52,92,203 ; vsubps %ymm3,%ymm9,%ymm9 @@ -564,7 +564,7 @@ _sk_colordodge_hsw LABEL PROC PUBLIC _sk_hardlight_hsw _sk_hardlight_hsw LABEL PROC - DB 196,98,125,24,5,57,63,0,0 ; vbroadcastss 0x3f39(%rip),%ymm8 # 472c <_sk_callback_hsw+0x16f> + DB 196,98,125,24,5,149,64,0,0 ; vbroadcastss 0x4095(%rip),%ymm8 # 4888 <_sk_callback_hsw+0x170> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -613,7 +613,7 @@ _sk_hardlight_hsw LABEL PROC PUBLIC _sk_overlay_hsw _sk_overlay_hsw LABEL PROC - DB 196,98,125,24,5,113,62,0,0 ; vbroadcastss 0x3e71(%rip),%ymm8 # 4730 <_sk_callback_hsw+0x173> + DB 196,98,125,24,5,205,63,0,0 ; vbroadcastss 0x3fcd(%rip),%ymm8 # 488c <_sk_callback_hsw+0x174> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -673,10 +673,10 @@ _sk_softlight_hsw LABEL PROC DB 196,65,20,88,197 ; vaddps %ymm13,%ymm13,%ymm8 DB 196,65,60,88,192 ; vaddps %ymm8,%ymm8,%ymm8 DB 196,66,61,168,192 ; vfmadd213ps %ymm8,%ymm8,%ymm8 - DB 196,98,125,24,29,120,61,0,0 ; vbroadcastss 0x3d78(%rip),%ymm11 # 4738 <_sk_callback_hsw+0x17b> + DB 196,98,125,24,29,212,62,0,0 ; vbroadcastss 0x3ed4(%rip),%ymm11 # 4894 <_sk_callback_hsw+0x17c> DB 196,65,20,88,227 ; vaddps %ymm11,%ymm13,%ymm12 DB 196,65,28,89,192 ; vmulps %ymm8,%ymm12,%ymm8 - DB 196,98,125,24,37,105,61,0,0 ; vbroadcastss 0x3d69(%rip),%ymm12 # 473c <_sk_callback_hsw+0x17f> + DB 196,98,125,24,37,197,62,0,0 ; vbroadcastss 0x3ec5(%rip),%ymm12 # 4898 <_sk_callback_hsw+0x180> DB 196,66,21,184,196 ; vfmadd231ps %ymm12,%ymm13,%ymm8 DB 196,65,124,82,245 ; vrsqrtps %ymm13,%ymm14 DB 196,65,124,83,246 ; vrcpps %ymm14,%ymm14 @@ -686,7 +686,7 @@ _sk_softlight_hsw LABEL PROC DB 197,4,194,255,2 ; vcmpleps %ymm7,%ymm15,%ymm15 DB 196,67,13,74,240,240 ; vblendvps %ymm15,%ymm8,%ymm14,%ymm14 DB 197,116,88,249 ; vaddps %ymm1,%ymm1,%ymm15 - DB 196,98,125,24,5,44,61,0,0 ; vbroadcastss 0x3d2c(%rip),%ymm8 # 4734 <_sk_callback_hsw+0x177> + DB 196,98,125,24,5,136,62,0,0 ; vbroadcastss 0x3e88(%rip),%ymm8 # 4890 <_sk_callback_hsw+0x178> DB 196,65,60,92,237 ; vsubps %ymm13,%ymm8,%ymm13 DB 197,132,92,195 ; vsubps %ymm3,%ymm15,%ymm0 DB 196,98,125,168,235 ; vfmadd213ps %ymm3,%ymm0,%ymm13 @@ -799,11 +799,11 @@ _sk_hue_hsw LABEL PROC DB 196,65,28,89,210 ; vmulps %ymm10,%ymm12,%ymm10 DB 196,65,44,94,214 ; vdivps %ymm14,%ymm10,%ymm10 DB 196,67,45,74,224,240 ; vblendvps %ymm15,%ymm8,%ymm10,%ymm12 - DB 196,98,125,24,53,43,59,0,0 ; vbroadcastss 0x3b2b(%rip),%ymm14 # 4740 <_sk_callback_hsw+0x183> - DB 196,98,125,24,61,38,59,0,0 ; vbroadcastss 0x3b26(%rip),%ymm15 # 4744 <_sk_callback_hsw+0x187> + DB 196,98,125,24,53,135,60,0,0 ; vbroadcastss 0x3c87(%rip),%ymm14 # 489c <_sk_callback_hsw+0x184> + DB 196,98,125,24,61,130,60,0,0 ; vbroadcastss 0x3c82(%rip),%ymm15 # 48a0 <_sk_callback_hsw+0x188> DB 196,65,84,89,239 ; vmulps %ymm15,%ymm5,%ymm13 DB 196,66,93,184,238 ; vfmadd231ps %ymm14,%ymm4,%ymm13 - DB 196,226,125,24,5,23,59,0,0 ; vbroadcastss 0x3b17(%rip),%ymm0 # 4748 <_sk_callback_hsw+0x18b> + DB 196,226,125,24,5,115,60,0,0 ; vbroadcastss 0x3c73(%rip),%ymm0 # 48a4 <_sk_callback_hsw+0x18c> DB 196,98,77,184,232 ; vfmadd231ps %ymm0,%ymm6,%ymm13 DB 196,65,116,89,215 ; vmulps %ymm15,%ymm1,%ymm10 DB 196,66,53,184,214 ; vfmadd231ps %ymm14,%ymm9,%ymm10 @@ -858,7 +858,7 @@ _sk_hue_hsw LABEL PROC DB 196,193,124,95,192 ; vmaxps %ymm8,%ymm0,%ymm0 DB 196,65,36,95,200 ; vmaxps %ymm8,%ymm11,%ymm9 DB 196,65,116,95,192 ; vmaxps %ymm8,%ymm1,%ymm8 - DB 196,226,125,24,13,4,58,0,0 ; vbroadcastss 0x3a04(%rip),%ymm1 # 474c <_sk_callback_hsw+0x18f> + DB 196,226,125,24,13,96,59,0,0 ; vbroadcastss 0x3b60(%rip),%ymm1 # 48a8 <_sk_callback_hsw+0x190> DB 197,116,92,215 ; vsubps %ymm7,%ymm1,%ymm10 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 197,116,92,219 ; vsubps %ymm3,%ymm1,%ymm11 @@ -912,11 +912,11 @@ _sk_saturation_hsw LABEL PROC DB 196,65,28,89,210 ; vmulps %ymm10,%ymm12,%ymm10 DB 196,65,44,94,214 ; vdivps %ymm14,%ymm10,%ymm10 DB 196,67,45,74,224,240 ; vblendvps %ymm15,%ymm8,%ymm10,%ymm12 - DB 196,98,125,24,53,21,57,0,0 ; vbroadcastss 0x3915(%rip),%ymm14 # 4750 <_sk_callback_hsw+0x193> - DB 196,98,125,24,61,16,57,0,0 ; vbroadcastss 0x3910(%rip),%ymm15 # 4754 <_sk_callback_hsw+0x197> + DB 196,98,125,24,53,113,58,0,0 ; vbroadcastss 0x3a71(%rip),%ymm14 # 48ac <_sk_callback_hsw+0x194> + DB 196,98,125,24,61,108,58,0,0 ; vbroadcastss 0x3a6c(%rip),%ymm15 # 48b0 <_sk_callback_hsw+0x198> DB 196,65,84,89,239 ; vmulps %ymm15,%ymm5,%ymm13 DB 196,66,93,184,238 ; vfmadd231ps %ymm14,%ymm4,%ymm13 - DB 196,226,125,24,5,1,57,0,0 ; vbroadcastss 0x3901(%rip),%ymm0 # 4758 <_sk_callback_hsw+0x19b> + DB 196,226,125,24,5,93,58,0,0 ; vbroadcastss 0x3a5d(%rip),%ymm0 # 48b4 <_sk_callback_hsw+0x19c> DB 196,98,77,184,232 ; vfmadd231ps %ymm0,%ymm6,%ymm13 DB 196,65,116,89,215 ; vmulps %ymm15,%ymm1,%ymm10 DB 196,66,53,184,214 ; vfmadd231ps %ymm14,%ymm9,%ymm10 @@ -971,7 +971,7 @@ _sk_saturation_hsw LABEL PROC DB 196,193,124,95,192 ; vmaxps %ymm8,%ymm0,%ymm0 DB 196,65,36,95,200 ; vmaxps %ymm8,%ymm11,%ymm9 DB 196,65,116,95,192 ; vmaxps %ymm8,%ymm1,%ymm8 - DB 196,226,125,24,13,238,55,0,0 ; vbroadcastss 0x37ee(%rip),%ymm1 # 475c <_sk_callback_hsw+0x19f> + DB 196,226,125,24,13,74,57,0,0 ; vbroadcastss 0x394a(%rip),%ymm1 # 48b8 <_sk_callback_hsw+0x1a0> DB 197,116,92,215 ; vsubps %ymm7,%ymm1,%ymm10 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 197,116,92,219 ; vsubps %ymm3,%ymm1,%ymm11 @@ -999,11 +999,11 @@ _sk_color_hsw LABEL PROC DB 197,108,89,199 ; vmulps %ymm7,%ymm2,%ymm8 DB 197,116,89,215 ; vmulps %ymm7,%ymm1,%ymm10 DB 197,52,89,223 ; vmulps %ymm7,%ymm9,%ymm11 - DB 196,98,125,24,45,129,55,0,0 ; vbroadcastss 0x3781(%rip),%ymm13 # 4760 <_sk_callback_hsw+0x1a3> - DB 196,98,125,24,53,124,55,0,0 ; vbroadcastss 0x377c(%rip),%ymm14 # 4764 <_sk_callback_hsw+0x1a7> + DB 196,98,125,24,45,221,56,0,0 ; vbroadcastss 0x38dd(%rip),%ymm13 # 48bc <_sk_callback_hsw+0x1a4> + DB 196,98,125,24,53,216,56,0,0 ; vbroadcastss 0x38d8(%rip),%ymm14 # 48c0 <_sk_callback_hsw+0x1a8> DB 196,65,84,89,230 ; vmulps %ymm14,%ymm5,%ymm12 DB 196,66,93,184,229 ; vfmadd231ps %ymm13,%ymm4,%ymm12 - DB 196,98,125,24,61,109,55,0,0 ; vbroadcastss 0x376d(%rip),%ymm15 # 4768 <_sk_callback_hsw+0x1ab> + DB 196,98,125,24,61,201,56,0,0 ; vbroadcastss 0x38c9(%rip),%ymm15 # 48c4 <_sk_callback_hsw+0x1ac> DB 196,66,77,184,231 ; vfmadd231ps %ymm15,%ymm6,%ymm12 DB 196,65,44,89,206 ; vmulps %ymm14,%ymm10,%ymm9 DB 196,66,61,184,205 ; vfmadd231ps %ymm13,%ymm8,%ymm9 @@ -1059,7 +1059,7 @@ _sk_color_hsw LABEL PROC DB 196,193,116,95,206 ; vmaxps %ymm14,%ymm1,%ymm1 DB 196,65,44,95,198 ; vmaxps %ymm14,%ymm10,%ymm8 DB 196,65,124,95,206 ; vmaxps %ymm14,%ymm0,%ymm9 - DB 196,226,125,24,5,79,54,0,0 ; vbroadcastss 0x364f(%rip),%ymm0 # 476c <_sk_callback_hsw+0x1af> + DB 196,226,125,24,5,171,55,0,0 ; vbroadcastss 0x37ab(%rip),%ymm0 # 48c8 <_sk_callback_hsw+0x1b0> DB 197,124,92,215 ; vsubps %ymm7,%ymm0,%ymm10 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 197,124,92,219 ; vsubps %ymm3,%ymm0,%ymm11 @@ -1087,11 +1087,11 @@ _sk_luminosity_hsw LABEL PROC DB 197,100,89,196 ; vmulps %ymm4,%ymm3,%ymm8 DB 197,100,89,213 ; vmulps %ymm5,%ymm3,%ymm10 DB 197,100,89,222 ; vmulps %ymm6,%ymm3,%ymm11 - DB 196,98,125,24,45,226,53,0,0 ; vbroadcastss 0x35e2(%rip),%ymm13 # 4770 <_sk_callback_hsw+0x1b3> - DB 196,98,125,24,53,221,53,0,0 ; vbroadcastss 0x35dd(%rip),%ymm14 # 4774 <_sk_callback_hsw+0x1b7> + DB 196,98,125,24,45,62,55,0,0 ; vbroadcastss 0x373e(%rip),%ymm13 # 48cc <_sk_callback_hsw+0x1b4> + DB 196,98,125,24,53,57,55,0,0 ; vbroadcastss 0x3739(%rip),%ymm14 # 48d0 <_sk_callback_hsw+0x1b8> DB 196,65,116,89,230 ; vmulps %ymm14,%ymm1,%ymm12 DB 196,66,109,184,229 ; vfmadd231ps %ymm13,%ymm2,%ymm12 - DB 196,98,125,24,61,206,53,0,0 ; vbroadcastss 0x35ce(%rip),%ymm15 # 4778 <_sk_callback_hsw+0x1bb> + DB 196,98,125,24,61,42,55,0,0 ; vbroadcastss 0x372a(%rip),%ymm15 # 48d4 <_sk_callback_hsw+0x1bc> DB 196,66,53,184,231 ; vfmadd231ps %ymm15,%ymm9,%ymm12 DB 196,65,44,89,206 ; vmulps %ymm14,%ymm10,%ymm9 DB 196,66,61,184,205 ; vfmadd231ps %ymm13,%ymm8,%ymm9 @@ -1147,7 +1147,7 @@ _sk_luminosity_hsw LABEL PROC DB 196,193,116,95,206 ; vmaxps %ymm14,%ymm1,%ymm1 DB 196,65,44,95,198 ; vmaxps %ymm14,%ymm10,%ymm8 DB 196,65,124,95,206 ; vmaxps %ymm14,%ymm0,%ymm9 - DB 196,226,125,24,5,176,52,0,0 ; vbroadcastss 0x34b0(%rip),%ymm0 # 477c <_sk_callback_hsw+0x1bf> + DB 196,226,125,24,5,12,54,0,0 ; vbroadcastss 0x360c(%rip),%ymm0 # 48d8 <_sk_callback_hsw+0x1c0> DB 197,124,92,215 ; vsubps %ymm7,%ymm0,%ymm10 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 197,124,92,219 ; vsubps %ymm3,%ymm0,%ymm11 @@ -1177,7 +1177,7 @@ _sk_clamp_0_hsw LABEL PROC PUBLIC _sk_clamp_1_hsw _sk_clamp_1_hsw LABEL PROC - DB 196,98,125,24,5,73,52,0,0 ; vbroadcastss 0x3449(%rip),%ymm8 # 4780 <_sk_callback_hsw+0x1c3> + DB 196,98,125,24,5,165,53,0,0 ; vbroadcastss 0x35a5(%rip),%ymm8 # 48dc <_sk_callback_hsw+0x1c4> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 @@ -1187,7 +1187,7 @@ _sk_clamp_1_hsw LABEL PROC PUBLIC _sk_clamp_a_hsw _sk_clamp_a_hsw LABEL PROC - DB 196,98,125,24,5,44,52,0,0 ; vbroadcastss 0x342c(%rip),%ymm8 # 4784 <_sk_callback_hsw+0x1c7> + DB 196,98,125,24,5,136,53,0,0 ; vbroadcastss 0x3588(%rip),%ymm8 # 48e0 <_sk_callback_hsw+0x1c8> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 197,252,93,195 ; vminps %ymm3,%ymm0,%ymm0 DB 197,244,93,203 ; vminps %ymm3,%ymm1,%ymm1 @@ -1259,7 +1259,7 @@ PUBLIC _sk_unpremul_hsw _sk_unpremul_hsw LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,65,100,194,200,0 ; vcmpeqps %ymm8,%ymm3,%ymm9 - DB 196,98,125,24,21,116,51,0,0 ; vbroadcastss 0x3374(%rip),%ymm10 # 4788 <_sk_callback_hsw+0x1cb> + DB 196,98,125,24,21,208,52,0,0 ; vbroadcastss 0x34d0(%rip),%ymm10 # 48e4 <_sk_callback_hsw+0x1cc> DB 197,44,94,211 ; vdivps %ymm3,%ymm10,%ymm10 DB 196,67,45,74,192,144 ; vblendvps %ymm9,%ymm8,%ymm10,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 @@ -1270,16 +1270,16 @@ _sk_unpremul_hsw LABEL PROC PUBLIC _sk_from_srgb_hsw _sk_from_srgb_hsw LABEL PROC - DB 196,98,125,24,5,85,51,0,0 ; vbroadcastss 0x3355(%rip),%ymm8 # 478c <_sk_callback_hsw+0x1cf> + DB 196,98,125,24,5,177,52,0,0 ; vbroadcastss 0x34b1(%rip),%ymm8 # 48e8 <_sk_callback_hsw+0x1d0> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 197,124,89,208 ; vmulps %ymm0,%ymm0,%ymm10 - DB 196,98,125,24,29,71,51,0,0 ; vbroadcastss 0x3347(%rip),%ymm11 # 4790 <_sk_callback_hsw+0x1d3> - DB 196,98,125,24,37,66,51,0,0 ; vbroadcastss 0x3342(%rip),%ymm12 # 4794 <_sk_callback_hsw+0x1d7> + DB 196,98,125,24,29,163,52,0,0 ; vbroadcastss 0x34a3(%rip),%ymm11 # 48ec <_sk_callback_hsw+0x1d4> + DB 196,98,125,24,37,158,52,0,0 ; vbroadcastss 0x349e(%rip),%ymm12 # 48f0 <_sk_callback_hsw+0x1d8> DB 196,65,124,40,236 ; vmovaps %ymm12,%ymm13 DB 196,66,125,168,235 ; vfmadd213ps %ymm11,%ymm0,%ymm13 - DB 196,98,125,24,53,51,51,0,0 ; vbroadcastss 0x3333(%rip),%ymm14 # 4798 <_sk_callback_hsw+0x1db> + DB 196,98,125,24,53,143,52,0,0 ; vbroadcastss 0x348f(%rip),%ymm14 # 48f4 <_sk_callback_hsw+0x1dc> DB 196,66,45,168,238 ; vfmadd213ps %ymm14,%ymm10,%ymm13 - DB 196,98,125,24,21,41,51,0,0 ; vbroadcastss 0x3329(%rip),%ymm10 # 479c <_sk_callback_hsw+0x1df> + DB 196,98,125,24,21,133,52,0,0 ; vbroadcastss 0x3485(%rip),%ymm10 # 48f8 <_sk_callback_hsw+0x1e0> DB 196,193,124,194,194,1 ; vcmpltps %ymm10,%ymm0,%ymm0 DB 196,195,21,74,193,0 ; vblendvps %ymm0,%ymm9,%ymm13,%ymm0 DB 196,65,116,89,200 ; vmulps %ymm8,%ymm1,%ymm9 @@ -1303,16 +1303,16 @@ _sk_to_srgb_hsw LABEL PROC DB 197,124,82,192 ; vrsqrtps %ymm0,%ymm8 DB 196,65,124,83,200 ; vrcpps %ymm8,%ymm9 DB 196,65,124,82,208 ; vrsqrtps %ymm8,%ymm10 - DB 196,98,125,24,5,195,50,0,0 ; vbroadcastss 0x32c3(%rip),%ymm8 # 47a0 <_sk_callback_hsw+0x1e3> + DB 196,98,125,24,5,31,52,0,0 ; vbroadcastss 0x341f(%rip),%ymm8 # 48fc <_sk_callback_hsw+0x1e4> DB 196,65,124,89,216 ; vmulps %ymm8,%ymm0,%ymm11 - DB 196,98,125,24,37,185,50,0,0 ; vbroadcastss 0x32b9(%rip),%ymm12 # 47a4 <_sk_callback_hsw+0x1e7> - DB 196,98,125,24,45,180,50,0,0 ; vbroadcastss 0x32b4(%rip),%ymm13 # 47a8 <_sk_callback_hsw+0x1eb> + DB 196,98,125,24,37,21,52,0,0 ; vbroadcastss 0x3415(%rip),%ymm12 # 4900 <_sk_callback_hsw+0x1e8> + DB 196,98,125,24,45,16,52,0,0 ; vbroadcastss 0x3410(%rip),%ymm13 # 4904 <_sk_callback_hsw+0x1ec> DB 196,66,21,168,204 ; vfmadd213ps %ymm12,%ymm13,%ymm9 - DB 196,98,125,24,53,170,50,0,0 ; vbroadcastss 0x32aa(%rip),%ymm14 # 47ac <_sk_callback_hsw+0x1ef> + DB 196,98,125,24,53,6,52,0,0 ; vbroadcastss 0x3406(%rip),%ymm14 # 4908 <_sk_callback_hsw+0x1f0> DB 196,66,13,184,202 ; vfmadd231ps %ymm10,%ymm14,%ymm9 - DB 196,98,125,24,21,160,50,0,0 ; vbroadcastss 0x32a0(%rip),%ymm10 # 47b0 <_sk_callback_hsw+0x1f3> + DB 196,98,125,24,21,252,51,0,0 ; vbroadcastss 0x33fc(%rip),%ymm10 # 490c <_sk_callback_hsw+0x1f4> DB 196,65,44,93,201 ; vminps %ymm9,%ymm10,%ymm9 - DB 196,98,125,24,61,150,50,0,0 ; vbroadcastss 0x3296(%rip),%ymm15 # 47b4 <_sk_callback_hsw+0x1f7> + DB 196,98,125,24,61,242,51,0,0 ; vbroadcastss 0x33f2(%rip),%ymm15 # 4910 <_sk_callback_hsw+0x1f8> DB 196,193,124,194,199,1 ; vcmpltps %ymm15,%ymm0,%ymm0 DB 196,195,53,74,195,0 ; vblendvps %ymm0,%ymm11,%ymm9,%ymm0 DB 197,124,82,201 ; vrsqrtps %ymm1,%ymm9 @@ -1343,26 +1343,26 @@ _sk_rgb_to_hsl_hsw LABEL PROC DB 197,124,93,201 ; vminps %ymm1,%ymm0,%ymm9 DB 197,52,93,202 ; vminps %ymm2,%ymm9,%ymm9 DB 196,65,60,92,209 ; vsubps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,29,16,50,0,0 ; vbroadcastss 0x3210(%rip),%ymm11 # 47b8 <_sk_callback_hsw+0x1fb> + DB 196,98,125,24,29,108,51,0,0 ; vbroadcastss 0x336c(%rip),%ymm11 # 4914 <_sk_callback_hsw+0x1fc> DB 196,65,36,94,218 ; vdivps %ymm10,%ymm11,%ymm11 DB 197,116,92,226 ; vsubps %ymm2,%ymm1,%ymm12 DB 197,116,194,234,1 ; vcmpltps %ymm2,%ymm1,%ymm13 - DB 196,98,125,24,53,253,49,0,0 ; vbroadcastss 0x31fd(%rip),%ymm14 # 47bc <_sk_callback_hsw+0x1ff> + DB 196,98,125,24,53,89,51,0,0 ; vbroadcastss 0x3359(%rip),%ymm14 # 4918 <_sk_callback_hsw+0x200> DB 196,65,4,87,255 ; vxorps %ymm15,%ymm15,%ymm15 DB 196,67,5,74,238,208 ; vblendvps %ymm13,%ymm14,%ymm15,%ymm13 DB 196,66,37,168,229 ; vfmadd213ps %ymm13,%ymm11,%ymm12 DB 197,236,92,208 ; vsubps %ymm0,%ymm2,%ymm2 DB 197,124,92,233 ; vsubps %ymm1,%ymm0,%ymm13 - DB 196,98,125,24,53,228,49,0,0 ; vbroadcastss 0x31e4(%rip),%ymm14 # 47c4 <_sk_callback_hsw+0x207> + DB 196,98,125,24,53,64,51,0,0 ; vbroadcastss 0x3340(%rip),%ymm14 # 4920 <_sk_callback_hsw+0x208> DB 196,66,37,168,238 ; vfmadd213ps %ymm14,%ymm11,%ymm13 - DB 196,98,125,24,53,210,49,0,0 ; vbroadcastss 0x31d2(%rip),%ymm14 # 47c0 <_sk_callback_hsw+0x203> + DB 196,98,125,24,53,46,51,0,0 ; vbroadcastss 0x332e(%rip),%ymm14 # 491c <_sk_callback_hsw+0x204> DB 196,194,37,168,214 ; vfmadd213ps %ymm14,%ymm11,%ymm2 DB 197,188,194,201,0 ; vcmpeqps %ymm1,%ymm8,%ymm1 DB 196,227,21,74,202,16 ; vblendvps %ymm1,%ymm2,%ymm13,%ymm1 DB 197,188,194,192,0 ; vcmpeqps %ymm0,%ymm8,%ymm0 DB 196,195,117,74,196,0 ; vblendvps %ymm0,%ymm12,%ymm1,%ymm0 DB 196,193,60,88,201 ; vaddps %ymm9,%ymm8,%ymm1 - DB 196,98,125,24,29,181,49,0,0 ; vbroadcastss 0x31b5(%rip),%ymm11 # 47cc <_sk_callback_hsw+0x20f> + DB 196,98,125,24,29,17,51,0,0 ; vbroadcastss 0x3311(%rip),%ymm11 # 4928 <_sk_callback_hsw+0x210> DB 196,193,116,89,211 ; vmulps %ymm11,%ymm1,%ymm2 DB 197,36,194,218,1 ; vcmpltps %ymm2,%ymm11,%ymm11 DB 196,65,12,92,224 ; vsubps %ymm8,%ymm14,%ymm12 @@ -1372,7 +1372,7 @@ _sk_rgb_to_hsl_hsw LABEL PROC DB 197,172,94,201 ; vdivps %ymm1,%ymm10,%ymm1 DB 196,195,125,74,199,128 ; vblendvps %ymm8,%ymm15,%ymm0,%ymm0 DB 196,195,117,74,207,128 ; vblendvps %ymm8,%ymm15,%ymm1,%ymm1 - DB 196,98,125,24,5,120,49,0,0 ; vbroadcastss 0x3178(%rip),%ymm8 # 47c8 <_sk_callback_hsw+0x20b> + DB 196,98,125,24,5,212,50,0,0 ; vbroadcastss 0x32d4(%rip),%ymm8 # 4924 <_sk_callback_hsw+0x20c> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -1387,30 +1387,30 @@ _sk_hsl_to_rgb_hsw LABEL PROC DB 197,252,17,28,36 ; vmovups %ymm3,(%rsp) DB 197,252,40,233 ; vmovaps %ymm1,%ymm5 DB 197,252,40,224 ; vmovaps %ymm0,%ymm4 - DB 196,98,125,24,5,63,49,0,0 ; vbroadcastss 0x313f(%rip),%ymm8 # 47d0 <_sk_callback_hsw+0x213> + DB 196,98,125,24,5,155,50,0,0 ; vbroadcastss 0x329b(%rip),%ymm8 # 492c <_sk_callback_hsw+0x214> DB 197,60,194,202,2 ; vcmpleps %ymm2,%ymm8,%ymm9 DB 197,84,89,210 ; vmulps %ymm2,%ymm5,%ymm10 DB 196,65,84,92,218 ; vsubps %ymm10,%ymm5,%ymm11 DB 196,67,45,74,203,144 ; vblendvps %ymm9,%ymm11,%ymm10,%ymm9 DB 197,52,88,210 ; vaddps %ymm2,%ymm9,%ymm10 - DB 196,98,125,24,13,34,49,0,0 ; vbroadcastss 0x3122(%rip),%ymm9 # 47d4 <_sk_callback_hsw+0x217> + DB 196,98,125,24,13,126,50,0,0 ; vbroadcastss 0x327e(%rip),%ymm9 # 4930 <_sk_callback_hsw+0x218> DB 196,66,109,170,202 ; vfmsub213ps %ymm10,%ymm2,%ymm9 - DB 196,98,125,24,29,24,49,0,0 ; vbroadcastss 0x3118(%rip),%ymm11 # 47d8 <_sk_callback_hsw+0x21b> + DB 196,98,125,24,29,116,50,0,0 ; vbroadcastss 0x3274(%rip),%ymm11 # 4934 <_sk_callback_hsw+0x21c> DB 196,65,92,88,219 ; vaddps %ymm11,%ymm4,%ymm11 DB 196,67,125,8,227,1 ; vroundps $0x1,%ymm11,%ymm12 DB 196,65,36,92,252 ; vsubps %ymm12,%ymm11,%ymm15 DB 196,65,44,92,217 ; vsubps %ymm9,%ymm10,%ymm11 - DB 196,98,125,24,45,2,49,0,0 ; vbroadcastss 0x3102(%rip),%ymm13 # 47e0 <_sk_callback_hsw+0x223> + DB 196,98,125,24,45,94,50,0,0 ; vbroadcastss 0x325e(%rip),%ymm13 # 493c <_sk_callback_hsw+0x224> DB 196,193,4,89,197 ; vmulps %ymm13,%ymm15,%ymm0 - DB 196,98,125,24,53,248,48,0,0 ; vbroadcastss 0x30f8(%rip),%ymm14 # 47e4 <_sk_callback_hsw+0x227> + DB 196,98,125,24,53,84,50,0,0 ; vbroadcastss 0x3254(%rip),%ymm14 # 4940 <_sk_callback_hsw+0x228> DB 197,12,92,224 ; vsubps %ymm0,%ymm14,%ymm12 DB 196,66,37,168,225 ; vfmadd213ps %ymm9,%ymm11,%ymm12 - DB 196,226,125,24,29,222,48,0,0 ; vbroadcastss 0x30de(%rip),%ymm3 # 47dc <_sk_callback_hsw+0x21f> + DB 196,226,125,24,29,58,50,0,0 ; vbroadcastss 0x323a(%rip),%ymm3 # 4938 <_sk_callback_hsw+0x220> DB 196,193,100,194,255,2 ; vcmpleps %ymm15,%ymm3,%ymm7 DB 196,195,29,74,249,112 ; vblendvps %ymm7,%ymm9,%ymm12,%ymm7 DB 196,65,60,194,231,2 ; vcmpleps %ymm15,%ymm8,%ymm12 DB 196,227,45,74,255,192 ; vblendvps %ymm12,%ymm7,%ymm10,%ymm7 - DB 196,98,125,24,37,201,48,0,0 ; vbroadcastss 0x30c9(%rip),%ymm12 # 47e8 <_sk_callback_hsw+0x22b> + DB 196,98,125,24,37,37,50,0,0 ; vbroadcastss 0x3225(%rip),%ymm12 # 4944 <_sk_callback_hsw+0x22c> DB 196,65,28,194,255,2 ; vcmpleps %ymm15,%ymm12,%ymm15 DB 196,194,37,168,193 ; vfmadd213ps %ymm9,%ymm11,%ymm0 DB 196,99,125,74,255,240 ; vblendvps %ymm15,%ymm7,%ymm0,%ymm15 @@ -1426,7 +1426,7 @@ _sk_hsl_to_rgb_hsw LABEL PROC DB 197,156,194,192,2 ; vcmpleps %ymm0,%ymm12,%ymm0 DB 196,194,37,168,249 ; vfmadd213ps %ymm9,%ymm11,%ymm7 DB 196,227,69,74,201,0 ; vblendvps %ymm0,%ymm1,%ymm7,%ymm1 - DB 196,226,125,24,5,117,48,0,0 ; vbroadcastss 0x3075(%rip),%ymm0 # 47ec <_sk_callback_hsw+0x22f> + DB 196,226,125,24,5,209,49,0,0 ; vbroadcastss 0x31d1(%rip),%ymm0 # 4948 <_sk_callback_hsw+0x230> DB 197,220,88,192 ; vaddps %ymm0,%ymm4,%ymm0 DB 196,227,125,8,224,1 ; vroundps $0x1,%ymm0,%ymm4 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 @@ -1476,7 +1476,7 @@ _sk_scale_u8_hsw LABEL PROC DB 197,122,126,0 ; vmovq (%rax),%xmm8 DB 196,66,125,49,192 ; vpmovzxbd %xmm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,175,47,0,0 ; vbroadcastss 0x2faf(%rip),%ymm9 # 47f0 <_sk_callback_hsw+0x233> + DB 196,98,125,24,13,11,49,0,0 ; vbroadcastss 0x310b(%rip),%ymm9 # 494c <_sk_callback_hsw+0x234> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -1524,7 +1524,7 @@ _sk_lerp_u8_hsw LABEL PROC DB 197,122,126,0 ; vmovq (%rax),%xmm8 DB 196,66,125,49,192 ; vpmovzxbd %xmm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,28,47,0,0 ; vbroadcastss 0x2f1c(%rip),%ymm9 # 47f4 <_sk_callback_hsw+0x237> + DB 196,98,125,24,13,120,48,0,0 ; vbroadcastss 0x3078(%rip),%ymm9 # 4950 <_sk_callback_hsw+0x238> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,226,61,168,196 ; vfmadd213ps %ymm4,%ymm8,%ymm0 @@ -1558,20 +1558,20 @@ _sk_lerp_565_hsw LABEL PROC DB 15,133,169,0,0,0 ; jne 19e4 <_sk_lerp_565_hsw+0xb7> DB 196,65,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm8 DB 196,66,125,51,192 ; vpmovzxwd %xmm8,%ymm8 - DB 196,98,125,88,13,169,46,0,0 ; vpbroadcastd 0x2ea9(%rip),%ymm9 # 47f8 <_sk_callback_hsw+0x23b> + DB 196,98,125,88,13,5,48,0,0 ; vpbroadcastd 0x3005(%rip),%ymm9 # 4954 <_sk_callback_hsw+0x23c> DB 196,65,61,219,201 ; vpand %ymm9,%ymm8,%ymm9 DB 196,65,124,91,201 ; vcvtdq2ps %ymm9,%ymm9 - DB 196,98,125,24,21,154,46,0,0 ; vbroadcastss 0x2e9a(%rip),%ymm10 # 47fc <_sk_callback_hsw+0x23f> + DB 196,98,125,24,21,246,47,0,0 ; vbroadcastss 0x2ff6(%rip),%ymm10 # 4958 <_sk_callback_hsw+0x240> DB 196,65,52,89,202 ; vmulps %ymm10,%ymm9,%ymm9 - DB 196,98,125,88,21,144,46,0,0 ; vpbroadcastd 0x2e90(%rip),%ymm10 # 4800 <_sk_callback_hsw+0x243> + DB 196,98,125,88,21,236,47,0,0 ; vpbroadcastd 0x2fec(%rip),%ymm10 # 495c <_sk_callback_hsw+0x244> DB 196,65,61,219,210 ; vpand %ymm10,%ymm8,%ymm10 DB 196,65,124,91,210 ; vcvtdq2ps %ymm10,%ymm10 - DB 196,98,125,24,29,129,46,0,0 ; vbroadcastss 0x2e81(%rip),%ymm11 # 4804 <_sk_callback_hsw+0x247> + DB 196,98,125,24,29,221,47,0,0 ; vbroadcastss 0x2fdd(%rip),%ymm11 # 4960 <_sk_callback_hsw+0x248> DB 196,65,44,89,211 ; vmulps %ymm11,%ymm10,%ymm10 - DB 196,98,125,88,29,119,46,0,0 ; vpbroadcastd 0x2e77(%rip),%ymm11 # 4808 <_sk_callback_hsw+0x24b> + DB 196,98,125,88,29,211,47,0,0 ; vpbroadcastd 0x2fd3(%rip),%ymm11 # 4964 <_sk_callback_hsw+0x24c> DB 196,65,61,219,195 ; vpand %ymm11,%ymm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,29,104,46,0,0 ; vbroadcastss 0x2e68(%rip),%ymm11 # 480c <_sk_callback_hsw+0x24f> + DB 196,98,125,24,29,196,47,0,0 ; vbroadcastss 0x2fc4(%rip),%ymm11 # 4968 <_sk_callback_hsw+0x250> DB 196,65,60,89,195 ; vmulps %ymm11,%ymm8,%ymm8 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,226,53,168,196 ; vfmadd213ps %ymm4,%ymm9,%ymm0 @@ -1641,21 +1641,21 @@ _sk_load_tables_hsw LABEL PROC DB 77,133,192 ; test %r8,%r8 DB 117,105 ; jne 1aee <_sk_load_tables_hsw+0x7e> DB 196,193,126,111,25 ; vmovdqu (%r9),%ymm3 - DB 197,229,219,13,46,48,0,0 ; vpand 0x302e(%rip),%ymm3,%ymm1 # 4ac0 <_sk_callback_hsw+0x503> + DB 197,229,219,13,142,49,0,0 ; vpand 0x318e(%rip),%ymm3,%ymm1 # 4c20 <_sk_callback_hsw+0x508> DB 196,65,61,118,192 ; vpcmpeqd %ymm8,%ymm8,%ymm8 DB 72,139,72,8 ; mov 0x8(%rax),%rcx DB 76,139,72,16 ; mov 0x10(%rax),%r9 DB 197,237,118,210 ; vpcmpeqd %ymm2,%ymm2,%ymm2 DB 196,226,109,146,4,137 ; vgatherdps %ymm2,(%rcx,%ymm1,4),%ymm0 - DB 196,226,101,0,21,46,48,0,0 ; vpshufb 0x302e(%rip),%ymm3,%ymm2 # 4ae0 <_sk_callback_hsw+0x523> + DB 196,226,101,0,21,142,49,0,0 ; vpshufb 0x318e(%rip),%ymm3,%ymm2 # 4c40 <_sk_callback_hsw+0x528> DB 196,65,53,118,201 ; vpcmpeqd %ymm9,%ymm9,%ymm9 DB 196,194,53,146,12,145 ; vgatherdps %ymm9,(%r9,%ymm2,4),%ymm1 DB 72,139,64,24 ; mov 0x18(%rax),%rax - DB 196,98,101,0,13,54,48,0,0 ; vpshufb 0x3036(%rip),%ymm3,%ymm9 # 4b00 <_sk_callback_hsw+0x543> + DB 196,98,101,0,13,150,49,0,0 ; vpshufb 0x3196(%rip),%ymm3,%ymm9 # 4c60 <_sk_callback_hsw+0x548> DB 196,162,61,146,20,136 ; vgatherdps %ymm8,(%rax,%ymm9,4),%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,46,45,0,0 ; vbroadcastss 0x2d2e(%rip),%ymm8 # 4810 <_sk_callback_hsw+0x253> + DB 196,98,125,24,5,138,46,0,0 ; vbroadcastss 0x2e8a(%rip),%ymm8 # 496c <_sk_callback_hsw+0x254> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 76,137,193 ; mov %r8,%rcx @@ -1692,7 +1692,7 @@ _sk_load_tables_u16_be_hsw LABEL PROC DB 197,185,108,200 ; vpunpcklqdq %xmm0,%xmm8,%xmm1 DB 197,185,109,208 ; vpunpckhqdq %xmm0,%xmm8,%xmm2 DB 197,49,108,195 ; vpunpcklqdq %xmm3,%xmm9,%xmm8 - DB 197,121,111,21,194,48,0,0 ; vmovdqa 0x30c2(%rip),%xmm10 # 4c40 <_sk_callback_hsw+0x683> + DB 197,121,111,21,34,50,0,0 ; vmovdqa 0x3222(%rip),%xmm10 # 4da0 <_sk_callback_hsw+0x688> DB 196,193,113,219,194 ; vpand %xmm10,%xmm1,%xmm0 DB 196,226,125,51,200 ; vpmovzxwd %xmm0,%ymm1 DB 196,65,37,118,219 ; vpcmpeqd %ymm11,%ymm11,%ymm11 @@ -1714,7 +1714,7 @@ _sk_load_tables_u16_be_hsw LABEL PROC DB 197,185,235,219 ; vpor %xmm3,%xmm8,%xmm3 DB 196,226,125,51,219 ; vpmovzxwd %xmm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,39,44,0,0 ; vbroadcastss 0x2c27(%rip),%ymm8 # 4814 <_sk_callback_hsw+0x257> + DB 196,98,125,24,5,131,45,0,0 ; vbroadcastss 0x2d83(%rip),%ymm8 # 4970 <_sk_callback_hsw+0x258> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -1772,7 +1772,7 @@ _sk_load_tables_rgb_u16_be_hsw LABEL PROC DB 197,185,108,218 ; vpunpcklqdq %xmm2,%xmm8,%xmm3 DB 197,185,109,210 ; vpunpckhqdq %xmm2,%xmm8,%xmm2 DB 197,121,108,193 ; vpunpcklqdq %xmm1,%xmm0,%xmm8 - DB 197,121,111,13,98,47,0,0 ; vmovdqa 0x2f62(%rip),%xmm9 # 4c50 <_sk_callback_hsw+0x693> + DB 197,121,111,13,194,48,0,0 ; vmovdqa 0x30c2(%rip),%xmm9 # 4db0 <_sk_callback_hsw+0x698> DB 196,193,97,219,193 ; vpand %xmm9,%xmm3,%xmm0 DB 196,226,125,51,200 ; vpmovzxwd %xmm0,%ymm1 DB 197,229,118,219 ; vpcmpeqd %ymm3,%ymm3,%ymm3 @@ -1789,7 +1789,7 @@ _sk_load_tables_rgb_u16_be_hsw LABEL PROC DB 196,98,125,51,194 ; vpmovzxwd %xmm2,%ymm8 DB 196,162,101,146,20,128 ; vgatherdps %ymm3,(%rax,%ymm8,4),%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,213,42,0,0 ; vbroadcastss 0x2ad5(%rip),%ymm3 # 4818 <_sk_callback_hsw+0x25b> + DB 196,226,125,24,29,49,44,0,0 ; vbroadcastss 0x2c31(%rip),%ymm3 # 4974 <_sk_callback_hsw+0x25c> DB 255,224 ; jmpq *%rax DB 196,129,121,110,4,72 ; vmovd (%r8,%r9,2),%xmm0 DB 196,129,121,196,68,72,4,2 ; vpinsrw $0x2,0x4(%r8,%r9,2),%xmm0,%xmm0 @@ -1834,7 +1834,7 @@ _sk_byte_tables_hsw LABEL PROC DB 65,84 ; push %r12 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,19,42,0,0 ; vbroadcastss 0x2a13(%rip),%ymm8 # 481c <_sk_callback_hsw+0x25f> + DB 196,98,125,24,5,111,43,0,0 ; vbroadcastss 0x2b6f(%rip),%ymm8 # 4978 <_sk_callback_hsw+0x260> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,195,249,22,192,1 ; vpextrq $0x1,%xmm0,%r8 @@ -1871,7 +1871,7 @@ _sk_byte_tables_hsw LABEL PROC DB 196,227,121,32,197,7 ; vpinsrb $0x7,%ebp,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,100,41,0,0 ; vbroadcastss 0x2964(%rip),%ymm9 # 4820 <_sk_callback_hsw+0x263> + DB 196,98,125,24,13,192,42,0,0 ; vbroadcastss 0x2ac0(%rip),%ymm9 # 497c <_sk_callback_hsw+0x264> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -2030,7 +2030,7 @@ _sk_byte_tables_rgb_hsw LABEL PROC DB 196,227,121,32,197,7 ; vpinsrb $0x7,%ebp,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,157,38,0,0 ; vbroadcastss 0x269d(%rip),%ymm9 # 4824 <_sk_callback_hsw+0x267> + DB 196,98,125,24,13,249,39,0,0 ; vbroadcastss 0x27f9(%rip),%ymm9 # 4980 <_sk_callback_hsw+0x268> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -2183,33 +2183,33 @@ _sk_parametric_r_hsw LABEL PROC DB 196,66,125,168,211 ; vfmadd213ps %ymm11,%ymm0,%ymm10 DB 196,226,125,24,0 ; vbroadcastss (%rax),%ymm0 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,80,36,0,0 ; vbroadcastss 0x2450(%rip),%ymm12 # 4828 <_sk_callback_hsw+0x26b> - DB 196,98,125,24,45,75,36,0,0 ; vbroadcastss 0x244b(%rip),%ymm13 # 482c <_sk_callback_hsw+0x26f> + DB 196,98,125,24,37,172,37,0,0 ; vbroadcastss 0x25ac(%rip),%ymm12 # 4984 <_sk_callback_hsw+0x26c> + DB 196,98,125,24,45,167,37,0,0 ; vbroadcastss 0x25a7(%rip),%ymm13 # 4988 <_sk_callback_hsw+0x270> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,65,36,0,0 ; vbroadcastss 0x2441(%rip),%ymm13 # 4830 <_sk_callback_hsw+0x273> + DB 196,98,125,24,45,157,37,0,0 ; vbroadcastss 0x259d(%rip),%ymm13 # 498c <_sk_callback_hsw+0x274> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,55,36,0,0 ; vbroadcastss 0x2437(%rip),%ymm13 # 4834 <_sk_callback_hsw+0x277> + DB 196,98,125,24,45,147,37,0,0 ; vbroadcastss 0x2593(%rip),%ymm13 # 4990 <_sk_callback_hsw+0x278> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,45,36,0,0 ; vbroadcastss 0x242d(%rip),%ymm11 # 4838 <_sk_callback_hsw+0x27b> + DB 196,98,125,24,29,137,37,0,0 ; vbroadcastss 0x2589(%rip),%ymm11 # 4994 <_sk_callback_hsw+0x27c> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,35,36,0,0 ; vbroadcastss 0x2423(%rip),%ymm12 # 483c <_sk_callback_hsw+0x27f> + DB 196,98,125,24,37,127,37,0,0 ; vbroadcastss 0x257f(%rip),%ymm12 # 4998 <_sk_callback_hsw+0x280> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,25,36,0,0 ; vbroadcastss 0x2419(%rip),%ymm12 # 4840 <_sk_callback_hsw+0x283> + DB 196,98,125,24,37,117,37,0,0 ; vbroadcastss 0x2575(%rip),%ymm12 # 499c <_sk_callback_hsw+0x284> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 196,99,125,8,208,1 ; vroundps $0x1,%ymm0,%ymm10 DB 196,65,124,92,210 ; vsubps %ymm10,%ymm0,%ymm10 - DB 196,98,125,24,29,250,35,0,0 ; vbroadcastss 0x23fa(%rip),%ymm11 # 4844 <_sk_callback_hsw+0x287> + DB 196,98,125,24,29,86,37,0,0 ; vbroadcastss 0x2556(%rip),%ymm11 # 49a0 <_sk_callback_hsw+0x288> DB 196,193,124,88,195 ; vaddps %ymm11,%ymm0,%ymm0 - DB 196,98,125,24,29,240,35,0,0 ; vbroadcastss 0x23f0(%rip),%ymm11 # 4848 <_sk_callback_hsw+0x28b> + DB 196,98,125,24,29,76,37,0,0 ; vbroadcastss 0x254c(%rip),%ymm11 # 49a4 <_sk_callback_hsw+0x28c> DB 196,98,45,172,216 ; vfnmadd213ps %ymm0,%ymm10,%ymm11 - DB 196,226,125,24,5,230,35,0,0 ; vbroadcastss 0x23e6(%rip),%ymm0 # 484c <_sk_callback_hsw+0x28f> + DB 196,226,125,24,5,66,37,0,0 ; vbroadcastss 0x2542(%rip),%ymm0 # 49a8 <_sk_callback_hsw+0x290> DB 196,193,124,92,194 ; vsubps %ymm10,%ymm0,%ymm0 - DB 196,98,125,24,21,220,35,0,0 ; vbroadcastss 0x23dc(%rip),%ymm10 # 4850 <_sk_callback_hsw+0x293> + DB 196,98,125,24,21,56,37,0,0 ; vbroadcastss 0x2538(%rip),%ymm10 # 49ac <_sk_callback_hsw+0x294> DB 197,172,94,192 ; vdivps %ymm0,%ymm10,%ymm0 DB 197,164,88,192 ; vaddps %ymm0,%ymm11,%ymm0 - DB 196,98,125,24,21,207,35,0,0 ; vbroadcastss 0x23cf(%rip),%ymm10 # 4854 <_sk_callback_hsw+0x297> + DB 196,98,125,24,21,43,37,0,0 ; vbroadcastss 0x252b(%rip),%ymm10 # 49b0 <_sk_callback_hsw+0x298> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -2217,7 +2217,7 @@ _sk_parametric_r_hsw LABEL PROC DB 196,195,125,74,193,128 ; vblendvps %ymm8,%ymm9,%ymm0,%ymm0 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,124,95,192 ; vmaxps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,166,35,0,0 ; vbroadcastss 0x23a6(%rip),%ymm8 # 4858 <_sk_callback_hsw+0x29b> + DB 196,98,125,24,5,2,37,0,0 ; vbroadcastss 0x2502(%rip),%ymm8 # 49b4 <_sk_callback_hsw+0x29c> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2235,33 +2235,33 @@ _sk_parametric_g_hsw LABEL PROC DB 196,66,117,168,211 ; vfmadd213ps %ymm11,%ymm1,%ymm10 DB 196,226,125,24,8 ; vbroadcastss (%rax),%ymm1 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,94,35,0,0 ; vbroadcastss 0x235e(%rip),%ymm12 # 485c <_sk_callback_hsw+0x29f> - DB 196,98,125,24,45,89,35,0,0 ; vbroadcastss 0x2359(%rip),%ymm13 # 4860 <_sk_callback_hsw+0x2a3> + DB 196,98,125,24,37,186,36,0,0 ; vbroadcastss 0x24ba(%rip),%ymm12 # 49b8 <_sk_callback_hsw+0x2a0> + DB 196,98,125,24,45,181,36,0,0 ; vbroadcastss 0x24b5(%rip),%ymm13 # 49bc <_sk_callback_hsw+0x2a4> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,79,35,0,0 ; vbroadcastss 0x234f(%rip),%ymm13 # 4864 <_sk_callback_hsw+0x2a7> + DB 196,98,125,24,45,171,36,0,0 ; vbroadcastss 0x24ab(%rip),%ymm13 # 49c0 <_sk_callback_hsw+0x2a8> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,69,35,0,0 ; vbroadcastss 0x2345(%rip),%ymm13 # 4868 <_sk_callback_hsw+0x2ab> + DB 196,98,125,24,45,161,36,0,0 ; vbroadcastss 0x24a1(%rip),%ymm13 # 49c4 <_sk_callback_hsw+0x2ac> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,59,35,0,0 ; vbroadcastss 0x233b(%rip),%ymm11 # 486c <_sk_callback_hsw+0x2af> + DB 196,98,125,24,29,151,36,0,0 ; vbroadcastss 0x2497(%rip),%ymm11 # 49c8 <_sk_callback_hsw+0x2b0> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,49,35,0,0 ; vbroadcastss 0x2331(%rip),%ymm12 # 4870 <_sk_callback_hsw+0x2b3> + DB 196,98,125,24,37,141,36,0,0 ; vbroadcastss 0x248d(%rip),%ymm12 # 49cc <_sk_callback_hsw+0x2b4> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,39,35,0,0 ; vbroadcastss 0x2327(%rip),%ymm12 # 4874 <_sk_callback_hsw+0x2b7> + DB 196,98,125,24,37,131,36,0,0 ; vbroadcastss 0x2483(%rip),%ymm12 # 49d0 <_sk_callback_hsw+0x2b8> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,116,89,202 ; vmulps %ymm10,%ymm1,%ymm1 DB 196,99,125,8,209,1 ; vroundps $0x1,%ymm1,%ymm10 DB 196,65,116,92,210 ; vsubps %ymm10,%ymm1,%ymm10 - DB 196,98,125,24,29,8,35,0,0 ; vbroadcastss 0x2308(%rip),%ymm11 # 4878 <_sk_callback_hsw+0x2bb> + DB 196,98,125,24,29,100,36,0,0 ; vbroadcastss 0x2464(%rip),%ymm11 # 49d4 <_sk_callback_hsw+0x2bc> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,254,34,0,0 ; vbroadcastss 0x22fe(%rip),%ymm11 # 487c <_sk_callback_hsw+0x2bf> + DB 196,98,125,24,29,90,36,0,0 ; vbroadcastss 0x245a(%rip),%ymm11 # 49d8 <_sk_callback_hsw+0x2c0> DB 196,98,45,172,217 ; vfnmadd213ps %ymm1,%ymm10,%ymm11 - DB 196,226,125,24,13,244,34,0,0 ; vbroadcastss 0x22f4(%rip),%ymm1 # 4880 <_sk_callback_hsw+0x2c3> + DB 196,226,125,24,13,80,36,0,0 ; vbroadcastss 0x2450(%rip),%ymm1 # 49dc <_sk_callback_hsw+0x2c4> DB 196,193,116,92,202 ; vsubps %ymm10,%ymm1,%ymm1 - DB 196,98,125,24,21,234,34,0,0 ; vbroadcastss 0x22ea(%rip),%ymm10 # 4884 <_sk_callback_hsw+0x2c7> + DB 196,98,125,24,21,70,36,0,0 ; vbroadcastss 0x2446(%rip),%ymm10 # 49e0 <_sk_callback_hsw+0x2c8> DB 197,172,94,201 ; vdivps %ymm1,%ymm10,%ymm1 DB 197,164,88,201 ; vaddps %ymm1,%ymm11,%ymm1 - DB 196,98,125,24,21,221,34,0,0 ; vbroadcastss 0x22dd(%rip),%ymm10 # 4888 <_sk_callback_hsw+0x2cb> + DB 196,98,125,24,21,57,36,0,0 ; vbroadcastss 0x2439(%rip),%ymm10 # 49e4 <_sk_callback_hsw+0x2cc> DB 196,193,116,89,202 ; vmulps %ymm10,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -2269,7 +2269,7 @@ _sk_parametric_g_hsw LABEL PROC DB 196,195,117,74,201,128 ; vblendvps %ymm8,%ymm9,%ymm1,%ymm1 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,116,95,200 ; vmaxps %ymm8,%ymm1,%ymm1 - DB 196,98,125,24,5,180,34,0,0 ; vbroadcastss 0x22b4(%rip),%ymm8 # 488c <_sk_callback_hsw+0x2cf> + DB 196,98,125,24,5,16,36,0,0 ; vbroadcastss 0x2410(%rip),%ymm8 # 49e8 <_sk_callback_hsw+0x2d0> DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2287,33 +2287,33 @@ _sk_parametric_b_hsw LABEL PROC DB 196,66,109,168,211 ; vfmadd213ps %ymm11,%ymm2,%ymm10 DB 196,226,125,24,16 ; vbroadcastss (%rax),%ymm2 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,108,34,0,0 ; vbroadcastss 0x226c(%rip),%ymm12 # 4890 <_sk_callback_hsw+0x2d3> - DB 196,98,125,24,45,103,34,0,0 ; vbroadcastss 0x2267(%rip),%ymm13 # 4894 <_sk_callback_hsw+0x2d7> + DB 196,98,125,24,37,200,35,0,0 ; vbroadcastss 0x23c8(%rip),%ymm12 # 49ec <_sk_callback_hsw+0x2d4> + DB 196,98,125,24,45,195,35,0,0 ; vbroadcastss 0x23c3(%rip),%ymm13 # 49f0 <_sk_callback_hsw+0x2d8> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,93,34,0,0 ; vbroadcastss 0x225d(%rip),%ymm13 # 4898 <_sk_callback_hsw+0x2db> + DB 196,98,125,24,45,185,35,0,0 ; vbroadcastss 0x23b9(%rip),%ymm13 # 49f4 <_sk_callback_hsw+0x2dc> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,83,34,0,0 ; vbroadcastss 0x2253(%rip),%ymm13 # 489c <_sk_callback_hsw+0x2df> + DB 196,98,125,24,45,175,35,0,0 ; vbroadcastss 0x23af(%rip),%ymm13 # 49f8 <_sk_callback_hsw+0x2e0> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,73,34,0,0 ; vbroadcastss 0x2249(%rip),%ymm11 # 48a0 <_sk_callback_hsw+0x2e3> + DB 196,98,125,24,29,165,35,0,0 ; vbroadcastss 0x23a5(%rip),%ymm11 # 49fc <_sk_callback_hsw+0x2e4> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,63,34,0,0 ; vbroadcastss 0x223f(%rip),%ymm12 # 48a4 <_sk_callback_hsw+0x2e7> + DB 196,98,125,24,37,155,35,0,0 ; vbroadcastss 0x239b(%rip),%ymm12 # 4a00 <_sk_callback_hsw+0x2e8> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,53,34,0,0 ; vbroadcastss 0x2235(%rip),%ymm12 # 48a8 <_sk_callback_hsw+0x2eb> + DB 196,98,125,24,37,145,35,0,0 ; vbroadcastss 0x2391(%rip),%ymm12 # 4a04 <_sk_callback_hsw+0x2ec> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 196,99,125,8,210,1 ; vroundps $0x1,%ymm2,%ymm10 DB 196,65,108,92,210 ; vsubps %ymm10,%ymm2,%ymm10 - DB 196,98,125,24,29,22,34,0,0 ; vbroadcastss 0x2216(%rip),%ymm11 # 48ac <_sk_callback_hsw+0x2ef> + DB 196,98,125,24,29,114,35,0,0 ; vbroadcastss 0x2372(%rip),%ymm11 # 4a08 <_sk_callback_hsw+0x2f0> DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 - DB 196,98,125,24,29,12,34,0,0 ; vbroadcastss 0x220c(%rip),%ymm11 # 48b0 <_sk_callback_hsw+0x2f3> + DB 196,98,125,24,29,104,35,0,0 ; vbroadcastss 0x2368(%rip),%ymm11 # 4a0c <_sk_callback_hsw+0x2f4> DB 196,98,45,172,218 ; vfnmadd213ps %ymm2,%ymm10,%ymm11 - DB 196,226,125,24,21,2,34,0,0 ; vbroadcastss 0x2202(%rip),%ymm2 # 48b4 <_sk_callback_hsw+0x2f7> + DB 196,226,125,24,21,94,35,0,0 ; vbroadcastss 0x235e(%rip),%ymm2 # 4a10 <_sk_callback_hsw+0x2f8> DB 196,193,108,92,210 ; vsubps %ymm10,%ymm2,%ymm2 - DB 196,98,125,24,21,248,33,0,0 ; vbroadcastss 0x21f8(%rip),%ymm10 # 48b8 <_sk_callback_hsw+0x2fb> + DB 196,98,125,24,21,84,35,0,0 ; vbroadcastss 0x2354(%rip),%ymm10 # 4a14 <_sk_callback_hsw+0x2fc> DB 197,172,94,210 ; vdivps %ymm2,%ymm10,%ymm2 DB 197,164,88,210 ; vaddps %ymm2,%ymm11,%ymm2 - DB 196,98,125,24,21,235,33,0,0 ; vbroadcastss 0x21eb(%rip),%ymm10 # 48bc <_sk_callback_hsw+0x2ff> + DB 196,98,125,24,21,71,35,0,0 ; vbroadcastss 0x2347(%rip),%ymm10 # 4a18 <_sk_callback_hsw+0x300> DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 197,253,91,210 ; vcvtps2dq %ymm2,%ymm2 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -2321,7 +2321,7 @@ _sk_parametric_b_hsw LABEL PROC DB 196,195,109,74,209,128 ; vblendvps %ymm8,%ymm9,%ymm2,%ymm2 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,108,95,208 ; vmaxps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,194,33,0,0 ; vbroadcastss 0x21c2(%rip),%ymm8 # 48c0 <_sk_callback_hsw+0x303> + DB 196,98,125,24,5,30,35,0,0 ; vbroadcastss 0x231e(%rip),%ymm8 # 4a1c <_sk_callback_hsw+0x304> DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2339,33 +2339,33 @@ _sk_parametric_a_hsw LABEL PROC DB 196,66,101,168,211 ; vfmadd213ps %ymm11,%ymm3,%ymm10 DB 196,226,125,24,24 ; vbroadcastss (%rax),%ymm3 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,122,33,0,0 ; vbroadcastss 0x217a(%rip),%ymm12 # 48c4 <_sk_callback_hsw+0x307> - DB 196,98,125,24,45,117,33,0,0 ; vbroadcastss 0x2175(%rip),%ymm13 # 48c8 <_sk_callback_hsw+0x30b> + DB 196,98,125,24,37,214,34,0,0 ; vbroadcastss 0x22d6(%rip),%ymm12 # 4a20 <_sk_callback_hsw+0x308> + DB 196,98,125,24,45,209,34,0,0 ; vbroadcastss 0x22d1(%rip),%ymm13 # 4a24 <_sk_callback_hsw+0x30c> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,107,33,0,0 ; vbroadcastss 0x216b(%rip),%ymm13 # 48cc <_sk_callback_hsw+0x30f> + DB 196,98,125,24,45,199,34,0,0 ; vbroadcastss 0x22c7(%rip),%ymm13 # 4a28 <_sk_callback_hsw+0x310> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,97,33,0,0 ; vbroadcastss 0x2161(%rip),%ymm13 # 48d0 <_sk_callback_hsw+0x313> + DB 196,98,125,24,45,189,34,0,0 ; vbroadcastss 0x22bd(%rip),%ymm13 # 4a2c <_sk_callback_hsw+0x314> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,87,33,0,0 ; vbroadcastss 0x2157(%rip),%ymm11 # 48d4 <_sk_callback_hsw+0x317> + DB 196,98,125,24,29,179,34,0,0 ; vbroadcastss 0x22b3(%rip),%ymm11 # 4a30 <_sk_callback_hsw+0x318> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,77,33,0,0 ; vbroadcastss 0x214d(%rip),%ymm12 # 48d8 <_sk_callback_hsw+0x31b> + DB 196,98,125,24,37,169,34,0,0 ; vbroadcastss 0x22a9(%rip),%ymm12 # 4a34 <_sk_callback_hsw+0x31c> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,67,33,0,0 ; vbroadcastss 0x2143(%rip),%ymm12 # 48dc <_sk_callback_hsw+0x31f> + DB 196,98,125,24,37,159,34,0,0 ; vbroadcastss 0x229f(%rip),%ymm12 # 4a38 <_sk_callback_hsw+0x320> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 196,99,125,8,211,1 ; vroundps $0x1,%ymm3,%ymm10 DB 196,65,100,92,210 ; vsubps %ymm10,%ymm3,%ymm10 - DB 196,98,125,24,29,36,33,0,0 ; vbroadcastss 0x2124(%rip),%ymm11 # 48e0 <_sk_callback_hsw+0x323> + DB 196,98,125,24,29,128,34,0,0 ; vbroadcastss 0x2280(%rip),%ymm11 # 4a3c <_sk_callback_hsw+0x324> DB 196,193,100,88,219 ; vaddps %ymm11,%ymm3,%ymm3 - DB 196,98,125,24,29,26,33,0,0 ; vbroadcastss 0x211a(%rip),%ymm11 # 48e4 <_sk_callback_hsw+0x327> + DB 196,98,125,24,29,118,34,0,0 ; vbroadcastss 0x2276(%rip),%ymm11 # 4a40 <_sk_callback_hsw+0x328> DB 196,98,45,172,219 ; vfnmadd213ps %ymm3,%ymm10,%ymm11 - DB 196,226,125,24,29,16,33,0,0 ; vbroadcastss 0x2110(%rip),%ymm3 # 48e8 <_sk_callback_hsw+0x32b> + DB 196,226,125,24,29,108,34,0,0 ; vbroadcastss 0x226c(%rip),%ymm3 # 4a44 <_sk_callback_hsw+0x32c> DB 196,193,100,92,218 ; vsubps %ymm10,%ymm3,%ymm3 - DB 196,98,125,24,21,6,33,0,0 ; vbroadcastss 0x2106(%rip),%ymm10 # 48ec <_sk_callback_hsw+0x32f> + DB 196,98,125,24,21,98,34,0,0 ; vbroadcastss 0x2262(%rip),%ymm10 # 4a48 <_sk_callback_hsw+0x330> DB 197,172,94,219 ; vdivps %ymm3,%ymm10,%ymm3 DB 197,164,88,219 ; vaddps %ymm3,%ymm11,%ymm3 - DB 196,98,125,24,21,249,32,0,0 ; vbroadcastss 0x20f9(%rip),%ymm10 # 48f0 <_sk_callback_hsw+0x333> + DB 196,98,125,24,21,85,34,0,0 ; vbroadcastss 0x2255(%rip),%ymm10 # 4a4c <_sk_callback_hsw+0x334> DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 197,253,91,219 ; vcvtps2dq %ymm3,%ymm3 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -2373,33 +2373,33 @@ _sk_parametric_a_hsw LABEL PROC DB 196,195,101,74,217,128 ; vblendvps %ymm8,%ymm9,%ymm3,%ymm3 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,100,95,216 ; vmaxps %ymm8,%ymm3,%ymm3 - DB 196,98,125,24,5,208,32,0,0 ; vbroadcastss 0x20d0(%rip),%ymm8 # 48f4 <_sk_callback_hsw+0x337> + DB 196,98,125,24,5,44,34,0,0 ; vbroadcastss 0x222c(%rip),%ymm8 # 4a50 <_sk_callback_hsw+0x338> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax PUBLIC _sk_lab_to_xyz_hsw _sk_lab_to_xyz_hsw LABEL PROC - DB 196,98,125,24,5,194,32,0,0 ; vbroadcastss 0x20c2(%rip),%ymm8 # 48f8 <_sk_callback_hsw+0x33b> - DB 196,98,125,24,13,189,32,0,0 ; vbroadcastss 0x20bd(%rip),%ymm9 # 48fc <_sk_callback_hsw+0x33f> - DB 196,98,125,24,21,184,32,0,0 ; vbroadcastss 0x20b8(%rip),%ymm10 # 4900 <_sk_callback_hsw+0x343> + DB 196,98,125,24,5,30,34,0,0 ; vbroadcastss 0x221e(%rip),%ymm8 # 4a54 <_sk_callback_hsw+0x33c> + DB 196,98,125,24,13,25,34,0,0 ; vbroadcastss 0x2219(%rip),%ymm9 # 4a58 <_sk_callback_hsw+0x340> + DB 196,98,125,24,21,20,34,0,0 ; vbroadcastss 0x2214(%rip),%ymm10 # 4a5c <_sk_callback_hsw+0x344> DB 196,194,53,168,202 ; vfmadd213ps %ymm10,%ymm9,%ymm1 DB 196,194,53,168,210 ; vfmadd213ps %ymm10,%ymm9,%ymm2 - DB 196,98,125,24,13,169,32,0,0 ; vbroadcastss 0x20a9(%rip),%ymm9 # 4904 <_sk_callback_hsw+0x347> + DB 196,98,125,24,13,5,34,0,0 ; vbroadcastss 0x2205(%rip),%ymm9 # 4a60 <_sk_callback_hsw+0x348> DB 196,66,125,184,200 ; vfmadd231ps %ymm8,%ymm0,%ymm9 - DB 196,226,125,24,5,159,32,0,0 ; vbroadcastss 0x209f(%rip),%ymm0 # 4908 <_sk_callback_hsw+0x34b> + DB 196,226,125,24,5,251,33,0,0 ; vbroadcastss 0x21fb(%rip),%ymm0 # 4a64 <_sk_callback_hsw+0x34c> DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 - DB 196,98,125,24,5,150,32,0,0 ; vbroadcastss 0x2096(%rip),%ymm8 # 490c <_sk_callback_hsw+0x34f> + DB 196,98,125,24,5,242,33,0,0 ; vbroadcastss 0x21f2(%rip),%ymm8 # 4a68 <_sk_callback_hsw+0x350> DB 196,98,117,168,192 ; vfmadd213ps %ymm0,%ymm1,%ymm8 - DB 196,98,125,24,13,140,32,0,0 ; vbroadcastss 0x208c(%rip),%ymm9 # 4910 <_sk_callback_hsw+0x353> + DB 196,98,125,24,13,232,33,0,0 ; vbroadcastss 0x21e8(%rip),%ymm9 # 4a6c <_sk_callback_hsw+0x354> DB 196,98,109,172,200 ; vfnmadd213ps %ymm0,%ymm2,%ymm9 DB 196,193,60,89,200 ; vmulps %ymm8,%ymm8,%ymm1 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 - DB 196,226,125,24,21,121,32,0,0 ; vbroadcastss 0x2079(%rip),%ymm2 # 4914 <_sk_callback_hsw+0x357> + DB 196,226,125,24,21,213,33,0,0 ; vbroadcastss 0x21d5(%rip),%ymm2 # 4a70 <_sk_callback_hsw+0x358> DB 197,108,194,209,1 ; vcmpltps %ymm1,%ymm2,%ymm10 - DB 196,98,125,24,29,111,32,0,0 ; vbroadcastss 0x206f(%rip),%ymm11 # 4918 <_sk_callback_hsw+0x35b> + DB 196,98,125,24,29,203,33,0,0 ; vbroadcastss 0x21cb(%rip),%ymm11 # 4a74 <_sk_callback_hsw+0x35c> DB 196,65,60,88,195 ; vaddps %ymm11,%ymm8,%ymm8 - DB 196,98,125,24,37,101,32,0,0 ; vbroadcastss 0x2065(%rip),%ymm12 # 491c <_sk_callback_hsw+0x35f> + DB 196,98,125,24,37,193,33,0,0 ; vbroadcastss 0x21c1(%rip),%ymm12 # 4a78 <_sk_callback_hsw+0x360> DB 196,65,60,89,196 ; vmulps %ymm12,%ymm8,%ymm8 DB 196,99,61,74,193,160 ; vblendvps %ymm10,%ymm1,%ymm8,%ymm8 DB 197,252,89,200 ; vmulps %ymm0,%ymm0,%ymm1 @@ -2414,9 +2414,9 @@ _sk_lab_to_xyz_hsw LABEL PROC DB 196,65,52,88,203 ; vaddps %ymm11,%ymm9,%ymm9 DB 196,65,52,89,204 ; vmulps %ymm12,%ymm9,%ymm9 DB 196,227,53,74,208,32 ; vblendvps %ymm2,%ymm0,%ymm9,%ymm2 - DB 196,226,125,24,5,26,32,0,0 ; vbroadcastss 0x201a(%rip),%ymm0 # 4920 <_sk_callback_hsw+0x363> + DB 196,226,125,24,5,118,33,0,0 ; vbroadcastss 0x2176(%rip),%ymm0 # 4a7c <_sk_callback_hsw+0x364> DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 - DB 196,98,125,24,5,17,32,0,0 ; vbroadcastss 0x2011(%rip),%ymm8 # 4924 <_sk_callback_hsw+0x367> + DB 196,98,125,24,5,109,33,0,0 ; vbroadcastss 0x216d(%rip),%ymm8 # 4a80 <_sk_callback_hsw+0x368> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2432,7 +2432,7 @@ _sk_load_a8_hsw LABEL PROC DB 197,250,126,0 ; vmovq (%rax),%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,230,31,0,0 ; vbroadcastss 0x1fe6(%rip),%ymm1 # 4928 <_sk_callback_hsw+0x36b> + DB 196,226,125,24,13,66,33,0,0 ; vbroadcastss 0x2142(%rip),%ymm1 # 4a84 <_sk_callback_hsw+0x36c> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -2495,7 +2495,7 @@ _sk_gather_a8_hsw LABEL PROC DB 196,227,121,32,192,7 ; vpinsrb $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,241,30,0,0 ; vbroadcastss 0x1ef1(%rip),%ymm1 # 492c <_sk_callback_hsw+0x36f> + DB 196,226,125,24,13,77,32,0,0 ; vbroadcastss 0x204d(%rip),%ymm1 # 4a88 <_sk_callback_hsw+0x370> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -2511,7 +2511,7 @@ PUBLIC _sk_store_a8_hsw _sk_store_a8_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,204,30,0,0 ; vbroadcastss 0x1ecc(%rip),%ymm8 # 4930 <_sk_callback_hsw+0x373> + DB 196,98,125,24,5,40,32,0,0 ; vbroadcastss 0x2028(%rip),%ymm8 # 4a8c <_sk_callback_hsw+0x374> DB 196,65,100,89,192 ; vmulps %ymm8,%ymm3,%ymm8 DB 196,65,125,91,192 ; vcvtps2dq %ymm8,%ymm8 DB 196,67,125,25,193,1 ; vextractf128 $0x1,%ymm8,%xmm9 @@ -2576,10 +2576,10 @@ _sk_load_g8_hsw LABEL PROC DB 197,250,126,0 ; vmovq (%rax),%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,2,30,0,0 ; vbroadcastss 0x1e02(%rip),%ymm1 # 4934 <_sk_callback_hsw+0x377> + DB 196,226,125,24,13,94,31,0,0 ; vbroadcastss 0x1f5e(%rip),%ymm1 # 4a90 <_sk_callback_hsw+0x378> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,247,29,0,0 ; vbroadcastss 0x1df7(%rip),%ymm3 # 4938 <_sk_callback_hsw+0x37b> + DB 196,226,125,24,29,83,31,0,0 ; vbroadcastss 0x1f53(%rip),%ymm3 # 4a94 <_sk_callback_hsw+0x37c> DB 76,137,193 ; mov %r8,%rcx DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 @@ -2639,10 +2639,10 @@ _sk_gather_g8_hsw LABEL PROC DB 196,227,121,32,192,7 ; vpinsrb $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,12,29,0,0 ; vbroadcastss 0x1d0c(%rip),%ymm1 # 493c <_sk_callback_hsw+0x37f> + DB 196,226,125,24,13,104,30,0,0 ; vbroadcastss 0x1e68(%rip),%ymm1 # 4a98 <_sk_callback_hsw+0x380> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,1,29,0,0 ; vbroadcastss 0x1d01(%rip),%ymm3 # 4940 <_sk_callback_hsw+0x383> + DB 196,226,125,24,29,93,30,0,0 ; vbroadcastss 0x1e5d(%rip),%ymm3 # 4a9c <_sk_callback_hsw+0x384> DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 DB 91 ; pop %rbx @@ -2696,14 +2696,14 @@ _sk_gather_i8_hsw LABEL PROC DB 73,139,64,8 ; mov 0x8(%r8),%rax DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 DB 196,226,117,144,28,128 ; vpgatherdd %ymm1,(%rax,%ymm0,4),%ymm3 - DB 197,229,219,5,17,30,0,0 ; vpand 0x1e11(%rip),%ymm3,%ymm0 # 4b20 <_sk_callback_hsw+0x563> + DB 197,229,219,5,113,31,0,0 ; vpand 0x1f71(%rip),%ymm3,%ymm0 # 4c80 <_sk_callback_hsw+0x568> DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,40,28,0,0 ; vbroadcastss 0x1c28(%rip),%ymm8 # 4944 <_sk_callback_hsw+0x387> + DB 196,98,125,24,5,132,29,0,0 ; vbroadcastss 0x1d84(%rip),%ymm8 # 4aa0 <_sk_callback_hsw+0x388> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,226,101,0,13,22,30,0,0 ; vpshufb 0x1e16(%rip),%ymm3,%ymm1 # 4b40 <_sk_callback_hsw+0x583> + DB 196,226,101,0,13,118,31,0,0 ; vpshufb 0x1f76(%rip),%ymm3,%ymm1 # 4ca0 <_sk_callback_hsw+0x588> DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,226,101,0,21,36,30,0,0 ; vpshufb 0x1e24(%rip),%ymm3,%ymm2 # 4b60 <_sk_callback_hsw+0x5a3> + DB 196,226,101,0,21,132,31,0,0 ; vpshufb 0x1f84(%rip),%ymm3,%ymm2 # 4cc0 <_sk_callback_hsw+0x5a8> DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 @@ -2725,23 +2725,23 @@ _sk_load_565_hsw LABEL PROC DB 117,114 ; jne 2ddc <_sk_load_565_hsw+0x7c> DB 196,193,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm0 DB 196,226,125,51,208 ; vpmovzxwd %xmm0,%ymm2 - DB 196,226,125,88,5,202,27,0,0 ; vpbroadcastd 0x1bca(%rip),%ymm0 # 4948 <_sk_callback_hsw+0x38b> + DB 196,226,125,88,5,38,29,0,0 ; vpbroadcastd 0x1d26(%rip),%ymm0 # 4aa4 <_sk_callback_hsw+0x38c> DB 197,237,219,192 ; vpand %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,189,27,0,0 ; vbroadcastss 0x1bbd(%rip),%ymm1 # 494c <_sk_callback_hsw+0x38f> + DB 196,226,125,24,13,25,29,0,0 ; vbroadcastss 0x1d19(%rip),%ymm1 # 4aa8 <_sk_callback_hsw+0x390> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,180,27,0,0 ; vpbroadcastd 0x1bb4(%rip),%ymm1 # 4950 <_sk_callback_hsw+0x393> + DB 196,226,125,88,13,16,29,0,0 ; vpbroadcastd 0x1d10(%rip),%ymm1 # 4aac <_sk_callback_hsw+0x394> DB 197,237,219,201 ; vpand %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,167,27,0,0 ; vbroadcastss 0x1ba7(%rip),%ymm3 # 4954 <_sk_callback_hsw+0x397> + DB 196,226,125,24,29,3,29,0,0 ; vbroadcastss 0x1d03(%rip),%ymm3 # 4ab0 <_sk_callback_hsw+0x398> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,88,29,158,27,0,0 ; vpbroadcastd 0x1b9e(%rip),%ymm3 # 4958 <_sk_callback_hsw+0x39b> + DB 196,226,125,88,29,250,28,0,0 ; vpbroadcastd 0x1cfa(%rip),%ymm3 # 4ab4 <_sk_callback_hsw+0x39c> DB 197,237,219,211 ; vpand %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,145,27,0,0 ; vbroadcastss 0x1b91(%rip),%ymm3 # 495c <_sk_callback_hsw+0x39f> + DB 196,226,125,24,29,237,28,0,0 ; vbroadcastss 0x1ced(%rip),%ymm3 # 4ab8 <_sk_callback_hsw+0x3a0> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,134,27,0,0 ; vbroadcastss 0x1b86(%rip),%ymm3 # 4960 <_sk_callback_hsw+0x3a3> + DB 196,226,125,24,29,226,28,0,0 ; vbroadcastss 0x1ce2(%rip),%ymm3 # 4abc <_sk_callback_hsw+0x3a4> DB 255,224 ; jmpq *%rax DB 65,137,200 ; mov %ecx,%r8d DB 65,128,224,7 ; and $0x7,%r8b @@ -2830,23 +2830,23 @@ _sk_gather_565_hsw LABEL PROC DB 65,15,183,4,88 ; movzwl (%r8,%rbx,2),%eax DB 197,249,196,192,7 ; vpinsrw $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,51,208 ; vpmovzxwd %xmm0,%ymm2 - DB 196,226,125,88,5,73,26,0,0 ; vpbroadcastd 0x1a49(%rip),%ymm0 # 4964 <_sk_callback_hsw+0x3a7> + DB 196,226,125,88,5,165,27,0,0 ; vpbroadcastd 0x1ba5(%rip),%ymm0 # 4ac0 <_sk_callback_hsw+0x3a8> DB 197,237,219,192 ; vpand %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,60,26,0,0 ; vbroadcastss 0x1a3c(%rip),%ymm1 # 4968 <_sk_callback_hsw+0x3ab> + DB 196,226,125,24,13,152,27,0,0 ; vbroadcastss 0x1b98(%rip),%ymm1 # 4ac4 <_sk_callback_hsw+0x3ac> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,51,26,0,0 ; vpbroadcastd 0x1a33(%rip),%ymm1 # 496c <_sk_callback_hsw+0x3af> + DB 196,226,125,88,13,143,27,0,0 ; vpbroadcastd 0x1b8f(%rip),%ymm1 # 4ac8 <_sk_callback_hsw+0x3b0> DB 197,237,219,201 ; vpand %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,38,26,0,0 ; vbroadcastss 0x1a26(%rip),%ymm3 # 4970 <_sk_callback_hsw+0x3b3> + DB 196,226,125,24,29,130,27,0,0 ; vbroadcastss 0x1b82(%rip),%ymm3 # 4acc <_sk_callback_hsw+0x3b4> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,88,29,29,26,0,0 ; vpbroadcastd 0x1a1d(%rip),%ymm3 # 4974 <_sk_callback_hsw+0x3b7> + DB 196,226,125,88,29,121,27,0,0 ; vpbroadcastd 0x1b79(%rip),%ymm3 # 4ad0 <_sk_callback_hsw+0x3b8> DB 197,237,219,211 ; vpand %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,16,26,0,0 ; vbroadcastss 0x1a10(%rip),%ymm3 # 4978 <_sk_callback_hsw+0x3bb> + DB 196,226,125,24,29,108,27,0,0 ; vbroadcastss 0x1b6c(%rip),%ymm3 # 4ad4 <_sk_callback_hsw+0x3bc> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,5,26,0,0 ; vbroadcastss 0x1a05(%rip),%ymm3 # 497c <_sk_callback_hsw+0x3bf> + DB 196,226,125,24,29,97,27,0,0 ; vbroadcastss 0x1b61(%rip),%ymm3 # 4ad8 <_sk_callback_hsw+0x3c0> DB 91 ; pop %rbx DB 65,92 ; pop %r12 DB 65,94 ; pop %r14 @@ -2857,11 +2857,11 @@ PUBLIC _sk_store_565_hsw _sk_store_565_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,242,25,0,0 ; vbroadcastss 0x19f2(%rip),%ymm8 # 4980 <_sk_callback_hsw+0x3c3> + DB 196,98,125,24,5,78,27,0,0 ; vbroadcastss 0x1b4e(%rip),%ymm8 # 4adc <_sk_callback_hsw+0x3c4> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,53,114,241,11 ; vpslld $0xb,%ymm9,%ymm9 - DB 196,98,125,24,21,221,25,0,0 ; vbroadcastss 0x19dd(%rip),%ymm10 # 4984 <_sk_callback_hsw+0x3c7> + DB 196,98,125,24,21,57,27,0,0 ; vbroadcastss 0x1b39(%rip),%ymm10 # 4ae0 <_sk_callback_hsw+0x3c8> DB 196,65,116,89,210 ; vmulps %ymm10,%ymm1,%ymm10 DB 196,65,125,91,210 ; vcvtps2dq %ymm10,%ymm10 DB 196,193,45,114,242,5 ; vpslld $0x5,%ymm10,%ymm10 @@ -2927,25 +2927,25 @@ _sk_load_4444_hsw LABEL PROC DB 15,133,138,0,0,0 ; jne 30f8 <_sk_load_4444_hsw+0x98> DB 196,193,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm0 DB 196,226,125,51,216 ; vpmovzxwd %xmm0,%ymm3 - DB 196,226,125,88,5,6,25,0,0 ; vpbroadcastd 0x1906(%rip),%ymm0 # 4988 <_sk_callback_hsw+0x3cb> + DB 196,226,125,88,5,98,26,0,0 ; vpbroadcastd 0x1a62(%rip),%ymm0 # 4ae4 <_sk_callback_hsw+0x3cc> DB 197,229,219,192 ; vpand %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,249,24,0,0 ; vbroadcastss 0x18f9(%rip),%ymm1 # 498c <_sk_callback_hsw+0x3cf> + DB 196,226,125,24,13,85,26,0,0 ; vbroadcastss 0x1a55(%rip),%ymm1 # 4ae8 <_sk_callback_hsw+0x3d0> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,240,24,0,0 ; vpbroadcastd 0x18f0(%rip),%ymm1 # 4990 <_sk_callback_hsw+0x3d3> + DB 196,226,125,88,13,76,26,0,0 ; vpbroadcastd 0x1a4c(%rip),%ymm1 # 4aec <_sk_callback_hsw+0x3d4> DB 197,229,219,201 ; vpand %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,227,24,0,0 ; vbroadcastss 0x18e3(%rip),%ymm2 # 4994 <_sk_callback_hsw+0x3d7> + DB 196,226,125,24,21,63,26,0,0 ; vbroadcastss 0x1a3f(%rip),%ymm2 # 4af0 <_sk_callback_hsw+0x3d8> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,88,21,218,24,0,0 ; vpbroadcastd 0x18da(%rip),%ymm2 # 4998 <_sk_callback_hsw+0x3db> + DB 196,226,125,88,21,54,26,0,0 ; vpbroadcastd 0x1a36(%rip),%ymm2 # 4af4 <_sk_callback_hsw+0x3dc> DB 197,229,219,210 ; vpand %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,205,24,0,0 ; vbroadcastss 0x18cd(%rip),%ymm8 # 499c <_sk_callback_hsw+0x3df> + DB 196,98,125,24,5,41,26,0,0 ; vbroadcastss 0x1a29(%rip),%ymm8 # 4af8 <_sk_callback_hsw+0x3e0> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,88,5,195,24,0,0 ; vpbroadcastd 0x18c3(%rip),%ymm8 # 49a0 <_sk_callback_hsw+0x3e3> + DB 196,98,125,88,5,31,26,0,0 ; vpbroadcastd 0x1a1f(%rip),%ymm8 # 4afc <_sk_callback_hsw+0x3e4> DB 196,193,101,219,216 ; vpand %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,181,24,0,0 ; vbroadcastss 0x18b5(%rip),%ymm8 # 49a4 <_sk_callback_hsw+0x3e7> + DB 196,98,125,24,5,17,26,0,0 ; vbroadcastss 0x1a11(%rip),%ymm8 # 4b00 <_sk_callback_hsw+0x3e8> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -3036,25 +3036,25 @@ _sk_gather_4444_hsw LABEL PROC DB 65,15,183,4,88 ; movzwl (%r8,%rbx,2),%eax DB 197,249,196,192,7 ; vpinsrw $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,51,216 ; vpmovzxwd %xmm0,%ymm3 - DB 196,226,125,88,5,109,23,0,0 ; vpbroadcastd 0x176d(%rip),%ymm0 # 49a8 <_sk_callback_hsw+0x3eb> + DB 196,226,125,88,5,201,24,0,0 ; vpbroadcastd 0x18c9(%rip),%ymm0 # 4b04 <_sk_callback_hsw+0x3ec> DB 197,229,219,192 ; vpand %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,96,23,0,0 ; vbroadcastss 0x1760(%rip),%ymm1 # 49ac <_sk_callback_hsw+0x3ef> + DB 196,226,125,24,13,188,24,0,0 ; vbroadcastss 0x18bc(%rip),%ymm1 # 4b08 <_sk_callback_hsw+0x3f0> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,87,23,0,0 ; vpbroadcastd 0x1757(%rip),%ymm1 # 49b0 <_sk_callback_hsw+0x3f3> + DB 196,226,125,88,13,179,24,0,0 ; vpbroadcastd 0x18b3(%rip),%ymm1 # 4b0c <_sk_callback_hsw+0x3f4> DB 197,229,219,201 ; vpand %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,74,23,0,0 ; vbroadcastss 0x174a(%rip),%ymm2 # 49b4 <_sk_callback_hsw+0x3f7> + DB 196,226,125,24,21,166,24,0,0 ; vbroadcastss 0x18a6(%rip),%ymm2 # 4b10 <_sk_callback_hsw+0x3f8> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,88,21,65,23,0,0 ; vpbroadcastd 0x1741(%rip),%ymm2 # 49b8 <_sk_callback_hsw+0x3fb> + DB 196,226,125,88,21,157,24,0,0 ; vpbroadcastd 0x189d(%rip),%ymm2 # 4b14 <_sk_callback_hsw+0x3fc> DB 197,229,219,210 ; vpand %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,52,23,0,0 ; vbroadcastss 0x1734(%rip),%ymm8 # 49bc <_sk_callback_hsw+0x3ff> + DB 196,98,125,24,5,144,24,0,0 ; vbroadcastss 0x1890(%rip),%ymm8 # 4b18 <_sk_callback_hsw+0x400> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,88,5,42,23,0,0 ; vpbroadcastd 0x172a(%rip),%ymm8 # 49c0 <_sk_callback_hsw+0x403> + DB 196,98,125,88,5,134,24,0,0 ; vpbroadcastd 0x1886(%rip),%ymm8 # 4b1c <_sk_callback_hsw+0x404> DB 196,193,101,219,216 ; vpand %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,28,23,0,0 ; vbroadcastss 0x171c(%rip),%ymm8 # 49c4 <_sk_callback_hsw+0x407> + DB 196,98,125,24,5,120,24,0,0 ; vbroadcastss 0x1878(%rip),%ymm8 # 4b20 <_sk_callback_hsw+0x408> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -3067,7 +3067,7 @@ PUBLIC _sk_store_4444_hsw _sk_store_4444_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,2,23,0,0 ; vbroadcastss 0x1702(%rip),%ymm8 # 49c8 <_sk_callback_hsw+0x40b> + DB 196,98,125,24,5,94,24,0,0 ; vbroadcastss 0x185e(%rip),%ymm8 # 4b24 <_sk_callback_hsw+0x40c> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,53,114,241,12 ; vpslld $0xc,%ymm9,%ymm9 @@ -3141,14 +3141,14 @@ _sk_load_8888_hsw LABEL PROC DB 77,133,192 ; test %r8,%r8 DB 117,88 ; jne 3411 <_sk_load_8888_hsw+0x6d> DB 196,193,126,111,25 ; vmovdqu (%r9),%ymm3 - DB 197,229,219,5,186,23,0,0 ; vpand 0x17ba(%rip),%ymm3,%ymm0 # 4b80 <_sk_callback_hsw+0x5c3> + DB 197,229,219,5,26,25,0,0 ; vpand 0x191a(%rip),%ymm3,%ymm0 # 4ce0 <_sk_callback_hsw+0x5c8> DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,249,21,0,0 ; vbroadcastss 0x15f9(%rip),%ymm8 # 49cc <_sk_callback_hsw+0x40f> + DB 196,98,125,24,5,85,23,0,0 ; vbroadcastss 0x1755(%rip),%ymm8 # 4b28 <_sk_callback_hsw+0x410> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,226,101,0,13,191,23,0,0 ; vpshufb 0x17bf(%rip),%ymm3,%ymm1 # 4ba0 <_sk_callback_hsw+0x5e3> + DB 196,226,101,0,13,31,25,0,0 ; vpshufb 0x191f(%rip),%ymm3,%ymm1 # 4d00 <_sk_callback_hsw+0x5e8> DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,226,101,0,21,205,23,0,0 ; vpshufb 0x17cd(%rip),%ymm3,%ymm2 # 4bc0 <_sk_callback_hsw+0x603> + DB 196,226,101,0,21,45,25,0,0 ; vpshufb 0x192d(%rip),%ymm3,%ymm2 # 4d20 <_sk_callback_hsw+0x608> DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 @@ -3178,14 +3178,14 @@ _sk_gather_8888_hsw LABEL PROC DB 197,245,254,192 ; vpaddd %ymm0,%ymm1,%ymm0 DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 DB 196,194,117,144,28,128 ; vpgatherdd %ymm1,(%r8,%ymm0,4),%ymm3 - DB 197,229,219,5,123,23,0,0 ; vpand 0x177b(%rip),%ymm3,%ymm0 # 4be0 <_sk_callback_hsw+0x623> + DB 197,229,219,5,219,24,0,0 ; vpand 0x18db(%rip),%ymm3,%ymm0 # 4d40 <_sk_callback_hsw+0x628> DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,94,21,0,0 ; vbroadcastss 0x155e(%rip),%ymm8 # 49d0 <_sk_callback_hsw+0x413> + DB 196,98,125,24,5,186,22,0,0 ; vbroadcastss 0x16ba(%rip),%ymm8 # 4b2c <_sk_callback_hsw+0x414> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,226,101,0,13,128,23,0,0 ; vpshufb 0x1780(%rip),%ymm3,%ymm1 # 4c00 <_sk_callback_hsw+0x643> + DB 196,226,101,0,13,224,24,0,0 ; vpshufb 0x18e0(%rip),%ymm3,%ymm1 # 4d60 <_sk_callback_hsw+0x648> DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,226,101,0,21,142,23,0,0 ; vpshufb 0x178e(%rip),%ymm3,%ymm2 # 4c20 <_sk_callback_hsw+0x663> + DB 196,226,101,0,21,238,24,0,0 ; vpshufb 0x18ee(%rip),%ymm3,%ymm2 # 4d80 <_sk_callback_hsw+0x668> DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 @@ -3200,7 +3200,7 @@ _sk_store_8888_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 DB 76,3,8 ; add (%rax),%r9 - DB 196,98,125,24,5,14,21,0,0 ; vbroadcastss 0x150e(%rip),%ymm8 # 49d4 <_sk_callback_hsw+0x417> + DB 196,98,125,24,5,106,22,0,0 ; vbroadcastss 0x166a(%rip),%ymm8 # 4b30 <_sk_callback_hsw+0x418> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,65,116,89,208 ; vmulps %ymm8,%ymm1,%ymm10 @@ -3389,7 +3389,7 @@ _sk_load_u16_be_hsw LABEL PROC DB 197,241,235,192 ; vpor %xmm0,%xmm1,%xmm0 DB 196,226,125,51,192 ; vpmovzxwd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,21,5,18,0,0 ; vbroadcastss 0x1205(%rip),%ymm10 # 49d8 <_sk_callback_hsw+0x41b> + DB 196,98,125,24,21,97,19,0,0 ; vbroadcastss 0x1361(%rip),%ymm10 # 4b34 <_sk_callback_hsw+0x41c> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,185,109,202 ; vpunpckhqdq %xmm2,%xmm8,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -3471,7 +3471,7 @@ _sk_load_rgb_u16_be_hsw LABEL PROC DB 197,241,235,192 ; vpor %xmm0,%xmm1,%xmm0 DB 196,226,125,51,192 ; vpmovzxwd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,21,150,16,0,0 ; vbroadcastss 0x1096(%rip),%ymm10 # 49dc <_sk_callback_hsw+0x41f> + DB 196,98,125,24,21,242,17,0,0 ; vbroadcastss 0x11f2(%rip),%ymm10 # 4b38 <_sk_callback_hsw+0x420> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,185,109,202 ; vpunpckhqdq %xmm2,%xmm8,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -3488,7 +3488,7 @@ _sk_load_rgb_u16_be_hsw LABEL PROC DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,74,16,0,0 ; vbroadcastss 0x104a(%rip),%ymm3 # 49e0 <_sk_callback_hsw+0x423> + DB 196,226,125,24,29,166,17,0,0 ; vbroadcastss 0x11a6(%rip),%ymm3 # 4b3c <_sk_callback_hsw+0x424> DB 255,224 ; jmpq *%rax DB 196,193,121,110,4,64 ; vmovd (%r8,%rax,2),%xmm0 DB 196,193,121,196,68,64,4,2 ; vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 @@ -3529,7 +3529,7 @@ _sk_store_u16_be_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,189,0,0,0,0 ; lea 0x0(,%rdi,4),%rax - DB 196,98,125,24,5,135,15,0,0 ; vbroadcastss 0xf87(%rip),%ymm8 # 49e4 <_sk_callback_hsw+0x427> + DB 196,98,125,24,5,227,16,0,0 ; vbroadcastss 0x10e3(%rip),%ymm8 # 4b40 <_sk_callback_hsw+0x428> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,67,125,25,202,1 ; vextractf128 $0x1,%ymm9,%xmm10 @@ -3771,11 +3771,11 @@ _sk_mirror_y_hsw LABEL PROC PUBLIC _sk_luminance_to_alpha_hsw _sk_luminance_to_alpha_hsw LABEL PROC - DB 196,226,125,24,29,215,11,0,0 ; vbroadcastss 0xbd7(%rip),%ymm3 # 49e8 <_sk_callback_hsw+0x42b> - DB 196,98,125,24,5,210,11,0,0 ; vbroadcastss 0xbd2(%rip),%ymm8 # 49ec <_sk_callback_hsw+0x42f> + DB 196,226,125,24,29,51,13,0,0 ; vbroadcastss 0xd33(%rip),%ymm3 # 4b44 <_sk_callback_hsw+0x42c> + DB 196,98,125,24,5,46,13,0,0 ; vbroadcastss 0xd2e(%rip),%ymm8 # 4b48 <_sk_callback_hsw+0x430> DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 196,226,125,184,203 ; vfmadd231ps %ymm3,%ymm0,%ymm1 - DB 196,226,125,24,29,195,11,0,0 ; vbroadcastss 0xbc3(%rip),%ymm3 # 49f0 <_sk_callback_hsw+0x433> + DB 196,226,125,24,29,31,13,0,0 ; vbroadcastss 0xd1f(%rip),%ymm3 # 4b4c <_sk_callback_hsw+0x434> DB 196,226,109,168,217 ; vfmadd213ps %ymm1,%ymm2,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -3901,52 +3901,140 @@ _sk_matrix_perspective_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax +PUBLIC _sk_evenly_spaced_gradient_hsw +_sk_evenly_spaced_gradient_hsw LABEL PROC + DB 72,173 ; lods %ds:(%rsi),%rax + DB 76,139,8 ; mov (%rax),%r9 + DB 76,139,64,8 ; mov 0x8(%rax),%r8 + DB 77,137,202 ; mov %r9,%r10 + DB 73,255,202 ; dec %r10 + DB 120,7 ; js 4068 <_sk_evenly_spaced_gradient_hsw+0x18> + DB 196,193,242,42,202 ; vcvtsi2ss %r10,%xmm1,%xmm1 + DB 235,22 ; jmp 407e <_sk_evenly_spaced_gradient_hsw+0x2e> + DB 77,137,211 ; mov %r10,%r11 + DB 73,209,235 ; shr %r11 + DB 65,131,226,1 ; and $0x1,%r10d + DB 77,9,218 ; or %r11,%r10 + DB 196,193,242,42,202 ; vcvtsi2ss %r10,%xmm1,%xmm1 + DB 197,242,88,201 ; vaddss %xmm1,%xmm1,%xmm1 + DB 196,226,125,24,201 ; vbroadcastss %xmm1,%ymm1 + DB 197,244,89,200 ; vmulps %ymm0,%ymm1,%ymm1 + DB 197,126,91,217 ; vcvttps2dq %ymm1,%ymm11 + DB 73,131,249,8 ; cmp $0x8,%r9 + DB 119,70 ; ja 40d7 <_sk_evenly_spaced_gradient_hsw+0x87> + DB 196,66,37,22,0 ; vpermps (%r8),%ymm11,%ymm8 + DB 76,139,64,40 ; mov 0x28(%rax),%r8 + DB 196,66,37,22,8 ; vpermps (%r8),%ymm11,%ymm9 + DB 76,139,64,16 ; mov 0x10(%rax),%r8 + DB 76,139,72,24 ; mov 0x18(%rax),%r9 + DB 196,194,37,22,8 ; vpermps (%r8),%ymm11,%ymm1 + DB 76,139,64,48 ; mov 0x30(%rax),%r8 + DB 196,66,37,22,16 ; vpermps (%r8),%ymm11,%ymm10 + DB 196,194,37,22,17 ; vpermps (%r9),%ymm11,%ymm2 + DB 76,139,64,56 ; mov 0x38(%rax),%r8 + DB 196,66,37,22,32 ; vpermps (%r8),%ymm11,%ymm12 + DB 76,139,64,32 ; mov 0x20(%rax),%r8 + DB 196,194,37,22,24 ; vpermps (%r8),%ymm11,%ymm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 196,98,37,22,40 ; vpermps (%rax),%ymm11,%ymm13 + DB 235,110 ; jmp 4145 <_sk_evenly_spaced_gradient_hsw+0xf5> + DB 196,65,13,118,246 ; vpcmpeqd %ymm14,%ymm14,%ymm14 + DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 + DB 196,2,117,146,4,152 ; vgatherdps %ymm1,(%r8,%ymm11,4),%ymm8 + DB 76,139,64,40 ; mov 0x28(%rax),%r8 + DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 + DB 196,2,117,146,12,152 ; vgatherdps %ymm1,(%r8,%ymm11,4),%ymm9 + DB 76,139,64,16 ; mov 0x10(%rax),%r8 + DB 76,139,72,24 ; mov 0x18(%rax),%r9 + DB 197,237,118,210 ; vpcmpeqd %ymm2,%ymm2,%ymm2 + DB 196,130,109,146,12,152 ; vgatherdps %ymm2,(%r8,%ymm11,4),%ymm1 + DB 76,139,64,48 ; mov 0x30(%rax),%r8 + DB 197,237,118,210 ; vpcmpeqd %ymm2,%ymm2,%ymm2 + DB 196,2,109,146,20,152 ; vgatherdps %ymm2,(%r8,%ymm11,4),%ymm10 + DB 197,229,118,219 ; vpcmpeqd %ymm3,%ymm3,%ymm3 + DB 196,130,101,146,20,153 ; vgatherdps %ymm3,(%r9,%ymm11,4),%ymm2 + DB 76,139,64,56 ; mov 0x38(%rax),%r8 + DB 197,229,118,219 ; vpcmpeqd %ymm3,%ymm3,%ymm3 + DB 196,2,101,146,36,152 ; vgatherdps %ymm3,(%r8,%ymm11,4),%ymm12 + DB 76,139,64,32 ; mov 0x20(%rax),%r8 + DB 196,65,21,118,237 ; vpcmpeqd %ymm13,%ymm13,%ymm13 + DB 196,130,21,146,28,152 ; vgatherdps %ymm13,(%r8,%ymm11,4),%ymm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 196,34,13,146,44,152 ; vgatherdps %ymm14,(%rax,%ymm11,4),%ymm13 + DB 196,66,125,168,193 ; vfmadd213ps %ymm9,%ymm0,%ymm8 + DB 196,194,125,168,202 ; vfmadd213ps %ymm10,%ymm0,%ymm1 + DB 196,194,125,168,212 ; vfmadd213ps %ymm12,%ymm0,%ymm2 + DB 196,194,125,168,221 ; vfmadd213ps %ymm13,%ymm0,%ymm3 + DB 72,173 ; lods %ds:(%rsi),%rax + DB 197,124,41,192 ; vmovaps %ymm8,%ymm0 + DB 255,224 ; jmpq *%rax + PUBLIC _sk_gradient_hsw _sk_gradient_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,64,16 ; vbroadcastss 0x10(%rax),%ymm8 - DB 196,98,125,24,88,20 ; vbroadcastss 0x14(%rax),%ymm11 - DB 196,98,125,24,80,24 ; vbroadcastss 0x18(%rax),%ymm10 - DB 196,98,125,24,72,28 ; vbroadcastss 0x1c(%rax),%ymm9 DB 76,139,0 ; mov (%rax),%r8 - DB 77,133,192 ; test %r8,%r8 - DB 15,132,143,0,0,0 ; je 4105 <_sk_gradient_hsw+0xb5> - DB 72,139,64,8 ; mov 0x8(%rax),%rax - DB 72,131,192,32 ; add $0x20,%rax - DB 196,65,28,87,228 ; vxorps %ymm12,%ymm12,%ymm12 - DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 - DB 197,236,87,210 ; vxorps %ymm2,%ymm2,%ymm2 - DB 197,244,87,201 ; vxorps %ymm1,%ymm1,%ymm1 - DB 196,98,125,24,104,224 ; vbroadcastss -0x20(%rax),%ymm13 - DB 196,65,124,194,237,1 ; vcmpltps %ymm13,%ymm0,%ymm13 - DB 196,98,125,24,112,228 ; vbroadcastss -0x1c(%rax),%ymm14 - DB 196,67,13,74,228,208 ; vblendvps %ymm13,%ymm12,%ymm14,%ymm12 - DB 196,98,125,24,112,232 ; vbroadcastss -0x18(%rax),%ymm14 - DB 196,227,13,74,201,208 ; vblendvps %ymm13,%ymm1,%ymm14,%ymm1 - DB 196,98,125,24,112,236 ; vbroadcastss -0x14(%rax),%ymm14 - DB 196,227,13,74,210,208 ; vblendvps %ymm13,%ymm2,%ymm14,%ymm2 - DB 196,98,125,24,112,240 ; vbroadcastss -0x10(%rax),%ymm14 - DB 196,227,13,74,219,208 ; vblendvps %ymm13,%ymm3,%ymm14,%ymm3 - DB 196,98,125,24,112,244 ; vbroadcastss -0xc(%rax),%ymm14 - DB 196,67,13,74,192,208 ; vblendvps %ymm13,%ymm8,%ymm14,%ymm8 - DB 196,98,125,24,112,248 ; vbroadcastss -0x8(%rax),%ymm14 - DB 196,67,13,74,219,208 ; vblendvps %ymm13,%ymm11,%ymm14,%ymm11 - DB 196,98,125,24,112,252 ; vbroadcastss -0x4(%rax),%ymm14 - DB 196,67,13,74,210,208 ; vblendvps %ymm13,%ymm10,%ymm14,%ymm10 - DB 196,98,125,24,48 ; vbroadcastss (%rax),%ymm14 - DB 196,67,13,74,201,208 ; vblendvps %ymm13,%ymm9,%ymm14,%ymm9 - DB 72,131,192,36 ; add $0x24,%rax - DB 73,255,200 ; dec %r8 - DB 117,140 ; jne 408f <_sk_gradient_hsw+0x3f> - DB 235,17 ; jmp 4116 <_sk_gradient_hsw+0xc6> + DB 73,131,248,1 ; cmp $0x1,%r8 + DB 15,134,180,0,0,0 ; jbe 4224 <_sk_gradient_hsw+0xc3> + DB 76,139,72,72 ; mov 0x48(%rax),%r9 DB 197,244,87,201 ; vxorps %ymm1,%ymm1,%ymm1 - DB 197,236,87,210 ; vxorps %ymm2,%ymm2,%ymm2 - DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 - DB 196,65,28,87,228 ; vxorps %ymm12,%ymm12,%ymm12 - DB 196,66,125,184,196 ; vfmadd231ps %ymm12,%ymm0,%ymm8 + DB 65,186,1,0,0,0 ; mov $0x1,%r10d + DB 196,226,125,24,21,201,9,0,0 ; vbroadcastss 0x9c9(%rip),%ymm2 # 4b50 <_sk_callback_hsw+0x438> + DB 196,65,53,239,201 ; vpxor %ymm9,%ymm9,%ymm9 + DB 196,130,125,24,28,145 ; vbroadcastss (%r9,%r10,4),%ymm3 + DB 197,228,194,216,2 ; vcmpleps %ymm0,%ymm3,%ymm3 + DB 196,227,117,74,218,48 ; vblendvps %ymm3,%ymm2,%ymm1,%ymm3 + DB 196,65,101,254,201 ; vpaddd %ymm9,%ymm3,%ymm9 + DB 73,255,194 ; inc %r10 + DB 77,57,208 ; cmp %r10,%r8 + DB 117,226 ; jne 418c <_sk_gradient_hsw+0x2b> + DB 76,139,72,8 ; mov 0x8(%rax),%r9 + DB 73,131,248,8 ; cmp $0x8,%r8 + DB 118,121 ; jbe 422d <_sk_gradient_hsw+0xcc> + DB 196,65,13,118,246 ; vpcmpeqd %ymm14,%ymm14,%ymm14 + DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 + DB 196,2,117,146,4,137 ; vgatherdps %ymm1,(%r9,%ymm9,4),%ymm8 + DB 76,139,64,40 ; mov 0x28(%rax),%r8 + DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 + DB 196,2,117,146,20,136 ; vgatherdps %ymm1,(%r8,%ymm9,4),%ymm10 + DB 76,139,64,16 ; mov 0x10(%rax),%r8 + DB 76,139,72,24 ; mov 0x18(%rax),%r9 + DB 197,237,118,210 ; vpcmpeqd %ymm2,%ymm2,%ymm2 + DB 196,130,109,146,12,136 ; vgatherdps %ymm2,(%r8,%ymm9,4),%ymm1 + DB 76,139,64,48 ; mov 0x30(%rax),%r8 + DB 197,237,118,210 ; vpcmpeqd %ymm2,%ymm2,%ymm2 + DB 196,2,109,146,28,136 ; vgatherdps %ymm2,(%r8,%ymm9,4),%ymm11 + DB 197,229,118,219 ; vpcmpeqd %ymm3,%ymm3,%ymm3 + DB 196,130,101,146,20,137 ; vgatherdps %ymm3,(%r9,%ymm9,4),%ymm2 + DB 76,139,64,56 ; mov 0x38(%rax),%r8 + DB 197,229,118,219 ; vpcmpeqd %ymm3,%ymm3,%ymm3 + DB 196,2,101,146,36,136 ; vgatherdps %ymm3,(%r8,%ymm9,4),%ymm12 + DB 76,139,64,32 ; mov 0x20(%rax),%r8 + DB 196,65,21,118,237 ; vpcmpeqd %ymm13,%ymm13,%ymm13 + DB 196,130,21,146,28,136 ; vgatherdps %ymm13,(%r8,%ymm9,4),%ymm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 196,34,13,146,44,136 ; vgatherdps %ymm14,(%rax,%ymm9,4),%ymm13 + DB 235,77 ; jmp 4271 <_sk_gradient_hsw+0x110> + DB 76,139,72,8 ; mov 0x8(%rax),%r9 + DB 196,65,52,87,201 ; vxorps %ymm9,%ymm9,%ymm9 + DB 196,66,53,22,1 ; vpermps (%r9),%ymm9,%ymm8 + DB 76,139,64,40 ; mov 0x28(%rax),%r8 + DB 196,66,53,22,16 ; vpermps (%r8),%ymm9,%ymm10 + DB 76,139,64,16 ; mov 0x10(%rax),%r8 + DB 76,139,72,24 ; mov 0x18(%rax),%r9 + DB 196,194,53,22,8 ; vpermps (%r8),%ymm9,%ymm1 + DB 76,139,64,48 ; mov 0x30(%rax),%r8 + DB 196,66,53,22,24 ; vpermps (%r8),%ymm9,%ymm11 + DB 196,194,53,22,17 ; vpermps (%r9),%ymm9,%ymm2 + DB 76,139,64,56 ; mov 0x38(%rax),%r8 + DB 196,66,53,22,32 ; vpermps (%r8),%ymm9,%ymm12 + DB 76,139,64,32 ; mov 0x20(%rax),%r8 + DB 196,194,53,22,24 ; vpermps (%r8),%ymm9,%ymm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 196,98,53,22,40 ; vpermps (%rax),%ymm9,%ymm13 + DB 196,66,125,168,194 ; vfmadd213ps %ymm10,%ymm0,%ymm8 DB 196,194,125,168,203 ; vfmadd213ps %ymm11,%ymm0,%ymm1 - DB 196,194,125,168,210 ; vfmadd213ps %ymm10,%ymm0,%ymm2 - DB 196,194,125,168,217 ; vfmadd213ps %ymm9,%ymm0,%ymm3 + DB 196,194,125,168,212 ; vfmadd213ps %ymm12,%ymm0,%ymm2 + DB 196,194,125,168,221 ; vfmadd213ps %ymm13,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,124,41,192 ; vmovaps %ymm8,%ymm0 DB 255,224 ; jmpq *%rax @@ -3981,24 +4069,24 @@ _sk_xy_to_unit_angle_hsw LABEL PROC DB 196,65,52,95,226 ; vmaxps %ymm10,%ymm9,%ymm12 DB 196,65,36,94,220 ; vdivps %ymm12,%ymm11,%ymm11 DB 196,65,36,89,227 ; vmulps %ymm11,%ymm11,%ymm12 - DB 196,98,125,24,45,67,8,0,0 ; vbroadcastss 0x843(%rip),%ymm13 # 49f4 <_sk_callback_hsw+0x437> - DB 196,98,125,24,53,62,8,0,0 ; vbroadcastss 0x83e(%rip),%ymm14 # 49f8 <_sk_callback_hsw+0x43b> + DB 196,98,125,24,45,72,8,0,0 ; vbroadcastss 0x848(%rip),%ymm13 # 4b54 <_sk_callback_hsw+0x43c> + DB 196,98,125,24,53,67,8,0,0 ; vbroadcastss 0x843(%rip),%ymm14 # 4b58 <_sk_callback_hsw+0x440> DB 196,66,29,184,245 ; vfmadd231ps %ymm13,%ymm12,%ymm14 - DB 196,98,125,24,45,52,8,0,0 ; vbroadcastss 0x834(%rip),%ymm13 # 49fc <_sk_callback_hsw+0x43f> + DB 196,98,125,24,45,57,8,0,0 ; vbroadcastss 0x839(%rip),%ymm13 # 4b5c <_sk_callback_hsw+0x444> DB 196,66,29,184,238 ; vfmadd231ps %ymm14,%ymm12,%ymm13 - DB 196,98,125,24,53,42,8,0,0 ; vbroadcastss 0x82a(%rip),%ymm14 # 4a00 <_sk_callback_hsw+0x443> + DB 196,98,125,24,53,47,8,0,0 ; vbroadcastss 0x82f(%rip),%ymm14 # 4b60 <_sk_callback_hsw+0x448> DB 196,66,29,184,245 ; vfmadd231ps %ymm13,%ymm12,%ymm14 DB 196,65,36,89,222 ; vmulps %ymm14,%ymm11,%ymm11 DB 196,65,52,194,202,1 ; vcmpltps %ymm10,%ymm9,%ymm9 - DB 196,98,125,24,21,21,8,0,0 ; vbroadcastss 0x815(%rip),%ymm10 # 4a04 <_sk_callback_hsw+0x447> + DB 196,98,125,24,21,26,8,0,0 ; vbroadcastss 0x81a(%rip),%ymm10 # 4b64 <_sk_callback_hsw+0x44c> DB 196,65,44,92,211 ; vsubps %ymm11,%ymm10,%ymm10 DB 196,67,37,74,202,144 ; vblendvps %ymm9,%ymm10,%ymm11,%ymm9 DB 196,193,124,194,192,1 ; vcmpltps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,21,255,7,0,0 ; vbroadcastss 0x7ff(%rip),%ymm10 # 4a08 <_sk_callback_hsw+0x44b> + DB 196,98,125,24,21,4,8,0,0 ; vbroadcastss 0x804(%rip),%ymm10 # 4b68 <_sk_callback_hsw+0x450> DB 196,65,44,92,209 ; vsubps %ymm9,%ymm10,%ymm10 DB 196,195,53,74,194,0 ; vblendvps %ymm0,%ymm10,%ymm9,%ymm0 DB 196,65,116,194,200,1 ; vcmpltps %ymm8,%ymm1,%ymm9 - DB 196,98,125,24,21,233,7,0,0 ; vbroadcastss 0x7e9(%rip),%ymm10 # 4a0c <_sk_callback_hsw+0x44f> + DB 196,98,125,24,21,238,7,0,0 ; vbroadcastss 0x7ee(%rip),%ymm10 # 4b6c <_sk_callback_hsw+0x454> DB 197,44,92,208 ; vsubps %ymm0,%ymm10,%ymm10 DB 196,195,125,74,194,144 ; vblendvps %ymm9,%ymm10,%ymm0,%ymm0 DB 196,65,124,194,200,3 ; vcmpunordps %ymm8,%ymm0,%ymm9 @@ -4018,7 +4106,7 @@ _sk_xy_to_radius_hsw LABEL PROC PUBLIC _sk_save_xy_hsw _sk_save_xy_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,178,7,0,0 ; vbroadcastss 0x7b2(%rip),%ymm8 # 4a10 <_sk_callback_hsw+0x453> + DB 196,98,125,24,5,183,7,0,0 ; vbroadcastss 0x7b7(%rip),%ymm8 # 4b70 <_sk_callback_hsw+0x458> DB 196,65,124,88,200 ; vaddps %ymm8,%ymm0,%ymm9 DB 196,67,125,8,209,1 ; vroundps $0x1,%ymm9,%ymm10 DB 196,65,52,92,202 ; vsubps %ymm10,%ymm9,%ymm9 @@ -4048,9 +4136,9 @@ _sk_accumulate_hsw LABEL PROC PUBLIC _sk_bilinear_nx_hsw _sk_bilinear_nx_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,70,7,0,0 ; vbroadcastss 0x746(%rip),%ymm0 # 4a14 <_sk_callback_hsw+0x457> + DB 196,226,125,24,5,75,7,0,0 ; vbroadcastss 0x74b(%rip),%ymm0 # 4b74 <_sk_callback_hsw+0x45c> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,61,7,0,0 ; vbroadcastss 0x73d(%rip),%ymm8 # 4a18 <_sk_callback_hsw+0x45b> + DB 196,98,125,24,5,66,7,0,0 ; vbroadcastss 0x742(%rip),%ymm8 # 4b78 <_sk_callback_hsw+0x460> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -4059,7 +4147,7 @@ _sk_bilinear_nx_hsw LABEL PROC PUBLIC _sk_bilinear_px_hsw _sk_bilinear_px_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,37,7,0,0 ; vbroadcastss 0x725(%rip),%ymm0 # 4a1c <_sk_callback_hsw+0x45f> + DB 196,226,125,24,5,42,7,0,0 ; vbroadcastss 0x72a(%rip),%ymm0 # 4b7c <_sk_callback_hsw+0x464> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -4069,9 +4157,9 @@ _sk_bilinear_px_hsw LABEL PROC PUBLIC _sk_bilinear_ny_hsw _sk_bilinear_ny_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,9,7,0,0 ; vbroadcastss 0x709(%rip),%ymm1 # 4a20 <_sk_callback_hsw+0x463> + DB 196,226,125,24,13,14,7,0,0 ; vbroadcastss 0x70e(%rip),%ymm1 # 4b80 <_sk_callback_hsw+0x468> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,255,6,0,0 ; vbroadcastss 0x6ff(%rip),%ymm8 # 4a24 <_sk_callback_hsw+0x467> + DB 196,98,125,24,5,4,7,0,0 ; vbroadcastss 0x704(%rip),%ymm8 # 4b84 <_sk_callback_hsw+0x46c> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -4080,7 +4168,7 @@ _sk_bilinear_ny_hsw LABEL PROC PUBLIC _sk_bilinear_py_hsw _sk_bilinear_py_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,231,6,0,0 ; vbroadcastss 0x6e7(%rip),%ymm1 # 4a28 <_sk_callback_hsw+0x46b> + DB 196,226,125,24,13,236,6,0,0 ; vbroadcastss 0x6ec(%rip),%ymm1 # 4b88 <_sk_callback_hsw+0x470> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -4090,13 +4178,13 @@ _sk_bilinear_py_hsw LABEL PROC PUBLIC _sk_bicubic_n3x_hsw _sk_bicubic_n3x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,202,6,0,0 ; vbroadcastss 0x6ca(%rip),%ymm0 # 4a2c <_sk_callback_hsw+0x46f> + DB 196,226,125,24,5,207,6,0,0 ; vbroadcastss 0x6cf(%rip),%ymm0 # 4b8c <_sk_callback_hsw+0x474> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,193,6,0,0 ; vbroadcastss 0x6c1(%rip),%ymm8 # 4a30 <_sk_callback_hsw+0x473> + DB 196,98,125,24,5,198,6,0,0 ; vbroadcastss 0x6c6(%rip),%ymm8 # 4b90 <_sk_callback_hsw+0x478> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,178,6,0,0 ; vbroadcastss 0x6b2(%rip),%ymm10 # 4a34 <_sk_callback_hsw+0x477> - DB 196,98,125,24,29,173,6,0,0 ; vbroadcastss 0x6ad(%rip),%ymm11 # 4a38 <_sk_callback_hsw+0x47b> + DB 196,98,125,24,21,183,6,0,0 ; vbroadcastss 0x6b7(%rip),%ymm10 # 4b94 <_sk_callback_hsw+0x47c> + DB 196,98,125,24,29,178,6,0,0 ; vbroadcastss 0x6b2(%rip),%ymm11 # 4b98 <_sk_callback_hsw+0x480> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,36,89,193 ; vmulps %ymm9,%ymm11,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -4106,16 +4194,16 @@ _sk_bicubic_n3x_hsw LABEL PROC PUBLIC _sk_bicubic_n1x_hsw _sk_bicubic_n1x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,144,6,0,0 ; vbroadcastss 0x690(%rip),%ymm0 # 4a3c <_sk_callback_hsw+0x47f> + DB 196,226,125,24,5,149,6,0,0 ; vbroadcastss 0x695(%rip),%ymm0 # 4b9c <_sk_callback_hsw+0x484> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,135,6,0,0 ; vbroadcastss 0x687(%rip),%ymm8 # 4a40 <_sk_callback_hsw+0x483> + DB 196,98,125,24,5,140,6,0,0 ; vbroadcastss 0x68c(%rip),%ymm8 # 4ba0 <_sk_callback_hsw+0x488> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,125,6,0,0 ; vbroadcastss 0x67d(%rip),%ymm9 # 4a44 <_sk_callback_hsw+0x487> - DB 196,98,125,24,21,120,6,0,0 ; vbroadcastss 0x678(%rip),%ymm10 # 4a48 <_sk_callback_hsw+0x48b> + DB 196,98,125,24,13,130,6,0,0 ; vbroadcastss 0x682(%rip),%ymm9 # 4ba4 <_sk_callback_hsw+0x48c> + DB 196,98,125,24,21,125,6,0,0 ; vbroadcastss 0x67d(%rip),%ymm10 # 4ba8 <_sk_callback_hsw+0x490> DB 196,66,61,168,209 ; vfmadd213ps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,13,110,6,0,0 ; vbroadcastss 0x66e(%rip),%ymm9 # 4a4c <_sk_callback_hsw+0x48f> + DB 196,98,125,24,13,115,6,0,0 ; vbroadcastss 0x673(%rip),%ymm9 # 4bac <_sk_callback_hsw+0x494> DB 196,66,61,184,202 ; vfmadd231ps %ymm10,%ymm8,%ymm9 - DB 196,98,125,24,21,100,6,0,0 ; vbroadcastss 0x664(%rip),%ymm10 # 4a50 <_sk_callback_hsw+0x493> + DB 196,98,125,24,21,105,6,0,0 ; vbroadcastss 0x669(%rip),%ymm10 # 4bb0 <_sk_callback_hsw+0x498> DB 196,66,61,184,209 ; vfmadd231ps %ymm9,%ymm8,%ymm10 DB 197,124,17,144,128,0,0,0 ; vmovups %ymm10,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -4124,14 +4212,14 @@ _sk_bicubic_n1x_hsw LABEL PROC PUBLIC _sk_bicubic_p1x_hsw _sk_bicubic_p1x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,76,6,0,0 ; vbroadcastss 0x64c(%rip),%ymm8 # 4a54 <_sk_callback_hsw+0x497> + DB 196,98,125,24,5,81,6,0,0 ; vbroadcastss 0x651(%rip),%ymm8 # 4bb4 <_sk_callback_hsw+0x49c> DB 197,188,88,0 ; vaddps (%rax),%ymm8,%ymm0 DB 197,124,16,72,64 ; vmovups 0x40(%rax),%ymm9 - DB 196,98,125,24,21,62,6,0,0 ; vbroadcastss 0x63e(%rip),%ymm10 # 4a58 <_sk_callback_hsw+0x49b> - DB 196,98,125,24,29,57,6,0,0 ; vbroadcastss 0x639(%rip),%ymm11 # 4a5c <_sk_callback_hsw+0x49f> + DB 196,98,125,24,21,67,6,0,0 ; vbroadcastss 0x643(%rip),%ymm10 # 4bb8 <_sk_callback_hsw+0x4a0> + DB 196,98,125,24,29,62,6,0,0 ; vbroadcastss 0x63e(%rip),%ymm11 # 4bbc <_sk_callback_hsw+0x4a4> DB 196,66,53,168,218 ; vfmadd213ps %ymm10,%ymm9,%ymm11 DB 196,66,53,168,216 ; vfmadd213ps %ymm8,%ymm9,%ymm11 - DB 196,98,125,24,5,42,6,0,0 ; vbroadcastss 0x62a(%rip),%ymm8 # 4a60 <_sk_callback_hsw+0x4a3> + DB 196,98,125,24,5,47,6,0,0 ; vbroadcastss 0x62f(%rip),%ymm8 # 4bc0 <_sk_callback_hsw+0x4a8> DB 196,66,53,184,195 ; vfmadd231ps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -4140,12 +4228,12 @@ _sk_bicubic_p1x_hsw LABEL PROC PUBLIC _sk_bicubic_p3x_hsw _sk_bicubic_p3x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,18,6,0,0 ; vbroadcastss 0x612(%rip),%ymm0 # 4a64 <_sk_callback_hsw+0x4a7> + DB 196,226,125,24,5,23,6,0,0 ; vbroadcastss 0x617(%rip),%ymm0 # 4bc4 <_sk_callback_hsw+0x4ac> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,255,5,0,0 ; vbroadcastss 0x5ff(%rip),%ymm10 # 4a68 <_sk_callback_hsw+0x4ab> - DB 196,98,125,24,29,250,5,0,0 ; vbroadcastss 0x5fa(%rip),%ymm11 # 4a6c <_sk_callback_hsw+0x4af> + DB 196,98,125,24,21,4,6,0,0 ; vbroadcastss 0x604(%rip),%ymm10 # 4bc8 <_sk_callback_hsw+0x4b0> + DB 196,98,125,24,29,255,5,0,0 ; vbroadcastss 0x5ff(%rip),%ymm11 # 4bcc <_sk_callback_hsw+0x4b4> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,52,89,195 ; vmulps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -4155,13 +4243,13 @@ _sk_bicubic_p3x_hsw LABEL PROC PUBLIC _sk_bicubic_n3y_hsw _sk_bicubic_n3y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,221,5,0,0 ; vbroadcastss 0x5dd(%rip),%ymm1 # 4a70 <_sk_callback_hsw+0x4b3> + DB 196,226,125,24,13,226,5,0,0 ; vbroadcastss 0x5e2(%rip),%ymm1 # 4bd0 <_sk_callback_hsw+0x4b8> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,211,5,0,0 ; vbroadcastss 0x5d3(%rip),%ymm8 # 4a74 <_sk_callback_hsw+0x4b7> + DB 196,98,125,24,5,216,5,0,0 ; vbroadcastss 0x5d8(%rip),%ymm8 # 4bd4 <_sk_callback_hsw+0x4bc> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,196,5,0,0 ; vbroadcastss 0x5c4(%rip),%ymm10 # 4a78 <_sk_callback_hsw+0x4bb> - DB 196,98,125,24,29,191,5,0,0 ; vbroadcastss 0x5bf(%rip),%ymm11 # 4a7c <_sk_callback_hsw+0x4bf> + DB 196,98,125,24,21,201,5,0,0 ; vbroadcastss 0x5c9(%rip),%ymm10 # 4bd8 <_sk_callback_hsw+0x4c0> + DB 196,98,125,24,29,196,5,0,0 ; vbroadcastss 0x5c4(%rip),%ymm11 # 4bdc <_sk_callback_hsw+0x4c4> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,36,89,193 ; vmulps %ymm9,%ymm11,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -4171,16 +4259,16 @@ _sk_bicubic_n3y_hsw LABEL PROC PUBLIC _sk_bicubic_n1y_hsw _sk_bicubic_n1y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,162,5,0,0 ; vbroadcastss 0x5a2(%rip),%ymm1 # 4a80 <_sk_callback_hsw+0x4c3> + DB 196,226,125,24,13,167,5,0,0 ; vbroadcastss 0x5a7(%rip),%ymm1 # 4be0 <_sk_callback_hsw+0x4c8> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,152,5,0,0 ; vbroadcastss 0x598(%rip),%ymm8 # 4a84 <_sk_callback_hsw+0x4c7> + DB 196,98,125,24,5,157,5,0,0 ; vbroadcastss 0x59d(%rip),%ymm8 # 4be4 <_sk_callback_hsw+0x4cc> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,142,5,0,0 ; vbroadcastss 0x58e(%rip),%ymm9 # 4a88 <_sk_callback_hsw+0x4cb> - DB 196,98,125,24,21,137,5,0,0 ; vbroadcastss 0x589(%rip),%ymm10 # 4a8c <_sk_callback_hsw+0x4cf> + DB 196,98,125,24,13,147,5,0,0 ; vbroadcastss 0x593(%rip),%ymm9 # 4be8 <_sk_callback_hsw+0x4d0> + DB 196,98,125,24,21,142,5,0,0 ; vbroadcastss 0x58e(%rip),%ymm10 # 4bec <_sk_callback_hsw+0x4d4> DB 196,66,61,168,209 ; vfmadd213ps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,13,127,5,0,0 ; vbroadcastss 0x57f(%rip),%ymm9 # 4a90 <_sk_callback_hsw+0x4d3> + DB 196,98,125,24,13,132,5,0,0 ; vbroadcastss 0x584(%rip),%ymm9 # 4bf0 <_sk_callback_hsw+0x4d8> DB 196,66,61,184,202 ; vfmadd231ps %ymm10,%ymm8,%ymm9 - DB 196,98,125,24,21,117,5,0,0 ; vbroadcastss 0x575(%rip),%ymm10 # 4a94 <_sk_callback_hsw+0x4d7> + DB 196,98,125,24,21,122,5,0,0 ; vbroadcastss 0x57a(%rip),%ymm10 # 4bf4 <_sk_callback_hsw+0x4dc> DB 196,66,61,184,209 ; vfmadd231ps %ymm9,%ymm8,%ymm10 DB 197,124,17,144,160,0,0,0 ; vmovups %ymm10,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -4189,14 +4277,14 @@ _sk_bicubic_n1y_hsw LABEL PROC PUBLIC _sk_bicubic_p1y_hsw _sk_bicubic_p1y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,93,5,0,0 ; vbroadcastss 0x55d(%rip),%ymm8 # 4a98 <_sk_callback_hsw+0x4db> + DB 196,98,125,24,5,98,5,0,0 ; vbroadcastss 0x562(%rip),%ymm8 # 4bf8 <_sk_callback_hsw+0x4e0> DB 197,188,88,72,32 ; vaddps 0x20(%rax),%ymm8,%ymm1 DB 197,124,16,72,96 ; vmovups 0x60(%rax),%ymm9 - DB 196,98,125,24,21,78,5,0,0 ; vbroadcastss 0x54e(%rip),%ymm10 # 4a9c <_sk_callback_hsw+0x4df> - DB 196,98,125,24,29,73,5,0,0 ; vbroadcastss 0x549(%rip),%ymm11 # 4aa0 <_sk_callback_hsw+0x4e3> + DB 196,98,125,24,21,83,5,0,0 ; vbroadcastss 0x553(%rip),%ymm10 # 4bfc <_sk_callback_hsw+0x4e4> + DB 196,98,125,24,29,78,5,0,0 ; vbroadcastss 0x54e(%rip),%ymm11 # 4c00 <_sk_callback_hsw+0x4e8> DB 196,66,53,168,218 ; vfmadd213ps %ymm10,%ymm9,%ymm11 DB 196,66,53,168,216 ; vfmadd213ps %ymm8,%ymm9,%ymm11 - DB 196,98,125,24,5,58,5,0,0 ; vbroadcastss 0x53a(%rip),%ymm8 # 4aa4 <_sk_callback_hsw+0x4e7> + DB 196,98,125,24,5,63,5,0,0 ; vbroadcastss 0x53f(%rip),%ymm8 # 4c04 <_sk_callback_hsw+0x4ec> DB 196,66,53,184,195 ; vfmadd231ps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -4205,12 +4293,12 @@ _sk_bicubic_p1y_hsw LABEL PROC PUBLIC _sk_bicubic_p3y_hsw _sk_bicubic_p3y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,34,5,0,0 ; vbroadcastss 0x522(%rip),%ymm1 # 4aa8 <_sk_callback_hsw+0x4eb> + DB 196,226,125,24,13,39,5,0,0 ; vbroadcastss 0x527(%rip),%ymm1 # 4c08 <_sk_callback_hsw+0x4f0> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,14,5,0,0 ; vbroadcastss 0x50e(%rip),%ymm10 # 4aac <_sk_callback_hsw+0x4ef> - DB 196,98,125,24,29,9,5,0,0 ; vbroadcastss 0x509(%rip),%ymm11 # 4ab0 <_sk_callback_hsw+0x4f3> + DB 196,98,125,24,21,19,5,0,0 ; vbroadcastss 0x513(%rip),%ymm10 # 4c0c <_sk_callback_hsw+0x4f4> + DB 196,98,125,24,29,14,5,0,0 ; vbroadcastss 0x50e(%rip),%ymm11 # 4c10 <_sk_callback_hsw+0x4f8> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,52,89,195 ; vmulps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -4324,25 +4412,25 @@ ALIGN 4 DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 4789 <.literal4+0xb1> + DB 71,225,61 ; rex.RXB loope 48e5 <.literal4+0xb1> DB 0,0 ; add %al,(%rax) DB 128,63,154 ; cmpb $0x9a,(%rdi) DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 4799 <.literal4+0xc1> + DB 71,225,61 ; rex.RXB loope 48f5 <.literal4+0xc1> DB 0,0 ; add %al,(%rax) DB 128,63,154 ; cmpb $0x9a,(%rdi) DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 47a9 <.literal4+0xd1> + DB 71,225,61 ; rex.RXB loope 4905 <.literal4+0xd1> DB 0,0 ; add %al,(%rax) DB 128,63,154 ; cmpb $0x9a,(%rdi) DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 47b9 <.literal4+0xe1> + DB 71,225,61 ; rex.RXB loope 4915 <.literal4+0xe1> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -4392,7 +4480,7 @@ ALIGN 4 DB 190,129,128,128,59 ; mov $0x3b808081,%esi DB 129,128,128,59,0,248,0,0,8,33 ; addl $0x21080000,-0x7ffc480(%rax) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4809 <.literal4+0x131> + DB 224,7 ; loopne 4965 <.literal4+0x131> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -4408,10 +4496,10 @@ ALIGN 4 DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) DB 0,52,255 ; add %dh,(%rdi,%rdi,8) DB 255 ; (bad) - DB 127,0 ; jg 4830 <.literal4+0x158> + DB 127,0 ; jg 498c <.literal4+0x158> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 48a9 <.literal4+0x1d1> + DB 119,115 ; ja 4a05 <.literal4+0x1d1> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -4425,10 +4513,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4864 <.literal4+0x18c> + DB 127,0 ; jg 49c0 <.literal4+0x18c> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 48dd <.literal4+0x205> + DB 119,115 ; ja 4a39 <.literal4+0x205> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -4442,10 +4530,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4898 <.literal4+0x1c0> + DB 127,0 ; jg 49f4 <.literal4+0x1c0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4911 <.literal4+0x239> + DB 119,115 ; ja 4a6d <.literal4+0x239> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -4459,10 +4547,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 48cc <.literal4+0x1f4> + DB 127,0 ; jg 4a28 <.literal4+0x1f4> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4945 <.literal4+0x26d> + DB 119,115 ; ja 4aa1 <.literal4+0x26d> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -4475,7 +4563,7 @@ ALIGN 4 DB 0,75,0 ; add %cl,0x0(%rbx) DB 0,128,63,0,0,200 ; add %al,-0x37ffffc1(%rax) DB 66,0,0 ; rex.X add %al,(%rax) - DB 127,67 ; jg 4943 <.literal4+0x26b> + DB 127,67 ; jg 4a9f <.literal4+0x26b> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -4487,10 +4575,10 @@ ALIGN 4 DB 190,80,128,3,62 ; mov $0x3e038050,%esi DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4963 <.literal4+0x28b> + DB 118,63 ; jbe 4abf <.literal4+0x28b> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 4977 <.literal4+0x29f> + DB 127,67 ; jg 4ad3 <.literal4+0x29f> DB 129,128,128,59,0,0,128,63,129,128 ; addl $0x80813f80,0x3b80(%rax) DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,128,63,129,128,128 ; add %al,-0x7f7f7ec1(%rax) @@ -4499,7 +4587,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4959 <.literal4+0x281> + DB 224,7 ; loopne 4ab5 <.literal4+0x281> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -4511,7 +4599,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4975 <.literal4+0x29d> + DB 224,7 ; loopne 4ad1 <.literal4+0x29d> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -4522,7 +4610,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 49ca <.literal4+0x2f2> + DB 124,66 ; jl 4b26 <.literal4+0x2f2> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 137,136,136,55,0,15 ; mov %ecx,0xf003788(%rax) @@ -4540,9 +4628,9 @@ ALIGN 4 DB 137,136,136,59,15,0 ; mov %ecx,0xf3b88(%rax) DB 0,0 ; add %al,(%rax) DB 137,136,136,61,0,0 ; mov %ecx,0x3d88(%rax) - DB 112,65 ; jo 4a0d <.literal4+0x335> + DB 112,65 ; jo 4b69 <.literal4+0x335> DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 4a1b <.literal4+0x343> + DB 127,67 ; jg 4b77 <.literal4+0x343> DB 128,0,128 ; addb $0x80,(%rax) DB 55 ; (bad) DB 128,0,128 ; addb $0x80,(%rax) @@ -4550,7 +4638,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 255 ; (bad) - DB 127,71 ; jg 4a2f <.literal4+0x357> + DB 127,71 ; jg 4b8b <.literal4+0x357> DB 208 ; (bad) DB 179,89 ; mov $0x59,%bl DB 62,89 ; ds pop %rcx @@ -4558,9 +4646,12 @@ ALIGN 4 DB 55 ; (bad) DB 63 ; (bad) DB 152 ; cwtl - DB 221,147,61,111,43,231 ; fstl -0x18d490c3(%rbx) - DB 187,159,215,202,60 ; mov $0x3ccad79f,%ebx - DB 212 ; (bad) + DB 221,147,61,1,0,0 ; fstl 0x13d(%rbx) + DB 0,111,43 ; add %ch,0x2b(%rdi) + DB 231,187 ; out %eax,$0xbb + DB 159 ; lahf + DB 215 ; xlat %ds:(%rbx) + DB 202,60,212 ; lret $0xd43c DB 100,84 ; fs push %rsp DB 189,169,240,34,62 ; mov $0x3e22f0a9,%ebp DB 0,0 ; add %al,(%rax) @@ -4647,16 +4738,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004ae8 <_sk_callback_hsw+0xa00052b> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004c48 <_sk_callback_hsw+0xa000530> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004af0 <_sk_callback_hsw+0x12000533> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004c50 <_sk_callback_hsw+0x12000538> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004af8 <_sk_callback_hsw+0x1a00053b> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004c58 <_sk_callback_hsw+0x1a000540> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004b00 <_sk_callback_hsw+0x3000543> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004c60 <_sk_callback_hsw+0x3000548> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4699,16 +4790,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004b48 <_sk_callback_hsw+0xa00058b> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004ca8 <_sk_callback_hsw+0xa000590> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004b50 <_sk_callback_hsw+0x12000593> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004cb0 <_sk_callback_hsw+0x12000598> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004b58 <_sk_callback_hsw+0x1a00059b> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004cb8 <_sk_callback_hsw+0x1a0005a0> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004b60 <_sk_callback_hsw+0x30005a3> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004cc0 <_sk_callback_hsw+0x30005a8> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4751,16 +4842,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004ba8 <_sk_callback_hsw+0xa0005eb> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004d08 <_sk_callback_hsw+0xa0005f0> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004bb0 <_sk_callback_hsw+0x120005f3> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004d10 <_sk_callback_hsw+0x120005f8> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004bb8 <_sk_callback_hsw+0x1a0005fb> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004d18 <_sk_callback_hsw+0x1a000600> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004bc0 <_sk_callback_hsw+0x3000603> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004d20 <_sk_callback_hsw+0x3000608> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4803,16 +4894,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004c08 <_sk_callback_hsw+0xa00064b> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004d68 <_sk_callback_hsw+0xa000650> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004c10 <_sk_callback_hsw+0x12000653> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004d70 <_sk_callback_hsw+0x12000658> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004c18 <_sk_callback_hsw+0x1a00065b> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004d78 <_sk_callback_hsw+0x1a000660> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004c20 <_sk_callback_hsw+0x3000663> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004d80 <_sk_callback_hsw+0x3000668> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4954,14 +5045,14 @@ _sk_seed_shader_avx LABEL PROC DB 197,249,112,192,0 ; vpshufd $0x0,%xmm0,%xmm0 DB 196,227,125,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,248,92,0,0 ; vbroadcastss 0x5cf8(%rip),%ymm1 # 5e58 <_sk_callback_avx+0x11c> + DB 196,226,125,24,13,224,98,0,0 ; vbroadcastss 0x62e0(%rip),%ymm1 # 6440 <_sk_callback_avx+0x11a> DB 197,252,88,193 ; vaddps %ymm1,%ymm0,%ymm0 DB 197,252,88,2 ; vaddps (%rdx),%ymm0,%ymm0 DB 196,226,125,24,16 ; vbroadcastss (%rax),%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 197,236,88,201 ; vaddps %ymm1,%ymm2,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,21,220,92,0,0 ; vbroadcastss 0x5cdc(%rip),%ymm2 # 5e5c <_sk_callback_avx+0x120> + DB 196,226,125,24,21,196,98,0,0 ; vbroadcastss 0x62c4(%rip),%ymm2 # 6444 <_sk_callback_avx+0x11e> DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 DB 197,220,87,228 ; vxorps %ymm4,%ymm4,%ymm4 DB 197,212,87,237 ; vxorps %ymm5,%ymm5,%ymm5 @@ -4981,7 +5072,7 @@ _sk_dither_avx LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 196,66,125,24,8 ; vbroadcastss (%r8),%ymm9 DB 196,65,60,87,209 ; vxorps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,29,148,92,0,0 ; vbroadcastss 0x5c94(%rip),%ymm11 # 5e60 <_sk_callback_avx+0x124> + DB 196,98,125,24,29,124,98,0,0 ; vbroadcastss 0x627c(%rip),%ymm11 # 6448 <_sk_callback_avx+0x122> DB 196,65,44,84,203 ; vandps %ymm11,%ymm10,%ymm9 DB 196,193,25,114,241,5 ; vpslld $0x5,%xmm9,%xmm12 DB 196,67,125,25,201,1 ; vextractf128 $0x1,%ymm9,%xmm9 @@ -4992,8 +5083,8 @@ _sk_dither_avx LABEL PROC DB 196,67,125,25,219,1 ; vextractf128 $0x1,%ymm11,%xmm11 DB 196,193,33,114,243,4 ; vpslld $0x4,%xmm11,%xmm11 DB 196,67,29,24,219,1 ; vinsertf128 $0x1,%xmm11,%ymm12,%ymm11 - DB 196,98,125,24,37,85,92,0,0 ; vbroadcastss 0x5c55(%rip),%ymm12 # 5e64 <_sk_callback_avx+0x128> - DB 196,98,125,24,45,80,92,0,0 ; vbroadcastss 0x5c50(%rip),%ymm13 # 5e68 <_sk_callback_avx+0x12c> + DB 196,98,125,24,37,61,98,0,0 ; vbroadcastss 0x623d(%rip),%ymm12 # 644c <_sk_callback_avx+0x126> + DB 196,98,125,24,45,56,98,0,0 ; vbroadcastss 0x6238(%rip),%ymm13 # 6450 <_sk_callback_avx+0x12a> DB 196,65,44,84,245 ; vandps %ymm13,%ymm10,%ymm14 DB 196,193,1,114,246,2 ; vpslld $0x2,%xmm14,%xmm15 DB 196,67,125,25,246,1 ; vextractf128 $0x1,%ymm14,%xmm14 @@ -5020,9 +5111,9 @@ _sk_dither_avx LABEL PROC DB 196,65,60,86,193 ; vorps %ymm9,%ymm8,%ymm8 DB 196,65,60,86,194 ; vorps %ymm10,%ymm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,187,91,0,0 ; vbroadcastss 0x5bbb(%rip),%ymm9 # 5e6c <_sk_callback_avx+0x130> + DB 196,98,125,24,13,163,97,0,0 ; vbroadcastss 0x61a3(%rip),%ymm9 # 6454 <_sk_callback_avx+0x12e> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,24,13,177,91,0,0 ; vbroadcastss 0x5bb1(%rip),%ymm9 # 5e70 <_sk_callback_avx+0x134> + DB 196,98,125,24,13,153,97,0,0 ; vbroadcastss 0x6199(%rip),%ymm9 # 6458 <_sk_callback_avx+0x132> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 196,98,125,24,72,8 ; vbroadcastss 0x8(%rax),%ymm9 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 @@ -5074,7 +5165,7 @@ _sk_clear_avx LABEL PROC PUBLIC _sk_srcatop_avx _sk_srcatop_avx LABEL PROC DB 197,252,89,199 ; vmulps %ymm7,%ymm0,%ymm0 - DB 196,98,125,24,5,37,91,0,0 ; vbroadcastss 0x5b25(%rip),%ymm8 # 5e74 <_sk_callback_avx+0x138> + DB 196,98,125,24,5,13,97,0,0 ; vbroadcastss 0x610d(%rip),%ymm8 # 645c <_sk_callback_avx+0x136> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,204 ; vmulps %ymm4,%ymm8,%ymm9 DB 197,180,88,192 ; vaddps %ymm0,%ymm9,%ymm0 @@ -5093,7 +5184,7 @@ _sk_srcatop_avx LABEL PROC PUBLIC _sk_dstatop_avx _sk_dstatop_avx LABEL PROC DB 197,100,89,196 ; vmulps %ymm4,%ymm3,%ymm8 - DB 196,98,125,24,13,231,90,0,0 ; vbroadcastss 0x5ae7(%rip),%ymm9 # 5e78 <_sk_callback_avx+0x13c> + DB 196,98,125,24,13,207,96,0,0 ; vbroadcastss 0x60cf(%rip),%ymm9 # 6460 <_sk_callback_avx+0x13a> DB 197,52,92,207 ; vsubps %ymm7,%ymm9,%ymm9 DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 DB 197,188,88,192 ; vaddps %ymm0,%ymm8,%ymm0 @@ -5129,7 +5220,7 @@ _sk_dstin_avx LABEL PROC PUBLIC _sk_srcout_avx _sk_srcout_avx LABEL PROC - DB 196,98,125,24,5,134,90,0,0 ; vbroadcastss 0x5a86(%rip),%ymm8 # 5e7c <_sk_callback_avx+0x140> + DB 196,98,125,24,5,110,96,0,0 ; vbroadcastss 0x606e(%rip),%ymm8 # 6464 <_sk_callback_avx+0x13e> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -5140,7 +5231,7 @@ _sk_srcout_avx LABEL PROC PUBLIC _sk_dstout_avx _sk_dstout_avx LABEL PROC - DB 196,226,125,24,5,105,90,0,0 ; vbroadcastss 0x5a69(%rip),%ymm0 # 5e80 <_sk_callback_avx+0x144> + DB 196,226,125,24,5,81,96,0,0 ; vbroadcastss 0x6051(%rip),%ymm0 # 6468 <_sk_callback_avx+0x142> DB 197,252,92,219 ; vsubps %ymm3,%ymm0,%ymm3 DB 197,228,89,196 ; vmulps %ymm4,%ymm3,%ymm0 DB 197,228,89,205 ; vmulps %ymm5,%ymm3,%ymm1 @@ -5151,7 +5242,7 @@ _sk_dstout_avx LABEL PROC PUBLIC _sk_srcover_avx _sk_srcover_avx LABEL PROC - DB 196,98,125,24,5,76,90,0,0 ; vbroadcastss 0x5a4c(%rip),%ymm8 # 5e84 <_sk_callback_avx+0x148> + DB 196,98,125,24,5,52,96,0,0 ; vbroadcastss 0x6034(%rip),%ymm8 # 646c <_sk_callback_avx+0x146> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,204 ; vmulps %ymm4,%ymm8,%ymm9 DB 197,180,88,192 ; vaddps %ymm0,%ymm9,%ymm0 @@ -5166,7 +5257,7 @@ _sk_srcover_avx LABEL PROC PUBLIC _sk_dstover_avx _sk_dstover_avx LABEL PROC - DB 196,98,125,24,5,31,90,0,0 ; vbroadcastss 0x5a1f(%rip),%ymm8 # 5e88 <_sk_callback_avx+0x14c> + DB 196,98,125,24,5,7,96,0,0 ; vbroadcastss 0x6007(%rip),%ymm8 # 6470 <_sk_callback_avx+0x14a> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,252,88,196 ; vaddps %ymm4,%ymm0,%ymm0 @@ -5190,7 +5281,7 @@ _sk_modulate_avx LABEL PROC PUBLIC _sk_multiply_avx _sk_multiply_avx LABEL PROC - DB 196,98,125,24,5,222,89,0,0 ; vbroadcastss 0x59de(%rip),%ymm8 # 5e8c <_sk_callback_avx+0x150> + DB 196,98,125,24,5,198,95,0,0 ; vbroadcastss 0x5fc6(%rip),%ymm8 # 6474 <_sk_callback_avx+0x14e> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,208 ; vmulps %ymm0,%ymm9,%ymm10 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -5244,7 +5335,7 @@ _sk_screen_avx LABEL PROC PUBLIC _sk_xor__avx _sk_xor__avx LABEL PROC - DB 196,98,125,24,5,45,89,0,0 ; vbroadcastss 0x592d(%rip),%ymm8 # 5e90 <_sk_callback_avx+0x154> + DB 196,98,125,24,5,21,95,0,0 ; vbroadcastss 0x5f15(%rip),%ymm8 # 6478 <_sk_callback_avx+0x152> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -5279,7 +5370,7 @@ _sk_darken_avx LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,95,209 ; vmaxps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,173,88,0,0 ; vbroadcastss 0x58ad(%rip),%ymm8 # 5e94 <_sk_callback_avx+0x158> + DB 196,98,125,24,5,149,94,0,0 ; vbroadcastss 0x5e95(%rip),%ymm8 # 647c <_sk_callback_avx+0x156> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -5303,7 +5394,7 @@ _sk_lighten_avx LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,89,88,0,0 ; vbroadcastss 0x5859(%rip),%ymm8 # 5e98 <_sk_callback_avx+0x15c> + DB 196,98,125,24,5,65,94,0,0 ; vbroadcastss 0x5e41(%rip),%ymm8 # 6480 <_sk_callback_avx+0x15a> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -5330,7 +5421,7 @@ _sk_difference_avx LABEL PROC DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,249,87,0,0 ; vbroadcastss 0x57f9(%rip),%ymm8 # 5e9c <_sk_callback_avx+0x160> + DB 196,98,125,24,5,225,93,0,0 ; vbroadcastss 0x5de1(%rip),%ymm8 # 6484 <_sk_callback_avx+0x15e> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -5351,7 +5442,7 @@ _sk_exclusion_avx LABEL PROC DB 197,236,89,214 ; vmulps %ymm6,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,180,87,0,0 ; vbroadcastss 0x57b4(%rip),%ymm8 # 5ea0 <_sk_callback_avx+0x164> + DB 196,98,125,24,5,156,93,0,0 ; vbroadcastss 0x5d9c(%rip),%ymm8 # 6488 <_sk_callback_avx+0x162> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -5360,7 +5451,7 @@ _sk_exclusion_avx LABEL PROC PUBLIC _sk_colorburn_avx _sk_colorburn_avx LABEL PROC - DB 196,98,125,24,5,159,87,0,0 ; vbroadcastss 0x579f(%rip),%ymm8 # 5ea4 <_sk_callback_avx+0x168> + DB 196,98,125,24,5,135,93,0,0 ; vbroadcastss 0x5d87(%rip),%ymm8 # 648c <_sk_callback_avx+0x166> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,216 ; vmulps %ymm0,%ymm9,%ymm11 DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 @@ -5420,7 +5511,7 @@ _sk_colorburn_avx LABEL PROC PUBLIC _sk_colordodge_avx _sk_colordodge_avx LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 - DB 196,98,125,24,13,155,86,0,0 ; vbroadcastss 0x569b(%rip),%ymm9 # 5ea8 <_sk_callback_avx+0x16c> + DB 196,98,125,24,13,131,92,0,0 ; vbroadcastss 0x5c83(%rip),%ymm9 # 6490 <_sk_callback_avx+0x16a> DB 197,52,92,215 ; vsubps %ymm7,%ymm9,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,52,92,203 ; vsubps %ymm3,%ymm9,%ymm9 @@ -5475,7 +5566,7 @@ _sk_colordodge_avx LABEL PROC PUBLIC _sk_hardlight_avx _sk_hardlight_avx LABEL PROC - DB 196,98,125,24,5,173,85,0,0 ; vbroadcastss 0x55ad(%rip),%ymm8 # 5eac <_sk_callback_avx+0x170> + DB 196,98,125,24,5,149,91,0,0 ; vbroadcastss 0x5b95(%rip),%ymm8 # 6494 <_sk_callback_avx+0x16e> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,200 ; vmulps %ymm0,%ymm10,%ymm9 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -5528,7 +5619,7 @@ _sk_hardlight_avx LABEL PROC PUBLIC _sk_overlay_avx _sk_overlay_avx LABEL PROC - DB 196,98,125,24,5,214,84,0,0 ; vbroadcastss 0x54d6(%rip),%ymm8 # 5eb0 <_sk_callback_avx+0x174> + DB 196,98,125,24,5,190,90,0,0 ; vbroadcastss 0x5abe(%rip),%ymm8 # 6498 <_sk_callback_avx+0x172> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,200 ; vmulps %ymm0,%ymm10,%ymm9 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -5593,10 +5684,10 @@ _sk_softlight_avx LABEL PROC DB 196,65,60,88,192 ; vaddps %ymm8,%ymm8,%ymm8 DB 196,65,60,89,216 ; vmulps %ymm8,%ymm8,%ymm11 DB 196,65,60,88,195 ; vaddps %ymm11,%ymm8,%ymm8 - DB 196,98,125,24,29,201,83,0,0 ; vbroadcastss 0x53c9(%rip),%ymm11 # 5eb8 <_sk_callback_avx+0x17c> + DB 196,98,125,24,29,177,89,0,0 ; vbroadcastss 0x59b1(%rip),%ymm11 # 64a0 <_sk_callback_avx+0x17a> DB 196,65,28,88,235 ; vaddps %ymm11,%ymm12,%ymm13 DB 196,65,20,89,192 ; vmulps %ymm8,%ymm13,%ymm8 - DB 196,98,125,24,45,186,83,0,0 ; vbroadcastss 0x53ba(%rip),%ymm13 # 5ebc <_sk_callback_avx+0x180> + DB 196,98,125,24,45,162,89,0,0 ; vbroadcastss 0x59a2(%rip),%ymm13 # 64a4 <_sk_callback_avx+0x17e> DB 196,65,28,89,245 ; vmulps %ymm13,%ymm12,%ymm14 DB 196,65,12,88,192 ; vaddps %ymm8,%ymm14,%ymm8 DB 196,65,124,82,244 ; vrsqrtps %ymm12,%ymm14 @@ -5607,7 +5698,7 @@ _sk_softlight_avx LABEL PROC DB 197,4,194,255,2 ; vcmpleps %ymm7,%ymm15,%ymm15 DB 196,67,13,74,240,240 ; vblendvps %ymm15,%ymm8,%ymm14,%ymm14 DB 197,116,88,249 ; vaddps %ymm1,%ymm1,%ymm15 - DB 196,98,125,24,5,120,83,0,0 ; vbroadcastss 0x5378(%rip),%ymm8 # 5eb4 <_sk_callback_avx+0x178> + DB 196,98,125,24,5,96,89,0,0 ; vbroadcastss 0x5960(%rip),%ymm8 # 649c <_sk_callback_avx+0x176> DB 196,65,60,92,228 ; vsubps %ymm12,%ymm8,%ymm12 DB 197,132,92,195 ; vsubps %ymm3,%ymm15,%ymm0 DB 196,65,124,89,228 ; vmulps %ymm12,%ymm0,%ymm12 @@ -5734,12 +5825,12 @@ _sk_hue_avx LABEL PROC DB 196,65,28,89,219 ; vmulps %ymm11,%ymm12,%ymm11 DB 196,65,36,94,222 ; vdivps %ymm14,%ymm11,%ymm11 DB 196,67,37,74,224,240 ; vblendvps %ymm15,%ymm8,%ymm11,%ymm12 - DB 196,98,125,24,53,66,81,0,0 ; vbroadcastss 0x5142(%rip),%ymm14 # 5ec0 <_sk_callback_avx+0x184> + DB 196,98,125,24,53,42,87,0,0 ; vbroadcastss 0x572a(%rip),%ymm14 # 64a8 <_sk_callback_avx+0x182> DB 196,65,92,89,222 ; vmulps %ymm14,%ymm4,%ymm11 - DB 196,98,125,24,61,56,81,0,0 ; vbroadcastss 0x5138(%rip),%ymm15 # 5ec4 <_sk_callback_avx+0x188> + DB 196,98,125,24,61,32,87,0,0 ; vbroadcastss 0x5720(%rip),%ymm15 # 64ac <_sk_callback_avx+0x186> DB 196,65,84,89,239 ; vmulps %ymm15,%ymm5,%ymm13 DB 196,65,36,88,221 ; vaddps %ymm13,%ymm11,%ymm11 - DB 196,226,125,24,5,41,81,0,0 ; vbroadcastss 0x5129(%rip),%ymm0 # 5ec8 <_sk_callback_avx+0x18c> + DB 196,226,125,24,5,17,87,0,0 ; vbroadcastss 0x5711(%rip),%ymm0 # 64b0 <_sk_callback_avx+0x18a> DB 197,76,89,232 ; vmulps %ymm0,%ymm6,%ymm13 DB 196,65,36,88,221 ; vaddps %ymm13,%ymm11,%ymm11 DB 196,65,52,89,238 ; vmulps %ymm14,%ymm9,%ymm13 @@ -5800,7 +5891,7 @@ _sk_hue_avx LABEL PROC DB 196,65,36,95,208 ; vmaxps %ymm8,%ymm11,%ymm10 DB 196,195,109,74,209,240 ; vblendvps %ymm15,%ymm9,%ymm2,%ymm2 DB 196,193,108,95,208 ; vmaxps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,2,80,0,0 ; vbroadcastss 0x5002(%rip),%ymm8 # 5ecc <_sk_callback_avx+0x190> + DB 196,98,125,24,5,234,85,0,0 ; vbroadcastss 0x55ea(%rip),%ymm8 # 64b4 <_sk_callback_avx+0x18e> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,180,89,201 ; vmulps %ymm1,%ymm9,%ymm1 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -5857,12 +5948,12 @@ _sk_saturation_avx LABEL PROC DB 196,65,28,89,219 ; vmulps %ymm11,%ymm12,%ymm11 DB 196,65,36,94,222 ; vdivps %ymm14,%ymm11,%ymm11 DB 196,67,37,74,224,240 ; vblendvps %ymm15,%ymm8,%ymm11,%ymm12 - DB 196,98,125,24,53,10,79,0,0 ; vbroadcastss 0x4f0a(%rip),%ymm14 # 5ed0 <_sk_callback_avx+0x194> + DB 196,98,125,24,53,242,84,0,0 ; vbroadcastss 0x54f2(%rip),%ymm14 # 64b8 <_sk_callback_avx+0x192> DB 196,65,92,89,222 ; vmulps %ymm14,%ymm4,%ymm11 - DB 196,98,125,24,61,0,79,0,0 ; vbroadcastss 0x4f00(%rip),%ymm15 # 5ed4 <_sk_callback_avx+0x198> + DB 196,98,125,24,61,232,84,0,0 ; vbroadcastss 0x54e8(%rip),%ymm15 # 64bc <_sk_callback_avx+0x196> DB 196,65,84,89,239 ; vmulps %ymm15,%ymm5,%ymm13 DB 196,65,36,88,221 ; vaddps %ymm13,%ymm11,%ymm11 - DB 196,226,125,24,5,241,78,0,0 ; vbroadcastss 0x4ef1(%rip),%ymm0 # 5ed8 <_sk_callback_avx+0x19c> + DB 196,226,125,24,5,217,84,0,0 ; vbroadcastss 0x54d9(%rip),%ymm0 # 64c0 <_sk_callback_avx+0x19a> DB 197,76,89,232 ; vmulps %ymm0,%ymm6,%ymm13 DB 196,65,36,88,221 ; vaddps %ymm13,%ymm11,%ymm11 DB 196,65,52,89,238 ; vmulps %ymm14,%ymm9,%ymm13 @@ -5923,7 +6014,7 @@ _sk_saturation_avx LABEL PROC DB 196,65,36,95,208 ; vmaxps %ymm8,%ymm11,%ymm10 DB 196,195,109,74,209,240 ; vblendvps %ymm15,%ymm9,%ymm2,%ymm2 DB 196,193,108,95,208 ; vmaxps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,202,77,0,0 ; vbroadcastss 0x4dca(%rip),%ymm8 # 5edc <_sk_callback_avx+0x1a0> + DB 196,98,125,24,5,178,83,0,0 ; vbroadcastss 0x53b2(%rip),%ymm8 # 64c4 <_sk_callback_avx+0x19e> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,180,89,201 ; vmulps %ymm1,%ymm9,%ymm1 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -5952,12 +6043,12 @@ _sk_color_avx LABEL PROC DB 197,252,17,68,36,32 ; vmovups %ymm0,0x20(%rsp) DB 197,124,89,199 ; vmulps %ymm7,%ymm0,%ymm8 DB 197,116,89,207 ; vmulps %ymm7,%ymm1,%ymm9 - DB 196,98,125,24,45,90,77,0,0 ; vbroadcastss 0x4d5a(%rip),%ymm13 # 5ee0 <_sk_callback_avx+0x1a4> + DB 196,98,125,24,45,66,83,0,0 ; vbroadcastss 0x5342(%rip),%ymm13 # 64c8 <_sk_callback_avx+0x1a2> DB 196,65,92,89,213 ; vmulps %ymm13,%ymm4,%ymm10 - DB 196,98,125,24,53,80,77,0,0 ; vbroadcastss 0x4d50(%rip),%ymm14 # 5ee4 <_sk_callback_avx+0x1a8> + DB 196,98,125,24,53,56,83,0,0 ; vbroadcastss 0x5338(%rip),%ymm14 # 64cc <_sk_callback_avx+0x1a6> DB 196,65,84,89,222 ; vmulps %ymm14,%ymm5,%ymm11 DB 196,65,44,88,211 ; vaddps %ymm11,%ymm10,%ymm10 - DB 196,98,125,24,61,65,77,0,0 ; vbroadcastss 0x4d41(%rip),%ymm15 # 5ee8 <_sk_callback_avx+0x1ac> + DB 196,98,125,24,61,41,83,0,0 ; vbroadcastss 0x5329(%rip),%ymm15 # 64d0 <_sk_callback_avx+0x1aa> DB 196,65,76,89,223 ; vmulps %ymm15,%ymm6,%ymm11 DB 196,193,44,88,195 ; vaddps %ymm11,%ymm10,%ymm0 DB 196,65,60,89,221 ; vmulps %ymm13,%ymm8,%ymm11 @@ -6020,7 +6111,7 @@ _sk_color_avx LABEL PROC DB 196,65,44,95,207 ; vmaxps %ymm15,%ymm10,%ymm9 DB 196,195,37,74,192,0 ; vblendvps %ymm0,%ymm8,%ymm11,%ymm0 DB 196,65,124,95,199 ; vmaxps %ymm15,%ymm0,%ymm8 - DB 196,226,125,24,5,8,76,0,0 ; vbroadcastss 0x4c08(%rip),%ymm0 # 5eec <_sk_callback_avx+0x1b0> + DB 196,226,125,24,5,240,81,0,0 ; vbroadcastss 0x51f0(%rip),%ymm0 # 64d4 <_sk_callback_avx+0x1ae> DB 197,124,92,215 ; vsubps %ymm7,%ymm0,%ymm10 DB 197,172,89,84,36,32 ; vmulps 0x20(%rsp),%ymm10,%ymm2 DB 197,124,92,219 ; vsubps %ymm3,%ymm0,%ymm11 @@ -6050,12 +6141,12 @@ _sk_luminosity_avx LABEL PROC DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 DB 197,100,89,196 ; vmulps %ymm4,%ymm3,%ymm8 DB 197,100,89,205 ; vmulps %ymm5,%ymm3,%ymm9 - DB 196,98,125,24,45,148,75,0,0 ; vbroadcastss 0x4b94(%rip),%ymm13 # 5ef0 <_sk_callback_avx+0x1b4> + DB 196,98,125,24,45,124,81,0,0 ; vbroadcastss 0x517c(%rip),%ymm13 # 64d8 <_sk_callback_avx+0x1b2> DB 196,65,108,89,213 ; vmulps %ymm13,%ymm2,%ymm10 - DB 196,98,125,24,53,138,75,0,0 ; vbroadcastss 0x4b8a(%rip),%ymm14 # 5ef4 <_sk_callback_avx+0x1b8> + DB 196,98,125,24,53,114,81,0,0 ; vbroadcastss 0x5172(%rip),%ymm14 # 64dc <_sk_callback_avx+0x1b6> DB 196,65,116,89,222 ; vmulps %ymm14,%ymm1,%ymm11 DB 196,65,44,88,211 ; vaddps %ymm11,%ymm10,%ymm10 - DB 196,98,125,24,61,123,75,0,0 ; vbroadcastss 0x4b7b(%rip),%ymm15 # 5ef8 <_sk_callback_avx+0x1bc> + DB 196,98,125,24,61,99,81,0,0 ; vbroadcastss 0x5163(%rip),%ymm15 # 64e0 <_sk_callback_avx+0x1ba> DB 196,65,28,89,223 ; vmulps %ymm15,%ymm12,%ymm11 DB 196,193,44,88,195 ; vaddps %ymm11,%ymm10,%ymm0 DB 196,65,60,89,221 ; vmulps %ymm13,%ymm8,%ymm11 @@ -6118,7 +6209,7 @@ _sk_luminosity_avx LABEL PROC DB 196,65,44,95,207 ; vmaxps %ymm15,%ymm10,%ymm9 DB 196,195,37,74,192,0 ; vblendvps %ymm0,%ymm8,%ymm11,%ymm0 DB 196,65,124,95,199 ; vmaxps %ymm15,%ymm0,%ymm8 - DB 196,226,125,24,5,66,74,0,0 ; vbroadcastss 0x4a42(%rip),%ymm0 # 5efc <_sk_callback_avx+0x1c0> + DB 196,226,125,24,5,42,80,0,0 ; vbroadcastss 0x502a(%rip),%ymm0 # 64e4 <_sk_callback_avx+0x1be> DB 197,124,92,215 ; vsubps %ymm7,%ymm0,%ymm10 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 197,124,92,219 ; vsubps %ymm3,%ymm0,%ymm11 @@ -6151,7 +6242,7 @@ _sk_clamp_0_avx LABEL PROC PUBLIC _sk_clamp_1_avx _sk_clamp_1_avx LABEL PROC - DB 196,98,125,24,5,210,73,0,0 ; vbroadcastss 0x49d2(%rip),%ymm8 # 5f00 <_sk_callback_avx+0x1c4> + DB 196,98,125,24,5,186,79,0,0 ; vbroadcastss 0x4fba(%rip),%ymm8 # 64e8 <_sk_callback_avx+0x1c2> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 @@ -6161,7 +6252,7 @@ _sk_clamp_1_avx LABEL PROC PUBLIC _sk_clamp_a_avx _sk_clamp_a_avx LABEL PROC - DB 196,98,125,24,5,181,73,0,0 ; vbroadcastss 0x49b5(%rip),%ymm8 # 5f04 <_sk_callback_avx+0x1c8> + DB 196,98,125,24,5,157,79,0,0 ; vbroadcastss 0x4f9d(%rip),%ymm8 # 64ec <_sk_callback_avx+0x1c6> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 197,252,93,195 ; vminps %ymm3,%ymm0,%ymm0 DB 197,244,93,203 ; vminps %ymm3,%ymm1,%ymm1 @@ -6233,7 +6324,7 @@ PUBLIC _sk_unpremul_avx _sk_unpremul_avx LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,65,100,194,200,0 ; vcmpeqps %ymm8,%ymm3,%ymm9 - DB 196,98,125,24,21,253,72,0,0 ; vbroadcastss 0x48fd(%rip),%ymm10 # 5f08 <_sk_callback_avx+0x1cc> + DB 196,98,125,24,21,229,78,0,0 ; vbroadcastss 0x4ee5(%rip),%ymm10 # 64f0 <_sk_callback_avx+0x1ca> DB 197,44,94,211 ; vdivps %ymm3,%ymm10,%ymm10 DB 196,67,45,74,192,144 ; vblendvps %ymm9,%ymm8,%ymm10,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 @@ -6244,17 +6335,17 @@ _sk_unpremul_avx LABEL PROC PUBLIC _sk_from_srgb_avx _sk_from_srgb_avx LABEL PROC - DB 196,98,125,24,5,222,72,0,0 ; vbroadcastss 0x48de(%rip),%ymm8 # 5f0c <_sk_callback_avx+0x1d0> + DB 196,98,125,24,5,198,78,0,0 ; vbroadcastss 0x4ec6(%rip),%ymm8 # 64f4 <_sk_callback_avx+0x1ce> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 197,124,89,208 ; vmulps %ymm0,%ymm0,%ymm10 - DB 196,98,125,24,29,208,72,0,0 ; vbroadcastss 0x48d0(%rip),%ymm11 # 5f10 <_sk_callback_avx+0x1d4> + DB 196,98,125,24,29,184,78,0,0 ; vbroadcastss 0x4eb8(%rip),%ymm11 # 64f8 <_sk_callback_avx+0x1d2> DB 196,65,124,89,227 ; vmulps %ymm11,%ymm0,%ymm12 - DB 196,98,125,24,45,198,72,0,0 ; vbroadcastss 0x48c6(%rip),%ymm13 # 5f14 <_sk_callback_avx+0x1d8> + DB 196,98,125,24,45,174,78,0,0 ; vbroadcastss 0x4eae(%rip),%ymm13 # 64fc <_sk_callback_avx+0x1d6> DB 196,65,28,88,229 ; vaddps %ymm13,%ymm12,%ymm12 DB 196,65,44,89,212 ; vmulps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,183,72,0,0 ; vbroadcastss 0x48b7(%rip),%ymm12 # 5f18 <_sk_callback_avx+0x1dc> + DB 196,98,125,24,37,159,78,0,0 ; vbroadcastss 0x4e9f(%rip),%ymm12 # 6500 <_sk_callback_avx+0x1da> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,53,173,72,0,0 ; vbroadcastss 0x48ad(%rip),%ymm14 # 5f1c <_sk_callback_avx+0x1e0> + DB 196,98,125,24,53,149,78,0,0 ; vbroadcastss 0x4e95(%rip),%ymm14 # 6504 <_sk_callback_avx+0x1de> DB 196,193,124,194,198,1 ; vcmpltps %ymm14,%ymm0,%ymm0 DB 196,195,45,74,193,0 ; vblendvps %ymm0,%ymm9,%ymm10,%ymm0 DB 196,65,116,89,200 ; vmulps %ymm8,%ymm1,%ymm9 @@ -6281,18 +6372,18 @@ _sk_to_srgb_avx LABEL PROC DB 197,124,82,192 ; vrsqrtps %ymm0,%ymm8 DB 196,65,124,83,200 ; vrcpps %ymm8,%ymm9 DB 196,65,124,82,208 ; vrsqrtps %ymm8,%ymm10 - DB 196,98,125,24,5,56,72,0,0 ; vbroadcastss 0x4838(%rip),%ymm8 # 5f20 <_sk_callback_avx+0x1e4> + DB 196,98,125,24,5,32,78,0,0 ; vbroadcastss 0x4e20(%rip),%ymm8 # 6508 <_sk_callback_avx+0x1e2> DB 196,65,124,89,216 ; vmulps %ymm8,%ymm0,%ymm11 - DB 196,98,125,24,37,46,72,0,0 ; vbroadcastss 0x482e(%rip),%ymm12 # 5f24 <_sk_callback_avx+0x1e8> + DB 196,98,125,24,37,22,78,0,0 ; vbroadcastss 0x4e16(%rip),%ymm12 # 650c <_sk_callback_avx+0x1e6> DB 196,65,52,89,204 ; vmulps %ymm12,%ymm9,%ymm9 - DB 196,98,125,24,45,36,72,0,0 ; vbroadcastss 0x4824(%rip),%ymm13 # 5f28 <_sk_callback_avx+0x1ec> + DB 196,98,125,24,45,12,78,0,0 ; vbroadcastss 0x4e0c(%rip),%ymm13 # 6510 <_sk_callback_avx+0x1ea> DB 196,65,52,88,205 ; vaddps %ymm13,%ymm9,%ymm9 - DB 196,98,125,24,53,26,72,0,0 ; vbroadcastss 0x481a(%rip),%ymm14 # 5f2c <_sk_callback_avx+0x1f0> + DB 196,98,125,24,53,2,78,0,0 ; vbroadcastss 0x4e02(%rip),%ymm14 # 6514 <_sk_callback_avx+0x1ee> DB 196,65,44,89,214 ; vmulps %ymm14,%ymm10,%ymm10 DB 196,65,44,88,201 ; vaddps %ymm9,%ymm10,%ymm9 - DB 196,98,125,24,21,11,72,0,0 ; vbroadcastss 0x480b(%rip),%ymm10 # 5f30 <_sk_callback_avx+0x1f4> + DB 196,98,125,24,21,243,77,0,0 ; vbroadcastss 0x4df3(%rip),%ymm10 # 6518 <_sk_callback_avx+0x1f2> DB 196,65,44,93,201 ; vminps %ymm9,%ymm10,%ymm9 - DB 196,98,125,24,61,1,72,0,0 ; vbroadcastss 0x4801(%rip),%ymm15 # 5f34 <_sk_callback_avx+0x1f8> + DB 196,98,125,24,61,233,77,0,0 ; vbroadcastss 0x4de9(%rip),%ymm15 # 651c <_sk_callback_avx+0x1f6> DB 196,193,124,194,199,1 ; vcmpltps %ymm15,%ymm0,%ymm0 DB 196,195,53,74,195,0 ; vblendvps %ymm0,%ymm11,%ymm9,%ymm0 DB 197,124,82,201 ; vrsqrtps %ymm1,%ymm9 @@ -6327,7 +6418,7 @@ _sk_rgb_to_hsl_avx LABEL PROC DB 197,124,93,201 ; vminps %ymm1,%ymm0,%ymm9 DB 197,52,93,202 ; vminps %ymm2,%ymm9,%ymm9 DB 196,65,60,92,209 ; vsubps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,29,103,71,0,0 ; vbroadcastss 0x4767(%rip),%ymm11 # 5f38 <_sk_callback_avx+0x1fc> + DB 196,98,125,24,29,79,77,0,0 ; vbroadcastss 0x4d4f(%rip),%ymm11 # 6520 <_sk_callback_avx+0x1fa> DB 196,65,36,94,218 ; vdivps %ymm10,%ymm11,%ymm11 DB 197,116,92,226 ; vsubps %ymm2,%ymm1,%ymm12 DB 196,65,28,89,227 ; vmulps %ymm11,%ymm12,%ymm12 @@ -6337,19 +6428,19 @@ _sk_rgb_to_hsl_avx LABEL PROC DB 196,193,108,89,211 ; vmulps %ymm11,%ymm2,%ymm2 DB 197,252,92,201 ; vsubps %ymm1,%ymm0,%ymm1 DB 196,193,116,89,203 ; vmulps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,64,71,0,0 ; vbroadcastss 0x4740(%rip),%ymm11 # 5f44 <_sk_callback_avx+0x208> + DB 196,98,125,24,29,40,77,0,0 ; vbroadcastss 0x4d28(%rip),%ymm11 # 652c <_sk_callback_avx+0x206> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,46,71,0,0 ; vbroadcastss 0x472e(%rip),%ymm11 # 5f40 <_sk_callback_avx+0x204> + DB 196,98,125,24,29,22,77,0,0 ; vbroadcastss 0x4d16(%rip),%ymm11 # 6528 <_sk_callback_avx+0x202> DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 DB 196,227,117,74,202,224 ; vblendvps %ymm14,%ymm2,%ymm1,%ymm1 - DB 196,226,125,24,21,22,71,0,0 ; vbroadcastss 0x4716(%rip),%ymm2 # 5f3c <_sk_callback_avx+0x200> + DB 196,226,125,24,21,254,76,0,0 ; vbroadcastss 0x4cfe(%rip),%ymm2 # 6524 <_sk_callback_avx+0x1fe> DB 196,65,12,87,246 ; vxorps %ymm14,%ymm14,%ymm14 DB 196,227,13,74,210,208 ; vblendvps %ymm13,%ymm2,%ymm14,%ymm2 DB 197,188,194,192,0 ; vcmpeqps %ymm0,%ymm8,%ymm0 DB 196,193,108,88,212 ; vaddps %ymm12,%ymm2,%ymm2 DB 196,227,117,74,194,0 ; vblendvps %ymm0,%ymm2,%ymm1,%ymm0 DB 196,193,60,88,201 ; vaddps %ymm9,%ymm8,%ymm1 - DB 196,98,125,24,37,253,70,0,0 ; vbroadcastss 0x46fd(%rip),%ymm12 # 5f4c <_sk_callback_avx+0x210> + DB 196,98,125,24,37,229,76,0,0 ; vbroadcastss 0x4ce5(%rip),%ymm12 # 6534 <_sk_callback_avx+0x20e> DB 196,193,116,89,212 ; vmulps %ymm12,%ymm1,%ymm2 DB 197,28,194,226,1 ; vcmpltps %ymm2,%ymm12,%ymm12 DB 196,65,36,92,216 ; vsubps %ymm8,%ymm11,%ymm11 @@ -6359,7 +6450,7 @@ _sk_rgb_to_hsl_avx LABEL PROC DB 197,172,94,201 ; vdivps %ymm1,%ymm10,%ymm1 DB 196,195,125,74,198,128 ; vblendvps %ymm8,%ymm14,%ymm0,%ymm0 DB 196,195,117,74,206,128 ; vblendvps %ymm8,%ymm14,%ymm1,%ymm1 - DB 196,98,125,24,5,192,70,0,0 ; vbroadcastss 0x46c0(%rip),%ymm8 # 5f48 <_sk_callback_avx+0x20c> + DB 196,98,125,24,5,168,76,0,0 ; vbroadcastss 0x4ca8(%rip),%ymm8 # 6530 <_sk_callback_avx+0x20a> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -6374,7 +6465,7 @@ _sk_hsl_to_rgb_avx LABEL PROC DB 197,252,17,28,36 ; vmovups %ymm3,(%rsp) DB 197,252,40,225 ; vmovaps %ymm1,%ymm4 DB 197,252,40,216 ; vmovaps %ymm0,%ymm3 - DB 196,98,125,24,5,135,70,0,0 ; vbroadcastss 0x4687(%rip),%ymm8 # 5f50 <_sk_callback_avx+0x214> + DB 196,98,125,24,5,111,76,0,0 ; vbroadcastss 0x4c6f(%rip),%ymm8 # 6538 <_sk_callback_avx+0x212> DB 197,60,194,202,2 ; vcmpleps %ymm2,%ymm8,%ymm9 DB 197,92,89,210 ; vmulps %ymm2,%ymm4,%ymm10 DB 196,65,92,92,218 ; vsubps %ymm10,%ymm4,%ymm11 @@ -6382,23 +6473,23 @@ _sk_hsl_to_rgb_avx LABEL PROC DB 197,52,88,210 ; vaddps %ymm2,%ymm9,%ymm10 DB 197,108,88,202 ; vaddps %ymm2,%ymm2,%ymm9 DB 196,65,52,92,202 ; vsubps %ymm10,%ymm9,%ymm9 - DB 196,98,125,24,29,97,70,0,0 ; vbroadcastss 0x4661(%rip),%ymm11 # 5f54 <_sk_callback_avx+0x218> + DB 196,98,125,24,29,73,76,0,0 ; vbroadcastss 0x4c49(%rip),%ymm11 # 653c <_sk_callback_avx+0x216> DB 196,65,100,88,219 ; vaddps %ymm11,%ymm3,%ymm11 DB 196,67,125,8,227,1 ; vroundps $0x1,%ymm11,%ymm12 DB 196,65,36,92,252 ; vsubps %ymm12,%ymm11,%ymm15 DB 196,65,44,92,217 ; vsubps %ymm9,%ymm10,%ymm11 - DB 196,98,125,24,37,75,70,0,0 ; vbroadcastss 0x464b(%rip),%ymm12 # 5f5c <_sk_callback_avx+0x220> + DB 196,98,125,24,37,51,76,0,0 ; vbroadcastss 0x4c33(%rip),%ymm12 # 6544 <_sk_callback_avx+0x21e> DB 196,193,4,89,196 ; vmulps %ymm12,%ymm15,%ymm0 - DB 196,98,125,24,45,65,70,0,0 ; vbroadcastss 0x4641(%rip),%ymm13 # 5f60 <_sk_callback_avx+0x224> + DB 196,98,125,24,45,41,76,0,0 ; vbroadcastss 0x4c29(%rip),%ymm13 # 6548 <_sk_callback_avx+0x222> DB 197,20,92,240 ; vsubps %ymm0,%ymm13,%ymm14 DB 196,65,36,89,246 ; vmulps %ymm14,%ymm11,%ymm14 DB 196,65,52,88,246 ; vaddps %ymm14,%ymm9,%ymm14 - DB 196,226,125,24,13,34,70,0,0 ; vbroadcastss 0x4622(%rip),%ymm1 # 5f58 <_sk_callback_avx+0x21c> + DB 196,226,125,24,13,10,76,0,0 ; vbroadcastss 0x4c0a(%rip),%ymm1 # 6540 <_sk_callback_avx+0x21a> DB 196,193,116,194,255,2 ; vcmpleps %ymm15,%ymm1,%ymm7 DB 196,195,13,74,249,112 ; vblendvps %ymm7,%ymm9,%ymm14,%ymm7 DB 196,65,60,194,247,2 ; vcmpleps %ymm15,%ymm8,%ymm14 DB 196,227,45,74,255,224 ; vblendvps %ymm14,%ymm7,%ymm10,%ymm7 - DB 196,98,125,24,53,13,70,0,0 ; vbroadcastss 0x460d(%rip),%ymm14 # 5f64 <_sk_callback_avx+0x228> + DB 196,98,125,24,53,245,75,0,0 ; vbroadcastss 0x4bf5(%rip),%ymm14 # 654c <_sk_callback_avx+0x226> DB 196,65,12,194,255,2 ; vcmpleps %ymm15,%ymm14,%ymm15 DB 196,193,124,89,195 ; vmulps %ymm11,%ymm0,%ymm0 DB 197,180,88,192 ; vaddps %ymm0,%ymm9,%ymm0 @@ -6417,7 +6508,7 @@ _sk_hsl_to_rgb_avx LABEL PROC DB 197,164,89,247 ; vmulps %ymm7,%ymm11,%ymm6 DB 197,180,88,246 ; vaddps %ymm6,%ymm9,%ymm6 DB 196,227,77,74,237,0 ; vblendvps %ymm0,%ymm5,%ymm6,%ymm5 - DB 196,226,125,24,5,175,69,0,0 ; vbroadcastss 0x45af(%rip),%ymm0 # 5f68 <_sk_callback_avx+0x22c> + DB 196,226,125,24,5,151,75,0,0 ; vbroadcastss 0x4b97(%rip),%ymm0 # 6550 <_sk_callback_avx+0x22a> DB 197,228,88,192 ; vaddps %ymm0,%ymm3,%ymm0 DB 196,227,125,8,216,1 ; vroundps $0x1,%ymm0,%ymm3 DB 197,252,92,195 ; vsubps %ymm3,%ymm0,%ymm0 @@ -6472,7 +6563,7 @@ _sk_scale_u8_avx LABEL PROC DB 196,66,121,49,192 ; vpmovzxbd %xmm8,%xmm8 DB 196,67,53,24,192,1 ; vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,210,68,0,0 ; vbroadcastss 0x44d2(%rip),%ymm9 # 5f6c <_sk_callback_avx+0x230> + DB 196,98,125,24,13,186,74,0,0 ; vbroadcastss 0x4aba(%rip),%ymm9 # 6554 <_sk_callback_avx+0x22e> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -6527,7 +6618,7 @@ _sk_lerp_u8_avx LABEL PROC DB 196,66,121,49,192 ; vpmovzxbd %xmm8,%xmm8 DB 196,67,53,24,192,1 ; vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,30,68,0,0 ; vbroadcastss 0x441e(%rip),%ymm9 # 5f70 <_sk_callback_avx+0x234> + DB 196,98,125,24,13,6,74,0,0 ; vbroadcastss 0x4a06(%rip),%ymm9 # 6558 <_sk_callback_avx+0x232> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 @@ -6568,20 +6659,20 @@ _sk_lerp_565_avx LABEL PROC DB 196,65,57,105,201 ; vpunpckhwd %xmm9,%xmm8,%xmm9 DB 196,66,121,51,192 ; vpmovzxwd %xmm8,%xmm8 DB 196,67,61,24,193,1 ; vinsertf128 $0x1,%xmm9,%ymm8,%ymm8 - DB 196,98,125,24,13,136,67,0,0 ; vbroadcastss 0x4388(%rip),%ymm9 # 5f74 <_sk_callback_avx+0x238> + DB 196,98,125,24,13,112,73,0,0 ; vbroadcastss 0x4970(%rip),%ymm9 # 655c <_sk_callback_avx+0x236> DB 196,65,60,84,201 ; vandps %ymm9,%ymm8,%ymm9 DB 196,65,124,91,201 ; vcvtdq2ps %ymm9,%ymm9 - DB 196,98,125,24,21,121,67,0,0 ; vbroadcastss 0x4379(%rip),%ymm10 # 5f78 <_sk_callback_avx+0x23c> + DB 196,98,125,24,21,97,73,0,0 ; vbroadcastss 0x4961(%rip),%ymm10 # 6560 <_sk_callback_avx+0x23a> DB 196,65,52,89,202 ; vmulps %ymm10,%ymm9,%ymm9 - DB 196,98,125,24,21,111,67,0,0 ; vbroadcastss 0x436f(%rip),%ymm10 # 5f7c <_sk_callback_avx+0x240> + DB 196,98,125,24,21,87,73,0,0 ; vbroadcastss 0x4957(%rip),%ymm10 # 6564 <_sk_callback_avx+0x23e> DB 196,65,60,84,210 ; vandps %ymm10,%ymm8,%ymm10 DB 196,65,124,91,210 ; vcvtdq2ps %ymm10,%ymm10 - DB 196,98,125,24,29,96,67,0,0 ; vbroadcastss 0x4360(%rip),%ymm11 # 5f80 <_sk_callback_avx+0x244> + DB 196,98,125,24,29,72,73,0,0 ; vbroadcastss 0x4948(%rip),%ymm11 # 6568 <_sk_callback_avx+0x242> DB 196,65,44,89,211 ; vmulps %ymm11,%ymm10,%ymm10 - DB 196,98,125,24,29,86,67,0,0 ; vbroadcastss 0x4356(%rip),%ymm11 # 5f84 <_sk_callback_avx+0x248> + DB 196,98,125,24,29,62,73,0,0 ; vbroadcastss 0x493e(%rip),%ymm11 # 656c <_sk_callback_avx+0x246> DB 196,65,60,84,195 ; vandps %ymm11,%ymm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,29,71,67,0,0 ; vbroadcastss 0x4347(%rip),%ymm11 # 5f88 <_sk_callback_avx+0x24c> + DB 196,98,125,24,29,47,73,0,0 ; vbroadcastss 0x492f(%rip),%ymm11 # 6570 <_sk_callback_avx+0x24a> DB 196,65,60,89,195 ; vmulps %ymm11,%ymm8,%ymm8 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 @@ -6661,7 +6752,7 @@ _sk_load_tables_avx LABEL PROC DB 65,85 ; push %r13 DB 65,84 ; push %r12 DB 83 ; push %rbx - DB 197,124,40,13,22,69,0,0 ; vmovaps 0x4516(%rip),%ymm9 # 6260 <_sk_callback_avx+0x524> + DB 197,124,40,13,22,75,0,0 ; vmovaps 0x4b16(%rip),%ymm9 # 6860 <_sk_callback_avx+0x53a> DB 196,193,60,84,193 ; vandps %ymm9,%ymm8,%ymm0 DB 196,193,249,126,193 ; vmovq %xmm0,%r9 DB 69,137,203 ; mov %r9d,%r11d @@ -6753,7 +6844,7 @@ _sk_load_tables_avx LABEL PROC DB 196,193,97,114,210,24 ; vpsrld $0x18,%xmm10,%xmm3 DB 196,227,61,24,219,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,83,64,0,0 ; vbroadcastss 0x4053(%rip),%ymm8 # 5f8c <_sk_callback_avx+0x250> + DB 196,98,125,24,5,59,70,0,0 ; vbroadcastss 0x463b(%rip),%ymm8 # 6574 <_sk_callback_avx+0x24e> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -6843,7 +6934,7 @@ _sk_load_tables_u16_be_avx LABEL PROC DB 197,177,108,208 ; vpunpcklqdq %xmm0,%xmm9,%xmm2 DB 197,177,109,200 ; vpunpckhqdq %xmm0,%xmm9,%xmm1 DB 196,65,57,108,212 ; vpunpcklqdq %xmm12,%xmm8,%xmm10 - DB 197,121,111,29,86,66,0,0 ; vmovdqa 0x4256(%rip),%xmm11 # 62e0 <_sk_callback_avx+0x5a4> + DB 197,121,111,29,86,72,0,0 ; vmovdqa 0x4856(%rip),%xmm11 # 68e0 <_sk_callback_avx+0x5ba> DB 196,193,105,219,195 ; vpand %xmm11,%xmm2,%xmm0 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 196,193,121,105,209 ; vpunpckhwd %xmm9,%xmm0,%xmm2 @@ -6942,7 +7033,7 @@ _sk_load_tables_u16_be_avx LABEL PROC DB 196,226,121,51,219 ; vpmovzxwd %xmm3,%xmm3 DB 196,195,101,24,216,1 ; vinsertf128 $0x1,%xmm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,4,61,0,0 ; vbroadcastss 0x3d04(%rip),%ymm8 # 5f90 <_sk_callback_avx+0x254> + DB 196,98,125,24,5,236,66,0,0 ; vbroadcastss 0x42ec(%rip),%ymm8 # 6578 <_sk_callback_avx+0x252> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -7012,7 +7103,7 @@ _sk_load_tables_rgb_u16_be_avx LABEL PROC DB 197,185,108,202 ; vpunpcklqdq %xmm2,%xmm8,%xmm1 DB 197,185,109,210 ; vpunpckhqdq %xmm2,%xmm8,%xmm2 DB 197,121,108,195 ; vpunpcklqdq %xmm3,%xmm0,%xmm8 - DB 197,121,111,13,79,63,0,0 ; vmovdqa 0x3f4f(%rip),%xmm9 # 62f0 <_sk_callback_avx+0x5b4> + DB 197,121,111,13,79,69,0,0 ; vmovdqa 0x454f(%rip),%xmm9 # 68f0 <_sk_callback_avx+0x5ca> DB 196,193,113,219,193 ; vpand %xmm9,%xmm1,%xmm0 DB 196,65,41,239,210 ; vpxor %xmm10,%xmm10,%xmm10 DB 196,193,121,105,202 ; vpunpckhwd %xmm10,%xmm0,%xmm1 @@ -7104,7 +7195,7 @@ _sk_load_tables_rgb_u16_be_avx LABEL PROC DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 DB 196,195,109,24,208,1 ; vinsertf128 $0x1,%xmm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,22,58,0,0 ; vbroadcastss 0x3a16(%rip),%ymm3 # 5f94 <_sk_callback_avx+0x258> + DB 196,226,125,24,29,254,63,0,0 ; vbroadcastss 0x3ffe(%rip),%ymm3 # 657c <_sk_callback_avx+0x256> DB 91 ; pop %rbx DB 65,92 ; pop %r12 DB 65,93 ; pop %r13 @@ -7155,7 +7246,7 @@ _sk_byte_tables_avx LABEL PROC DB 65,84 ; push %r12 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,74,57,0,0 ; vbroadcastss 0x394a(%rip),%ymm8 # 5f98 <_sk_callback_avx+0x25c> + DB 196,98,125,24,5,50,63,0,0 ; vbroadcastss 0x3f32(%rip),%ymm8 # 6580 <_sk_callback_avx+0x25a> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,195,249,22,192,1 ; vpextrq $0x1,%xmm0,%r8 @@ -7192,7 +7283,7 @@ _sk_byte_tables_avx LABEL PROC DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,53,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,152,56,0,0 ; vbroadcastss 0x3898(%rip),%ymm9 # 5f9c <_sk_callback_avx+0x260> + DB 196,98,125,24,13,128,62,0,0 ; vbroadcastss 0x3e80(%rip),%ymm9 # 6584 <_sk_callback_avx+0x25e> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -7352,7 +7443,7 @@ _sk_byte_tables_rgb_avx LABEL PROC DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,53,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,190,53,0,0 ; vbroadcastss 0x35be(%rip),%ymm9 # 5fa0 <_sk_callback_avx+0x264> + DB 196,98,125,24,13,166,59,0,0 ; vbroadcastss 0x3ba6(%rip),%ymm9 # 6588 <_sk_callback_avx+0x262> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -7639,36 +7730,36 @@ _sk_parametric_r_avx LABEL PROC DB 196,193,124,88,195 ; vaddps %ymm11,%ymm0,%ymm0 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,216 ; vcvtdq2ps %ymm0,%ymm11 - DB 196,98,125,24,37,28,49,0,0 ; vbroadcastss 0x311c(%rip),%ymm12 # 5fa4 <_sk_callback_avx+0x268> + DB 196,98,125,24,37,4,55,0,0 ; vbroadcastss 0x3704(%rip),%ymm12 # 658c <_sk_callback_avx+0x266> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,18,49,0,0 ; vbroadcastss 0x3112(%rip),%ymm12 # 5fa8 <_sk_callback_avx+0x26c> + DB 196,98,125,24,37,250,54,0,0 ; vbroadcastss 0x36fa(%rip),%ymm12 # 6590 <_sk_callback_avx+0x26a> DB 196,193,124,84,196 ; vandps %ymm12,%ymm0,%ymm0 - DB 196,98,125,24,37,8,49,0,0 ; vbroadcastss 0x3108(%rip),%ymm12 # 5fac <_sk_callback_avx+0x270> + DB 196,98,125,24,37,240,54,0,0 ; vbroadcastss 0x36f0(%rip),%ymm12 # 6594 <_sk_callback_avx+0x26e> DB 196,193,124,86,196 ; vorps %ymm12,%ymm0,%ymm0 - DB 196,98,125,24,37,254,48,0,0 ; vbroadcastss 0x30fe(%rip),%ymm12 # 5fb0 <_sk_callback_avx+0x274> + DB 196,98,125,24,37,230,54,0,0 ; vbroadcastss 0x36e6(%rip),%ymm12 # 6598 <_sk_callback_avx+0x272> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,244,48,0,0 ; vbroadcastss 0x30f4(%rip),%ymm12 # 5fb4 <_sk_callback_avx+0x278> + DB 196,98,125,24,37,220,54,0,0 ; vbroadcastss 0x36dc(%rip),%ymm12 # 659c <_sk_callback_avx+0x276> DB 196,65,124,89,228 ; vmulps %ymm12,%ymm0,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,229,48,0,0 ; vbroadcastss 0x30e5(%rip),%ymm12 # 5fb8 <_sk_callback_avx+0x27c> + DB 196,98,125,24,37,205,54,0,0 ; vbroadcastss 0x36cd(%rip),%ymm12 # 65a0 <_sk_callback_avx+0x27a> DB 196,193,124,88,196 ; vaddps %ymm12,%ymm0,%ymm0 - DB 196,98,125,24,37,219,48,0,0 ; vbroadcastss 0x30db(%rip),%ymm12 # 5fbc <_sk_callback_avx+0x280> + DB 196,98,125,24,37,195,54,0,0 ; vbroadcastss 0x36c3(%rip),%ymm12 # 65a4 <_sk_callback_avx+0x27e> DB 197,156,94,192 ; vdivps %ymm0,%ymm12,%ymm0 DB 197,164,92,192 ; vsubps %ymm0,%ymm11,%ymm0 DB 197,172,89,192 ; vmulps %ymm0,%ymm10,%ymm0 DB 196,99,125,8,208,1 ; vroundps $0x1,%ymm0,%ymm10 DB 196,65,124,92,210 ; vsubps %ymm10,%ymm0,%ymm10 - DB 196,98,125,24,29,191,48,0,0 ; vbroadcastss 0x30bf(%rip),%ymm11 # 5fc0 <_sk_callback_avx+0x284> + DB 196,98,125,24,29,167,54,0,0 ; vbroadcastss 0x36a7(%rip),%ymm11 # 65a8 <_sk_callback_avx+0x282> DB 196,193,124,88,195 ; vaddps %ymm11,%ymm0,%ymm0 - DB 196,98,125,24,29,181,48,0,0 ; vbroadcastss 0x30b5(%rip),%ymm11 # 5fc4 <_sk_callback_avx+0x288> + DB 196,98,125,24,29,157,54,0,0 ; vbroadcastss 0x369d(%rip),%ymm11 # 65ac <_sk_callback_avx+0x286> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,124,92,195 ; vsubps %ymm11,%ymm0,%ymm0 - DB 196,98,125,24,29,166,48,0,0 ; vbroadcastss 0x30a6(%rip),%ymm11 # 5fc8 <_sk_callback_avx+0x28c> + DB 196,98,125,24,29,142,54,0,0 ; vbroadcastss 0x368e(%rip),%ymm11 # 65b0 <_sk_callback_avx+0x28a> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,156,48,0,0 ; vbroadcastss 0x309c(%rip),%ymm11 # 5fcc <_sk_callback_avx+0x290> + DB 196,98,125,24,29,132,54,0,0 ; vbroadcastss 0x3684(%rip),%ymm11 # 65b4 <_sk_callback_avx+0x28e> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,124,88,194 ; vaddps %ymm10,%ymm0,%ymm0 - DB 196,98,125,24,21,141,48,0,0 ; vbroadcastss 0x308d(%rip),%ymm10 # 5fd0 <_sk_callback_avx+0x294> + DB 196,98,125,24,21,117,54,0,0 ; vbroadcastss 0x3675(%rip),%ymm10 # 65b8 <_sk_callback_avx+0x292> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -7676,7 +7767,7 @@ _sk_parametric_r_avx LABEL PROC DB 196,195,125,74,193,128 ; vblendvps %ymm8,%ymm9,%ymm0,%ymm0 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,124,95,192 ; vmaxps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,100,48,0,0 ; vbroadcastss 0x3064(%rip),%ymm8 # 5fd4 <_sk_callback_avx+0x298> + DB 196,98,125,24,5,76,54,0,0 ; vbroadcastss 0x364c(%rip),%ymm8 # 65bc <_sk_callback_avx+0x296> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7696,36 +7787,36 @@ _sk_parametric_g_avx LABEL PROC DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,217 ; vcvtdq2ps %ymm1,%ymm11 - DB 196,98,125,24,37,21,48,0,0 ; vbroadcastss 0x3015(%rip),%ymm12 # 5fd8 <_sk_callback_avx+0x29c> + DB 196,98,125,24,37,253,53,0,0 ; vbroadcastss 0x35fd(%rip),%ymm12 # 65c0 <_sk_callback_avx+0x29a> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,11,48,0,0 ; vbroadcastss 0x300b(%rip),%ymm12 # 5fdc <_sk_callback_avx+0x2a0> + DB 196,98,125,24,37,243,53,0,0 ; vbroadcastss 0x35f3(%rip),%ymm12 # 65c4 <_sk_callback_avx+0x29e> DB 196,193,116,84,204 ; vandps %ymm12,%ymm1,%ymm1 - DB 196,98,125,24,37,1,48,0,0 ; vbroadcastss 0x3001(%rip),%ymm12 # 5fe0 <_sk_callback_avx+0x2a4> + DB 196,98,125,24,37,233,53,0,0 ; vbroadcastss 0x35e9(%rip),%ymm12 # 65c8 <_sk_callback_avx+0x2a2> DB 196,193,116,86,204 ; vorps %ymm12,%ymm1,%ymm1 - DB 196,98,125,24,37,247,47,0,0 ; vbroadcastss 0x2ff7(%rip),%ymm12 # 5fe4 <_sk_callback_avx+0x2a8> + DB 196,98,125,24,37,223,53,0,0 ; vbroadcastss 0x35df(%rip),%ymm12 # 65cc <_sk_callback_avx+0x2a6> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,237,47,0,0 ; vbroadcastss 0x2fed(%rip),%ymm12 # 5fe8 <_sk_callback_avx+0x2ac> + DB 196,98,125,24,37,213,53,0,0 ; vbroadcastss 0x35d5(%rip),%ymm12 # 65d0 <_sk_callback_avx+0x2aa> DB 196,65,116,89,228 ; vmulps %ymm12,%ymm1,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,222,47,0,0 ; vbroadcastss 0x2fde(%rip),%ymm12 # 5fec <_sk_callback_avx+0x2b0> + DB 196,98,125,24,37,198,53,0,0 ; vbroadcastss 0x35c6(%rip),%ymm12 # 65d4 <_sk_callback_avx+0x2ae> DB 196,193,116,88,204 ; vaddps %ymm12,%ymm1,%ymm1 - DB 196,98,125,24,37,212,47,0,0 ; vbroadcastss 0x2fd4(%rip),%ymm12 # 5ff0 <_sk_callback_avx+0x2b4> + DB 196,98,125,24,37,188,53,0,0 ; vbroadcastss 0x35bc(%rip),%ymm12 # 65d8 <_sk_callback_avx+0x2b2> DB 197,156,94,201 ; vdivps %ymm1,%ymm12,%ymm1 DB 197,164,92,201 ; vsubps %ymm1,%ymm11,%ymm1 DB 197,172,89,201 ; vmulps %ymm1,%ymm10,%ymm1 DB 196,99,125,8,209,1 ; vroundps $0x1,%ymm1,%ymm10 DB 196,65,116,92,210 ; vsubps %ymm10,%ymm1,%ymm10 - DB 196,98,125,24,29,184,47,0,0 ; vbroadcastss 0x2fb8(%rip),%ymm11 # 5ff4 <_sk_callback_avx+0x2b8> + DB 196,98,125,24,29,160,53,0,0 ; vbroadcastss 0x35a0(%rip),%ymm11 # 65dc <_sk_callback_avx+0x2b6> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,174,47,0,0 ; vbroadcastss 0x2fae(%rip),%ymm11 # 5ff8 <_sk_callback_avx+0x2bc> + DB 196,98,125,24,29,150,53,0,0 ; vbroadcastss 0x3596(%rip),%ymm11 # 65e0 <_sk_callback_avx+0x2ba> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,116,92,203 ; vsubps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,159,47,0,0 ; vbroadcastss 0x2f9f(%rip),%ymm11 # 5ffc <_sk_callback_avx+0x2c0> + DB 196,98,125,24,29,135,53,0,0 ; vbroadcastss 0x3587(%rip),%ymm11 # 65e4 <_sk_callback_avx+0x2be> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,149,47,0,0 ; vbroadcastss 0x2f95(%rip),%ymm11 # 6000 <_sk_callback_avx+0x2c4> + DB 196,98,125,24,29,125,53,0,0 ; vbroadcastss 0x357d(%rip),%ymm11 # 65e8 <_sk_callback_avx+0x2c2> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,116,88,202 ; vaddps %ymm10,%ymm1,%ymm1 - DB 196,98,125,24,21,134,47,0,0 ; vbroadcastss 0x2f86(%rip),%ymm10 # 6004 <_sk_callback_avx+0x2c8> + DB 196,98,125,24,21,110,53,0,0 ; vbroadcastss 0x356e(%rip),%ymm10 # 65ec <_sk_callback_avx+0x2c6> DB 196,193,116,89,202 ; vmulps %ymm10,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -7733,7 +7824,7 @@ _sk_parametric_g_avx LABEL PROC DB 196,195,117,74,201,128 ; vblendvps %ymm8,%ymm9,%ymm1,%ymm1 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,116,95,200 ; vmaxps %ymm8,%ymm1,%ymm1 - DB 196,98,125,24,5,93,47,0,0 ; vbroadcastss 0x2f5d(%rip),%ymm8 # 6008 <_sk_callback_avx+0x2cc> + DB 196,98,125,24,5,69,53,0,0 ; vbroadcastss 0x3545(%rip),%ymm8 # 65f0 <_sk_callback_avx+0x2ca> DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7753,36 +7844,36 @@ _sk_parametric_b_avx LABEL PROC DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,218 ; vcvtdq2ps %ymm2,%ymm11 - DB 196,98,125,24,37,14,47,0,0 ; vbroadcastss 0x2f0e(%rip),%ymm12 # 600c <_sk_callback_avx+0x2d0> + DB 196,98,125,24,37,246,52,0,0 ; vbroadcastss 0x34f6(%rip),%ymm12 # 65f4 <_sk_callback_avx+0x2ce> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,4,47,0,0 ; vbroadcastss 0x2f04(%rip),%ymm12 # 6010 <_sk_callback_avx+0x2d4> + DB 196,98,125,24,37,236,52,0,0 ; vbroadcastss 0x34ec(%rip),%ymm12 # 65f8 <_sk_callback_avx+0x2d2> DB 196,193,108,84,212 ; vandps %ymm12,%ymm2,%ymm2 - DB 196,98,125,24,37,250,46,0,0 ; vbroadcastss 0x2efa(%rip),%ymm12 # 6014 <_sk_callback_avx+0x2d8> + DB 196,98,125,24,37,226,52,0,0 ; vbroadcastss 0x34e2(%rip),%ymm12 # 65fc <_sk_callback_avx+0x2d6> DB 196,193,108,86,212 ; vorps %ymm12,%ymm2,%ymm2 - DB 196,98,125,24,37,240,46,0,0 ; vbroadcastss 0x2ef0(%rip),%ymm12 # 6018 <_sk_callback_avx+0x2dc> + DB 196,98,125,24,37,216,52,0,0 ; vbroadcastss 0x34d8(%rip),%ymm12 # 6600 <_sk_callback_avx+0x2da> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,230,46,0,0 ; vbroadcastss 0x2ee6(%rip),%ymm12 # 601c <_sk_callback_avx+0x2e0> + DB 196,98,125,24,37,206,52,0,0 ; vbroadcastss 0x34ce(%rip),%ymm12 # 6604 <_sk_callback_avx+0x2de> DB 196,65,108,89,228 ; vmulps %ymm12,%ymm2,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,215,46,0,0 ; vbroadcastss 0x2ed7(%rip),%ymm12 # 6020 <_sk_callback_avx+0x2e4> + DB 196,98,125,24,37,191,52,0,0 ; vbroadcastss 0x34bf(%rip),%ymm12 # 6608 <_sk_callback_avx+0x2e2> DB 196,193,108,88,212 ; vaddps %ymm12,%ymm2,%ymm2 - DB 196,98,125,24,37,205,46,0,0 ; vbroadcastss 0x2ecd(%rip),%ymm12 # 6024 <_sk_callback_avx+0x2e8> + DB 196,98,125,24,37,181,52,0,0 ; vbroadcastss 0x34b5(%rip),%ymm12 # 660c <_sk_callback_avx+0x2e6> DB 197,156,94,210 ; vdivps %ymm2,%ymm12,%ymm2 DB 197,164,92,210 ; vsubps %ymm2,%ymm11,%ymm2 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 196,99,125,8,210,1 ; vroundps $0x1,%ymm2,%ymm10 DB 196,65,108,92,210 ; vsubps %ymm10,%ymm2,%ymm10 - DB 196,98,125,24,29,177,46,0,0 ; vbroadcastss 0x2eb1(%rip),%ymm11 # 6028 <_sk_callback_avx+0x2ec> + DB 196,98,125,24,29,153,52,0,0 ; vbroadcastss 0x3499(%rip),%ymm11 # 6610 <_sk_callback_avx+0x2ea> DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 - DB 196,98,125,24,29,167,46,0,0 ; vbroadcastss 0x2ea7(%rip),%ymm11 # 602c <_sk_callback_avx+0x2f0> + DB 196,98,125,24,29,143,52,0,0 ; vbroadcastss 0x348f(%rip),%ymm11 # 6614 <_sk_callback_avx+0x2ee> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,108,92,211 ; vsubps %ymm11,%ymm2,%ymm2 - DB 196,98,125,24,29,152,46,0,0 ; vbroadcastss 0x2e98(%rip),%ymm11 # 6030 <_sk_callback_avx+0x2f4> + DB 196,98,125,24,29,128,52,0,0 ; vbroadcastss 0x3480(%rip),%ymm11 # 6618 <_sk_callback_avx+0x2f2> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,142,46,0,0 ; vbroadcastss 0x2e8e(%rip),%ymm11 # 6034 <_sk_callback_avx+0x2f8> + DB 196,98,125,24,29,118,52,0,0 ; vbroadcastss 0x3476(%rip),%ymm11 # 661c <_sk_callback_avx+0x2f6> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,108,88,210 ; vaddps %ymm10,%ymm2,%ymm2 - DB 196,98,125,24,21,127,46,0,0 ; vbroadcastss 0x2e7f(%rip),%ymm10 # 6038 <_sk_callback_avx+0x2fc> + DB 196,98,125,24,21,103,52,0,0 ; vbroadcastss 0x3467(%rip),%ymm10 # 6620 <_sk_callback_avx+0x2fa> DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 197,253,91,210 ; vcvtps2dq %ymm2,%ymm2 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -7790,7 +7881,7 @@ _sk_parametric_b_avx LABEL PROC DB 196,195,109,74,209,128 ; vblendvps %ymm8,%ymm9,%ymm2,%ymm2 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,108,95,208 ; vmaxps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,86,46,0,0 ; vbroadcastss 0x2e56(%rip),%ymm8 # 603c <_sk_callback_avx+0x300> + DB 196,98,125,24,5,62,52,0,0 ; vbroadcastss 0x343e(%rip),%ymm8 # 6624 <_sk_callback_avx+0x2fe> DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7810,36 +7901,36 @@ _sk_parametric_a_avx LABEL PROC DB 196,193,100,88,219 ; vaddps %ymm11,%ymm3,%ymm3 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,219 ; vcvtdq2ps %ymm3,%ymm11 - DB 196,98,125,24,37,7,46,0,0 ; vbroadcastss 0x2e07(%rip),%ymm12 # 6040 <_sk_callback_avx+0x304> + DB 196,98,125,24,37,239,51,0,0 ; vbroadcastss 0x33ef(%rip),%ymm12 # 6628 <_sk_callback_avx+0x302> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,253,45,0,0 ; vbroadcastss 0x2dfd(%rip),%ymm12 # 6044 <_sk_callback_avx+0x308> + DB 196,98,125,24,37,229,51,0,0 ; vbroadcastss 0x33e5(%rip),%ymm12 # 662c <_sk_callback_avx+0x306> DB 196,193,100,84,220 ; vandps %ymm12,%ymm3,%ymm3 - DB 196,98,125,24,37,243,45,0,0 ; vbroadcastss 0x2df3(%rip),%ymm12 # 6048 <_sk_callback_avx+0x30c> + DB 196,98,125,24,37,219,51,0,0 ; vbroadcastss 0x33db(%rip),%ymm12 # 6630 <_sk_callback_avx+0x30a> DB 196,193,100,86,220 ; vorps %ymm12,%ymm3,%ymm3 - DB 196,98,125,24,37,233,45,0,0 ; vbroadcastss 0x2de9(%rip),%ymm12 # 604c <_sk_callback_avx+0x310> + DB 196,98,125,24,37,209,51,0,0 ; vbroadcastss 0x33d1(%rip),%ymm12 # 6634 <_sk_callback_avx+0x30e> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,223,45,0,0 ; vbroadcastss 0x2ddf(%rip),%ymm12 # 6050 <_sk_callback_avx+0x314> + DB 196,98,125,24,37,199,51,0,0 ; vbroadcastss 0x33c7(%rip),%ymm12 # 6638 <_sk_callback_avx+0x312> DB 196,65,100,89,228 ; vmulps %ymm12,%ymm3,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,208,45,0,0 ; vbroadcastss 0x2dd0(%rip),%ymm12 # 6054 <_sk_callback_avx+0x318> + DB 196,98,125,24,37,184,51,0,0 ; vbroadcastss 0x33b8(%rip),%ymm12 # 663c <_sk_callback_avx+0x316> DB 196,193,100,88,220 ; vaddps %ymm12,%ymm3,%ymm3 - DB 196,98,125,24,37,198,45,0,0 ; vbroadcastss 0x2dc6(%rip),%ymm12 # 6058 <_sk_callback_avx+0x31c> + DB 196,98,125,24,37,174,51,0,0 ; vbroadcastss 0x33ae(%rip),%ymm12 # 6640 <_sk_callback_avx+0x31a> DB 197,156,94,219 ; vdivps %ymm3,%ymm12,%ymm3 DB 197,164,92,219 ; vsubps %ymm3,%ymm11,%ymm3 DB 197,172,89,219 ; vmulps %ymm3,%ymm10,%ymm3 DB 196,99,125,8,211,1 ; vroundps $0x1,%ymm3,%ymm10 DB 196,65,100,92,210 ; vsubps %ymm10,%ymm3,%ymm10 - DB 196,98,125,24,29,170,45,0,0 ; vbroadcastss 0x2daa(%rip),%ymm11 # 605c <_sk_callback_avx+0x320> + DB 196,98,125,24,29,146,51,0,0 ; vbroadcastss 0x3392(%rip),%ymm11 # 6644 <_sk_callback_avx+0x31e> DB 196,193,100,88,219 ; vaddps %ymm11,%ymm3,%ymm3 - DB 196,98,125,24,29,160,45,0,0 ; vbroadcastss 0x2da0(%rip),%ymm11 # 6060 <_sk_callback_avx+0x324> + DB 196,98,125,24,29,136,51,0,0 ; vbroadcastss 0x3388(%rip),%ymm11 # 6648 <_sk_callback_avx+0x322> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,100,92,219 ; vsubps %ymm11,%ymm3,%ymm3 - DB 196,98,125,24,29,145,45,0,0 ; vbroadcastss 0x2d91(%rip),%ymm11 # 6064 <_sk_callback_avx+0x328> + DB 196,98,125,24,29,121,51,0,0 ; vbroadcastss 0x3379(%rip),%ymm11 # 664c <_sk_callback_avx+0x326> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,135,45,0,0 ; vbroadcastss 0x2d87(%rip),%ymm11 # 6068 <_sk_callback_avx+0x32c> + DB 196,98,125,24,29,111,51,0,0 ; vbroadcastss 0x336f(%rip),%ymm11 # 6650 <_sk_callback_avx+0x32a> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,100,88,218 ; vaddps %ymm10,%ymm3,%ymm3 - DB 196,98,125,24,21,120,45,0,0 ; vbroadcastss 0x2d78(%rip),%ymm10 # 606c <_sk_callback_avx+0x330> + DB 196,98,125,24,21,96,51,0,0 ; vbroadcastss 0x3360(%rip),%ymm10 # 6654 <_sk_callback_avx+0x32e> DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 197,253,91,219 ; vcvtps2dq %ymm3,%ymm3 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -7847,38 +7938,38 @@ _sk_parametric_a_avx LABEL PROC DB 196,195,101,74,217,128 ; vblendvps %ymm8,%ymm9,%ymm3,%ymm3 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,100,95,216 ; vmaxps %ymm8,%ymm3,%ymm3 - DB 196,98,125,24,5,79,45,0,0 ; vbroadcastss 0x2d4f(%rip),%ymm8 # 6070 <_sk_callback_avx+0x334> + DB 196,98,125,24,5,55,51,0,0 ; vbroadcastss 0x3337(%rip),%ymm8 # 6658 <_sk_callback_avx+0x332> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax PUBLIC _sk_lab_to_xyz_avx _sk_lab_to_xyz_avx LABEL PROC - DB 196,98,125,24,5,65,45,0,0 ; vbroadcastss 0x2d41(%rip),%ymm8 # 6074 <_sk_callback_avx+0x338> + DB 196,98,125,24,5,41,51,0,0 ; vbroadcastss 0x3329(%rip),%ymm8 # 665c <_sk_callback_avx+0x336> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,55,45,0,0 ; vbroadcastss 0x2d37(%rip),%ymm8 # 6078 <_sk_callback_avx+0x33c> + DB 196,98,125,24,5,31,51,0,0 ; vbroadcastss 0x331f(%rip),%ymm8 # 6660 <_sk_callback_avx+0x33a> DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,98,125,24,13,45,45,0,0 ; vbroadcastss 0x2d2d(%rip),%ymm9 # 607c <_sk_callback_avx+0x340> + DB 196,98,125,24,13,21,51,0,0 ; vbroadcastss 0x3315(%rip),%ymm9 # 6664 <_sk_callback_avx+0x33e> DB 196,193,116,88,201 ; vaddps %ymm9,%ymm1,%ymm1 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 196,193,108,88,209 ; vaddps %ymm9,%ymm2,%ymm2 - DB 196,98,125,24,5,25,45,0,0 ; vbroadcastss 0x2d19(%rip),%ymm8 # 6080 <_sk_callback_avx+0x344> + DB 196,98,125,24,5,1,51,0,0 ; vbroadcastss 0x3301(%rip),%ymm8 # 6668 <_sk_callback_avx+0x342> DB 196,193,124,88,192 ; vaddps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,15,45,0,0 ; vbroadcastss 0x2d0f(%rip),%ymm8 # 6084 <_sk_callback_avx+0x348> + DB 196,98,125,24,5,247,50,0,0 ; vbroadcastss 0x32f7(%rip),%ymm8 # 666c <_sk_callback_avx+0x346> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,5,45,0,0 ; vbroadcastss 0x2d05(%rip),%ymm8 # 6088 <_sk_callback_avx+0x34c> + DB 196,98,125,24,5,237,50,0,0 ; vbroadcastss 0x32ed(%rip),%ymm8 # 6670 <_sk_callback_avx+0x34a> DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 197,252,88,201 ; vaddps %ymm1,%ymm0,%ymm1 - DB 196,98,125,24,5,247,44,0,0 ; vbroadcastss 0x2cf7(%rip),%ymm8 # 608c <_sk_callback_avx+0x350> + DB 196,98,125,24,5,223,50,0,0 ; vbroadcastss 0x32df(%rip),%ymm8 # 6674 <_sk_callback_avx+0x34e> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,252,92,210 ; vsubps %ymm2,%ymm0,%ymm2 DB 197,116,89,193 ; vmulps %ymm1,%ymm1,%ymm8 DB 196,65,116,89,192 ; vmulps %ymm8,%ymm1,%ymm8 - DB 196,98,125,24,13,224,44,0,0 ; vbroadcastss 0x2ce0(%rip),%ymm9 # 6090 <_sk_callback_avx+0x354> + DB 196,98,125,24,13,200,50,0,0 ; vbroadcastss 0x32c8(%rip),%ymm9 # 6678 <_sk_callback_avx+0x352> DB 196,65,52,194,208,1 ; vcmpltps %ymm8,%ymm9,%ymm10 - DB 196,98,125,24,29,213,44,0,0 ; vbroadcastss 0x2cd5(%rip),%ymm11 # 6094 <_sk_callback_avx+0x358> + DB 196,98,125,24,29,189,50,0,0 ; vbroadcastss 0x32bd(%rip),%ymm11 # 667c <_sk_callback_avx+0x356> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,37,203,44,0,0 ; vbroadcastss 0x2ccb(%rip),%ymm12 # 6098 <_sk_callback_avx+0x35c> + DB 196,98,125,24,37,179,50,0,0 ; vbroadcastss 0x32b3(%rip),%ymm12 # 6680 <_sk_callback_avx+0x35a> DB 196,193,116,89,204 ; vmulps %ymm12,%ymm1,%ymm1 DB 196,67,117,74,192,160 ; vblendvps %ymm10,%ymm8,%ymm1,%ymm8 DB 197,252,89,200 ; vmulps %ymm0,%ymm0,%ymm1 @@ -7893,9 +7984,9 @@ _sk_lab_to_xyz_avx LABEL PROC DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 DB 196,193,108,89,212 ; vmulps %ymm12,%ymm2,%ymm2 DB 196,227,109,74,208,144 ; vblendvps %ymm9,%ymm0,%ymm2,%ymm2 - DB 196,226,125,24,5,129,44,0,0 ; vbroadcastss 0x2c81(%rip),%ymm0 # 609c <_sk_callback_avx+0x360> + DB 196,226,125,24,5,105,50,0,0 ; vbroadcastss 0x3269(%rip),%ymm0 # 6684 <_sk_callback_avx+0x35e> DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 - DB 196,98,125,24,5,120,44,0,0 ; vbroadcastss 0x2c78(%rip),%ymm8 # 60a0 <_sk_callback_avx+0x364> + DB 196,98,125,24,5,96,50,0,0 ; vbroadcastss 0x3260(%rip),%ymm8 # 6688 <_sk_callback_avx+0x362> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7914,7 +8005,7 @@ _sk_load_a8_avx LABEL PROC DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,117,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,60,44,0,0 ; vbroadcastss 0x2c3c(%rip),%ymm1 # 60a4 <_sk_callback_avx+0x368> + DB 196,226,125,24,13,36,50,0,0 ; vbroadcastss 0x3224(%rip),%ymm1 # 668c <_sk_callback_avx+0x366> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -7981,7 +8072,7 @@ _sk_gather_a8_avx LABEL PROC DB 196,226,121,49,201 ; vpmovzxbd %xmm1,%xmm1 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,49,43,0,0 ; vbroadcastss 0x2b31(%rip),%ymm1 # 60a8 <_sk_callback_avx+0x36c> + DB 196,226,125,24,13,25,49,0,0 ; vbroadcastss 0x3119(%rip),%ymm1 # 6690 <_sk_callback_avx+0x36a> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -7997,7 +8088,7 @@ PUBLIC _sk_store_a8_avx _sk_store_a8_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,12,43,0,0 ; vbroadcastss 0x2b0c(%rip),%ymm8 # 60ac <_sk_callback_avx+0x370> + DB 196,98,125,24,5,244,48,0,0 ; vbroadcastss 0x30f4(%rip),%ymm8 # 6694 <_sk_callback_avx+0x36e> DB 196,65,100,89,192 ; vmulps %ymm8,%ymm3,%ymm8 DB 196,65,125,91,192 ; vcvtps2dq %ymm8,%ymm8 DB 196,67,125,25,193,1 ; vextractf128 $0x1,%ymm8,%xmm9 @@ -8065,10 +8156,10 @@ _sk_load_g8_avx LABEL PROC DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,117,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,49,42,0,0 ; vbroadcastss 0x2a31(%rip),%ymm1 # 60b0 <_sk_callback_avx+0x374> + DB 196,226,125,24,13,25,48,0,0 ; vbroadcastss 0x3019(%rip),%ymm1 # 6698 <_sk_callback_avx+0x372> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,38,42,0,0 ; vbroadcastss 0x2a26(%rip),%ymm3 # 60b4 <_sk_callback_avx+0x378> + DB 196,226,125,24,29,14,48,0,0 ; vbroadcastss 0x300e(%rip),%ymm3 # 669c <_sk_callback_avx+0x376> DB 76,137,193 ; mov %r8,%rcx DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 @@ -8132,10 +8223,10 @@ _sk_gather_g8_avx LABEL PROC DB 196,226,121,49,201 ; vpmovzxbd %xmm1,%xmm1 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,37,41,0,0 ; vbroadcastss 0x2925(%rip),%ymm1 # 60b8 <_sk_callback_avx+0x37c> + DB 196,226,125,24,13,13,47,0,0 ; vbroadcastss 0x2f0d(%rip),%ymm1 # 66a0 <_sk_callback_avx+0x37a> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,26,41,0,0 ; vbroadcastss 0x291a(%rip),%ymm3 # 60bc <_sk_callback_avx+0x380> + DB 196,226,125,24,29,2,47,0,0 ; vbroadcastss 0x2f02(%rip),%ymm3 # 66a4 <_sk_callback_avx+0x37e> DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 DB 91 ; pop %rbx @@ -8213,10 +8304,10 @@ _sk_gather_i8_avx LABEL PROC DB 196,163,121,34,4,163,2 ; vpinsrd $0x2,(%rbx,%r12,4),%xmm0,%xmm0 DB 196,163,121,34,28,19,3 ; vpinsrd $0x3,(%rbx,%r10,1),%xmm0,%xmm3 DB 196,227,61,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - DB 197,124,40,21,146,41,0,0 ; vmovaps 0x2992(%rip),%ymm10 # 6280 <_sk_callback_avx+0x544> + DB 197,124,40,21,146,47,0,0 ; vmovaps 0x2f92(%rip),%ymm10 # 6880 <_sk_callback_avx+0x55a> DB 196,193,124,84,194 ; vandps %ymm10,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,192,39,0,0 ; vbroadcastss 0x27c0(%rip),%ymm9 # 60c0 <_sk_callback_avx+0x384> + DB 196,98,125,24,13,168,45,0,0 ; vbroadcastss 0x2da8(%rip),%ymm9 # 66a8 <_sk_callback_avx+0x382> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,113,114,208,8 ; vpsrld $0x8,%xmm8,%xmm1 DB 197,233,114,211,8 ; vpsrld $0x8,%xmm3,%xmm2 @@ -8254,23 +8345,23 @@ _sk_load_565_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,209,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - DB 196,226,125,24,5,42,39,0,0 ; vbroadcastss 0x272a(%rip),%ymm0 # 60c4 <_sk_callback_avx+0x388> + DB 196,226,125,24,5,18,45,0,0 ; vbroadcastss 0x2d12(%rip),%ymm0 # 66ac <_sk_callback_avx+0x386> DB 197,236,84,192 ; vandps %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,29,39,0,0 ; vbroadcastss 0x271d(%rip),%ymm1 # 60c8 <_sk_callback_avx+0x38c> + DB 196,226,125,24,13,5,45,0,0 ; vbroadcastss 0x2d05(%rip),%ymm1 # 66b0 <_sk_callback_avx+0x38a> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,20,39,0,0 ; vbroadcastss 0x2714(%rip),%ymm1 # 60cc <_sk_callback_avx+0x390> + DB 196,226,125,24,13,252,44,0,0 ; vbroadcastss 0x2cfc(%rip),%ymm1 # 66b4 <_sk_callback_avx+0x38e> DB 197,236,84,201 ; vandps %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,7,39,0,0 ; vbroadcastss 0x2707(%rip),%ymm3 # 60d0 <_sk_callback_avx+0x394> + DB 196,226,125,24,29,239,44,0,0 ; vbroadcastss 0x2cef(%rip),%ymm3 # 66b8 <_sk_callback_avx+0x392> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,24,29,254,38,0,0 ; vbroadcastss 0x26fe(%rip),%ymm3 # 60d4 <_sk_callback_avx+0x398> + DB 196,226,125,24,29,230,44,0,0 ; vbroadcastss 0x2ce6(%rip),%ymm3 # 66bc <_sk_callback_avx+0x396> DB 197,236,84,211 ; vandps %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,241,38,0,0 ; vbroadcastss 0x26f1(%rip),%ymm3 # 60d8 <_sk_callback_avx+0x39c> + DB 196,226,125,24,29,217,44,0,0 ; vbroadcastss 0x2cd9(%rip),%ymm3 # 66c0 <_sk_callback_avx+0x39a> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,230,38,0,0 ; vbroadcastss 0x26e6(%rip),%ymm3 # 60dc <_sk_callback_avx+0x3a0> + DB 196,226,125,24,29,206,44,0,0 ; vbroadcastss 0x2cce(%rip),%ymm3 # 66c4 <_sk_callback_avx+0x39e> DB 255,224 ; jmpq *%rax DB 65,137,200 ; mov %ecx,%r8d DB 65,128,224,7 ; and $0x7,%r8b @@ -8367,23 +8458,23 @@ _sk_gather_565_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,209,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - DB 196,226,125,24,5,134,37,0,0 ; vbroadcastss 0x2586(%rip),%ymm0 # 60e0 <_sk_callback_avx+0x3a4> + DB 196,226,125,24,5,110,43,0,0 ; vbroadcastss 0x2b6e(%rip),%ymm0 # 66c8 <_sk_callback_avx+0x3a2> DB 197,236,84,192 ; vandps %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,121,37,0,0 ; vbroadcastss 0x2579(%rip),%ymm1 # 60e4 <_sk_callback_avx+0x3a8> + DB 196,226,125,24,13,97,43,0,0 ; vbroadcastss 0x2b61(%rip),%ymm1 # 66cc <_sk_callback_avx+0x3a6> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,112,37,0,0 ; vbroadcastss 0x2570(%rip),%ymm1 # 60e8 <_sk_callback_avx+0x3ac> + DB 196,226,125,24,13,88,43,0,0 ; vbroadcastss 0x2b58(%rip),%ymm1 # 66d0 <_sk_callback_avx+0x3aa> DB 197,236,84,201 ; vandps %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,99,37,0,0 ; vbroadcastss 0x2563(%rip),%ymm3 # 60ec <_sk_callback_avx+0x3b0> + DB 196,226,125,24,29,75,43,0,0 ; vbroadcastss 0x2b4b(%rip),%ymm3 # 66d4 <_sk_callback_avx+0x3ae> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,24,29,90,37,0,0 ; vbroadcastss 0x255a(%rip),%ymm3 # 60f0 <_sk_callback_avx+0x3b4> + DB 196,226,125,24,29,66,43,0,0 ; vbroadcastss 0x2b42(%rip),%ymm3 # 66d8 <_sk_callback_avx+0x3b2> DB 197,236,84,211 ; vandps %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,77,37,0,0 ; vbroadcastss 0x254d(%rip),%ymm3 # 60f4 <_sk_callback_avx+0x3b8> + DB 196,226,125,24,29,53,43,0,0 ; vbroadcastss 0x2b35(%rip),%ymm3 # 66dc <_sk_callback_avx+0x3b6> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,66,37,0,0 ; vbroadcastss 0x2542(%rip),%ymm3 # 60f8 <_sk_callback_avx+0x3bc> + DB 196,226,125,24,29,42,43,0,0 ; vbroadcastss 0x2b2a(%rip),%ymm3 # 66e0 <_sk_callback_avx+0x3ba> DB 91 ; pop %rbx DB 65,92 ; pop %r12 DB 65,94 ; pop %r14 @@ -8395,14 +8486,14 @@ PUBLIC _sk_store_565_avx _sk_store_565_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,46,37,0,0 ; vbroadcastss 0x252e(%rip),%ymm8 # 60fc <_sk_callback_avx+0x3c0> + DB 196,98,125,24,5,22,43,0,0 ; vbroadcastss 0x2b16(%rip),%ymm8 # 66e4 <_sk_callback_avx+0x3be> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,41,114,241,11 ; vpslld $0xb,%xmm9,%xmm10 DB 196,67,125,25,201,1 ; vextractf128 $0x1,%ymm9,%xmm9 DB 196,193,49,114,241,11 ; vpslld $0xb,%xmm9,%xmm9 DB 196,67,45,24,201,1 ; vinsertf128 $0x1,%xmm9,%ymm10,%ymm9 - DB 196,98,125,24,21,7,37,0,0 ; vbroadcastss 0x2507(%rip),%ymm10 # 6100 <_sk_callback_avx+0x3c4> + DB 196,98,125,24,21,239,42,0,0 ; vbroadcastss 0x2aef(%rip),%ymm10 # 66e8 <_sk_callback_avx+0x3c2> DB 196,65,116,89,210 ; vmulps %ymm10,%ymm1,%ymm10 DB 196,65,125,91,210 ; vcvtps2dq %ymm10,%ymm10 DB 196,193,33,114,242,5 ; vpslld $0x5,%xmm10,%xmm11 @@ -8474,25 +8565,25 @@ _sk_load_4444_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - DB 196,226,125,24,5,16,36,0,0 ; vbroadcastss 0x2410(%rip),%ymm0 # 6104 <_sk_callback_avx+0x3c8> + DB 196,226,125,24,5,248,41,0,0 ; vbroadcastss 0x29f8(%rip),%ymm0 # 66ec <_sk_callback_avx+0x3c6> DB 197,228,84,192 ; vandps %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,3,36,0,0 ; vbroadcastss 0x2403(%rip),%ymm1 # 6108 <_sk_callback_avx+0x3cc> + DB 196,226,125,24,13,235,41,0,0 ; vbroadcastss 0x29eb(%rip),%ymm1 # 66f0 <_sk_callback_avx+0x3ca> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,250,35,0,0 ; vbroadcastss 0x23fa(%rip),%ymm1 # 610c <_sk_callback_avx+0x3d0> + DB 196,226,125,24,13,226,41,0,0 ; vbroadcastss 0x29e2(%rip),%ymm1 # 66f4 <_sk_callback_avx+0x3ce> DB 197,228,84,201 ; vandps %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,237,35,0,0 ; vbroadcastss 0x23ed(%rip),%ymm2 # 6110 <_sk_callback_avx+0x3d4> + DB 196,226,125,24,21,213,41,0,0 ; vbroadcastss 0x29d5(%rip),%ymm2 # 66f8 <_sk_callback_avx+0x3d2> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,24,21,228,35,0,0 ; vbroadcastss 0x23e4(%rip),%ymm2 # 6114 <_sk_callback_avx+0x3d8> + DB 196,226,125,24,21,204,41,0,0 ; vbroadcastss 0x29cc(%rip),%ymm2 # 66fc <_sk_callback_avx+0x3d6> DB 197,228,84,210 ; vandps %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,215,35,0,0 ; vbroadcastss 0x23d7(%rip),%ymm8 # 6118 <_sk_callback_avx+0x3dc> + DB 196,98,125,24,5,191,41,0,0 ; vbroadcastss 0x29bf(%rip),%ymm8 # 6700 <_sk_callback_avx+0x3da> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,205,35,0,0 ; vbroadcastss 0x23cd(%rip),%ymm8 # 611c <_sk_callback_avx+0x3e0> + DB 196,98,125,24,5,181,41,0,0 ; vbroadcastss 0x29b5(%rip),%ymm8 # 6704 <_sk_callback_avx+0x3de> DB 196,193,100,84,216 ; vandps %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,191,35,0,0 ; vbroadcastss 0x23bf(%rip),%ymm8 # 6120 <_sk_callback_avx+0x3e4> + DB 196,98,125,24,5,167,41,0,0 ; vbroadcastss 0x29a7(%rip),%ymm8 # 6708 <_sk_callback_avx+0x3e2> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -8592,25 +8683,25 @@ _sk_gather_4444_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - DB 196,226,125,24,5,86,34,0,0 ; vbroadcastss 0x2256(%rip),%ymm0 # 6124 <_sk_callback_avx+0x3e8> + DB 196,226,125,24,5,62,40,0,0 ; vbroadcastss 0x283e(%rip),%ymm0 # 670c <_sk_callback_avx+0x3e6> DB 197,228,84,192 ; vandps %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,73,34,0,0 ; vbroadcastss 0x2249(%rip),%ymm1 # 6128 <_sk_callback_avx+0x3ec> + DB 196,226,125,24,13,49,40,0,0 ; vbroadcastss 0x2831(%rip),%ymm1 # 6710 <_sk_callback_avx+0x3ea> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,64,34,0,0 ; vbroadcastss 0x2240(%rip),%ymm1 # 612c <_sk_callback_avx+0x3f0> + DB 196,226,125,24,13,40,40,0,0 ; vbroadcastss 0x2828(%rip),%ymm1 # 6714 <_sk_callback_avx+0x3ee> DB 197,228,84,201 ; vandps %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,51,34,0,0 ; vbroadcastss 0x2233(%rip),%ymm2 # 6130 <_sk_callback_avx+0x3f4> + DB 196,226,125,24,21,27,40,0,0 ; vbroadcastss 0x281b(%rip),%ymm2 # 6718 <_sk_callback_avx+0x3f2> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,24,21,42,34,0,0 ; vbroadcastss 0x222a(%rip),%ymm2 # 6134 <_sk_callback_avx+0x3f8> + DB 196,226,125,24,21,18,40,0,0 ; vbroadcastss 0x2812(%rip),%ymm2 # 671c <_sk_callback_avx+0x3f6> DB 197,228,84,210 ; vandps %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,29,34,0,0 ; vbroadcastss 0x221d(%rip),%ymm8 # 6138 <_sk_callback_avx+0x3fc> + DB 196,98,125,24,5,5,40,0,0 ; vbroadcastss 0x2805(%rip),%ymm8 # 6720 <_sk_callback_avx+0x3fa> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,19,34,0,0 ; vbroadcastss 0x2213(%rip),%ymm8 # 613c <_sk_callback_avx+0x400> + DB 196,98,125,24,5,251,39,0,0 ; vbroadcastss 0x27fb(%rip),%ymm8 # 6724 <_sk_callback_avx+0x3fe> DB 196,193,100,84,216 ; vandps %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,5,34,0,0 ; vbroadcastss 0x2205(%rip),%ymm8 # 6140 <_sk_callback_avx+0x404> + DB 196,98,125,24,5,237,39,0,0 ; vbroadcastss 0x27ed(%rip),%ymm8 # 6728 <_sk_callback_avx+0x402> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -8624,7 +8715,7 @@ PUBLIC _sk_store_4444_avx _sk_store_4444_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,234,33,0,0 ; vbroadcastss 0x21ea(%rip),%ymm8 # 6144 <_sk_callback_avx+0x408> + DB 196,98,125,24,5,210,39,0,0 ; vbroadcastss 0x27d2(%rip),%ymm8 # 672c <_sk_callback_avx+0x406> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,41,114,241,12 ; vpslld $0xc,%xmm9,%xmm10 @@ -8703,10 +8794,10 @@ _sk_load_8888_avx LABEL PROC DB 72,133,201 ; test %rcx,%rcx DB 15,133,135,0,0,0 ; jne 4101 <_sk_load_8888_avx+0x95> DB 196,65,124,16,12,186 ; vmovups (%r10,%rdi,4),%ymm9 - DB 197,124,40,21,24,34,0,0 ; vmovaps 0x2218(%rip),%ymm10 # 62a0 <_sk_callback_avx+0x564> + DB 197,124,40,21,24,40,0,0 ; vmovaps 0x2818(%rip),%ymm10 # 68a0 <_sk_callback_avx+0x57a> DB 196,193,52,84,194 ; vandps %ymm10,%ymm9,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,174,32,0,0 ; vbroadcastss 0x20ae(%rip),%ymm8 # 6148 <_sk_callback_avx+0x40c> + DB 196,98,125,24,5,150,38,0,0 ; vbroadcastss 0x2696(%rip),%ymm8 # 6730 <_sk_callback_avx+0x40a> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 196,193,113,114,209,8 ; vpsrld $0x8,%xmm9,%xmm1 DB 196,99,125,25,203,1 ; vextractf128 $0x1,%ymm9,%xmm3 @@ -8819,10 +8910,10 @@ _sk_gather_8888_avx LABEL PROC DB 196,131,121,34,4,152,2 ; vpinsrd $0x2,(%r8,%r11,4),%xmm0,%xmm0 DB 196,131,121,34,28,144,3 ; vpinsrd $0x3,(%r8,%r10,4),%xmm0,%xmm3 DB 196,227,61,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - DB 197,124,40,21,66,32,0,0 ; vmovaps 0x2042(%rip),%ymm10 # 62c0 <_sk_callback_avx+0x584> + DB 197,124,40,21,66,38,0,0 ; vmovaps 0x2642(%rip),%ymm10 # 68c0 <_sk_callback_avx+0x59a> DB 196,193,124,84,194 ; vandps %ymm10,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,188,30,0,0 ; vbroadcastss 0x1ebc(%rip),%ymm9 # 614c <_sk_callback_avx+0x410> + DB 196,98,125,24,13,164,36,0,0 ; vbroadcastss 0x24a4(%rip),%ymm9 # 6734 <_sk_callback_avx+0x40e> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,113,114,208,8 ; vpsrld $0x8,%xmm8,%xmm1 DB 197,233,114,211,8 ; vpsrld $0x8,%xmm3,%xmm2 @@ -8852,7 +8943,7 @@ PUBLIC _sk_store_8888_avx _sk_store_8888_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,74,30,0,0 ; vbroadcastss 0x1e4a(%rip),%ymm8 # 6150 <_sk_callback_avx+0x414> + DB 196,98,125,24,5,50,36,0,0 ; vbroadcastss 0x2432(%rip),%ymm8 # 6738 <_sk_callback_avx+0x412> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,65,116,89,208 ; vmulps %ymm8,%ymm1,%ymm10 @@ -8955,13 +9046,13 @@ _sk_load_f16_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 - DB 196,98,125,24,37,175,28,0,0 ; vbroadcastss 0x1caf(%rip),%ymm12 # 6154 <_sk_callback_avx+0x418> + DB 196,98,125,24,37,151,34,0,0 ; vbroadcastss 0x2297(%rip),%ymm12 # 673c <_sk_callback_avx+0x416> DB 196,193,124,84,204 ; vandps %ymm12,%ymm0,%ymm1 DB 197,252,87,193 ; vxorps %ymm1,%ymm0,%ymm0 DB 196,195,125,25,198,1 ; vextractf128 $0x1,%ymm0,%xmm14 - DB 196,98,121,24,29,155,28,0,0 ; vbroadcastss 0x1c9b(%rip),%xmm11 # 6158 <_sk_callback_avx+0x41c> + DB 196,98,121,24,29,131,34,0,0 ; vbroadcastss 0x2283(%rip),%xmm11 # 6740 <_sk_callback_avx+0x41a> DB 196,193,8,87,219 ; vxorps %xmm11,%xmm14,%xmm3 - DB 196,98,121,24,45,145,28,0,0 ; vbroadcastss 0x1c91(%rip),%xmm13 # 615c <_sk_callback_avx+0x420> + DB 196,98,121,24,45,121,34,0,0 ; vbroadcastss 0x2279(%rip),%xmm13 # 6744 <_sk_callback_avx+0x41e> DB 197,145,102,219 ; vpcmpgtd %xmm3,%xmm13,%xmm3 DB 196,65,120,87,211 ; vxorps %xmm11,%xmm0,%xmm10 DB 196,65,17,102,210 ; vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -8975,7 +9066,7 @@ _sk_load_f16_avx LABEL PROC DB 196,227,125,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 DB 197,252,86,193 ; vorps %ymm1,%ymm0,%ymm0 DB 196,227,125,25,193,1 ; vextractf128 $0x1,%ymm0,%xmm1 - DB 196,226,121,24,29,71,28,0,0 ; vbroadcastss 0x1c47(%rip),%xmm3 # 6160 <_sk_callback_avx+0x424> + DB 196,226,121,24,29,47,34,0,0 ; vbroadcastss 0x222f(%rip),%xmm3 # 6748 <_sk_callback_avx+0x422> DB 197,241,254,203 ; vpaddd %xmm3,%xmm1,%xmm1 DB 197,249,254,195 ; vpaddd %xmm3,%xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 @@ -9152,13 +9243,13 @@ _sk_gather_f16_avx LABEL PROC DB 197,249,105,210 ; vpunpckhwd %xmm2,%xmm0,%xmm2 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,194,1 ; vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 - DB 196,98,125,24,37,7,25,0,0 ; vbroadcastss 0x1907(%rip),%ymm12 # 6164 <_sk_callback_avx+0x428> + DB 196,98,125,24,37,239,30,0,0 ; vbroadcastss 0x1eef(%rip),%ymm12 # 674c <_sk_callback_avx+0x426> DB 196,193,124,84,212 ; vandps %ymm12,%ymm0,%ymm2 DB 197,252,87,194 ; vxorps %ymm2,%ymm0,%ymm0 DB 196,195,125,25,198,1 ; vextractf128 $0x1,%ymm0,%xmm14 - DB 196,98,121,24,29,243,24,0,0 ; vbroadcastss 0x18f3(%rip),%xmm11 # 6168 <_sk_callback_avx+0x42c> + DB 196,98,121,24,29,219,30,0,0 ; vbroadcastss 0x1edb(%rip),%xmm11 # 6750 <_sk_callback_avx+0x42a> DB 196,193,8,87,219 ; vxorps %xmm11,%xmm14,%xmm3 - DB 196,98,121,24,45,233,24,0,0 ; vbroadcastss 0x18e9(%rip),%xmm13 # 616c <_sk_callback_avx+0x430> + DB 196,98,121,24,45,209,30,0,0 ; vbroadcastss 0x1ed1(%rip),%xmm13 # 6754 <_sk_callback_avx+0x42e> DB 197,145,102,219 ; vpcmpgtd %xmm3,%xmm13,%xmm3 DB 196,65,120,87,211 ; vxorps %xmm11,%xmm0,%xmm10 DB 196,65,17,102,210 ; vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -9172,7 +9263,7 @@ _sk_gather_f16_avx LABEL PROC DB 196,227,125,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 DB 197,252,86,194 ; vorps %ymm2,%ymm0,%ymm0 DB 196,227,125,25,194,1 ; vextractf128 $0x1,%ymm0,%xmm2 - DB 196,226,121,24,29,159,24,0,0 ; vbroadcastss 0x189f(%rip),%xmm3 # 6170 <_sk_callback_avx+0x434> + DB 196,226,121,24,29,135,30,0,0 ; vbroadcastss 0x1e87(%rip),%xmm3 # 6758 <_sk_callback_avx+0x432> DB 197,233,254,211 ; vpaddd %xmm3,%xmm2,%xmm2 DB 197,249,254,195 ; vpaddd %xmm3,%xmm0,%xmm0 DB 196,227,125,24,194,1 ; vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 @@ -9274,12 +9365,12 @@ _sk_store_f16_avx LABEL PROC DB 197,252,17,180,36,128,0,0,0 ; vmovups %ymm6,0x80(%rsp) DB 197,252,17,108,36,96 ; vmovups %ymm5,0x60(%rsp) DB 197,252,17,100,36,64 ; vmovups %ymm4,0x40(%rsp) - DB 196,98,125,24,13,172,22,0,0 ; vbroadcastss 0x16ac(%rip),%ymm9 # 6174 <_sk_callback_avx+0x438> + DB 196,98,125,24,13,148,28,0,0 ; vbroadcastss 0x1c94(%rip),%ymm9 # 675c <_sk_callback_avx+0x436> DB 196,65,124,84,209 ; vandps %ymm9,%ymm0,%ymm10 DB 197,252,17,4,36 ; vmovups %ymm0,(%rsp) DB 196,65,124,87,218 ; vxorps %ymm10,%ymm0,%ymm11 DB 196,67,125,25,220,1 ; vextractf128 $0x1,%ymm11,%xmm12 - DB 196,98,121,24,5,146,22,0,0 ; vbroadcastss 0x1692(%rip),%xmm8 # 6178 <_sk_callback_avx+0x43c> + DB 196,98,121,24,5,122,28,0,0 ; vbroadcastss 0x1c7a(%rip),%xmm8 # 6760 <_sk_callback_avx+0x43a> DB 196,65,57,102,236 ; vpcmpgtd %xmm12,%xmm8,%xmm13 DB 196,65,57,102,243 ; vpcmpgtd %xmm11,%xmm8,%xmm14 DB 196,67,13,24,237,1 ; vinsertf128 $0x1,%xmm13,%ymm14,%ymm13 @@ -9289,7 +9380,7 @@ _sk_store_f16_avx LABEL PROC DB 196,67,13,24,242,1 ; vinsertf128 $0x1,%xmm10,%ymm14,%ymm14 DB 196,193,33,114,211,13 ; vpsrld $0xd,%xmm11,%xmm11 DB 196,193,25,114,212,13 ; vpsrld $0xd,%xmm12,%xmm12 - DB 196,98,125,24,21,89,22,0,0 ; vbroadcastss 0x1659(%rip),%ymm10 # 617c <_sk_callback_avx+0x440> + DB 196,98,125,24,21,65,28,0,0 ; vbroadcastss 0x1c41(%rip),%ymm10 # 6764 <_sk_callback_avx+0x43e> DB 196,65,12,86,242 ; vorps %ymm10,%ymm14,%ymm14 DB 196,67,125,25,247,1 ; vextractf128 $0x1,%ymm14,%xmm15 DB 196,65,1,254,228 ; vpaddd %xmm12,%xmm15,%xmm12 @@ -9432,7 +9523,7 @@ _sk_load_u16_be_avx LABEL PROC DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,29,168,19,0,0 ; vbroadcastss 0x13a8(%rip),%ymm11 # 6180 <_sk_callback_avx+0x444> + DB 196,98,125,24,29,144,25,0,0 ; vbroadcastss 0x1990(%rip),%ymm11 # 6768 <_sk_callback_avx+0x442> DB 196,193,124,89,195 ; vmulps %ymm11,%ymm0,%ymm0 DB 197,177,109,202 ; vpunpckhqdq %xmm2,%xmm9,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -9523,7 +9614,7 @@ _sk_load_rgb_u16_be_avx LABEL PROC DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,29,8,18,0,0 ; vbroadcastss 0x1208(%rip),%ymm11 # 6184 <_sk_callback_avx+0x448> + DB 196,98,125,24,29,240,23,0,0 ; vbroadcastss 0x17f0(%rip),%ymm11 # 676c <_sk_callback_avx+0x446> DB 196,193,124,89,195 ; vmulps %ymm11,%ymm0,%ymm0 DB 197,185,109,202 ; vpunpckhqdq %xmm2,%xmm8,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -9544,7 +9635,7 @@ _sk_load_rgb_u16_be_avx LABEL PROC DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,211 ; vmulps %ymm11,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,165,17,0,0 ; vbroadcastss 0x11a5(%rip),%ymm3 # 6188 <_sk_callback_avx+0x44c> + DB 196,226,125,24,29,141,23,0,0 ; vbroadcastss 0x178d(%rip),%ymm3 # 6770 <_sk_callback_avx+0x44a> DB 255,224 ; jmpq *%rax DB 196,193,121,110,4,64 ; vmovd (%r8,%rax,2),%xmm0 DB 196,193,121,196,68,64,4,2 ; vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 @@ -9585,7 +9676,7 @@ _sk_store_u16_be_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,189,0,0,0,0 ; lea 0x0(,%rdi,4),%rax - DB 196,98,125,24,5,226,16,0,0 ; vbroadcastss 0x10e2(%rip),%ymm8 # 618c <_sk_callback_avx+0x450> + DB 196,98,125,24,5,202,22,0,0 ; vbroadcastss 0x16ca(%rip),%ymm8 # 6774 <_sk_callback_avx+0x44e> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,67,125,25,202,1 ; vextractf128 $0x1,%ymm9,%xmm10 @@ -9833,12 +9924,12 @@ _sk_mirror_y_avx LABEL PROC PUBLIC _sk_luminance_to_alpha_avx _sk_luminance_to_alpha_avx LABEL PROC - DB 196,226,125,24,29,7,13,0,0 ; vbroadcastss 0xd07(%rip),%ymm3 # 6190 <_sk_callback_avx+0x454> + DB 196,226,125,24,29,239,18,0,0 ; vbroadcastss 0x12ef(%rip),%ymm3 # 6778 <_sk_callback_avx+0x452> DB 197,252,89,195 ; vmulps %ymm3,%ymm0,%ymm0 - DB 196,226,125,24,29,254,12,0,0 ; vbroadcastss 0xcfe(%rip),%ymm3 # 6194 <_sk_callback_avx+0x458> + DB 196,226,125,24,29,230,18,0,0 ; vbroadcastss 0x12e6(%rip),%ymm3 # 677c <_sk_callback_avx+0x456> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 DB 197,252,88,193 ; vaddps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,241,12,0,0 ; vbroadcastss 0xcf1(%rip),%ymm1 # 6198 <_sk_callback_avx+0x45c> + DB 196,226,125,24,13,217,18,0,0 ; vbroadcastss 0x12d9(%rip),%ymm1 # 6780 <_sk_callback_avx+0x45a> DB 197,236,89,201 ; vmulps %ymm1,%ymm2,%ymm1 DB 197,252,88,217 ; vaddps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -9997,58 +10088,344 @@ _sk_matrix_perspective_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax +PUBLIC _sk_evenly_spaced_gradient_avx +_sk_evenly_spaced_gradient_avx LABEL PROC + DB 85 ; push %rbp + DB 65,87 ; push %r15 + DB 65,86 ; push %r14 + DB 65,85 ; push %r13 + DB 65,84 ; push %r12 + DB 83 ; push %rbx + DB 72,173 ; lods %ds:(%rsi),%rax + DB 72,139,24 ; mov (%rax),%rbx + DB 72,139,104,8 ; mov 0x8(%rax),%rbp + DB 72,255,203 ; dec %rbx + DB 120,7 ; js 5764 <_sk_evenly_spaced_gradient_avx+0x1f> + DB 196,225,242,42,203 ; vcvtsi2ss %rbx,%xmm1,%xmm1 + DB 235,21 ; jmp 5779 <_sk_evenly_spaced_gradient_avx+0x34> + DB 73,137,216 ; mov %rbx,%r8 + DB 73,209,232 ; shr %r8 + DB 131,227,1 ; and $0x1,%ebx + DB 76,9,195 ; or %r8,%rbx + DB 196,225,242,42,203 ; vcvtsi2ss %rbx,%xmm1,%xmm1 + DB 197,242,88,201 ; vaddss %xmm1,%xmm1,%xmm1 + DB 196,227,121,4,201,0 ; vpermilps $0x0,%xmm1,%xmm1 + DB 196,227,117,24,201,1 ; vinsertf128 $0x1,%xmm1,%ymm1,%ymm1 + DB 197,244,89,200 ; vmulps %ymm0,%ymm1,%ymm1 + DB 197,254,91,201 ; vcvttps2dq %ymm1,%ymm1 + DB 196,195,249,22,200,1 ; vpextrq $0x1,%xmm1,%r8 + DB 69,137,193 ; mov %r8d,%r9d + DB 73,193,232,32 ; shr $0x20,%r8 + DB 196,193,249,126,202 ; vmovq %xmm1,%r10 + DB 69,137,211 ; mov %r10d,%r11d + DB 73,193,234,32 ; shr $0x20,%r10 + DB 196,227,125,25,201,1 ; vextractf128 $0x1,%ymm1,%xmm1 + DB 196,195,249,22,207,1 ; vpextrq $0x1,%xmm1,%r15 + DB 69,137,254 ; mov %r15d,%r14d + DB 73,193,239,32 ; shr $0x20,%r15 + DB 196,193,249,126,205 ; vmovq %xmm1,%r13 + DB 69,137,236 ; mov %r13d,%r12d + DB 73,193,237,32 ; shr $0x20,%r13 + DB 196,161,122,16,76,165,0 ; vmovss 0x0(%rbp,%r12,4),%xmm1 + DB 196,163,113,33,76,173,0,16 ; vinsertps $0x10,0x0(%rbp,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,84,181,0 ; vmovss 0x0(%rbp,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,84,189,0 ; vmovss 0x0(%rbp,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,84,157,0 ; vmovss 0x0(%rbp,%r11,4),%xmm2 + DB 196,163,105,33,84,149,0,16 ; vinsertps $0x10,0x0(%rbp,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,92,141,0 ; vmovss 0x0(%rbp,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,92,133,0 ; vmovss 0x0(%rbp,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm8 + DB 72,139,88,40 ; mov 0x28(%rax),%rbx + DB 196,161,122,16,20,163 ; vmovss (%rbx,%r12,4),%xmm2 + DB 196,163,105,33,20,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm2,%xmm2 + DB 196,161,122,16,28,179 ; vmovss (%rbx,%r14,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,187 ; vmovss (%rbx,%r15,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,155 ; vmovss (%rbx,%r11,4),%xmm3 + DB 196,163,97,33,28,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm3,%xmm3 + DB 196,161,122,16,12,139 ; vmovss (%rbx,%r9,4),%xmm1 + DB 196,227,97,33,201,32 ; vinsertps $0x20,%xmm1,%xmm3,%xmm1 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,113,33,203,48 ; vinsertps $0x30,%xmm3,%xmm1,%xmm1 + DB 196,99,117,24,226,1 ; vinsertf128 $0x1,%xmm2,%ymm1,%ymm12 + DB 72,139,88,16 ; mov 0x10(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,28,179 ; vmovss (%rbx,%r14,4),%xmm3 + DB 196,227,113,33,203,32 ; vinsertps $0x20,%xmm3,%xmm1,%xmm1 + DB 196,161,122,16,28,187 ; vmovss (%rbx,%r15,4),%xmm3 + DB 196,227,113,33,203,48 ; vinsertps $0x30,%xmm3,%xmm1,%xmm1 + DB 196,161,122,16,28,155 ; vmovss (%rbx,%r11,4),%xmm3 + DB 196,163,97,33,28,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm3,%xmm3 + DB 196,161,122,16,20,139 ; vmovss (%rbx,%r9,4),%xmm2 + DB 196,227,97,33,210,32 ; vinsertps $0x20,%xmm2,%xmm3,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,233,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm13 + DB 72,139,88,48 ; mov 0x30(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,201,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm9 + DB 72,139,88,24 ; mov 0x18(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,209,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm10 + DB 72,139,88,56 ; mov 0x38(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm11 + DB 72,139,88,32 ; mov 0x20(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,241,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm14 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 196,161,122,16,12,160 ; vmovss (%rax,%r12,4),%xmm1 + DB 196,163,113,33,12,168,16 ; vinsertps $0x10,(%rax,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,176 ; vmovss (%rax,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,184 ; vmovss (%rax,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,152 ; vmovss (%rax,%r11,4),%xmm2 + DB 196,163,105,33,20,144,16 ; vinsertps $0x10,(%rax,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,136 ; vmovss (%rax,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,128 ; vmovss (%rax,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,227,109,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm3 + DB 197,188,89,200 ; vmulps %ymm0,%ymm8,%ymm1 + DB 196,65,116,88,196 ; vaddps %ymm12,%ymm1,%ymm8 + DB 197,148,89,200 ; vmulps %ymm0,%ymm13,%ymm1 + DB 196,193,116,88,201 ; vaddps %ymm9,%ymm1,%ymm1 + DB 197,172,89,208 ; vmulps %ymm0,%ymm10,%ymm2 + DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 + DB 197,140,89,192 ; vmulps %ymm0,%ymm14,%ymm0 + DB 197,252,88,219 ; vaddps %ymm3,%ymm0,%ymm3 + DB 72,173 ; lods %ds:(%rsi),%rax + DB 197,124,41,192 ; vmovaps %ymm8,%ymm0 + DB 91 ; pop %rbx + DB 65,92 ; pop %r12 + DB 65,93 ; pop %r13 + DB 65,94 ; pop %r14 + DB 65,95 ; pop %r15 + DB 93 ; pop %rbp + DB 255,224 ; jmpq *%rax + PUBLIC _sk_gradient_avx _sk_gradient_avx LABEL PROC + DB 85 ; push %rbp + DB 65,87 ; push %r15 + DB 65,86 ; push %r14 + DB 65,85 ; push %r13 + DB 65,84 ; push %r12 + DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,64,16 ; vbroadcastss 0x10(%rax),%ymm8 - DB 196,226,125,24,72,20 ; vbroadcastss 0x14(%rax),%ymm1 - DB 196,226,125,24,80,24 ; vbroadcastss 0x18(%rax),%ymm2 - DB 196,226,125,24,88,28 ; vbroadcastss 0x1c(%rax),%ymm3 DB 76,139,0 ; mov (%rax),%r8 - DB 77,133,192 ; test %r8,%r8 - DB 15,132,146,0,0,0 ; je 57fd <_sk_gradient_avx+0xb8> - DB 72,139,64,8 ; mov 0x8(%rax),%rax - DB 72,131,192,32 ; add $0x20,%rax - DB 196,65,28,87,228 ; vxorps %ymm12,%ymm12,%ymm12 - DB 196,65,52,87,201 ; vxorps %ymm9,%ymm9,%ymm9 - DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 - DB 196,65,36,87,219 ; vxorps %ymm11,%ymm11,%ymm11 - DB 196,98,125,24,104,224 ; vbroadcastss -0x20(%rax),%ymm13 - DB 196,65,124,194,237,1 ; vcmpltps %ymm13,%ymm0,%ymm13 - DB 196,98,125,24,112,228 ; vbroadcastss -0x1c(%rax),%ymm14 - DB 196,67,13,74,228,208 ; vblendvps %ymm13,%ymm12,%ymm14,%ymm12 - DB 196,98,125,24,112,232 ; vbroadcastss -0x18(%rax),%ymm14 - DB 196,67,13,74,219,208 ; vblendvps %ymm13,%ymm11,%ymm14,%ymm11 - DB 196,98,125,24,112,236 ; vbroadcastss -0x14(%rax),%ymm14 - DB 196,67,13,74,210,208 ; vblendvps %ymm13,%ymm10,%ymm14,%ymm10 - DB 196,98,125,24,112,240 ; vbroadcastss -0x10(%rax),%ymm14 - DB 196,67,13,74,201,208 ; vblendvps %ymm13,%ymm9,%ymm14,%ymm9 - DB 196,98,125,24,112,244 ; vbroadcastss -0xc(%rax),%ymm14 - DB 196,67,13,74,192,208 ; vblendvps %ymm13,%ymm8,%ymm14,%ymm8 - DB 196,98,125,24,112,248 ; vbroadcastss -0x8(%rax),%ymm14 - DB 196,227,13,74,201,208 ; vblendvps %ymm13,%ymm1,%ymm14,%ymm1 - DB 196,98,125,24,112,252 ; vbroadcastss -0x4(%rax),%ymm14 - DB 196,227,13,74,210,208 ; vblendvps %ymm13,%ymm2,%ymm14,%ymm2 - DB 196,98,125,24,48 ; vbroadcastss (%rax),%ymm14 - DB 196,227,13,74,219,208 ; vblendvps %ymm13,%ymm3,%ymm14,%ymm3 - DB 72,131,192,36 ; add $0x24,%rax + DB 197,244,87,201 ; vxorps %ymm1,%ymm1,%ymm1 + DB 73,131,248,2 ; cmp $0x2,%r8 + DB 114,80 ; jb 5b07 <_sk_gradient_avx+0x69> + DB 72,139,88,72 ; mov 0x48(%rax),%rbx DB 73,255,200 ; dec %r8 - DB 117,140 ; jne 5787 <_sk_gradient_avx+0x42> - DB 235,20 ; jmp 5811 <_sk_gradient_avx+0xcc> - DB 196,65,36,87,219 ; vxorps %ymm11,%ymm11,%ymm11 - DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 + DB 72,131,195,4 ; add $0x4,%rbx DB 196,65,52,87,201 ; vxorps %ymm9,%ymm9,%ymm9 - DB 196,65,28,87,228 ; vxorps %ymm12,%ymm12,%ymm12 - DB 197,28,89,224 ; vmulps %ymm0,%ymm12,%ymm12 - DB 196,65,60,88,196 ; vaddps %ymm12,%ymm8,%ymm8 - DB 197,36,89,216 ; vmulps %ymm0,%ymm11,%ymm11 - DB 197,164,88,201 ; vaddps %ymm1,%ymm11,%ymm1 - DB 197,44,89,208 ; vmulps %ymm0,%ymm10,%ymm10 - DB 197,172,88,210 ; vaddps %ymm2,%ymm10,%ymm2 - DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 + DB 196,98,125,24,21,180,12,0,0 ; vbroadcastss 0xcb4(%rip),%ymm10 # 6784 <_sk_callback_avx+0x45e> + DB 197,244,87,201 ; vxorps %ymm1,%ymm1,%ymm1 + DB 196,98,125,24,3 ; vbroadcastss (%rbx),%ymm8 + DB 197,60,194,192,2 ; vcmpleps %ymm0,%ymm8,%ymm8 + DB 196,67,53,74,194,128 ; vblendvps %ymm8,%ymm10,%ymm9,%ymm8 + DB 196,99,125,25,194,1 ; vextractf128 $0x1,%ymm8,%xmm2 + DB 196,227,125,25,203,1 ; vextractf128 $0x1,%ymm1,%xmm3 + DB 197,233,254,211 ; vpaddd %xmm3,%xmm2,%xmm2 + DB 197,185,254,201 ; vpaddd %xmm1,%xmm8,%xmm1 + DB 196,227,117,24,202,1 ; vinsertf128 $0x1,%xmm2,%ymm1,%ymm1 + DB 72,131,195,4 ; add $0x4,%rbx + DB 73,255,200 ; dec %r8 + DB 117,205 ; jne 5ad4 <_sk_gradient_avx+0x36> + DB 196,195,249,22,200,1 ; vpextrq $0x1,%xmm1,%r8 + DB 69,137,193 ; mov %r8d,%r9d + DB 73,193,232,32 ; shr $0x20,%r8 + DB 196,193,249,126,202 ; vmovq %xmm1,%r10 + DB 69,137,211 ; mov %r10d,%r11d + DB 73,193,234,32 ; shr $0x20,%r10 + DB 196,227,125,25,201,1 ; vextractf128 $0x1,%ymm1,%xmm1 + DB 196,195,249,22,207,1 ; vpextrq $0x1,%xmm1,%r15 + DB 69,137,254 ; mov %r15d,%r14d + DB 73,193,239,32 ; shr $0x20,%r15 + DB 196,193,249,126,205 ; vmovq %xmm1,%r13 + DB 69,137,236 ; mov %r13d,%r12d + DB 73,193,237,32 ; shr $0x20,%r13 + DB 72,139,104,8 ; mov 0x8(%rax),%rbp + DB 72,139,88,16 ; mov 0x10(%rax),%rbx + DB 196,161,122,16,76,165,0 ; vmovss 0x0(%rbp,%r12,4),%xmm1 + DB 196,163,113,33,76,173,0,16 ; vinsertps $0x10,0x0(%rbp,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,84,181,0 ; vmovss 0x0(%rbp,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,84,189,0 ; vmovss 0x0(%rbp,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,84,157,0 ; vmovss 0x0(%rbp,%r11,4),%xmm2 + DB 196,163,105,33,84,149,0,16 ; vinsertps $0x10,0x0(%rbp,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,92,141,0 ; vmovss 0x0(%rbp,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,92,133,0 ; vmovss 0x0(%rbp,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm8 + DB 72,139,104,40 ; mov 0x28(%rax),%rbp + DB 196,161,122,16,84,165,0 ; vmovss 0x0(%rbp,%r12,4),%xmm2 + DB 196,163,105,33,84,173,0,16 ; vinsertps $0x10,0x0(%rbp,%r13,4),%xmm2,%xmm2 + DB 196,161,122,16,92,181,0 ; vmovss 0x0(%rbp,%r14,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,92,189,0 ; vmovss 0x0(%rbp,%r15,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,92,157,0 ; vmovss 0x0(%rbp,%r11,4),%xmm3 + DB 196,163,97,33,92,149,0,16 ; vinsertps $0x10,0x0(%rbp,%r10,4),%xmm3,%xmm3 + DB 196,161,122,16,76,141,0 ; vmovss 0x0(%rbp,%r9,4),%xmm1 + DB 196,227,97,33,201,32 ; vinsertps $0x20,%xmm1,%xmm3,%xmm1 + DB 196,161,122,16,92,133,0 ; vmovss 0x0(%rbp,%r8,4),%xmm3 + DB 196,227,113,33,203,48 ; vinsertps $0x30,%xmm3,%xmm1,%xmm1 + DB 196,99,117,24,226,1 ; vinsertf128 $0x1,%xmm2,%ymm1,%ymm12 + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,28,179 ; vmovss (%rbx,%r14,4),%xmm3 + DB 196,227,113,33,203,32 ; vinsertps $0x20,%xmm3,%xmm1,%xmm1 + DB 196,161,122,16,28,187 ; vmovss (%rbx,%r15,4),%xmm3 + DB 196,227,113,33,203,48 ; vinsertps $0x30,%xmm3,%xmm1,%xmm1 + DB 196,161,122,16,28,155 ; vmovss (%rbx,%r11,4),%xmm3 + DB 196,163,97,33,28,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm3,%xmm3 + DB 196,161,122,16,20,139 ; vmovss (%rbx,%r9,4),%xmm2 + DB 196,227,97,33,210,32 ; vinsertps $0x20,%xmm2,%xmm3,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,233,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm13 + DB 72,139,88,48 ; mov 0x30(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,201,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm9 + DB 72,139,88,24 ; mov 0x18(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,209,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm10 + DB 72,139,88,56 ; mov 0x38(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm11 + DB 72,139,88,32 ; mov 0x20(%rax),%rbx + DB 196,161,122,16,12,163 ; vmovss (%rbx,%r12,4),%xmm1 + DB 196,163,113,33,12,171,16 ; vinsertps $0x10,(%rbx,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,179 ; vmovss (%rbx,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,187 ; vmovss (%rbx,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,155 ; vmovss (%rbx,%r11,4),%xmm2 + DB 196,163,105,33,20,147,16 ; vinsertps $0x10,(%rbx,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,139 ; vmovss (%rbx,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,131 ; vmovss (%rbx,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,99,109,24,241,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm14 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 196,161,122,16,12,160 ; vmovss (%rax,%r12,4),%xmm1 + DB 196,163,113,33,12,168,16 ; vinsertps $0x10,(%rax,%r13,4),%xmm1,%xmm1 + DB 196,161,122,16,20,176 ; vmovss (%rax,%r14,4),%xmm2 + DB 196,227,113,33,202,32 ; vinsertps $0x20,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,184 ; vmovss (%rax,%r15,4),%xmm2 + DB 196,227,113,33,202,48 ; vinsertps $0x30,%xmm2,%xmm1,%xmm1 + DB 196,161,122,16,20,152 ; vmovss (%rax,%r11,4),%xmm2 + DB 196,163,105,33,20,144,16 ; vinsertps $0x10,(%rax,%r10,4),%xmm2,%xmm2 + DB 196,161,122,16,28,136 ; vmovss (%rax,%r9,4),%xmm3 + DB 196,227,105,33,211,32 ; vinsertps $0x20,%xmm3,%xmm2,%xmm2 + DB 196,161,122,16,28,128 ; vmovss (%rax,%r8,4),%xmm3 + DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 + DB 196,227,109,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm2,%ymm3 + DB 197,188,89,200 ; vmulps %ymm0,%ymm8,%ymm1 + DB 196,65,116,88,196 ; vaddps %ymm12,%ymm1,%ymm8 + DB 197,148,89,200 ; vmulps %ymm0,%ymm13,%ymm1 + DB 196,193,116,88,201 ; vaddps %ymm9,%ymm1,%ymm1 + DB 197,172,89,208 ; vmulps %ymm0,%ymm10,%ymm2 + DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 + DB 197,140,89,192 ; vmulps %ymm0,%ymm14,%ymm0 DB 197,252,88,219 ; vaddps %ymm3,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,124,41,192 ; vmovaps %ymm8,%ymm0 + DB 91 ; pop %rbx + DB 65,92 ; pop %r12 + DB 65,93 ; pop %r13 + DB 65,94 ; pop %r14 + DB 65,95 ; pop %r15 + DB 93 ; pop %rbp DB 255,224 ; jmpq *%rax PUBLIC _sk_evenly_spaced_2_stop_gradient_avx @@ -10085,27 +10462,27 @@ _sk_xy_to_unit_angle_avx LABEL PROC DB 196,65,52,95,226 ; vmaxps %ymm10,%ymm9,%ymm12 DB 196,65,36,94,220 ; vdivps %ymm12,%ymm11,%ymm11 DB 196,65,36,89,227 ; vmulps %ymm11,%ymm11,%ymm12 - DB 196,98,125,24,45,214,8,0,0 ; vbroadcastss 0x8d6(%rip),%ymm13 # 619c <_sk_callback_avx+0x460> + DB 196,98,125,24,45,216,8,0,0 ; vbroadcastss 0x8d8(%rip),%ymm13 # 6788 <_sk_callback_avx+0x462> DB 196,65,28,89,237 ; vmulps %ymm13,%ymm12,%ymm13 - DB 196,98,125,24,53,204,8,0,0 ; vbroadcastss 0x8cc(%rip),%ymm14 # 61a0 <_sk_callback_avx+0x464> + DB 196,98,125,24,53,206,8,0,0 ; vbroadcastss 0x8ce(%rip),%ymm14 # 678c <_sk_callback_avx+0x466> DB 196,65,20,88,238 ; vaddps %ymm14,%ymm13,%ymm13 DB 196,65,28,89,237 ; vmulps %ymm13,%ymm12,%ymm13 - DB 196,98,125,24,53,189,8,0,0 ; vbroadcastss 0x8bd(%rip),%ymm14 # 61a4 <_sk_callback_avx+0x468> + DB 196,98,125,24,53,191,8,0,0 ; vbroadcastss 0x8bf(%rip),%ymm14 # 6790 <_sk_callback_avx+0x46a> DB 196,65,20,88,238 ; vaddps %ymm14,%ymm13,%ymm13 DB 196,65,28,89,229 ; vmulps %ymm13,%ymm12,%ymm12 - DB 196,98,125,24,45,174,8,0,0 ; vbroadcastss 0x8ae(%rip),%ymm13 # 61a8 <_sk_callback_avx+0x46c> + DB 196,98,125,24,45,176,8,0,0 ; vbroadcastss 0x8b0(%rip),%ymm13 # 6794 <_sk_callback_avx+0x46e> DB 196,65,28,88,229 ; vaddps %ymm13,%ymm12,%ymm12 DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 DB 196,65,52,194,202,1 ; vcmpltps %ymm10,%ymm9,%ymm9 - DB 196,98,125,24,21,153,8,0,0 ; vbroadcastss 0x899(%rip),%ymm10 # 61ac <_sk_callback_avx+0x470> + DB 196,98,125,24,21,155,8,0,0 ; vbroadcastss 0x89b(%rip),%ymm10 # 6798 <_sk_callback_avx+0x472> DB 196,65,44,92,211 ; vsubps %ymm11,%ymm10,%ymm10 DB 196,67,37,74,202,144 ; vblendvps %ymm9,%ymm10,%ymm11,%ymm9 DB 196,193,124,194,192,1 ; vcmpltps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,21,131,8,0,0 ; vbroadcastss 0x883(%rip),%ymm10 # 61b0 <_sk_callback_avx+0x474> + DB 196,98,125,24,21,133,8,0,0 ; vbroadcastss 0x885(%rip),%ymm10 # 679c <_sk_callback_avx+0x476> DB 196,65,44,92,209 ; vsubps %ymm9,%ymm10,%ymm10 DB 196,195,53,74,194,0 ; vblendvps %ymm0,%ymm10,%ymm9,%ymm0 DB 196,65,116,194,200,1 ; vcmpltps %ymm8,%ymm1,%ymm9 - DB 196,98,125,24,21,109,8,0,0 ; vbroadcastss 0x86d(%rip),%ymm10 # 61b4 <_sk_callback_avx+0x478> + DB 196,98,125,24,21,111,8,0,0 ; vbroadcastss 0x86f(%rip),%ymm10 # 67a0 <_sk_callback_avx+0x47a> DB 197,44,92,208 ; vsubps %ymm0,%ymm10,%ymm10 DB 196,195,125,74,194,144 ; vblendvps %ymm9,%ymm10,%ymm0,%ymm0 DB 196,65,124,194,200,3 ; vcmpunordps %ymm8,%ymm0,%ymm9 @@ -10126,7 +10503,7 @@ _sk_xy_to_radius_avx LABEL PROC PUBLIC _sk_save_xy_avx _sk_save_xy_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,51,8,0,0 ; vbroadcastss 0x833(%rip),%ymm8 # 61b8 <_sk_callback_avx+0x47c> + DB 196,98,125,24,5,53,8,0,0 ; vbroadcastss 0x835(%rip),%ymm8 # 67a4 <_sk_callback_avx+0x47e> DB 196,65,124,88,200 ; vaddps %ymm8,%ymm0,%ymm9 DB 196,67,125,8,209,1 ; vroundps $0x1,%ymm9,%ymm10 DB 196,65,52,92,202 ; vsubps %ymm10,%ymm9,%ymm9 @@ -10159,9 +10536,9 @@ _sk_accumulate_avx LABEL PROC PUBLIC _sk_bilinear_nx_avx _sk_bilinear_nx_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,191,7,0,0 ; vbroadcastss 0x7bf(%rip),%ymm0 # 61bc <_sk_callback_avx+0x480> + DB 196,226,125,24,5,193,7,0,0 ; vbroadcastss 0x7c1(%rip),%ymm0 # 67a8 <_sk_callback_avx+0x482> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,182,7,0,0 ; vbroadcastss 0x7b6(%rip),%ymm8 # 61c0 <_sk_callback_avx+0x484> + DB 196,98,125,24,5,184,7,0,0 ; vbroadcastss 0x7b8(%rip),%ymm8 # 67ac <_sk_callback_avx+0x486> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -10170,7 +10547,7 @@ _sk_bilinear_nx_avx LABEL PROC PUBLIC _sk_bilinear_px_avx _sk_bilinear_px_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,158,7,0,0 ; vbroadcastss 0x79e(%rip),%ymm0 # 61c4 <_sk_callback_avx+0x488> + DB 196,226,125,24,5,160,7,0,0 ; vbroadcastss 0x7a0(%rip),%ymm0 # 67b0 <_sk_callback_avx+0x48a> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -10180,9 +10557,9 @@ _sk_bilinear_px_avx LABEL PROC PUBLIC _sk_bilinear_ny_avx _sk_bilinear_ny_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,130,7,0,0 ; vbroadcastss 0x782(%rip),%ymm1 # 61c8 <_sk_callback_avx+0x48c> + DB 196,226,125,24,13,132,7,0,0 ; vbroadcastss 0x784(%rip),%ymm1 # 67b4 <_sk_callback_avx+0x48e> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,120,7,0,0 ; vbroadcastss 0x778(%rip),%ymm8 # 61cc <_sk_callback_avx+0x490> + DB 196,98,125,24,5,122,7,0,0 ; vbroadcastss 0x77a(%rip),%ymm8 # 67b8 <_sk_callback_avx+0x492> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -10191,7 +10568,7 @@ _sk_bilinear_ny_avx LABEL PROC PUBLIC _sk_bilinear_py_avx _sk_bilinear_py_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,96,7,0,0 ; vbroadcastss 0x760(%rip),%ymm1 # 61d0 <_sk_callback_avx+0x494> + DB 196,226,125,24,13,98,7,0,0 ; vbroadcastss 0x762(%rip),%ymm1 # 67bc <_sk_callback_avx+0x496> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -10201,14 +10578,14 @@ _sk_bilinear_py_avx LABEL PROC PUBLIC _sk_bicubic_n3x_avx _sk_bicubic_n3x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,67,7,0,0 ; vbroadcastss 0x743(%rip),%ymm0 # 61d4 <_sk_callback_avx+0x498> + DB 196,226,125,24,5,69,7,0,0 ; vbroadcastss 0x745(%rip),%ymm0 # 67c0 <_sk_callback_avx+0x49a> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,58,7,0,0 ; vbroadcastss 0x73a(%rip),%ymm8 # 61d8 <_sk_callback_avx+0x49c> + DB 196,98,125,24,5,60,7,0,0 ; vbroadcastss 0x73c(%rip),%ymm8 # 67c4 <_sk_callback_avx+0x49e> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,43,7,0,0 ; vbroadcastss 0x72b(%rip),%ymm10 # 61dc <_sk_callback_avx+0x4a0> + DB 196,98,125,24,21,45,7,0,0 ; vbroadcastss 0x72d(%rip),%ymm10 # 67c8 <_sk_callback_avx+0x4a2> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,33,7,0,0 ; vbroadcastss 0x721(%rip),%ymm10 # 61e0 <_sk_callback_avx+0x4a4> + DB 196,98,125,24,21,35,7,0,0 ; vbroadcastss 0x723(%rip),%ymm10 # 67cc <_sk_callback_avx+0x4a6> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -10218,19 +10595,19 @@ _sk_bicubic_n3x_avx LABEL PROC PUBLIC _sk_bicubic_n1x_avx _sk_bicubic_n1x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,4,7,0,0 ; vbroadcastss 0x704(%rip),%ymm0 # 61e4 <_sk_callback_avx+0x4a8> + DB 196,226,125,24,5,6,7,0,0 ; vbroadcastss 0x706(%rip),%ymm0 # 67d0 <_sk_callback_avx+0x4aa> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,251,6,0,0 ; vbroadcastss 0x6fb(%rip),%ymm8 # 61e8 <_sk_callback_avx+0x4ac> + DB 196,98,125,24,5,253,6,0,0 ; vbroadcastss 0x6fd(%rip),%ymm8 # 67d4 <_sk_callback_avx+0x4ae> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,241,6,0,0 ; vbroadcastss 0x6f1(%rip),%ymm9 # 61ec <_sk_callback_avx+0x4b0> + DB 196,98,125,24,13,243,6,0,0 ; vbroadcastss 0x6f3(%rip),%ymm9 # 67d8 <_sk_callback_avx+0x4b2> DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,231,6,0,0 ; vbroadcastss 0x6e7(%rip),%ymm10 # 61f0 <_sk_callback_avx+0x4b4> + DB 196,98,125,24,21,233,6,0,0 ; vbroadcastss 0x6e9(%rip),%ymm10 # 67dc <_sk_callback_avx+0x4b6> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,216,6,0,0 ; vbroadcastss 0x6d8(%rip),%ymm10 # 61f4 <_sk_callback_avx+0x4b8> + DB 196,98,125,24,21,218,6,0,0 ; vbroadcastss 0x6da(%rip),%ymm10 # 67e0 <_sk_callback_avx+0x4ba> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,24,13,201,6,0,0 ; vbroadcastss 0x6c9(%rip),%ymm9 # 61f8 <_sk_callback_avx+0x4bc> + DB 196,98,125,24,13,203,6,0,0 ; vbroadcastss 0x6cb(%rip),%ymm9 # 67e4 <_sk_callback_avx+0x4be> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -10239,17 +10616,17 @@ _sk_bicubic_n1x_avx LABEL PROC PUBLIC _sk_bicubic_p1x_avx _sk_bicubic_p1x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,177,6,0,0 ; vbroadcastss 0x6b1(%rip),%ymm8 # 61fc <_sk_callback_avx+0x4c0> + DB 196,98,125,24,5,179,6,0,0 ; vbroadcastss 0x6b3(%rip),%ymm8 # 67e8 <_sk_callback_avx+0x4c2> DB 197,188,88,0 ; vaddps (%rax),%ymm8,%ymm0 DB 197,124,16,72,64 ; vmovups 0x40(%rax),%ymm9 - DB 196,98,125,24,21,163,6,0,0 ; vbroadcastss 0x6a3(%rip),%ymm10 # 6200 <_sk_callback_avx+0x4c4> + DB 196,98,125,24,21,165,6,0,0 ; vbroadcastss 0x6a5(%rip),%ymm10 # 67ec <_sk_callback_avx+0x4c6> DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 - DB 196,98,125,24,29,153,6,0,0 ; vbroadcastss 0x699(%rip),%ymm11 # 6204 <_sk_callback_avx+0x4c8> + DB 196,98,125,24,29,155,6,0,0 ; vbroadcastss 0x69b(%rip),%ymm11 # 67f0 <_sk_callback_avx+0x4ca> DB 196,65,44,88,211 ; vaddps %ymm11,%ymm10,%ymm10 DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 DB 196,65,44,88,192 ; vaddps %ymm8,%ymm10,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 - DB 196,98,125,24,13,128,6,0,0 ; vbroadcastss 0x680(%rip),%ymm9 # 6208 <_sk_callback_avx+0x4cc> + DB 196,98,125,24,13,130,6,0,0 ; vbroadcastss 0x682(%rip),%ymm9 # 67f4 <_sk_callback_avx+0x4ce> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -10258,13 +10635,13 @@ _sk_bicubic_p1x_avx LABEL PROC PUBLIC _sk_bicubic_p3x_avx _sk_bicubic_p3x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,104,6,0,0 ; vbroadcastss 0x668(%rip),%ymm0 # 620c <_sk_callback_avx+0x4d0> + DB 196,226,125,24,5,106,6,0,0 ; vbroadcastss 0x66a(%rip),%ymm0 # 67f8 <_sk_callback_avx+0x4d2> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,85,6,0,0 ; vbroadcastss 0x655(%rip),%ymm10 # 6210 <_sk_callback_avx+0x4d4> + DB 196,98,125,24,21,87,6,0,0 ; vbroadcastss 0x657(%rip),%ymm10 # 67fc <_sk_callback_avx+0x4d6> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,75,6,0,0 ; vbroadcastss 0x64b(%rip),%ymm10 # 6214 <_sk_callback_avx+0x4d8> + DB 196,98,125,24,21,77,6,0,0 ; vbroadcastss 0x64d(%rip),%ymm10 # 6800 <_sk_callback_avx+0x4da> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -10274,14 +10651,14 @@ _sk_bicubic_p3x_avx LABEL PROC PUBLIC _sk_bicubic_n3y_avx _sk_bicubic_n3y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,46,6,0,0 ; vbroadcastss 0x62e(%rip),%ymm1 # 6218 <_sk_callback_avx+0x4dc> + DB 196,226,125,24,13,48,6,0,0 ; vbroadcastss 0x630(%rip),%ymm1 # 6804 <_sk_callback_avx+0x4de> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,36,6,0,0 ; vbroadcastss 0x624(%rip),%ymm8 # 621c <_sk_callback_avx+0x4e0> + DB 196,98,125,24,5,38,6,0,0 ; vbroadcastss 0x626(%rip),%ymm8 # 6808 <_sk_callback_avx+0x4e2> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,21,6,0,0 ; vbroadcastss 0x615(%rip),%ymm10 # 6220 <_sk_callback_avx+0x4e4> + DB 196,98,125,24,21,23,6,0,0 ; vbroadcastss 0x617(%rip),%ymm10 # 680c <_sk_callback_avx+0x4e6> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,11,6,0,0 ; vbroadcastss 0x60b(%rip),%ymm10 # 6224 <_sk_callback_avx+0x4e8> + DB 196,98,125,24,21,13,6,0,0 ; vbroadcastss 0x60d(%rip),%ymm10 # 6810 <_sk_callback_avx+0x4ea> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -10291,19 +10668,19 @@ _sk_bicubic_n3y_avx LABEL PROC PUBLIC _sk_bicubic_n1y_avx _sk_bicubic_n1y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,238,5,0,0 ; vbroadcastss 0x5ee(%rip),%ymm1 # 6228 <_sk_callback_avx+0x4ec> + DB 196,226,125,24,13,240,5,0,0 ; vbroadcastss 0x5f0(%rip),%ymm1 # 6814 <_sk_callback_avx+0x4ee> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,228,5,0,0 ; vbroadcastss 0x5e4(%rip),%ymm8 # 622c <_sk_callback_avx+0x4f0> + DB 196,98,125,24,5,230,5,0,0 ; vbroadcastss 0x5e6(%rip),%ymm8 # 6818 <_sk_callback_avx+0x4f2> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,218,5,0,0 ; vbroadcastss 0x5da(%rip),%ymm9 # 6230 <_sk_callback_avx+0x4f4> + DB 196,98,125,24,13,220,5,0,0 ; vbroadcastss 0x5dc(%rip),%ymm9 # 681c <_sk_callback_avx+0x4f6> DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,208,5,0,0 ; vbroadcastss 0x5d0(%rip),%ymm10 # 6234 <_sk_callback_avx+0x4f8> + DB 196,98,125,24,21,210,5,0,0 ; vbroadcastss 0x5d2(%rip),%ymm10 # 6820 <_sk_callback_avx+0x4fa> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,193,5,0,0 ; vbroadcastss 0x5c1(%rip),%ymm10 # 6238 <_sk_callback_avx+0x4fc> + DB 196,98,125,24,21,195,5,0,0 ; vbroadcastss 0x5c3(%rip),%ymm10 # 6824 <_sk_callback_avx+0x4fe> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,24,13,178,5,0,0 ; vbroadcastss 0x5b2(%rip),%ymm9 # 623c <_sk_callback_avx+0x500> + DB 196,98,125,24,13,180,5,0,0 ; vbroadcastss 0x5b4(%rip),%ymm9 # 6828 <_sk_callback_avx+0x502> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -10312,17 +10689,17 @@ _sk_bicubic_n1y_avx LABEL PROC PUBLIC _sk_bicubic_p1y_avx _sk_bicubic_p1y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,154,5,0,0 ; vbroadcastss 0x59a(%rip),%ymm8 # 6240 <_sk_callback_avx+0x504> + DB 196,98,125,24,5,156,5,0,0 ; vbroadcastss 0x59c(%rip),%ymm8 # 682c <_sk_callback_avx+0x506> DB 197,188,88,72,32 ; vaddps 0x20(%rax),%ymm8,%ymm1 DB 197,124,16,72,96 ; vmovups 0x60(%rax),%ymm9 - DB 196,98,125,24,21,139,5,0,0 ; vbroadcastss 0x58b(%rip),%ymm10 # 6244 <_sk_callback_avx+0x508> + DB 196,98,125,24,21,141,5,0,0 ; vbroadcastss 0x58d(%rip),%ymm10 # 6830 <_sk_callback_avx+0x50a> DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 - DB 196,98,125,24,29,129,5,0,0 ; vbroadcastss 0x581(%rip),%ymm11 # 6248 <_sk_callback_avx+0x50c> + DB 196,98,125,24,29,131,5,0,0 ; vbroadcastss 0x583(%rip),%ymm11 # 6834 <_sk_callback_avx+0x50e> DB 196,65,44,88,211 ; vaddps %ymm11,%ymm10,%ymm10 DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 DB 196,65,44,88,192 ; vaddps %ymm8,%ymm10,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 - DB 196,98,125,24,13,104,5,0,0 ; vbroadcastss 0x568(%rip),%ymm9 # 624c <_sk_callback_avx+0x510> + DB 196,98,125,24,13,106,5,0,0 ; vbroadcastss 0x56a(%rip),%ymm9 # 6838 <_sk_callback_avx+0x512> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -10331,13 +10708,13 @@ _sk_bicubic_p1y_avx LABEL PROC PUBLIC _sk_bicubic_p3y_avx _sk_bicubic_p3y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,80,5,0,0 ; vbroadcastss 0x550(%rip),%ymm1 # 6250 <_sk_callback_avx+0x514> + DB 196,226,125,24,13,82,5,0,0 ; vbroadcastss 0x552(%rip),%ymm1 # 683c <_sk_callback_avx+0x516> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,60,5,0,0 ; vbroadcastss 0x53c(%rip),%ymm10 # 6254 <_sk_callback_avx+0x518> + DB 196,98,125,24,21,62,5,0,0 ; vbroadcastss 0x53e(%rip),%ymm10 # 6840 <_sk_callback_avx+0x51a> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,50,5,0,0 ; vbroadcastss 0x532(%rip),%ymm10 # 6258 <_sk_callback_avx+0x51c> + DB 196,98,125,24,21,52,5,0,0 ; vbroadcastss 0x534(%rip),%ymm10 # 6844 <_sk_callback_avx+0x51e> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -10451,25 +10828,25 @@ ALIGN 4 DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 5f09 <.literal4+0xb1> + DB 71,225,61 ; rex.RXB loope 64f1 <.literal4+0xb1> DB 0,0 ; add %al,(%rax) DB 128,63,154 ; cmpb $0x9a,(%rdi) DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 5f19 <.literal4+0xc1> + DB 71,225,61 ; rex.RXB loope 6501 <.literal4+0xc1> DB 0,0 ; add %al,(%rax) DB 128,63,154 ; cmpb $0x9a,(%rdi) DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 5f29 <.literal4+0xd1> + DB 71,225,61 ; rex.RXB loope 6511 <.literal4+0xd1> DB 0,0 ; add %al,(%rax) DB 128,63,154 ; cmpb $0x9a,(%rdi) DB 153 ; cltd DB 153 ; cltd DB 62,61,10,23,63,174 ; ds cmp $0xae3f170a,%eax - DB 71,225,61 ; rex.RXB loope 5f39 <.literal4+0xe1> + DB 71,225,61 ; rex.RXB loope 6521 <.literal4+0xe1> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -10519,7 +10896,7 @@ ALIGN 4 DB 190,129,128,128,59 ; mov $0x3b808081,%esi DB 129,128,128,59,0,248,0,0,8,33 ; addl $0x21080000,-0x7ffc480(%rax) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 5f85 <.literal4+0x12d> + DB 224,7 ; loopne 656d <.literal4+0x12d> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -10535,10 +10912,10 @@ ALIGN 4 DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) DB 0,52,255 ; add %dh,(%rdi,%rdi,8) DB 255 ; (bad) - DB 127,0 ; jg 5fac <.literal4+0x154> + DB 127,0 ; jg 6594 <.literal4+0x154> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 6025 <.literal4+0x1cd> + DB 119,115 ; ja 660d <.literal4+0x1cd> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -10552,10 +10929,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 5fe0 <.literal4+0x188> + DB 127,0 ; jg 65c8 <.literal4+0x188> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 6059 <.literal4+0x201> + DB 119,115 ; ja 6641 <.literal4+0x201> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -10569,10 +10946,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 6014 <.literal4+0x1bc> + DB 127,0 ; jg 65fc <.literal4+0x1bc> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 608d <.literal4+0x235> + DB 119,115 ; ja 6675 <.literal4+0x235> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -10586,10 +10963,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 6048 <.literal4+0x1f0> + DB 127,0 ; jg 6630 <.literal4+0x1f0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 60c1 <.literal4+0x269> + DB 119,115 ; ja 66a9 <.literal4+0x269> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -10602,7 +10979,7 @@ ALIGN 4 DB 0,75,0 ; add %cl,0x0(%rbx) DB 0,128,63,0,0,200 ; add %al,-0x37ffffc1(%rax) DB 66,0,0 ; rex.X add %al,(%rax) - DB 127,67 ; jg 60bf <.literal4+0x267> + DB 127,67 ; jg 66a7 <.literal4+0x267> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -10614,10 +10991,10 @@ ALIGN 4 DB 190,80,128,3,62 ; mov $0x3e038050,%esi DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 60df <.literal4+0x287> + DB 118,63 ; jbe 66c7 <.literal4+0x287> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 60f3 <.literal4+0x29b> + DB 127,67 ; jg 66db <.literal4+0x29b> DB 129,128,128,59,0,0,128,63,129,128 ; addl $0x80813f80,0x3b80(%rax) DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,128,63,129,128,128 ; add %al,-0x7f7f7ec1(%rax) @@ -10626,7 +11003,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 60d5 <.literal4+0x27d> + DB 224,7 ; loopne 66bd <.literal4+0x27d> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -10638,7 +11015,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 60f1 <.literal4+0x299> + DB 224,7 ; loopne 66d9 <.literal4+0x299> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -10649,7 +11026,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 6146 <.literal4+0x2ee> + DB 124,66 ; jl 672e <.literal4+0x2ee> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 137,136,136,55,0,15 ; mov %ecx,0xf003788(%rax) @@ -10667,9 +11044,9 @@ ALIGN 4 DB 137,136,136,59,15,0 ; mov %ecx,0xf3b88(%rax) DB 0,0 ; add %al,(%rax) DB 137,136,136,61,0,0 ; mov %ecx,0x3d88(%rax) - DB 112,65 ; jo 6189 <.literal4+0x331> + DB 112,65 ; jo 6771 <.literal4+0x331> DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 6197 <.literal4+0x33f> + DB 127,67 ; jg 677f <.literal4+0x33f> DB 0,128,0,0,0,0 ; add %al,0x0(%rax) DB 0,128,0,4,0,128 ; add %al,-0x7ffffc00(%rax) DB 0,0 ; add %al,(%rax) @@ -10685,7 +11062,7 @@ ALIGN 4 DB 0,128,55,0,0,128 ; add %al,-0x7fffffc9(%rax) DB 63 ; (bad) DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 61d7 <.literal4+0x37f> + DB 127,71 ; jg 67bf <.literal4+0x37f> DB 208 ; (bad) DB 179,89 ; mov $0x59,%bl DB 62,89 ; ds pop %rcx @@ -10693,9 +11070,12 @@ ALIGN 4 DB 55 ; (bad) DB 63 ; (bad) DB 152 ; cwtl - DB 221,147,61,111,43,231 ; fstl -0x18d490c3(%rbx) - DB 187,159,215,202,60 ; mov $0x3ccad79f,%ebx - DB 212 ; (bad) + DB 221,147,61,1,0,0 ; fstl 0x13d(%rbx) + DB 0,111,43 ; add %ch,0x2b(%rdi) + DB 231,187 ; out %eax,$0xbb + DB 159 ; lahf + DB 215 ; xlat %ds:(%rbx) + DB 202,60,212 ; lret $0xd43c DB 100,84 ; fs push %rsp DB 189,169,240,34,62 ; mov $0x3e22f0a9,%ebp DB 0,0 ; add %al,(%rax) @@ -10933,7 +11313,7 @@ _sk_seed_shader_sse41 LABEL PROC DB 102,15,110,199 ; movd %edi,%xmm0 DB 102,15,112,192,0 ; pshufd $0x0,%xmm0,%xmm0 DB 15,91,200 ; cvtdq2ps %xmm0,%xmm1 - DB 15,40,21,65,68,0,0 ; movaps 0x4441(%rip),%xmm2 # 4550 <_sk_callback_sse41+0xb9> + DB 15,40,21,113,70,0,0 ; movaps 0x4671(%rip),%xmm2 # 4780 <_sk_callback_sse41+0xad> DB 15,88,202 ; addps %xmm2,%xmm1 DB 15,16,2 ; movups (%rdx),%xmm0 DB 15,88,193 ; addps %xmm1,%xmm0 @@ -10942,7 +11322,7 @@ _sk_seed_shader_sse41 LABEL PROC DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 15,88,202 ; addps %xmm2,%xmm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,21,48,68,0,0 ; movaps 0x4430(%rip),%xmm2 # 4560 <_sk_callback_sse41+0xc9> + DB 15,40,21,96,70,0,0 ; movaps 0x4660(%rip),%xmm2 # 4790 <_sk_callback_sse41+0xbd> DB 15,87,219 ; xorps %xmm3,%xmm3 DB 15,87,228 ; xorps %xmm4,%xmm4 DB 15,87,237 ; xorps %xmm5,%xmm5 @@ -10963,14 +11343,14 @@ _sk_dither_sse41 LABEL PROC DB 102,68,15,110,1 ; movd (%rcx),%xmm8 DB 102,69,15,112,192,0 ; pshufd $0x0,%xmm8,%xmm8 DB 102,69,15,239,193 ; pxor %xmm9,%xmm8 - DB 102,68,15,111,21,245,67,0,0 ; movdqa 0x43f5(%rip),%xmm10 # 4570 <_sk_callback_sse41+0xd9> + DB 102,68,15,111,21,37,70,0,0 ; movdqa 0x4625(%rip),%xmm10 # 47a0 <_sk_callback_sse41+0xcd> DB 102,69,15,111,216 ; movdqa %xmm8,%xmm11 DB 102,69,15,219,218 ; pand %xmm10,%xmm11 DB 102,65,15,114,243,5 ; pslld $0x5,%xmm11 DB 102,69,15,219,209 ; pand %xmm9,%xmm10 DB 102,65,15,114,242,4 ; pslld $0x4,%xmm10 - DB 102,68,15,111,37,225,67,0,0 ; movdqa 0x43e1(%rip),%xmm12 # 4580 <_sk_callback_sse41+0xe9> - DB 102,68,15,111,45,232,67,0,0 ; movdqa 0x43e8(%rip),%xmm13 # 4590 <_sk_callback_sse41+0xf9> + DB 102,68,15,111,37,17,70,0,0 ; movdqa 0x4611(%rip),%xmm12 # 47b0 <_sk_callback_sse41+0xdd> + DB 102,68,15,111,45,24,70,0,0 ; movdqa 0x4618(%rip),%xmm13 # 47c0 <_sk_callback_sse41+0xed> DB 102,69,15,111,240 ; movdqa %xmm8,%xmm14 DB 102,69,15,219,245 ; pand %xmm13,%xmm14 DB 102,65,15,114,246,2 ; pslld $0x2,%xmm14 @@ -10986,8 +11366,8 @@ _sk_dither_sse41 LABEL PROC DB 102,69,15,235,245 ; por %xmm13,%xmm14 DB 102,69,15,235,240 ; por %xmm8,%xmm14 DB 69,15,91,198 ; cvtdq2ps %xmm14,%xmm8 - DB 68,15,89,5,163,67,0,0 ; mulps 0x43a3(%rip),%xmm8 # 45a0 <_sk_callback_sse41+0x109> - DB 68,15,88,5,171,67,0,0 ; addps 0x43ab(%rip),%xmm8 # 45b0 <_sk_callback_sse41+0x119> + DB 68,15,89,5,211,69,0,0 ; mulps 0x45d3(%rip),%xmm8 # 47d0 <_sk_callback_sse41+0xfd> + DB 68,15,88,5,219,69,0,0 ; addps 0x45db(%rip),%xmm8 # 47e0 <_sk_callback_sse41+0x10d> DB 243,68,15,16,72,8 ; movss 0x8(%rax),%xmm9 DB 69,15,198,201,0 ; shufps $0x0,%xmm9,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 @@ -11043,7 +11423,7 @@ _sk_clear_sse41 LABEL PROC PUBLIC _sk_srcatop_sse41 _sk_srcatop_sse41 LABEL PROC DB 15,89,199 ; mulps %xmm7,%xmm0 - DB 68,15,40,5,46,67,0,0 ; movaps 0x432e(%rip),%xmm8 # 45c0 <_sk_callback_sse41+0x129> + DB 68,15,40,5,94,69,0,0 ; movaps 0x455e(%rip),%xmm8 # 47f0 <_sk_callback_sse41+0x11d> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -11066,7 +11446,7 @@ PUBLIC _sk_dstatop_sse41 _sk_dstatop_sse41 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 DB 68,15,89,196 ; mulps %xmm4,%xmm8 - DB 68,15,40,13,241,66,0,0 ; movaps 0x42f1(%rip),%xmm9 # 45d0 <_sk_callback_sse41+0x139> + DB 68,15,40,13,33,69,0,0 ; movaps 0x4521(%rip),%xmm9 # 4800 <_sk_callback_sse41+0x12d> DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,88,192 ; addps %xmm8,%xmm0 @@ -11107,7 +11487,7 @@ _sk_dstin_sse41 LABEL PROC PUBLIC _sk_srcout_sse41 _sk_srcout_sse41 LABEL PROC - DB 68,15,40,5,149,66,0,0 ; movaps 0x4295(%rip),%xmm8 # 45e0 <_sk_callback_sse41+0x149> + DB 68,15,40,5,197,68,0,0 ; movaps 0x44c5(%rip),%xmm8 # 4810 <_sk_callback_sse41+0x13d> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 @@ -11118,7 +11498,7 @@ _sk_srcout_sse41 LABEL PROC PUBLIC _sk_dstout_sse41 _sk_dstout_sse41 LABEL PROC - DB 68,15,40,5,133,66,0,0 ; movaps 0x4285(%rip),%xmm8 # 45f0 <_sk_callback_sse41+0x159> + DB 68,15,40,5,181,68,0,0 ; movaps 0x44b5(%rip),%xmm8 # 4820 <_sk_callback_sse41+0x14d> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 15,89,196 ; mulps %xmm4,%xmm0 @@ -11133,7 +11513,7 @@ _sk_dstout_sse41 LABEL PROC PUBLIC _sk_srcover_sse41 _sk_srcover_sse41 LABEL PROC - DB 68,15,40,5,104,66,0,0 ; movaps 0x4268(%rip),%xmm8 # 4600 <_sk_callback_sse41+0x169> + DB 68,15,40,5,152,68,0,0 ; movaps 0x4498(%rip),%xmm8 # 4830 <_sk_callback_sse41+0x15d> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -11151,7 +11531,7 @@ _sk_srcover_sse41 LABEL PROC PUBLIC _sk_dstover_sse41 _sk_dstover_sse41 LABEL PROC - DB 68,15,40,5,60,66,0,0 ; movaps 0x423c(%rip),%xmm8 # 4610 <_sk_callback_sse41+0x179> + DB 68,15,40,5,108,68,0,0 ; movaps 0x446c(%rip),%xmm8 # 4840 <_sk_callback_sse41+0x16d> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -11175,7 +11555,7 @@ _sk_modulate_sse41 LABEL PROC PUBLIC _sk_multiply_sse41 _sk_multiply_sse41 LABEL PROC - DB 68,15,40,5,16,66,0,0 ; movaps 0x4210(%rip),%xmm8 # 4620 <_sk_callback_sse41+0x189> + DB 68,15,40,5,64,68,0,0 ; movaps 0x4440(%rip),%xmm8 # 4850 <_sk_callback_sse41+0x17d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 69,15,40,209 ; movaps %xmm9,%xmm10 @@ -11245,7 +11625,7 @@ _sk_screen_sse41 LABEL PROC PUBLIC _sk_xor__sse41 _sk_xor__sse41 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 - DB 15,40,29,65,65,0,0 ; movaps 0x4141(%rip),%xmm3 # 4630 <_sk_callback_sse41+0x199> + DB 15,40,29,113,67,0,0 ; movaps 0x4371(%rip),%xmm3 # 4860 <_sk_callback_sse41+0x18d> DB 68,15,40,203 ; movaps %xmm3,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 @@ -11291,7 +11671,7 @@ _sk_darken_sse41 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,95,209 ; maxps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,172,64,0,0 ; movaps 0x40ac(%rip),%xmm2 # 4640 <_sk_callback_sse41+0x1a9> + DB 15,40,21,220,66,0,0 ; movaps 0x42dc(%rip),%xmm2 # 4870 <_sk_callback_sse41+0x19d> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -11323,7 +11703,7 @@ _sk_lighten_sse41 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,81,64,0,0 ; movaps 0x4051(%rip),%xmm2 # 4650 <_sk_callback_sse41+0x1b9> + DB 15,40,21,129,66,0,0 ; movaps 0x4281(%rip),%xmm2 # 4880 <_sk_callback_sse41+0x1ad> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -11358,7 +11738,7 @@ _sk_difference_sse41 LABEL PROC DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,235,63,0,0 ; movaps 0x3feb(%rip),%xmm2 # 4660 <_sk_callback_sse41+0x1c9> + DB 15,40,21,27,66,0,0 ; movaps 0x421b(%rip),%xmm2 # 4890 <_sk_callback_sse41+0x1bd> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -11383,7 +11763,7 @@ _sk_exclusion_sse41 LABEL PROC DB 15,89,214 ; mulps %xmm6,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,202 ; subps %xmm2,%xmm9 - DB 15,40,13,172,63,0,0 ; movaps 0x3fac(%rip),%xmm1 # 4670 <_sk_callback_sse41+0x1d9> + DB 15,40,13,220,65,0,0 ; movaps 0x41dc(%rip),%xmm1 # 48a0 <_sk_callback_sse41+0x1cd> DB 15,92,203 ; subps %xmm3,%xmm1 DB 15,89,207 ; mulps %xmm7,%xmm1 DB 15,88,217 ; addps %xmm1,%xmm3 @@ -11395,7 +11775,7 @@ _sk_exclusion_sse41 LABEL PROC PUBLIC _sk_colorburn_sse41 _sk_colorburn_sse41 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,40,21,155,63,0,0 ; movaps 0x3f9b(%rip),%xmm10 # 4680 <_sk_callback_sse41+0x1e9> + DB 68,15,40,21,203,65,0,0 ; movaps 0x41cb(%rip),%xmm10 # 48b0 <_sk_callback_sse41+0x1dd> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 69,15,40,203 ; movaps %xmm11,%xmm9 @@ -11475,7 +11855,7 @@ _sk_colorburn_sse41 LABEL PROC PUBLIC _sk_colordodge_sse41 _sk_colordodge_sse41 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,40,21,121,62,0,0 ; movaps 0x3e79(%rip),%xmm10 # 4690 <_sk_callback_sse41+0x1f9> + DB 68,15,40,21,169,64,0,0 ; movaps 0x40a9(%rip),%xmm10 # 48c0 <_sk_callback_sse41+0x1ed> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 69,15,40,227 ; movaps %xmm11,%xmm12 @@ -11556,7 +11936,7 @@ _sk_hardlight_sse41 LABEL PROC DB 15,40,244 ; movaps %xmm4,%xmm6 DB 15,40,227 ; movaps %xmm3,%xmm4 DB 68,15,40,200 ; movaps %xmm0,%xmm9 - DB 68,15,40,21,79,61,0,0 ; movaps 0x3d4f(%rip),%xmm10 # 46a0 <_sk_callback_sse41+0x209> + DB 68,15,40,21,127,63,0,0 ; movaps 0x3f7f(%rip),%xmm10 # 48d0 <_sk_callback_sse41+0x1fd> DB 65,15,40,234 ; movaps %xmm10,%xmm5 DB 15,92,239 ; subps %xmm7,%xmm5 DB 15,40,197 ; movaps %xmm5,%xmm0 @@ -11638,7 +12018,7 @@ PUBLIC _sk_overlay_sse41 _sk_overlay_sse41 LABEL PROC DB 68,15,40,201 ; movaps %xmm1,%xmm9 DB 68,15,40,240 ; movaps %xmm0,%xmm14 - DB 68,15,40,21,49,60,0,0 ; movaps 0x3c31(%rip),%xmm10 # 46b0 <_sk_callback_sse41+0x219> + DB 68,15,40,21,97,62,0,0 ; movaps 0x3e61(%rip),%xmm10 # 48e0 <_sk_callback_sse41+0x20d> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 65,15,40,195 ; movaps %xmm11,%xmm0 @@ -11722,7 +12102,7 @@ _sk_softlight_sse41 LABEL PROC DB 15,40,198 ; movaps %xmm6,%xmm0 DB 15,94,199 ; divps %xmm7,%xmm0 DB 65,15,84,193 ; andps %xmm9,%xmm0 - DB 15,40,13,4,59,0,0 ; movaps 0x3b04(%rip),%xmm1 # 46c0 <_sk_callback_sse41+0x229> + DB 15,40,13,52,61,0,0 ; movaps 0x3d34(%rip),%xmm1 # 48f0 <_sk_callback_sse41+0x21d> DB 68,15,40,209 ; movaps %xmm1,%xmm10 DB 68,15,92,208 ; subps %xmm0,%xmm10 DB 68,15,40,240 ; movaps %xmm0,%xmm14 @@ -11735,10 +12115,10 @@ _sk_softlight_sse41 LABEL PROC DB 15,40,208 ; movaps %xmm0,%xmm2 DB 15,89,210 ; mulps %xmm2,%xmm2 DB 15,88,208 ; addps %xmm0,%xmm2 - DB 68,15,40,45,226,58,0,0 ; movaps 0x3ae2(%rip),%xmm13 # 46d0 <_sk_callback_sse41+0x239> + DB 68,15,40,45,18,61,0,0 ; movaps 0x3d12(%rip),%xmm13 # 4900 <_sk_callback_sse41+0x22d> DB 69,15,88,245 ; addps %xmm13,%xmm14 DB 68,15,89,242 ; mulps %xmm2,%xmm14 - DB 68,15,40,37,226,58,0,0 ; movaps 0x3ae2(%rip),%xmm12 # 46e0 <_sk_callback_sse41+0x249> + DB 68,15,40,37,18,61,0,0 ; movaps 0x3d12(%rip),%xmm12 # 4910 <_sk_callback_sse41+0x23d> DB 69,15,89,252 ; mulps %xmm12,%xmm15 DB 69,15,88,254 ; addps %xmm14,%xmm15 DB 15,40,198 ; movaps %xmm6,%xmm0 @@ -11924,12 +12304,12 @@ _sk_hue_sse41 LABEL PROC DB 68,15,84,208 ; andps %xmm0,%xmm10 DB 15,84,200 ; andps %xmm0,%xmm1 DB 68,15,84,232 ; andps %xmm0,%xmm13 - DB 15,40,5,72,56,0,0 ; movaps 0x3848(%rip),%xmm0 # 46f0 <_sk_callback_sse41+0x259> + DB 15,40,5,120,58,0,0 ; movaps 0x3a78(%rip),%xmm0 # 4920 <_sk_callback_sse41+0x24d> DB 68,15,89,224 ; mulps %xmm0,%xmm12 - DB 15,40,21,77,56,0,0 ; movaps 0x384d(%rip),%xmm2 # 4700 <_sk_callback_sse41+0x269> + DB 15,40,21,125,58,0,0 ; movaps 0x3a7d(%rip),%xmm2 # 4930 <_sk_callback_sse41+0x25d> DB 15,89,250 ; mulps %xmm2,%xmm7 DB 65,15,88,252 ; addps %xmm12,%xmm7 - DB 68,15,40,53,78,56,0,0 ; movaps 0x384e(%rip),%xmm14 # 4710 <_sk_callback_sse41+0x279> + DB 68,15,40,53,126,58,0,0 ; movaps 0x3a7e(%rip),%xmm14 # 4940 <_sk_callback_sse41+0x26d> DB 68,15,40,252 ; movaps %xmm4,%xmm15 DB 69,15,89,254 ; mulps %xmm14,%xmm15 DB 68,15,88,255 ; addps %xmm7,%xmm15 @@ -12012,7 +12392,7 @@ _sk_hue_sse41 LABEL PROC DB 65,15,88,214 ; addps %xmm14,%xmm2 DB 15,40,196 ; movaps %xmm4,%xmm0 DB 102,15,56,20,202 ; blendvps %xmm0,%xmm2,%xmm1 - DB 68,15,40,13,19,55,0,0 ; movaps 0x3713(%rip),%xmm9 # 4720 <_sk_callback_sse41+0x289> + DB 68,15,40,13,67,57,0,0 ; movaps 0x3943(%rip),%xmm9 # 4950 <_sk_callback_sse41+0x27d> DB 65,15,40,225 ; movaps %xmm9,%xmm4 DB 15,92,229 ; subps %xmm5,%xmm4 DB 15,40,68,36,48 ; movaps 0x30(%rsp),%xmm0 @@ -12106,14 +12486,14 @@ _sk_saturation_sse41 LABEL PROC DB 68,15,84,215 ; andps %xmm7,%xmm10 DB 68,15,84,223 ; andps %xmm7,%xmm11 DB 68,15,84,199 ; andps %xmm7,%xmm8 - DB 15,40,21,198,53,0,0 ; movaps 0x35c6(%rip),%xmm2 # 4730 <_sk_callback_sse41+0x299> + DB 15,40,21,246,55,0,0 ; movaps 0x37f6(%rip),%xmm2 # 4960 <_sk_callback_sse41+0x28d> DB 15,40,221 ; movaps %xmm5,%xmm3 DB 15,89,218 ; mulps %xmm2,%xmm3 - DB 15,40,13,201,53,0,0 ; movaps 0x35c9(%rip),%xmm1 # 4740 <_sk_callback_sse41+0x2a9> + DB 15,40,13,249,55,0,0 ; movaps 0x37f9(%rip),%xmm1 # 4970 <_sk_callback_sse41+0x29d> DB 15,40,254 ; movaps %xmm6,%xmm7 DB 15,89,249 ; mulps %xmm1,%xmm7 DB 15,88,251 ; addps %xmm3,%xmm7 - DB 68,15,40,45,200,53,0,0 ; movaps 0x35c8(%rip),%xmm13 # 4750 <_sk_callback_sse41+0x2b9> + DB 68,15,40,45,248,55,0,0 ; movaps 0x37f8(%rip),%xmm13 # 4980 <_sk_callback_sse41+0x2ad> DB 69,15,89,245 ; mulps %xmm13,%xmm14 DB 68,15,88,247 ; addps %xmm7,%xmm14 DB 65,15,40,218 ; movaps %xmm10,%xmm3 @@ -12194,7 +12574,7 @@ _sk_saturation_sse41 LABEL PROC DB 65,15,88,253 ; addps %xmm13,%xmm7 DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 102,68,15,56,20,223 ; blendvps %xmm0,%xmm7,%xmm11 - DB 68,15,40,13,142,52,0,0 ; movaps 0x348e(%rip),%xmm9 # 4760 <_sk_callback_sse41+0x2c9> + DB 68,15,40,13,190,54,0,0 ; movaps 0x36be(%rip),%xmm9 # 4990 <_sk_callback_sse41+0x2bd> DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 68,15,92,204 ; subps %xmm4,%xmm9 DB 15,40,60,36 ; movaps (%rsp),%xmm7 @@ -12249,14 +12629,14 @@ _sk_color_sse41 LABEL PROC DB 15,40,231 ; movaps %xmm7,%xmm4 DB 68,15,89,244 ; mulps %xmm4,%xmm14 DB 15,89,204 ; mulps %xmm4,%xmm1 - DB 68,15,40,13,211,51,0,0 ; movaps 0x33d3(%rip),%xmm9 # 4770 <_sk_callback_sse41+0x2d9> + DB 68,15,40,13,3,54,0,0 ; movaps 0x3603(%rip),%xmm9 # 49a0 <_sk_callback_sse41+0x2cd> DB 65,15,40,250 ; movaps %xmm10,%xmm7 DB 65,15,89,249 ; mulps %xmm9,%xmm7 - DB 68,15,40,21,211,51,0,0 ; movaps 0x33d3(%rip),%xmm10 # 4780 <_sk_callback_sse41+0x2e9> + DB 68,15,40,21,3,54,0,0 ; movaps 0x3603(%rip),%xmm10 # 49b0 <_sk_callback_sse41+0x2dd> DB 65,15,40,219 ; movaps %xmm11,%xmm3 DB 65,15,89,218 ; mulps %xmm10,%xmm3 DB 15,88,223 ; addps %xmm7,%xmm3 - DB 68,15,40,29,208,51,0,0 ; movaps 0x33d0(%rip),%xmm11 # 4790 <_sk_callback_sse41+0x2f9> + DB 68,15,40,29,0,54,0,0 ; movaps 0x3600(%rip),%xmm11 # 49c0 <_sk_callback_sse41+0x2ed> DB 69,15,40,236 ; movaps %xmm12,%xmm13 DB 69,15,89,235 ; mulps %xmm11,%xmm13 DB 68,15,88,235 ; addps %xmm3,%xmm13 @@ -12341,7 +12721,7 @@ _sk_color_sse41 LABEL PROC DB 65,15,88,251 ; addps %xmm11,%xmm7 DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 102,15,56,20,207 ; blendvps %xmm0,%xmm7,%xmm1 - DB 68,15,40,13,140,50,0,0 ; movaps 0x328c(%rip),%xmm9 # 47a0 <_sk_callback_sse41+0x309> + DB 68,15,40,13,188,52,0,0 ; movaps 0x34bc(%rip),%xmm9 # 49d0 <_sk_callback_sse41+0x2fd> DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 15,92,196 ; subps %xmm4,%xmm0 DB 68,15,89,192 ; mulps %xmm0,%xmm8 @@ -12393,13 +12773,13 @@ _sk_luminosity_sse41 LABEL PROC DB 69,15,89,216 ; mulps %xmm8,%xmm11 DB 68,15,40,203 ; movaps %xmm3,%xmm9 DB 68,15,89,205 ; mulps %xmm5,%xmm9 - DB 68,15,40,5,222,49,0,0 ; movaps 0x31de(%rip),%xmm8 # 47b0 <_sk_callback_sse41+0x319> + DB 68,15,40,5,14,52,0,0 ; movaps 0x340e(%rip),%xmm8 # 49e0 <_sk_callback_sse41+0x30d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 - DB 68,15,40,21,226,49,0,0 ; movaps 0x31e2(%rip),%xmm10 # 47c0 <_sk_callback_sse41+0x329> + DB 68,15,40,21,18,52,0,0 ; movaps 0x3412(%rip),%xmm10 # 49f0 <_sk_callback_sse41+0x31d> DB 15,40,233 ; movaps %xmm1,%xmm5 DB 65,15,89,234 ; mulps %xmm10,%xmm5 DB 15,88,232 ; addps %xmm0,%xmm5 - DB 68,15,40,37,224,49,0,0 ; movaps 0x31e0(%rip),%xmm12 # 47d0 <_sk_callback_sse41+0x339> + DB 68,15,40,37,16,52,0,0 ; movaps 0x3410(%rip),%xmm12 # 4a00 <_sk_callback_sse41+0x32d> DB 68,15,40,242 ; movaps %xmm2,%xmm14 DB 69,15,89,244 ; mulps %xmm12,%xmm14 DB 68,15,88,245 ; addps %xmm5,%xmm14 @@ -12484,7 +12864,7 @@ _sk_luminosity_sse41 LABEL PROC DB 65,15,88,244 ; addps %xmm12,%xmm6 DB 65,15,40,195 ; movaps %xmm11,%xmm0 DB 102,68,15,56,20,206 ; blendvps %xmm0,%xmm6,%xmm9 - DB 15,40,5,150,48,0,0 ; movaps 0x3096(%rip),%xmm0 # 47e0 <_sk_callback_sse41+0x349> + DB 15,40,5,198,50,0,0 ; movaps 0x32c6(%rip),%xmm0 # 4a10 <_sk_callback_sse41+0x33d> DB 15,40,208 ; movaps %xmm0,%xmm2 DB 15,92,215 ; subps %xmm7,%xmm2 DB 15,89,226 ; mulps %xmm2,%xmm4 @@ -12530,7 +12910,7 @@ _sk_clamp_0_sse41 LABEL PROC PUBLIC _sk_clamp_1_sse41 _sk_clamp_1_sse41 LABEL PROC - DB 68,15,40,5,22,48,0,0 ; movaps 0x3016(%rip),%xmm8 # 47f0 <_sk_callback_sse41+0x359> + DB 68,15,40,5,70,50,0,0 ; movaps 0x3246(%rip),%xmm8 # 4a20 <_sk_callback_sse41+0x34d> DB 65,15,93,192 ; minps %xmm8,%xmm0 DB 65,15,93,200 ; minps %xmm8,%xmm1 DB 65,15,93,208 ; minps %xmm8,%xmm2 @@ -12540,7 +12920,7 @@ _sk_clamp_1_sse41 LABEL PROC PUBLIC _sk_clamp_a_sse41 _sk_clamp_a_sse41 LABEL PROC - DB 15,93,29,11,48,0,0 ; minps 0x300b(%rip),%xmm3 # 4800 <_sk_callback_sse41+0x369> + DB 15,93,29,59,50,0,0 ; minps 0x323b(%rip),%xmm3 # 4a30 <_sk_callback_sse41+0x35d> DB 15,93,195 ; minps %xmm3,%xmm0 DB 15,93,203 ; minps %xmm3,%xmm1 DB 15,93,211 ; minps %xmm3,%xmm2 @@ -12613,7 +12993,7 @@ _sk_premul_sse41 LABEL PROC PUBLIC _sk_unpremul_sse41 _sk_unpremul_sse41 LABEL PROC DB 69,15,87,192 ; xorps %xmm8,%xmm8 - DB 68,15,40,13,118,47,0,0 ; movaps 0x2f76(%rip),%xmm9 # 4810 <_sk_callback_sse41+0x379> + DB 68,15,40,13,166,49,0,0 ; movaps 0x31a6(%rip),%xmm9 # 4a40 <_sk_callback_sse41+0x36d> DB 68,15,94,203 ; divps %xmm3,%xmm9 DB 68,15,194,195,4 ; cmpneqps %xmm3,%xmm8 DB 69,15,84,193 ; andps %xmm9,%xmm8 @@ -12625,20 +13005,20 @@ _sk_unpremul_sse41 LABEL PROC PUBLIC _sk_from_srgb_sse41 _sk_from_srgb_sse41 LABEL PROC - DB 68,15,40,29,97,47,0,0 ; movaps 0x2f61(%rip),%xmm11 # 4820 <_sk_callback_sse41+0x389> + DB 68,15,40,29,145,49,0,0 ; movaps 0x3191(%rip),%xmm11 # 4a50 <_sk_callback_sse41+0x37d> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 DB 68,15,40,208 ; movaps %xmm0,%xmm10 DB 69,15,89,210 ; mulps %xmm10,%xmm10 - DB 68,15,40,37,89,47,0,0 ; movaps 0x2f59(%rip),%xmm12 # 4830 <_sk_callback_sse41+0x399> + DB 68,15,40,37,137,49,0,0 ; movaps 0x3189(%rip),%xmm12 # 4a60 <_sk_callback_sse41+0x38d> DB 68,15,40,192 ; movaps %xmm0,%xmm8 DB 69,15,89,196 ; mulps %xmm12,%xmm8 - DB 68,15,40,45,89,47,0,0 ; movaps 0x2f59(%rip),%xmm13 # 4840 <_sk_callback_sse41+0x3a9> + DB 68,15,40,45,137,49,0,0 ; movaps 0x3189(%rip),%xmm13 # 4a70 <_sk_callback_sse41+0x39d> DB 69,15,88,197 ; addps %xmm13,%xmm8 DB 69,15,89,194 ; mulps %xmm10,%xmm8 - DB 68,15,40,53,89,47,0,0 ; movaps 0x2f59(%rip),%xmm14 # 4850 <_sk_callback_sse41+0x3b9> + DB 68,15,40,53,137,49,0,0 ; movaps 0x3189(%rip),%xmm14 # 4a80 <_sk_callback_sse41+0x3ad> DB 69,15,88,198 ; addps %xmm14,%xmm8 - DB 68,15,40,61,93,47,0,0 ; movaps 0x2f5d(%rip),%xmm15 # 4860 <_sk_callback_sse41+0x3c9> + DB 68,15,40,61,141,49,0,0 ; movaps 0x318d(%rip),%xmm15 # 4a90 <_sk_callback_sse41+0x3bd> DB 65,15,194,199,1 ; cmpltps %xmm15,%xmm0 DB 102,69,15,56,20,193 ; blendvps %xmm0,%xmm9,%xmm8 DB 68,15,40,209 ; movaps %xmm1,%xmm10 @@ -12682,20 +13062,20 @@ _sk_to_srgb_sse41 LABEL PROC DB 68,15,82,192 ; rsqrtps %xmm0,%xmm8 DB 69,15,83,200 ; rcpps %xmm8,%xmm9 DB 69,15,82,208 ; rsqrtps %xmm8,%xmm10 - DB 68,15,40,29,202,46,0,0 ; movaps 0x2eca(%rip),%xmm11 # 4870 <_sk_callback_sse41+0x3d9> + DB 68,15,40,29,250,48,0,0 ; movaps 0x30fa(%rip),%xmm11 # 4aa0 <_sk_callback_sse41+0x3cd> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 65,15,89,203 ; mulps %xmm11,%xmm1 - DB 68,15,40,37,203,46,0,0 ; movaps 0x2ecb(%rip),%xmm12 # 4880 <_sk_callback_sse41+0x3e9> + DB 68,15,40,37,251,48,0,0 ; movaps 0x30fb(%rip),%xmm12 # 4ab0 <_sk_callback_sse41+0x3dd> DB 69,15,89,204 ; mulps %xmm12,%xmm9 - DB 68,15,40,45,207,46,0,0 ; movaps 0x2ecf(%rip),%xmm13 # 4890 <_sk_callback_sse41+0x3f9> + DB 68,15,40,45,255,48,0,0 ; movaps 0x30ff(%rip),%xmm13 # 4ac0 <_sk_callback_sse41+0x3ed> DB 69,15,88,205 ; addps %xmm13,%xmm9 - DB 68,15,40,53,211,46,0,0 ; movaps 0x2ed3(%rip),%xmm14 # 48a0 <_sk_callback_sse41+0x409> + DB 68,15,40,53,3,49,0,0 ; movaps 0x3103(%rip),%xmm14 # 4ad0 <_sk_callback_sse41+0x3fd> DB 69,15,89,214 ; mulps %xmm14,%xmm10 DB 69,15,88,209 ; addps %xmm9,%xmm10 - DB 68,15,40,5,211,46,0,0 ; movaps 0x2ed3(%rip),%xmm8 # 48b0 <_sk_callback_sse41+0x419> + DB 68,15,40,5,3,49,0,0 ; movaps 0x3103(%rip),%xmm8 # 4ae0 <_sk_callback_sse41+0x40d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,93,202 ; minps %xmm10,%xmm9 - DB 68,15,40,61,211,46,0,0 ; movaps 0x2ed3(%rip),%xmm15 # 48c0 <_sk_callback_sse41+0x429> + DB 68,15,40,61,3,49,0,0 ; movaps 0x3103(%rip),%xmm15 # 4af0 <_sk_callback_sse41+0x41d> DB 65,15,194,199,1 ; cmpltps %xmm15,%xmm0 DB 102,68,15,56,20,201 ; blendvps %xmm0,%xmm1,%xmm9 DB 15,82,194 ; rsqrtps %xmm2,%xmm0 @@ -12748,7 +13128,7 @@ _sk_rgb_to_hsl_sse41 LABEL PROC DB 68,15,93,226 ; minps %xmm2,%xmm12 DB 65,15,40,203 ; movaps %xmm11,%xmm1 DB 65,15,92,204 ; subps %xmm12,%xmm1 - DB 68,15,40,53,33,46,0,0 ; movaps 0x2e21(%rip),%xmm14 # 48d0 <_sk_callback_sse41+0x439> + DB 68,15,40,53,81,48,0,0 ; movaps 0x3051(%rip),%xmm14 # 4b00 <_sk_callback_sse41+0x42d> DB 68,15,94,241 ; divps %xmm1,%xmm14 DB 69,15,40,211 ; movaps %xmm11,%xmm10 DB 69,15,194,208,0 ; cmpeqps %xmm8,%xmm10 @@ -12757,27 +13137,27 @@ _sk_rgb_to_hsl_sse41 LABEL PROC DB 65,15,89,198 ; mulps %xmm14,%xmm0 DB 69,15,40,249 ; movaps %xmm9,%xmm15 DB 68,15,194,250,1 ; cmpltps %xmm2,%xmm15 - DB 68,15,84,61,8,46,0,0 ; andps 0x2e08(%rip),%xmm15 # 48e0 <_sk_callback_sse41+0x449> + DB 68,15,84,61,56,48,0,0 ; andps 0x3038(%rip),%xmm15 # 4b10 <_sk_callback_sse41+0x43d> DB 68,15,88,248 ; addps %xmm0,%xmm15 DB 65,15,40,195 ; movaps %xmm11,%xmm0 DB 65,15,194,193,0 ; cmpeqps %xmm9,%xmm0 DB 65,15,92,208 ; subps %xmm8,%xmm2 DB 65,15,89,214 ; mulps %xmm14,%xmm2 - DB 68,15,40,45,251,45,0,0 ; movaps 0x2dfb(%rip),%xmm13 # 48f0 <_sk_callback_sse41+0x459> + DB 68,15,40,45,43,48,0,0 ; movaps 0x302b(%rip),%xmm13 # 4b20 <_sk_callback_sse41+0x44d> DB 65,15,88,213 ; addps %xmm13,%xmm2 DB 69,15,92,193 ; subps %xmm9,%xmm8 DB 69,15,89,198 ; mulps %xmm14,%xmm8 - DB 68,15,88,5,247,45,0,0 ; addps 0x2df7(%rip),%xmm8 # 4900 <_sk_callback_sse41+0x469> + DB 68,15,88,5,39,48,0,0 ; addps 0x3027(%rip),%xmm8 # 4b30 <_sk_callback_sse41+0x45d> DB 102,68,15,56,20,194 ; blendvps %xmm0,%xmm2,%xmm8 DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 102,69,15,56,20,199 ; blendvps %xmm0,%xmm15,%xmm8 - DB 68,15,89,5,239,45,0,0 ; mulps 0x2def(%rip),%xmm8 # 4910 <_sk_callback_sse41+0x479> + DB 68,15,89,5,31,48,0,0 ; mulps 0x301f(%rip),%xmm8 # 4b40 <_sk_callback_sse41+0x46d> DB 69,15,40,203 ; movaps %xmm11,%xmm9 DB 69,15,194,204,4 ; cmpneqps %xmm12,%xmm9 DB 69,15,84,193 ; andps %xmm9,%xmm8 DB 69,15,92,235 ; subps %xmm11,%xmm13 DB 69,15,88,220 ; addps %xmm12,%xmm11 - DB 15,40,5,227,45,0,0 ; movaps 0x2de3(%rip),%xmm0 # 4920 <_sk_callback_sse41+0x489> + DB 15,40,5,19,48,0,0 ; movaps 0x3013(%rip),%xmm0 # 4b50 <_sk_callback_sse41+0x47d> DB 65,15,40,211 ; movaps %xmm11,%xmm2 DB 15,89,208 ; mulps %xmm0,%xmm2 DB 15,194,194,1 ; cmpltps %xmm2,%xmm0 @@ -12798,7 +13178,7 @@ _sk_hsl_to_rgb_sse41 LABEL PROC DB 15,41,100,36,32 ; movaps %xmm4,0x20(%rsp) DB 15,41,92,36,16 ; movaps %xmm3,0x10(%rsp) DB 68,15,40,208 ; movaps %xmm0,%xmm10 - DB 68,15,40,13,165,45,0,0 ; movaps 0x2da5(%rip),%xmm9 # 4930 <_sk_callback_sse41+0x499> + DB 68,15,40,13,213,47,0,0 ; movaps 0x2fd5(%rip),%xmm9 # 4b60 <_sk_callback_sse41+0x48d> DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 15,194,194,2 ; cmpleps %xmm2,%xmm0 DB 15,40,217 ; movaps %xmm1,%xmm3 @@ -12811,19 +13191,19 @@ _sk_hsl_to_rgb_sse41 LABEL PROC DB 15,41,20,36 ; movaps %xmm2,(%rsp) DB 69,15,88,192 ; addps %xmm8,%xmm8 DB 68,15,92,197 ; subps %xmm5,%xmm8 - DB 68,15,40,53,129,45,0,0 ; movaps 0x2d81(%rip),%xmm14 # 4940 <_sk_callback_sse41+0x4a9> + DB 68,15,40,53,177,47,0,0 ; movaps 0x2fb1(%rip),%xmm14 # 4b70 <_sk_callback_sse41+0x49d> DB 69,15,88,242 ; addps %xmm10,%xmm14 DB 102,65,15,58,8,198,1 ; roundps $0x1,%xmm14,%xmm0 DB 68,15,92,240 ; subps %xmm0,%xmm14 - DB 68,15,40,29,122,45,0,0 ; movaps 0x2d7a(%rip),%xmm11 # 4950 <_sk_callback_sse41+0x4b9> + DB 68,15,40,29,170,47,0,0 ; movaps 0x2faa(%rip),%xmm11 # 4b80 <_sk_callback_sse41+0x4ad> DB 65,15,40,195 ; movaps %xmm11,%xmm0 DB 65,15,194,198,2 ; cmpleps %xmm14,%xmm0 DB 15,40,245 ; movaps %xmm5,%xmm6 DB 65,15,92,240 ; subps %xmm8,%xmm6 - DB 15,40,61,115,45,0,0 ; movaps 0x2d73(%rip),%xmm7 # 4960 <_sk_callback_sse41+0x4c9> + DB 15,40,61,163,47,0,0 ; movaps 0x2fa3(%rip),%xmm7 # 4b90 <_sk_callback_sse41+0x4bd> DB 69,15,40,238 ; movaps %xmm14,%xmm13 DB 68,15,89,239 ; mulps %xmm7,%xmm13 - DB 15,40,29,116,45,0,0 ; movaps 0x2d74(%rip),%xmm3 # 4970 <_sk_callback_sse41+0x4d9> + DB 15,40,29,164,47,0,0 ; movaps 0x2fa4(%rip),%xmm3 # 4ba0 <_sk_callback_sse41+0x4cd> DB 68,15,40,227 ; movaps %xmm3,%xmm12 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 68,15,89,230 ; mulps %xmm6,%xmm12 @@ -12833,7 +13213,7 @@ _sk_hsl_to_rgb_sse41 LABEL PROC DB 65,15,194,198,2 ; cmpleps %xmm14,%xmm0 DB 68,15,40,253 ; movaps %xmm5,%xmm15 DB 102,69,15,56,20,252 ; blendvps %xmm0,%xmm12,%xmm15 - DB 68,15,40,37,83,45,0,0 ; movaps 0x2d53(%rip),%xmm12 # 4980 <_sk_callback_sse41+0x4e9> + DB 68,15,40,37,131,47,0,0 ; movaps 0x2f83(%rip),%xmm12 # 4bb0 <_sk_callback_sse41+0x4dd> DB 65,15,40,196 ; movaps %xmm12,%xmm0 DB 65,15,194,198,2 ; cmpleps %xmm14,%xmm0 DB 68,15,89,238 ; mulps %xmm6,%xmm13 @@ -12867,7 +13247,7 @@ _sk_hsl_to_rgb_sse41 LABEL PROC DB 65,15,40,198 ; movaps %xmm14,%xmm0 DB 15,40,20,36 ; movaps (%rsp),%xmm2 DB 102,15,56,20,202 ; blendvps %xmm0,%xmm2,%xmm1 - DB 68,15,88,21,204,44,0,0 ; addps 0x2ccc(%rip),%xmm10 # 4990 <_sk_callback_sse41+0x4f9> + DB 68,15,88,21,252,46,0,0 ; addps 0x2efc(%rip),%xmm10 # 4bc0 <_sk_callback_sse41+0x4ed> DB 102,65,15,58,8,194,1 ; roundps $0x1,%xmm10,%xmm0 DB 68,15,92,208 ; subps %xmm0,%xmm10 DB 69,15,194,218,2 ; cmpleps %xmm10,%xmm11 @@ -12916,7 +13296,7 @@ _sk_scale_u8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,68,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,37,44,0,0 ; mulps 0x2c25(%rip),%xmm8 # 49a0 <_sk_callback_sse41+0x509> + DB 68,15,89,5,85,46,0,0 ; mulps 0x2e55(%rip),%xmm8 # 4bd0 <_sk_callback_sse41+0x4fd> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 65,15,89,208 ; mulps %xmm8,%xmm2 @@ -12950,7 +13330,7 @@ _sk_lerp_u8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,68,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,209,43,0,0 ; mulps 0x2bd1(%rip),%xmm8 # 49b0 <_sk_callback_sse41+0x519> + DB 68,15,89,5,1,46,0,0 ; mulps 0x2e01(%rip),%xmm8 # 4be0 <_sk_callback_sse41+0x50d> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -12971,17 +13351,17 @@ _sk_lerp_565_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 102,68,15,56,51,20,120 ; pmovzxwd (%rax,%rdi,2),%xmm10 - DB 102,68,15,111,5,160,43,0,0 ; movdqa 0x2ba0(%rip),%xmm8 # 49c0 <_sk_callback_sse41+0x529> + DB 102,68,15,111,5,208,45,0,0 ; movdqa 0x2dd0(%rip),%xmm8 # 4bf0 <_sk_callback_sse41+0x51d> DB 102,69,15,219,194 ; pand %xmm10,%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,159,43,0,0 ; mulps 0x2b9f(%rip),%xmm8 # 49d0 <_sk_callback_sse41+0x539> - DB 102,68,15,111,13,166,43,0,0 ; movdqa 0x2ba6(%rip),%xmm9 # 49e0 <_sk_callback_sse41+0x549> + DB 68,15,89,5,207,45,0,0 ; mulps 0x2dcf(%rip),%xmm8 # 4c00 <_sk_callback_sse41+0x52d> + DB 102,68,15,111,13,214,45,0,0 ; movdqa 0x2dd6(%rip),%xmm9 # 4c10 <_sk_callback_sse41+0x53d> DB 102,69,15,219,202 ; pand %xmm10,%xmm9 DB 69,15,91,201 ; cvtdq2ps %xmm9,%xmm9 - DB 68,15,89,13,165,43,0,0 ; mulps 0x2ba5(%rip),%xmm9 # 49f0 <_sk_callback_sse41+0x559> - DB 102,68,15,219,21,172,43,0,0 ; pand 0x2bac(%rip),%xmm10 # 4a00 <_sk_callback_sse41+0x569> + DB 68,15,89,13,213,45,0,0 ; mulps 0x2dd5(%rip),%xmm9 # 4c20 <_sk_callback_sse41+0x54d> + DB 102,68,15,219,21,220,45,0,0 ; pand 0x2ddc(%rip),%xmm10 # 4c30 <_sk_callback_sse41+0x55d> DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 - DB 68,15,89,21,176,43,0,0 ; mulps 0x2bb0(%rip),%xmm10 # 4a10 <_sk_callback_sse41+0x579> + DB 68,15,89,21,224,45,0,0 ; mulps 0x2de0(%rip),%xmm10 # 4c40 <_sk_callback_sse41+0x56d> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -13010,7 +13390,7 @@ _sk_load_tables_sse41 LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,139,72,8 ; mov 0x8(%rax),%r9 DB 243,69,15,111,4,184 ; movdqu (%r8,%rdi,4),%xmm8 - DB 102,15,111,5,97,43,0,0 ; movdqa 0x2b61(%rip),%xmm0 # 4a20 <_sk_callback_sse41+0x589> + DB 102,15,111,5,145,45,0,0 ; movdqa 0x2d91(%rip),%xmm0 # 4c50 <_sk_callback_sse41+0x57d> DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,73,15,58,22,192,1 ; pextrq $0x1,%xmm0,%r8 DB 102,72,15,126,193 ; movq %xmm0,%rcx @@ -13025,7 +13405,7 @@ _sk_load_tables_sse41 LABEL PROC DB 102,15,58,33,193,48 ; insertps $0x30,%xmm1,%xmm0 DB 76,139,64,16 ; mov 0x10(%rax),%r8 DB 102,65,15,111,200 ; movdqa %xmm8,%xmm1 - DB 102,15,56,0,13,28,43,0,0 ; pshufb 0x2b1c(%rip),%xmm1 # 4a30 <_sk_callback_sse41+0x599> + DB 102,15,56,0,13,76,45,0,0 ; pshufb 0x2d4c(%rip),%xmm1 # 4c60 <_sk_callback_sse41+0x58d> DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 DB 102,72,15,126,201 ; movq %xmm1,%rcx DB 68,15,182,209 ; movzbl %cl,%r10d @@ -13040,7 +13420,7 @@ _sk_load_tables_sse41 LABEL PROC DB 102,15,58,33,202,48 ; insertps $0x30,%xmm2,%xmm1 DB 76,139,64,24 ; mov 0x18(%rax),%r8 DB 102,65,15,111,208 ; movdqa %xmm8,%xmm2 - DB 102,15,56,0,21,216,42,0,0 ; pshufb 0x2ad8(%rip),%xmm2 # 4a40 <_sk_callback_sse41+0x5a9> + DB 102,15,56,0,21,8,45,0,0 ; pshufb 0x2d08(%rip),%xmm2 # 4c70 <_sk_callback_sse41+0x59d> DB 102,72,15,58,22,209,1 ; pextrq $0x1,%xmm2,%rcx DB 102,72,15,126,208 ; movq %xmm2,%rax DB 68,15,182,200 ; movzbl %al,%r9d @@ -13055,7 +13435,7 @@ _sk_load_tables_sse41 LABEL PROC DB 102,15,58,33,211,48 ; insertps $0x30,%xmm3,%xmm2 DB 102,65,15,114,208,24 ; psrld $0x18,%xmm8 DB 65,15,91,216 ; cvtdq2ps %xmm8,%xmm3 - DB 15,89,29,149,42,0,0 ; mulps 0x2a95(%rip),%xmm3 # 4a50 <_sk_callback_sse41+0x5b9> + DB 15,89,29,197,44,0,0 ; mulps 0x2cc5(%rip),%xmm3 # 4c80 <_sk_callback_sse41+0x5ad> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13072,7 +13452,7 @@ _sk_load_tables_u16_be_sse41 LABEL PROC DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,97,200 ; punpcklwd %xmm0,%xmm1 DB 102,68,15,105,200 ; punpckhwd %xmm0,%xmm9 - DB 102,68,15,111,5,104,42,0,0 ; movdqa 0x2a68(%rip),%xmm8 # 4a60 <_sk_callback_sse41+0x5c9> + DB 102,68,15,111,5,152,44,0,0 ; movdqa 0x2c98(%rip),%xmm8 # 4c90 <_sk_callback_sse41+0x5bd> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,15,56,51,192 ; pmovzxwd %xmm0,%xmm0 @@ -13089,7 +13469,7 @@ _sk_load_tables_u16_be_sse41 LABEL PROC DB 243,67,15,16,20,8 ; movss (%r8,%r9,1),%xmm2 DB 102,15,58,33,194,48 ; insertps $0x30,%xmm2,%xmm0 DB 76,139,64,16 ; mov 0x10(%rax),%r8 - DB 102,15,56,0,13,27,42,0,0 ; pshufb 0x2a1b(%rip),%xmm1 # 4a70 <_sk_callback_sse41+0x5d9> + DB 102,15,56,0,13,75,44,0,0 ; pshufb 0x2c4b(%rip),%xmm1 # 4ca0 <_sk_callback_sse41+0x5cd> DB 102,15,56,51,201 ; pmovzxwd %xmm1,%xmm1 DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 DB 102,72,15,126,201 ; movq %xmm1,%rcx @@ -13125,7 +13505,7 @@ _sk_load_tables_u16_be_sse41 LABEL PROC DB 102,65,15,235,216 ; por %xmm8,%xmm3 DB 102,15,56,51,219 ; pmovzxwd %xmm3,%xmm3 DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,105,41,0,0 ; mulps 0x2969(%rip),%xmm3 # 4a80 <_sk_callback_sse41+0x5e9> + DB 15,89,29,153,43,0,0 ; mulps 0x2b99(%rip),%xmm3 # 4cb0 <_sk_callback_sse41+0x5dd> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13145,7 +13525,7 @@ _sk_load_tables_rgb_u16_be_sse41 LABEL PROC DB 102,68,15,97,200 ; punpcklwd %xmm0,%xmm9 DB 102,15,111,202 ; movdqa %xmm2,%xmm1 DB 102,65,15,97,201 ; punpcklwd %xmm9,%xmm1 - DB 102,68,15,111,5,43,41,0,0 ; movdqa 0x292b(%rip),%xmm8 # 4a90 <_sk_callback_sse41+0x5f9> + DB 102,68,15,111,5,91,43,0,0 ; movdqa 0x2b5b(%rip),%xmm8 # 4cc0 <_sk_callback_sse41+0x5ed> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,15,56,51,192 ; pmovzxwd %xmm0,%xmm0 @@ -13162,7 +13542,7 @@ _sk_load_tables_rgb_u16_be_sse41 LABEL PROC DB 243,67,15,16,28,8 ; movss (%r8,%r9,1),%xmm3 DB 102,15,58,33,195,48 ; insertps $0x30,%xmm3,%xmm0 DB 76,139,64,16 ; mov 0x10(%rax),%r8 - DB 102,15,56,0,13,222,40,0,0 ; pshufb 0x28de(%rip),%xmm1 # 4aa0 <_sk_callback_sse41+0x609> + DB 102,15,56,0,13,14,43,0,0 ; pshufb 0x2b0e(%rip),%xmm1 # 4cd0 <_sk_callback_sse41+0x5fd> DB 102,15,56,51,201 ; pmovzxwd %xmm1,%xmm1 DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 DB 102,72,15,126,201 ; movq %xmm1,%rcx @@ -13193,7 +13573,7 @@ _sk_load_tables_rgb_u16_be_sse41 LABEL PROC DB 243,65,15,16,28,8 ; movss (%r8,%rcx,1),%xmm3 DB 102,15,58,33,211,48 ; insertps $0x30,%xmm3,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,73,40,0,0 ; movaps 0x2849(%rip),%xmm3 # 4ab0 <_sk_callback_sse41+0x619> + DB 15,40,29,121,42,0,0 ; movaps 0x2a79(%rip),%xmm3 # 4ce0 <_sk_callback_sse41+0x60d> DB 255,224 ; jmpq *%rax PUBLIC _sk_byte_tables_sse41 @@ -13201,7 +13581,7 @@ _sk_byte_tables_sse41 LABEL PROC DB 65,86 ; push %r14 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,74,40,0,0 ; movaps 0x284a(%rip),%xmm8 # 4ac0 <_sk_callback_sse41+0x629> + DB 68,15,40,5,122,42,0,0 ; movaps 0x2a7a(%rip),%xmm8 # 4cf0 <_sk_callback_sse41+0x61d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,91,192 ; cvtps2dq %xmm0,%xmm0 DB 102,72,15,58,22,193,1 ; pextrq $0x1,%xmm0,%rcx @@ -13220,7 +13600,7 @@ _sk_byte_tables_sse41 LABEL PROC DB 102,15,58,32,193,3 ; pinsrb $0x3,%ecx,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,13,251,39,0,0 ; movaps 0x27fb(%rip),%xmm9 # 4ad0 <_sk_callback_sse41+0x639> + DB 68,15,40,13,43,42,0,0 ; movaps 0x2a2b(%rip),%xmm9 # 4d00 <_sk_callback_sse41+0x62d> DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -13309,7 +13689,7 @@ _sk_byte_tables_rgb_sse41 LABEL PROC DB 102,15,58,32,193,3 ; pinsrb $0x3,%ecx,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,13,131,38,0,0 ; movaps 0x2683(%rip),%xmm9 # 4ae0 <_sk_callback_sse41+0x649> + DB 68,15,40,13,179,40,0,0 ; movaps 0x28b3(%rip),%xmm9 # 4d10 <_sk_callback_sse41+0x63d> DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -13476,31 +13856,31 @@ _sk_parametric_r_sse41 LABEL PROC DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,194 ; cvtdq2ps %xmm10,%xmm8 - DB 68,15,89,5,218,35,0,0 ; mulps 0x23da(%rip),%xmm8 # 4af0 <_sk_callback_sse41+0x659> - DB 68,15,84,21,226,35,0,0 ; andps 0x23e2(%rip),%xmm10 # 4b00 <_sk_callback_sse41+0x669> - DB 68,15,86,21,234,35,0,0 ; orps 0x23ea(%rip),%xmm10 # 4b10 <_sk_callback_sse41+0x679> - DB 68,15,88,5,242,35,0,0 ; addps 0x23f2(%rip),%xmm8 # 4b20 <_sk_callback_sse41+0x689> - DB 68,15,40,37,250,35,0,0 ; movaps 0x23fa(%rip),%xmm12 # 4b30 <_sk_callback_sse41+0x699> + DB 68,15,89,5,10,38,0,0 ; mulps 0x260a(%rip),%xmm8 # 4d20 <_sk_callback_sse41+0x64d> + DB 68,15,84,21,18,38,0,0 ; andps 0x2612(%rip),%xmm10 # 4d30 <_sk_callback_sse41+0x65d> + DB 68,15,86,21,26,38,0,0 ; orps 0x261a(%rip),%xmm10 # 4d40 <_sk_callback_sse41+0x66d> + DB 68,15,88,5,34,38,0,0 ; addps 0x2622(%rip),%xmm8 # 4d50 <_sk_callback_sse41+0x67d> + DB 68,15,40,37,42,38,0,0 ; movaps 0x262a(%rip),%xmm12 # 4d60 <_sk_callback_sse41+0x68d> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,196 ; subps %xmm12,%xmm8 - DB 68,15,88,21,250,35,0,0 ; addps 0x23fa(%rip),%xmm10 # 4b40 <_sk_callback_sse41+0x6a9> - DB 68,15,40,37,2,36,0,0 ; movaps 0x2402(%rip),%xmm12 # 4b50 <_sk_callback_sse41+0x6b9> + DB 68,15,88,21,42,38,0,0 ; addps 0x262a(%rip),%xmm10 # 4d70 <_sk_callback_sse41+0x69d> + DB 68,15,40,37,50,38,0,0 ; movaps 0x2632(%rip),%xmm12 # 4d80 <_sk_callback_sse41+0x6ad> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,196 ; subps %xmm12,%xmm8 DB 69,15,89,195 ; mulps %xmm11,%xmm8 DB 102,69,15,58,8,208,1 ; roundps $0x1,%xmm8,%xmm10 DB 69,15,40,216 ; movaps %xmm8,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,5,239,35,0,0 ; addps 0x23ef(%rip),%xmm8 # 4b60 <_sk_callback_sse41+0x6c9> - DB 68,15,40,21,247,35,0,0 ; movaps 0x23f7(%rip),%xmm10 # 4b70 <_sk_callback_sse41+0x6d9> + DB 68,15,88,5,31,38,0,0 ; addps 0x261f(%rip),%xmm8 # 4d90 <_sk_callback_sse41+0x6bd> + DB 68,15,40,21,39,38,0,0 ; movaps 0x2627(%rip),%xmm10 # 4da0 <_sk_callback_sse41+0x6cd> DB 69,15,89,211 ; mulps %xmm11,%xmm10 DB 69,15,92,194 ; subps %xmm10,%xmm8 - DB 68,15,40,21,247,35,0,0 ; movaps 0x23f7(%rip),%xmm10 # 4b80 <_sk_callback_sse41+0x6e9> + DB 68,15,40,21,39,38,0,0 ; movaps 0x2627(%rip),%xmm10 # 4db0 <_sk_callback_sse41+0x6dd> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 68,15,40,29,251,35,0,0 ; movaps 0x23fb(%rip),%xmm11 # 4b90 <_sk_callback_sse41+0x6f9> + DB 68,15,40,29,43,38,0,0 ; movaps 0x262b(%rip),%xmm11 # 4dc0 <_sk_callback_sse41+0x6ed> DB 69,15,94,218 ; divps %xmm10,%xmm11 DB 69,15,88,216 ; addps %xmm8,%xmm11 - DB 68,15,89,29,251,35,0,0 ; mulps 0x23fb(%rip),%xmm11 # 4ba0 <_sk_callback_sse41+0x709> + DB 68,15,89,29,43,38,0,0 ; mulps 0x262b(%rip),%xmm11 # 4dd0 <_sk_callback_sse41+0x6fd> DB 102,69,15,91,211 ; cvtps2dq %xmm11,%xmm10 DB 243,68,15,16,64,20 ; movss 0x14(%rax),%xmm8 DB 69,15,198,192,0 ; shufps $0x0,%xmm8,%xmm8 @@ -13508,7 +13888,7 @@ _sk_parametric_r_sse41 LABEL PROC DB 102,69,15,56,20,193 ; blendvps %xmm0,%xmm9,%xmm8 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 68,15,95,192 ; maxps %xmm0,%xmm8 - DB 68,15,93,5,226,35,0,0 ; minps 0x23e2(%rip),%xmm8 # 4bb0 <_sk_callback_sse41+0x719> + DB 68,15,93,5,18,38,0,0 ; minps 0x2612(%rip),%xmm8 # 4de0 <_sk_callback_sse41+0x70d> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -13536,31 +13916,31 @@ _sk_parametric_g_sse41 LABEL PROC DB 68,15,88,217 ; addps %xmm1,%xmm11 DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 DB 69,15,91,227 ; cvtdq2ps %xmm11,%xmm12 - DB 68,15,89,37,131,35,0,0 ; mulps 0x2383(%rip),%xmm12 # 4bc0 <_sk_callback_sse41+0x729> - DB 68,15,84,29,139,35,0,0 ; andps 0x238b(%rip),%xmm11 # 4bd0 <_sk_callback_sse41+0x739> - DB 68,15,86,29,147,35,0,0 ; orps 0x2393(%rip),%xmm11 # 4be0 <_sk_callback_sse41+0x749> - DB 68,15,88,37,155,35,0,0 ; addps 0x239b(%rip),%xmm12 # 4bf0 <_sk_callback_sse41+0x759> - DB 15,40,13,164,35,0,0 ; movaps 0x23a4(%rip),%xmm1 # 4c00 <_sk_callback_sse41+0x769> + DB 68,15,89,37,179,37,0,0 ; mulps 0x25b3(%rip),%xmm12 # 4df0 <_sk_callback_sse41+0x71d> + DB 68,15,84,29,187,37,0,0 ; andps 0x25bb(%rip),%xmm11 # 4e00 <_sk_callback_sse41+0x72d> + DB 68,15,86,29,195,37,0,0 ; orps 0x25c3(%rip),%xmm11 # 4e10 <_sk_callback_sse41+0x73d> + DB 68,15,88,37,203,37,0,0 ; addps 0x25cb(%rip),%xmm12 # 4e20 <_sk_callback_sse41+0x74d> + DB 15,40,13,212,37,0,0 ; movaps 0x25d4(%rip),%xmm1 # 4e30 <_sk_callback_sse41+0x75d> DB 65,15,89,203 ; mulps %xmm11,%xmm1 DB 68,15,92,225 ; subps %xmm1,%xmm12 - DB 68,15,88,29,164,35,0,0 ; addps 0x23a4(%rip),%xmm11 # 4c10 <_sk_callback_sse41+0x779> - DB 15,40,13,173,35,0,0 ; movaps 0x23ad(%rip),%xmm1 # 4c20 <_sk_callback_sse41+0x789> + DB 68,15,88,29,212,37,0,0 ; addps 0x25d4(%rip),%xmm11 # 4e40 <_sk_callback_sse41+0x76d> + DB 15,40,13,221,37,0,0 ; movaps 0x25dd(%rip),%xmm1 # 4e50 <_sk_callback_sse41+0x77d> DB 65,15,94,203 ; divps %xmm11,%xmm1 DB 68,15,92,225 ; subps %xmm1,%xmm12 DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 102,69,15,58,8,212,1 ; roundps $0x1,%xmm12,%xmm10 DB 69,15,40,220 ; movaps %xmm12,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,37,154,35,0,0 ; addps 0x239a(%rip),%xmm12 # 4c30 <_sk_callback_sse41+0x799> - DB 15,40,13,163,35,0,0 ; movaps 0x23a3(%rip),%xmm1 # 4c40 <_sk_callback_sse41+0x7a9> + DB 68,15,88,37,202,37,0,0 ; addps 0x25ca(%rip),%xmm12 # 4e60 <_sk_callback_sse41+0x78d> + DB 15,40,13,211,37,0,0 ; movaps 0x25d3(%rip),%xmm1 # 4e70 <_sk_callback_sse41+0x79d> DB 65,15,89,203 ; mulps %xmm11,%xmm1 DB 68,15,92,225 ; subps %xmm1,%xmm12 - DB 68,15,40,21,163,35,0,0 ; movaps 0x23a3(%rip),%xmm10 # 4c50 <_sk_callback_sse41+0x7b9> + DB 68,15,40,21,211,37,0,0 ; movaps 0x25d3(%rip),%xmm10 # 4e80 <_sk_callback_sse41+0x7ad> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 15,40,13,168,35,0,0 ; movaps 0x23a8(%rip),%xmm1 # 4c60 <_sk_callback_sse41+0x7c9> + DB 15,40,13,216,37,0,0 ; movaps 0x25d8(%rip),%xmm1 # 4e90 <_sk_callback_sse41+0x7bd> DB 65,15,94,202 ; divps %xmm10,%xmm1 DB 65,15,88,204 ; addps %xmm12,%xmm1 - DB 15,89,13,169,35,0,0 ; mulps 0x23a9(%rip),%xmm1 # 4c70 <_sk_callback_sse41+0x7d9> + DB 15,89,13,217,37,0,0 ; mulps 0x25d9(%rip),%xmm1 # 4ea0 <_sk_callback_sse41+0x7cd> DB 102,68,15,91,209 ; cvtps2dq %xmm1,%xmm10 DB 243,15,16,72,20 ; movss 0x14(%rax),%xmm1 DB 15,198,201,0 ; shufps $0x0,%xmm1,%xmm1 @@ -13568,7 +13948,7 @@ _sk_parametric_g_sse41 LABEL PROC DB 102,65,15,56,20,201 ; blendvps %xmm0,%xmm9,%xmm1 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,95,200 ; maxps %xmm0,%xmm1 - DB 15,93,13,148,35,0,0 ; minps 0x2394(%rip),%xmm1 # 4c80 <_sk_callback_sse41+0x7e9> + DB 15,93,13,196,37,0,0 ; minps 0x25c4(%rip),%xmm1 # 4eb0 <_sk_callback_sse41+0x7dd> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -13596,31 +13976,31 @@ _sk_parametric_b_sse41 LABEL PROC DB 68,15,88,218 ; addps %xmm2,%xmm11 DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 DB 69,15,91,227 ; cvtdq2ps %xmm11,%xmm12 - DB 68,15,89,37,53,35,0,0 ; mulps 0x2335(%rip),%xmm12 # 4c90 <_sk_callback_sse41+0x7f9> - DB 68,15,84,29,61,35,0,0 ; andps 0x233d(%rip),%xmm11 # 4ca0 <_sk_callback_sse41+0x809> - DB 68,15,86,29,69,35,0,0 ; orps 0x2345(%rip),%xmm11 # 4cb0 <_sk_callback_sse41+0x819> - DB 68,15,88,37,77,35,0,0 ; addps 0x234d(%rip),%xmm12 # 4cc0 <_sk_callback_sse41+0x829> - DB 15,40,21,86,35,0,0 ; movaps 0x2356(%rip),%xmm2 # 4cd0 <_sk_callback_sse41+0x839> + DB 68,15,89,37,101,37,0,0 ; mulps 0x2565(%rip),%xmm12 # 4ec0 <_sk_callback_sse41+0x7ed> + DB 68,15,84,29,109,37,0,0 ; andps 0x256d(%rip),%xmm11 # 4ed0 <_sk_callback_sse41+0x7fd> + DB 68,15,86,29,117,37,0,0 ; orps 0x2575(%rip),%xmm11 # 4ee0 <_sk_callback_sse41+0x80d> + DB 68,15,88,37,125,37,0,0 ; addps 0x257d(%rip),%xmm12 # 4ef0 <_sk_callback_sse41+0x81d> + DB 15,40,21,134,37,0,0 ; movaps 0x2586(%rip),%xmm2 # 4f00 <_sk_callback_sse41+0x82d> DB 65,15,89,211 ; mulps %xmm11,%xmm2 DB 68,15,92,226 ; subps %xmm2,%xmm12 - DB 68,15,88,29,86,35,0,0 ; addps 0x2356(%rip),%xmm11 # 4ce0 <_sk_callback_sse41+0x849> - DB 15,40,21,95,35,0,0 ; movaps 0x235f(%rip),%xmm2 # 4cf0 <_sk_callback_sse41+0x859> + DB 68,15,88,29,134,37,0,0 ; addps 0x2586(%rip),%xmm11 # 4f10 <_sk_callback_sse41+0x83d> + DB 15,40,21,143,37,0,0 ; movaps 0x258f(%rip),%xmm2 # 4f20 <_sk_callback_sse41+0x84d> DB 65,15,94,211 ; divps %xmm11,%xmm2 DB 68,15,92,226 ; subps %xmm2,%xmm12 DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 102,69,15,58,8,212,1 ; roundps $0x1,%xmm12,%xmm10 DB 69,15,40,220 ; movaps %xmm12,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,37,76,35,0,0 ; addps 0x234c(%rip),%xmm12 # 4d00 <_sk_callback_sse41+0x869> - DB 15,40,21,85,35,0,0 ; movaps 0x2355(%rip),%xmm2 # 4d10 <_sk_callback_sse41+0x879> + DB 68,15,88,37,124,37,0,0 ; addps 0x257c(%rip),%xmm12 # 4f30 <_sk_callback_sse41+0x85d> + DB 15,40,21,133,37,0,0 ; movaps 0x2585(%rip),%xmm2 # 4f40 <_sk_callback_sse41+0x86d> DB 65,15,89,211 ; mulps %xmm11,%xmm2 DB 68,15,92,226 ; subps %xmm2,%xmm12 - DB 68,15,40,21,85,35,0,0 ; movaps 0x2355(%rip),%xmm10 # 4d20 <_sk_callback_sse41+0x889> + DB 68,15,40,21,133,37,0,0 ; movaps 0x2585(%rip),%xmm10 # 4f50 <_sk_callback_sse41+0x87d> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 15,40,21,90,35,0,0 ; movaps 0x235a(%rip),%xmm2 # 4d30 <_sk_callback_sse41+0x899> + DB 15,40,21,138,37,0,0 ; movaps 0x258a(%rip),%xmm2 # 4f60 <_sk_callback_sse41+0x88d> DB 65,15,94,210 ; divps %xmm10,%xmm2 DB 65,15,88,212 ; addps %xmm12,%xmm2 - DB 15,89,21,91,35,0,0 ; mulps 0x235b(%rip),%xmm2 # 4d40 <_sk_callback_sse41+0x8a9> + DB 15,89,21,139,37,0,0 ; mulps 0x258b(%rip),%xmm2 # 4f70 <_sk_callback_sse41+0x89d> DB 102,68,15,91,210 ; cvtps2dq %xmm2,%xmm10 DB 243,15,16,80,20 ; movss 0x14(%rax),%xmm2 DB 15,198,210,0 ; shufps $0x0,%xmm2,%xmm2 @@ -13628,7 +14008,7 @@ _sk_parametric_b_sse41 LABEL PROC DB 102,65,15,56,20,209 ; blendvps %xmm0,%xmm9,%xmm2 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,95,208 ; maxps %xmm0,%xmm2 - DB 15,93,21,70,35,0,0 ; minps 0x2346(%rip),%xmm2 # 4d50 <_sk_callback_sse41+0x8b9> + DB 15,93,21,118,37,0,0 ; minps 0x2576(%rip),%xmm2 # 4f80 <_sk_callback_sse41+0x8ad> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -13656,31 +14036,31 @@ _sk_parametric_a_sse41 LABEL PROC DB 68,15,88,219 ; addps %xmm3,%xmm11 DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 DB 69,15,91,227 ; cvtdq2ps %xmm11,%xmm12 - DB 68,15,89,37,231,34,0,0 ; mulps 0x22e7(%rip),%xmm12 # 4d60 <_sk_callback_sse41+0x8c9> - DB 68,15,84,29,239,34,0,0 ; andps 0x22ef(%rip),%xmm11 # 4d70 <_sk_callback_sse41+0x8d9> - DB 68,15,86,29,247,34,0,0 ; orps 0x22f7(%rip),%xmm11 # 4d80 <_sk_callback_sse41+0x8e9> - DB 68,15,88,37,255,34,0,0 ; addps 0x22ff(%rip),%xmm12 # 4d90 <_sk_callback_sse41+0x8f9> - DB 15,40,29,8,35,0,0 ; movaps 0x2308(%rip),%xmm3 # 4da0 <_sk_callback_sse41+0x909> + DB 68,15,89,37,23,37,0,0 ; mulps 0x2517(%rip),%xmm12 # 4f90 <_sk_callback_sse41+0x8bd> + DB 68,15,84,29,31,37,0,0 ; andps 0x251f(%rip),%xmm11 # 4fa0 <_sk_callback_sse41+0x8cd> + DB 68,15,86,29,39,37,0,0 ; orps 0x2527(%rip),%xmm11 # 4fb0 <_sk_callback_sse41+0x8dd> + DB 68,15,88,37,47,37,0,0 ; addps 0x252f(%rip),%xmm12 # 4fc0 <_sk_callback_sse41+0x8ed> + DB 15,40,29,56,37,0,0 ; movaps 0x2538(%rip),%xmm3 # 4fd0 <_sk_callback_sse41+0x8fd> DB 65,15,89,219 ; mulps %xmm11,%xmm3 DB 68,15,92,227 ; subps %xmm3,%xmm12 - DB 68,15,88,29,8,35,0,0 ; addps 0x2308(%rip),%xmm11 # 4db0 <_sk_callback_sse41+0x919> - DB 15,40,29,17,35,0,0 ; movaps 0x2311(%rip),%xmm3 # 4dc0 <_sk_callback_sse41+0x929> + DB 68,15,88,29,56,37,0,0 ; addps 0x2538(%rip),%xmm11 # 4fe0 <_sk_callback_sse41+0x90d> + DB 15,40,29,65,37,0,0 ; movaps 0x2541(%rip),%xmm3 # 4ff0 <_sk_callback_sse41+0x91d> DB 65,15,94,219 ; divps %xmm11,%xmm3 DB 68,15,92,227 ; subps %xmm3,%xmm12 DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 102,69,15,58,8,212,1 ; roundps $0x1,%xmm12,%xmm10 DB 69,15,40,220 ; movaps %xmm12,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,37,254,34,0,0 ; addps 0x22fe(%rip),%xmm12 # 4dd0 <_sk_callback_sse41+0x939> - DB 15,40,29,7,35,0,0 ; movaps 0x2307(%rip),%xmm3 # 4de0 <_sk_callback_sse41+0x949> + DB 68,15,88,37,46,37,0,0 ; addps 0x252e(%rip),%xmm12 # 5000 <_sk_callback_sse41+0x92d> + DB 15,40,29,55,37,0,0 ; movaps 0x2537(%rip),%xmm3 # 5010 <_sk_callback_sse41+0x93d> DB 65,15,89,219 ; mulps %xmm11,%xmm3 DB 68,15,92,227 ; subps %xmm3,%xmm12 - DB 68,15,40,21,7,35,0,0 ; movaps 0x2307(%rip),%xmm10 # 4df0 <_sk_callback_sse41+0x959> + DB 68,15,40,21,55,37,0,0 ; movaps 0x2537(%rip),%xmm10 # 5020 <_sk_callback_sse41+0x94d> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 15,40,29,12,35,0,0 ; movaps 0x230c(%rip),%xmm3 # 4e00 <_sk_callback_sse41+0x969> + DB 15,40,29,60,37,0,0 ; movaps 0x253c(%rip),%xmm3 # 5030 <_sk_callback_sse41+0x95d> DB 65,15,94,218 ; divps %xmm10,%xmm3 DB 65,15,88,220 ; addps %xmm12,%xmm3 - DB 15,89,29,13,35,0,0 ; mulps 0x230d(%rip),%xmm3 # 4e10 <_sk_callback_sse41+0x979> + DB 15,89,29,61,37,0,0 ; mulps 0x253d(%rip),%xmm3 # 5040 <_sk_callback_sse41+0x96d> DB 102,68,15,91,211 ; cvtps2dq %xmm3,%xmm10 DB 243,15,16,88,20 ; movss 0x14(%rax),%xmm3 DB 15,198,219,0 ; shufps $0x0,%xmm3,%xmm3 @@ -13688,7 +14068,7 @@ _sk_parametric_a_sse41 LABEL PROC DB 102,65,15,56,20,217 ; blendvps %xmm0,%xmm9,%xmm3 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,95,216 ; maxps %xmm0,%xmm3 - DB 15,93,29,248,34,0,0 ; minps 0x22f8(%rip),%xmm3 # 4e20 <_sk_callback_sse41+0x989> + DB 15,93,29,40,37,0,0 ; minps 0x2528(%rip),%xmm3 # 5050 <_sk_callback_sse41+0x97d> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -13696,29 +14076,29 @@ _sk_parametric_a_sse41 LABEL PROC PUBLIC _sk_lab_to_xyz_sse41 _sk_lab_to_xyz_sse41 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,89,5,244,34,0,0 ; mulps 0x22f4(%rip),%xmm8 # 4e30 <_sk_callback_sse41+0x999> - DB 68,15,40,13,252,34,0,0 ; movaps 0x22fc(%rip),%xmm9 # 4e40 <_sk_callback_sse41+0x9a9> + DB 68,15,89,5,36,37,0,0 ; mulps 0x2524(%rip),%xmm8 # 5060 <_sk_callback_sse41+0x98d> + DB 68,15,40,13,44,37,0,0 ; movaps 0x252c(%rip),%xmm9 # 5070 <_sk_callback_sse41+0x99d> DB 65,15,89,201 ; mulps %xmm9,%xmm1 - DB 15,40,5,1,35,0,0 ; movaps 0x2301(%rip),%xmm0 # 4e50 <_sk_callback_sse41+0x9b9> + DB 15,40,5,49,37,0,0 ; movaps 0x2531(%rip),%xmm0 # 5080 <_sk_callback_sse41+0x9ad> DB 15,88,200 ; addps %xmm0,%xmm1 DB 65,15,89,209 ; mulps %xmm9,%xmm2 DB 15,88,208 ; addps %xmm0,%xmm2 - DB 68,15,88,5,255,34,0,0 ; addps 0x22ff(%rip),%xmm8 # 4e60 <_sk_callback_sse41+0x9c9> - DB 68,15,89,5,7,35,0,0 ; mulps 0x2307(%rip),%xmm8 # 4e70 <_sk_callback_sse41+0x9d9> - DB 15,89,13,16,35,0,0 ; mulps 0x2310(%rip),%xmm1 # 4e80 <_sk_callback_sse41+0x9e9> + DB 68,15,88,5,47,37,0,0 ; addps 0x252f(%rip),%xmm8 # 5090 <_sk_callback_sse41+0x9bd> + DB 68,15,89,5,55,37,0,0 ; mulps 0x2537(%rip),%xmm8 # 50a0 <_sk_callback_sse41+0x9cd> + DB 15,89,13,64,37,0,0 ; mulps 0x2540(%rip),%xmm1 # 50b0 <_sk_callback_sse41+0x9dd> DB 65,15,88,200 ; addps %xmm8,%xmm1 - DB 15,89,21,21,35,0,0 ; mulps 0x2315(%rip),%xmm2 # 4e90 <_sk_callback_sse41+0x9f9> + DB 15,89,21,69,37,0,0 ; mulps 0x2545(%rip),%xmm2 # 50c0 <_sk_callback_sse41+0x9ed> DB 69,15,40,208 ; movaps %xmm8,%xmm10 DB 68,15,92,210 ; subps %xmm2,%xmm10 DB 68,15,40,217 ; movaps %xmm1,%xmm11 DB 69,15,89,219 ; mulps %xmm11,%xmm11 DB 68,15,89,217 ; mulps %xmm1,%xmm11 - DB 68,15,40,13,9,35,0,0 ; movaps 0x2309(%rip),%xmm9 # 4ea0 <_sk_callback_sse41+0xa09> + DB 68,15,40,13,57,37,0,0 ; movaps 0x2539(%rip),%xmm9 # 50d0 <_sk_callback_sse41+0x9fd> DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 65,15,194,195,1 ; cmpltps %xmm11,%xmm0 - DB 15,40,21,9,35,0,0 ; movaps 0x2309(%rip),%xmm2 # 4eb0 <_sk_callback_sse41+0xa19> + DB 15,40,21,57,37,0,0 ; movaps 0x2539(%rip),%xmm2 # 50e0 <_sk_callback_sse41+0xa0d> DB 15,88,202 ; addps %xmm2,%xmm1 - DB 68,15,40,37,14,35,0,0 ; movaps 0x230e(%rip),%xmm12 # 4ec0 <_sk_callback_sse41+0xa29> + DB 68,15,40,37,62,37,0,0 ; movaps 0x253e(%rip),%xmm12 # 50f0 <_sk_callback_sse41+0xa1d> DB 65,15,89,204 ; mulps %xmm12,%xmm1 DB 102,65,15,56,20,203 ; blendvps %xmm0,%xmm11,%xmm1 DB 69,15,40,216 ; movaps %xmm8,%xmm11 @@ -13737,8 +14117,8 @@ _sk_lab_to_xyz_sse41 LABEL PROC DB 65,15,89,212 ; mulps %xmm12,%xmm2 DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 102,65,15,56,20,211 ; blendvps %xmm0,%xmm11,%xmm2 - DB 15,89,13,199,34,0,0 ; mulps 0x22c7(%rip),%xmm1 # 4ed0 <_sk_callback_sse41+0xa39> - DB 15,89,21,208,34,0,0 ; mulps 0x22d0(%rip),%xmm2 # 4ee0 <_sk_callback_sse41+0xa49> + DB 15,89,13,247,36,0,0 ; mulps 0x24f7(%rip),%xmm1 # 5100 <_sk_callback_sse41+0xa2d> + DB 15,89,21,0,37,0,0 ; mulps 0x2500(%rip),%xmm2 # 5110 <_sk_callback_sse41+0xa3d> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,40,193 ; movaps %xmm1,%xmm0 DB 65,15,40,200 ; movaps %xmm8,%xmm1 @@ -13750,7 +14130,7 @@ _sk_load_a8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,192,34,0,0 ; mulps 0x22c0(%rip),%xmm3 # 4ef0 <_sk_callback_sse41+0xa59> + DB 15,89,29,240,36,0,0 ; mulps 0x24f0(%rip),%xmm3 # 5120 <_sk_callback_sse41+0xa4d> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,87,201 ; xorps %xmm1,%xmm1 @@ -13781,7 +14161,7 @@ _sk_gather_a8_sse41 LABEL PROC DB 102,15,58,32,192,3 ; pinsrb $0x3,%eax,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,84,34,0,0 ; mulps 0x2254(%rip),%xmm3 # 4f00 <_sk_callback_sse41+0xa69> + DB 15,89,29,132,36,0,0 ; mulps 0x2484(%rip),%xmm3 # 5130 <_sk_callback_sse41+0xa5d> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 102,15,239,201 ; pxor %xmm1,%xmm1 @@ -13792,7 +14172,7 @@ PUBLIC _sk_store_a8_sse41 _sk_store_a8_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,72,34,0,0 ; movaps 0x2248(%rip),%xmm8 # 4f10 <_sk_callback_sse41+0xa79> + DB 68,15,40,5,120,36,0,0 ; movaps 0x2478(%rip),%xmm8 # 5140 <_sk_callback_sse41+0xa6d> DB 68,15,89,195 ; mulps %xmm3,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 DB 102,69,15,56,43,192 ; packusdw %xmm8,%xmm8 @@ -13807,9 +14187,9 @@ _sk_load_g8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,37,34,0,0 ; mulps 0x2225(%rip),%xmm0 # 4f20 <_sk_callback_sse41+0xa89> + DB 15,89,5,85,36,0,0 ; mulps 0x2455(%rip),%xmm0 # 5150 <_sk_callback_sse41+0xa7d> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,44,34,0,0 ; movaps 0x222c(%rip),%xmm3 # 4f30 <_sk_callback_sse41+0xa99> + DB 15,40,29,92,36,0,0 ; movaps 0x245c(%rip),%xmm3 # 5160 <_sk_callback_sse41+0xa8d> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -13838,9 +14218,9 @@ _sk_gather_g8_sse41 LABEL PROC DB 102,15,58,32,192,3 ; pinsrb $0x3,%eax,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,197,33,0,0 ; mulps 0x21c5(%rip),%xmm0 # 4f40 <_sk_callback_sse41+0xaa9> + DB 15,89,5,245,35,0,0 ; mulps 0x23f5(%rip),%xmm0 # 5170 <_sk_callback_sse41+0xa9d> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,204,33,0,0 ; movaps 0x21cc(%rip),%xmm3 # 4f50 <_sk_callback_sse41+0xab9> + DB 15,40,29,252,35,0,0 ; movaps 0x23fc(%rip),%xmm3 # 5180 <_sk_callback_sse41+0xaad> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -13883,17 +14263,17 @@ _sk_gather_i8_sse41 LABEL PROC DB 102,15,58,34,28,8,1 ; pinsrd $0x1,(%rax,%rcx,1),%xmm3 DB 102,66,15,58,34,28,144,2 ; pinsrd $0x2,(%rax,%r10,4),%xmm3 DB 102,66,15,58,34,28,8,3 ; pinsrd $0x3,(%rax,%r9,1),%xmm3 - DB 102,15,111,5,35,33,0,0 ; movdqa 0x2123(%rip),%xmm0 # 4f60 <_sk_callback_sse41+0xac9> + DB 102,15,111,5,83,35,0,0 ; movdqa 0x2353(%rip),%xmm0 # 5190 <_sk_callback_sse41+0xabd> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,36,33,0,0 ; movaps 0x2124(%rip),%xmm8 # 4f70 <_sk_callback_sse41+0xad9> + DB 68,15,40,5,84,35,0,0 ; movaps 0x2354(%rip),%xmm8 # 51a0 <_sk_callback_sse41+0xacd> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 - DB 102,15,56,0,13,35,33,0,0 ; pshufb 0x2123(%rip),%xmm1 # 4f80 <_sk_callback_sse41+0xae9> + DB 102,15,56,0,13,83,35,0,0 ; pshufb 0x2353(%rip),%xmm1 # 51b0 <_sk_callback_sse41+0xadd> DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,111,211 ; movdqa %xmm3,%xmm2 - DB 102,15,56,0,21,31,33,0,0 ; pshufb 0x211f(%rip),%xmm2 # 4f90 <_sk_callback_sse41+0xaf9> + DB 102,15,56,0,21,79,35,0,0 ; pshufb 0x234f(%rip),%xmm2 # 51c0 <_sk_callback_sse41+0xaed> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 102,15,114,211,24 ; psrld $0x18,%xmm3 @@ -13907,19 +14287,19 @@ _sk_load_565_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,51,20,120 ; pmovzxwd (%rax,%rdi,2),%xmm2 - DB 102,15,111,5,5,33,0,0 ; movdqa 0x2105(%rip),%xmm0 # 4fa0 <_sk_callback_sse41+0xb09> + DB 102,15,111,5,53,35,0,0 ; movdqa 0x2335(%rip),%xmm0 # 51d0 <_sk_callback_sse41+0xafd> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,7,33,0,0 ; mulps 0x2107(%rip),%xmm0 # 4fb0 <_sk_callback_sse41+0xb19> - DB 102,15,111,13,15,33,0,0 ; movdqa 0x210f(%rip),%xmm1 # 4fc0 <_sk_callback_sse41+0xb29> + DB 15,89,5,55,35,0,0 ; mulps 0x2337(%rip),%xmm0 # 51e0 <_sk_callback_sse41+0xb0d> + DB 102,15,111,13,63,35,0,0 ; movdqa 0x233f(%rip),%xmm1 # 51f0 <_sk_callback_sse41+0xb1d> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,17,33,0,0 ; mulps 0x2111(%rip),%xmm1 # 4fd0 <_sk_callback_sse41+0xb39> - DB 102,15,219,21,25,33,0,0 ; pand 0x2119(%rip),%xmm2 # 4fe0 <_sk_callback_sse41+0xb49> + DB 15,89,13,65,35,0,0 ; mulps 0x2341(%rip),%xmm1 # 5200 <_sk_callback_sse41+0xb2d> + DB 102,15,219,21,73,35,0,0 ; pand 0x2349(%rip),%xmm2 # 5210 <_sk_callback_sse41+0xb3d> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,31,33,0,0 ; mulps 0x211f(%rip),%xmm2 # 4ff0 <_sk_callback_sse41+0xb59> + DB 15,89,21,79,35,0,0 ; mulps 0x234f(%rip),%xmm2 # 5220 <_sk_callback_sse41+0xb4d> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,38,33,0,0 ; movaps 0x2126(%rip),%xmm3 # 5000 <_sk_callback_sse41+0xb69> + DB 15,40,29,86,35,0,0 ; movaps 0x2356(%rip),%xmm3 # 5230 <_sk_callback_sse41+0xb5d> DB 255,224 ; jmpq *%rax PUBLIC _sk_gather_565_sse41 @@ -13945,31 +14325,31 @@ _sk_gather_565_sse41 LABEL PROC DB 65,15,183,4,65 ; movzwl (%r9,%rax,2),%eax DB 102,15,196,192,3 ; pinsrw $0x3,%eax,%xmm0 DB 102,15,56,51,208 ; pmovzxwd %xmm0,%xmm2 - DB 102,15,111,5,203,32,0,0 ; movdqa 0x20cb(%rip),%xmm0 # 5010 <_sk_callback_sse41+0xb79> + DB 102,15,111,5,251,34,0,0 ; movdqa 0x22fb(%rip),%xmm0 # 5240 <_sk_callback_sse41+0xb6d> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,205,32,0,0 ; mulps 0x20cd(%rip),%xmm0 # 5020 <_sk_callback_sse41+0xb89> - DB 102,15,111,13,213,32,0,0 ; movdqa 0x20d5(%rip),%xmm1 # 5030 <_sk_callback_sse41+0xb99> + DB 15,89,5,253,34,0,0 ; mulps 0x22fd(%rip),%xmm0 # 5250 <_sk_callback_sse41+0xb7d> + DB 102,15,111,13,5,35,0,0 ; movdqa 0x2305(%rip),%xmm1 # 5260 <_sk_callback_sse41+0xb8d> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,215,32,0,0 ; mulps 0x20d7(%rip),%xmm1 # 5040 <_sk_callback_sse41+0xba9> - DB 102,15,219,21,223,32,0,0 ; pand 0x20df(%rip),%xmm2 # 5050 <_sk_callback_sse41+0xbb9> + DB 15,89,13,7,35,0,0 ; mulps 0x2307(%rip),%xmm1 # 5270 <_sk_callback_sse41+0xb9d> + DB 102,15,219,21,15,35,0,0 ; pand 0x230f(%rip),%xmm2 # 5280 <_sk_callback_sse41+0xbad> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,229,32,0,0 ; mulps 0x20e5(%rip),%xmm2 # 5060 <_sk_callback_sse41+0xbc9> + DB 15,89,21,21,35,0,0 ; mulps 0x2315(%rip),%xmm2 # 5290 <_sk_callback_sse41+0xbbd> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,236,32,0,0 ; movaps 0x20ec(%rip),%xmm3 # 5070 <_sk_callback_sse41+0xbd9> + DB 15,40,29,28,35,0,0 ; movaps 0x231c(%rip),%xmm3 # 52a0 <_sk_callback_sse41+0xbcd> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_565_sse41 _sk_store_565_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,237,32,0,0 ; movaps 0x20ed(%rip),%xmm8 # 5080 <_sk_callback_sse41+0xbe9> + DB 68,15,40,5,29,35,0,0 ; movaps 0x231d(%rip),%xmm8 # 52b0 <_sk_callback_sse41+0xbdd> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 DB 102,65,15,114,241,11 ; pslld $0xb,%xmm9 - DB 68,15,40,21,226,32,0,0 ; movaps 0x20e2(%rip),%xmm10 # 5090 <_sk_callback_sse41+0xbf9> + DB 68,15,40,21,18,35,0,0 ; movaps 0x2312(%rip),%xmm10 # 52c0 <_sk_callback_sse41+0xbed> DB 68,15,89,209 ; mulps %xmm1,%xmm10 DB 102,69,15,91,210 ; cvtps2dq %xmm10,%xmm10 DB 102,65,15,114,242,5 ; pslld $0x5,%xmm10 @@ -13987,21 +14367,21 @@ _sk_load_4444_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,51,28,120 ; pmovzxwd (%rax,%rdi,2),%xmm3 - DB 102,15,111,5,173,32,0,0 ; movdqa 0x20ad(%rip),%xmm0 # 50a0 <_sk_callback_sse41+0xc09> + DB 102,15,111,5,221,34,0,0 ; movdqa 0x22dd(%rip),%xmm0 # 52d0 <_sk_callback_sse41+0xbfd> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,175,32,0,0 ; mulps 0x20af(%rip),%xmm0 # 50b0 <_sk_callback_sse41+0xc19> - DB 102,15,111,13,183,32,0,0 ; movdqa 0x20b7(%rip),%xmm1 # 50c0 <_sk_callback_sse41+0xc29> + DB 15,89,5,223,34,0,0 ; mulps 0x22df(%rip),%xmm0 # 52e0 <_sk_callback_sse41+0xc0d> + DB 102,15,111,13,231,34,0,0 ; movdqa 0x22e7(%rip),%xmm1 # 52f0 <_sk_callback_sse41+0xc1d> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,185,32,0,0 ; mulps 0x20b9(%rip),%xmm1 # 50d0 <_sk_callback_sse41+0xc39> - DB 102,15,111,21,193,32,0,0 ; movdqa 0x20c1(%rip),%xmm2 # 50e0 <_sk_callback_sse41+0xc49> + DB 15,89,13,233,34,0,0 ; mulps 0x22e9(%rip),%xmm1 # 5300 <_sk_callback_sse41+0xc2d> + DB 102,15,111,21,241,34,0,0 ; movdqa 0x22f1(%rip),%xmm2 # 5310 <_sk_callback_sse41+0xc3d> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,195,32,0,0 ; mulps 0x20c3(%rip),%xmm2 # 50f0 <_sk_callback_sse41+0xc59> - DB 102,15,219,29,203,32,0,0 ; pand 0x20cb(%rip),%xmm3 # 5100 <_sk_callback_sse41+0xc69> + DB 15,89,21,243,34,0,0 ; mulps 0x22f3(%rip),%xmm2 # 5320 <_sk_callback_sse41+0xc4d> + DB 102,15,219,29,251,34,0,0 ; pand 0x22fb(%rip),%xmm3 # 5330 <_sk_callback_sse41+0xc5d> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,209,32,0,0 ; mulps 0x20d1(%rip),%xmm3 # 5110 <_sk_callback_sse41+0xc79> + DB 15,89,29,1,35,0,0 ; mulps 0x2301(%rip),%xmm3 # 5340 <_sk_callback_sse41+0xc6d> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -14028,21 +14408,21 @@ _sk_gather_4444_sse41 LABEL PROC DB 65,15,183,4,65 ; movzwl (%r9,%rax,2),%eax DB 102,15,196,192,3 ; pinsrw $0x3,%eax,%xmm0 DB 102,15,56,51,216 ; pmovzxwd %xmm0,%xmm3 - DB 102,15,111,5,116,32,0,0 ; movdqa 0x2074(%rip),%xmm0 # 5120 <_sk_callback_sse41+0xc89> + DB 102,15,111,5,164,34,0,0 ; movdqa 0x22a4(%rip),%xmm0 # 5350 <_sk_callback_sse41+0xc7d> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,118,32,0,0 ; mulps 0x2076(%rip),%xmm0 # 5130 <_sk_callback_sse41+0xc99> - DB 102,15,111,13,126,32,0,0 ; movdqa 0x207e(%rip),%xmm1 # 5140 <_sk_callback_sse41+0xca9> + DB 15,89,5,166,34,0,0 ; mulps 0x22a6(%rip),%xmm0 # 5360 <_sk_callback_sse41+0xc8d> + DB 102,15,111,13,174,34,0,0 ; movdqa 0x22ae(%rip),%xmm1 # 5370 <_sk_callback_sse41+0xc9d> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,128,32,0,0 ; mulps 0x2080(%rip),%xmm1 # 5150 <_sk_callback_sse41+0xcb9> - DB 102,15,111,21,136,32,0,0 ; movdqa 0x2088(%rip),%xmm2 # 5160 <_sk_callback_sse41+0xcc9> + DB 15,89,13,176,34,0,0 ; mulps 0x22b0(%rip),%xmm1 # 5380 <_sk_callback_sse41+0xcad> + DB 102,15,111,21,184,34,0,0 ; movdqa 0x22b8(%rip),%xmm2 # 5390 <_sk_callback_sse41+0xcbd> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,138,32,0,0 ; mulps 0x208a(%rip),%xmm2 # 5170 <_sk_callback_sse41+0xcd9> - DB 102,15,219,29,146,32,0,0 ; pand 0x2092(%rip),%xmm3 # 5180 <_sk_callback_sse41+0xce9> + DB 15,89,21,186,34,0,0 ; mulps 0x22ba(%rip),%xmm2 # 53a0 <_sk_callback_sse41+0xccd> + DB 102,15,219,29,194,34,0,0 ; pand 0x22c2(%rip),%xmm3 # 53b0 <_sk_callback_sse41+0xcdd> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,152,32,0,0 ; mulps 0x2098(%rip),%xmm3 # 5190 <_sk_callback_sse41+0xcf9> + DB 15,89,29,200,34,0,0 ; mulps 0x22c8(%rip),%xmm3 # 53c0 <_sk_callback_sse41+0xced> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -14050,7 +14430,7 @@ PUBLIC _sk_store_4444_sse41 _sk_store_4444_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,151,32,0,0 ; movaps 0x2097(%rip),%xmm8 # 51a0 <_sk_callback_sse41+0xd09> + DB 68,15,40,5,199,34,0,0 ; movaps 0x22c7(%rip),%xmm8 # 53d0 <_sk_callback_sse41+0xcfd> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -14078,17 +14458,17 @@ _sk_load_8888_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 15,16,28,184 ; movups (%rax,%rdi,4),%xmm3 - DB 15,40,5,54,32,0,0 ; movaps 0x2036(%rip),%xmm0 # 51b0 <_sk_callback_sse41+0xd19> + DB 15,40,5,102,34,0,0 ; movaps 0x2266(%rip),%xmm0 # 53e0 <_sk_callback_sse41+0xd0d> DB 15,84,195 ; andps %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,56,32,0,0 ; movaps 0x2038(%rip),%xmm8 # 51c0 <_sk_callback_sse41+0xd29> + DB 68,15,40,5,104,34,0,0 ; movaps 0x2268(%rip),%xmm8 # 53f0 <_sk_callback_sse41+0xd1d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,40,203 ; movaps %xmm3,%xmm1 - DB 102,15,56,0,13,56,32,0,0 ; pshufb 0x2038(%rip),%xmm1 # 51d0 <_sk_callback_sse41+0xd39> + DB 102,15,56,0,13,104,34,0,0 ; pshufb 0x2268(%rip),%xmm1 # 5400 <_sk_callback_sse41+0xd2d> DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 15,40,211 ; movaps %xmm3,%xmm2 - DB 102,15,56,0,21,53,32,0,0 ; pshufb 0x2035(%rip),%xmm2 # 51e0 <_sk_callback_sse41+0xd49> + DB 102,15,56,0,21,101,34,0,0 ; pshufb 0x2265(%rip),%xmm2 # 5410 <_sk_callback_sse41+0xd3d> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 102,15,114,211,24 ; psrld $0x18,%xmm3 @@ -14117,17 +14497,17 @@ _sk_gather_8888_sse41 LABEL PROC DB 102,65,15,58,34,28,129,1 ; pinsrd $0x1,(%r9,%rax,4),%xmm3 DB 102,67,15,58,34,28,145,2 ; pinsrd $0x2,(%r9,%r10,4),%xmm3 DB 102,65,15,58,34,28,137,3 ; pinsrd $0x3,(%r9,%rcx,4),%xmm3 - DB 102,15,111,5,206,31,0,0 ; movdqa 0x1fce(%rip),%xmm0 # 51f0 <_sk_callback_sse41+0xd59> + DB 102,15,111,5,254,33,0,0 ; movdqa 0x21fe(%rip),%xmm0 # 5420 <_sk_callback_sse41+0xd4d> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,207,31,0,0 ; movaps 0x1fcf(%rip),%xmm8 # 5200 <_sk_callback_sse41+0xd69> + DB 68,15,40,5,255,33,0,0 ; movaps 0x21ff(%rip),%xmm8 # 5430 <_sk_callback_sse41+0xd5d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 - DB 102,15,56,0,13,206,31,0,0 ; pshufb 0x1fce(%rip),%xmm1 # 5210 <_sk_callback_sse41+0xd79> + DB 102,15,56,0,13,254,33,0,0 ; pshufb 0x21fe(%rip),%xmm1 # 5440 <_sk_callback_sse41+0xd6d> DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,111,211 ; movdqa %xmm3,%xmm2 - DB 102,15,56,0,21,202,31,0,0 ; pshufb 0x1fca(%rip),%xmm2 # 5220 <_sk_callback_sse41+0xd89> + DB 102,15,56,0,21,250,33,0,0 ; pshufb 0x21fa(%rip),%xmm2 # 5450 <_sk_callback_sse41+0xd7d> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 102,15,114,211,24 ; psrld $0x18,%xmm3 @@ -14140,7 +14520,7 @@ PUBLIC _sk_store_8888_sse41 _sk_store_8888_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,182,31,0,0 ; movaps 0x1fb6(%rip),%xmm8 # 5230 <_sk_callback_sse41+0xd99> + DB 68,15,40,5,230,33,0,0 ; movaps 0x21e6(%rip),%xmm8 # 5460 <_sk_callback_sse41+0xd8d> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -14175,18 +14555,18 @@ _sk_load_f16_sse41 LABEL PROC DB 102,68,15,97,216 ; punpcklwd %xmm0,%xmm11 DB 102,68,15,105,200 ; punpckhwd %xmm0,%xmm9 DB 102,65,15,56,51,203 ; pmovzxwd %xmm11,%xmm1 - DB 102,68,15,111,5,47,31,0,0 ; movdqa 0x1f2f(%rip),%xmm8 # 5240 <_sk_callback_sse41+0xda9> + DB 102,68,15,111,5,95,33,0,0 ; movdqa 0x215f(%rip),%xmm8 # 5470 <_sk_callback_sse41+0xd9d> DB 102,15,111,209 ; movdqa %xmm1,%xmm2 DB 102,65,15,219,208 ; pand %xmm8,%xmm2 DB 102,15,239,202 ; pxor %xmm2,%xmm1 - DB 102,15,111,29,42,31,0,0 ; movdqa 0x1f2a(%rip),%xmm3 # 5250 <_sk_callback_sse41+0xdb9> + DB 102,15,111,29,90,33,0,0 ; movdqa 0x215a(%rip),%xmm3 # 5480 <_sk_callback_sse41+0xdad> DB 102,15,114,242,16 ; pslld $0x10,%xmm2 DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,15,56,63,195 ; pmaxud %xmm3,%xmm0 DB 102,15,118,193 ; pcmpeqd %xmm1,%xmm0 DB 102,15,114,241,13 ; pslld $0xd,%xmm1 DB 102,15,235,202 ; por %xmm2,%xmm1 - DB 102,68,15,111,21,22,31,0,0 ; movdqa 0x1f16(%rip),%xmm10 # 5260 <_sk_callback_sse41+0xdc9> + DB 102,68,15,111,21,70,33,0,0 ; movdqa 0x2146(%rip),%xmm10 # 5490 <_sk_callback_sse41+0xdbd> DB 102,65,15,254,202 ; paddd %xmm10,%xmm1 DB 102,15,219,193 ; pand %xmm1,%xmm0 DB 102,65,15,115,219,8 ; psrldq $0x8,%xmm11 @@ -14257,18 +14637,18 @@ _sk_gather_f16_sse41 LABEL PROC DB 102,68,15,97,218 ; punpcklwd %xmm2,%xmm11 DB 102,68,15,105,202 ; punpckhwd %xmm2,%xmm9 DB 102,65,15,56,51,203 ; pmovzxwd %xmm11,%xmm1 - DB 102,68,15,111,5,212,29,0,0 ; movdqa 0x1dd4(%rip),%xmm8 # 5270 <_sk_callback_sse41+0xdd9> + DB 102,68,15,111,5,4,32,0,0 ; movdqa 0x2004(%rip),%xmm8 # 54a0 <_sk_callback_sse41+0xdcd> DB 102,15,111,209 ; movdqa %xmm1,%xmm2 DB 102,65,15,219,208 ; pand %xmm8,%xmm2 DB 102,15,239,202 ; pxor %xmm2,%xmm1 - DB 102,15,111,29,207,29,0,0 ; movdqa 0x1dcf(%rip),%xmm3 # 5280 <_sk_callback_sse41+0xde9> + DB 102,15,111,29,255,31,0,0 ; movdqa 0x1fff(%rip),%xmm3 # 54b0 <_sk_callback_sse41+0xddd> DB 102,15,114,242,16 ; pslld $0x10,%xmm2 DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,15,56,63,195 ; pmaxud %xmm3,%xmm0 DB 102,15,118,193 ; pcmpeqd %xmm1,%xmm0 DB 102,15,114,241,13 ; pslld $0xd,%xmm1 DB 102,15,235,202 ; por %xmm2,%xmm1 - DB 102,68,15,111,21,187,29,0,0 ; movdqa 0x1dbb(%rip),%xmm10 # 5290 <_sk_callback_sse41+0xdf9> + DB 102,68,15,111,21,235,31,0,0 ; movdqa 0x1feb(%rip),%xmm10 # 54c0 <_sk_callback_sse41+0xded> DB 102,65,15,254,202 ; paddd %xmm10,%xmm1 DB 102,15,219,193 ; pand %xmm1,%xmm0 DB 102,65,15,115,219,8 ; psrldq $0x8,%xmm11 @@ -14314,17 +14694,17 @@ PUBLIC _sk_store_f16_sse41 _sk_store_f16_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 102,68,15,111,21,241,28,0,0 ; movdqa 0x1cf1(%rip),%xmm10 # 52a0 <_sk_callback_sse41+0xe09> + DB 102,68,15,111,21,33,31,0,0 ; movdqa 0x1f21(%rip),%xmm10 # 54d0 <_sk_callback_sse41+0xdfd> DB 102,68,15,111,224 ; movdqa %xmm0,%xmm12 DB 102,68,15,111,232 ; movdqa %xmm0,%xmm13 DB 102,69,15,219,234 ; pand %xmm10,%xmm13 DB 102,69,15,239,229 ; pxor %xmm13,%xmm12 - DB 102,68,15,111,13,228,28,0,0 ; movdqa 0x1ce4(%rip),%xmm9 # 52b0 <_sk_callback_sse41+0xe19> + DB 102,68,15,111,13,20,31,0,0 ; movdqa 0x1f14(%rip),%xmm9 # 54e0 <_sk_callback_sse41+0xe0d> DB 102,65,15,114,213,16 ; psrld $0x10,%xmm13 DB 102,69,15,111,193 ; movdqa %xmm9,%xmm8 DB 102,69,15,102,196 ; pcmpgtd %xmm12,%xmm8 DB 102,65,15,114,212,13 ; psrld $0xd,%xmm12 - DB 102,68,15,111,29,213,28,0,0 ; movdqa 0x1cd5(%rip),%xmm11 # 52c0 <_sk_callback_sse41+0xe29> + DB 102,68,15,111,29,5,31,0,0 ; movdqa 0x1f05(%rip),%xmm11 # 54f0 <_sk_callback_sse41+0xe1d> DB 102,69,15,235,235 ; por %xmm11,%xmm13 DB 102,69,15,254,236 ; paddd %xmm12,%xmm13 DB 102,69,15,223,197 ; pandn %xmm13,%xmm8 @@ -14392,7 +14772,7 @@ _sk_load_u16_be_sse41 LABEL PROC DB 102,15,235,200 ; por %xmm0,%xmm1 DB 102,15,56,51,193 ; pmovzxwd %xmm1,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,164,27,0,0 ; movaps 0x1ba4(%rip),%xmm8 # 52d0 <_sk_callback_sse41+0xe39> + DB 68,15,40,5,212,29,0,0 ; movaps 0x1dd4(%rip),%xmm8 # 5500 <_sk_callback_sse41+0xe2d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -14442,7 +14822,7 @@ _sk_load_rgb_u16_be_sse41 LABEL PROC DB 102,15,235,193 ; por %xmm1,%xmm0 DB 102,15,56,51,192 ; pmovzxwd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,229,26,0,0 ; movaps 0x1ae5(%rip),%xmm8 # 52e0 <_sk_callback_sse41+0xe49> + DB 68,15,40,5,21,29,0,0 ; movaps 0x1d15(%rip),%xmm8 # 5510 <_sk_callback_sse41+0xe3d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -14459,14 +14839,14 @@ _sk_load_rgb_u16_be_sse41 LABEL PROC DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,172,26,0,0 ; movaps 0x1aac(%rip),%xmm3 # 52f0 <_sk_callback_sse41+0xe59> + DB 15,40,29,220,28,0,0 ; movaps 0x1cdc(%rip),%xmm3 # 5520 <_sk_callback_sse41+0xe4d> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_u16_be_sse41 _sk_store_u16_be_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,13,173,26,0,0 ; movaps 0x1aad(%rip),%xmm9 # 5300 <_sk_callback_sse41+0xe69> + DB 68,15,40,13,221,28,0,0 ; movaps 0x1cdd(%rip),%xmm9 # 5530 <_sk_callback_sse41+0xe5d> DB 68,15,40,192 ; movaps %xmm0,%xmm8 DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 @@ -14659,10 +15039,10 @@ _sk_mirror_y_sse41 LABEL PROC PUBLIC _sk_luminance_to_alpha_sse41 _sk_luminance_to_alpha_sse41 LABEL PROC DB 15,40,218 ; movaps %xmm2,%xmm3 - DB 15,89,5,9,24,0,0 ; mulps 0x1809(%rip),%xmm0 # 5310 <_sk_callback_sse41+0xe79> - DB 15,89,13,18,24,0,0 ; mulps 0x1812(%rip),%xmm1 # 5320 <_sk_callback_sse41+0xe89> + DB 15,89,5,57,26,0,0 ; mulps 0x1a39(%rip),%xmm0 # 5540 <_sk_callback_sse41+0xe6d> + DB 15,89,13,66,26,0,0 ; mulps 0x1a42(%rip),%xmm1 # 5550 <_sk_callback_sse41+0xe7d> DB 15,88,200 ; addps %xmm0,%xmm1 - DB 15,89,29,24,24,0,0 ; mulps 0x1818(%rip),%xmm3 # 5330 <_sk_callback_sse41+0xe99> + DB 15,89,29,72,26,0,0 ; mulps 0x1a48(%rip),%xmm3 # 5560 <_sk_callback_sse41+0xe8d> DB 15,88,217 ; addps %xmm1,%xmm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 @@ -14872,91 +15252,193 @@ _sk_matrix_perspective_sse41 LABEL PROC DB 65,15,40,201 ; movaps %xmm9,%xmm1 DB 255,224 ; jmpq *%rax -PUBLIC _sk_gradient_sse41 -_sk_gradient_sse41 LABEL PROC +PUBLIC _sk_evenly_spaced_gradient_sse41 +_sk_evenly_spaced_gradient_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 243,68,15,16,80,16 ; movss 0x10(%rax),%xmm10 - DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 - DB 243,68,15,16,88,20 ; movss 0x14(%rax),%xmm11 - DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 - DB 243,68,15,16,96,24 ; movss 0x18(%rax),%xmm12 - DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 - DB 243,68,15,16,104,28 ; movss 0x1c(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 DB 72,139,8 ; mov (%rax),%rcx - DB 72,133,201 ; test %rcx,%rcx - DB 15,132,4,1,0,0 ; je 3fc0 <_sk_gradient_sse41+0x13e> - DB 72,131,236,88 ; sub $0x58,%rsp - DB 15,41,36,36 ; movaps %xmm4,(%rsp) - DB 15,41,108,36,16 ; movaps %xmm5,0x10(%rsp) - DB 15,41,116,36,32 ; movaps %xmm6,0x20(%rsp) - DB 15,41,124,36,48 ; movaps %xmm7,0x30(%rsp) - DB 72,139,64,8 ; mov 0x8(%rax),%rax - DB 72,131,192,32 ; add $0x20,%rax - DB 69,15,87,201 ; xorps %xmm9,%xmm9 - DB 15,87,219 ; xorps %xmm3,%xmm3 - DB 15,87,210 ; xorps %xmm2,%xmm2 - DB 15,87,201 ; xorps %xmm1,%xmm1 - DB 15,40,233 ; movaps %xmm1,%xmm5 - DB 15,40,242 ; movaps %xmm2,%xmm6 - DB 15,40,251 ; movaps %xmm3,%xmm7 - DB 69,15,40,194 ; movaps %xmm10,%xmm8 - DB 69,15,40,243 ; movaps %xmm11,%xmm14 - DB 69,15,40,252 ; movaps %xmm12,%xmm15 - DB 68,15,41,108,36,64 ; movaps %xmm13,0x40(%rsp) - DB 65,15,40,201 ; movaps %xmm9,%xmm1 - DB 243,15,16,80,224 ; movss -0x20(%rax),%xmm2 - DB 243,68,15,16,72,228 ; movss -0x1c(%rax),%xmm9 - DB 15,198,210,0 ; shufps $0x0,%xmm2,%xmm2 - DB 15,40,224 ; movaps %xmm0,%xmm4 - DB 15,194,194,1 ; cmpltps %xmm2,%xmm0 - DB 69,15,198,201,0 ; shufps $0x0,%xmm9,%xmm9 - DB 102,68,15,56,20,201 ; blendvps %xmm0,%xmm1,%xmm9 - DB 243,15,16,72,232 ; movss -0x18(%rax),%xmm1 + DB 76,139,88,8 ; mov 0x8(%rax),%r11 + DB 72,255,201 ; dec %rcx + DB 120,7 ; js 3e97 <_sk_evenly_spaced_gradient_sse41+0x15> + DB 243,72,15,42,201 ; cvtsi2ss %rcx,%xmm1 + DB 235,21 ; jmp 3eac <_sk_evenly_spaced_gradient_sse41+0x2a> + DB 73,137,200 ; mov %rcx,%r8 + DB 73,209,232 ; shr %r8 + DB 131,225,1 ; and $0x1,%ecx + DB 76,9,193 ; or %r8,%rcx + DB 243,72,15,42,201 ; cvtsi2ss %rcx,%xmm1 + DB 243,15,88,201 ; addss %xmm1,%xmm1 DB 15,198,201,0 ; shufps $0x0,%xmm1,%xmm1 - DB 102,15,56,20,205 ; blendvps %xmm0,%xmm5,%xmm1 - DB 243,15,16,80,236 ; movss -0x14(%rax),%xmm2 - DB 15,198,210,0 ; shufps $0x0,%xmm2,%xmm2 - DB 102,15,56,20,214 ; blendvps %xmm0,%xmm6,%xmm2 - DB 243,15,16,88,240 ; movss -0x10(%rax),%xmm3 + DB 15,89,200 ; mulps %xmm0,%xmm1 + DB 243,15,91,201 ; cvttps2dq %xmm1,%xmm1 + DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 + DB 69,137,200 ; mov %r9d,%r8d + DB 73,193,233,32 ; shr $0x20,%r9 + DB 102,72,15,126,201 ; movq %xmm1,%rcx + DB 65,137,202 ; mov %ecx,%r10d + DB 72,193,233,32 ; shr $0x20,%rcx + DB 243,71,15,16,4,147 ; movss (%r11,%r10,4),%xmm8 + DB 102,69,15,58,33,4,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm8 + DB 243,67,15,16,12,131 ; movss (%r11,%r8,4),%xmm1 + DB 102,68,15,58,33,193,32 ; insertps $0x20,%xmm1,%xmm8 + DB 243,67,15,16,12,139 ; movss (%r11,%r9,4),%xmm1 + DB 102,68,15,58,33,193,48 ; insertps $0x30,%xmm1,%xmm8 + DB 76,139,88,40 ; mov 0x28(%rax),%r11 + DB 243,71,15,16,12,147 ; movss (%r11,%r10,4),%xmm9 + DB 102,69,15,58,33,12,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm9 + DB 243,67,15,16,12,131 ; movss (%r11,%r8,4),%xmm1 + DB 102,68,15,58,33,201,32 ; insertps $0x20,%xmm1,%xmm9 + DB 243,67,15,16,12,139 ; movss (%r11,%r9,4),%xmm1 + DB 102,68,15,58,33,201,48 ; insertps $0x30,%xmm1,%xmm9 + DB 76,139,88,16 ; mov 0x10(%rax),%r11 + DB 243,67,15,16,12,147 ; movss (%r11,%r10,4),%xmm1 + DB 102,65,15,58,33,12,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm1 + DB 243,67,15,16,20,131 ; movss (%r11,%r8,4),%xmm2 + DB 102,15,58,33,202,32 ; insertps $0x20,%xmm2,%xmm1 + DB 243,67,15,16,20,139 ; movss (%r11,%r9,4),%xmm2 + DB 102,15,58,33,202,48 ; insertps $0x30,%xmm2,%xmm1 + DB 76,139,88,48 ; mov 0x30(%rax),%r11 + DB 243,71,15,16,20,147 ; movss (%r11,%r10,4),%xmm10 + DB 102,69,15,58,33,20,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm10 + DB 243,67,15,16,20,131 ; movss (%r11,%r8,4),%xmm2 + DB 102,68,15,58,33,210,32 ; insertps $0x20,%xmm2,%xmm10 + DB 243,67,15,16,20,139 ; movss (%r11,%r9,4),%xmm2 + DB 102,68,15,58,33,210,48 ; insertps $0x30,%xmm2,%xmm10 + DB 76,139,88,24 ; mov 0x18(%rax),%r11 + DB 243,67,15,16,20,147 ; movss (%r11,%r10,4),%xmm2 + DB 102,65,15,58,33,20,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm2 + DB 243,67,15,16,28,131 ; movss (%r11,%r8,4),%xmm3 + DB 102,15,58,33,211,32 ; insertps $0x20,%xmm3,%xmm2 + DB 243,67,15,16,28,139 ; movss (%r11,%r9,4),%xmm3 + DB 102,15,58,33,211,48 ; insertps $0x30,%xmm3,%xmm2 + DB 76,139,88,56 ; mov 0x38(%rax),%r11 + DB 243,71,15,16,28,147 ; movss (%r11,%r10,4),%xmm11 + DB 102,69,15,58,33,28,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm11 + DB 243,67,15,16,28,131 ; movss (%r11,%r8,4),%xmm3 + DB 102,68,15,58,33,219,32 ; insertps $0x20,%xmm3,%xmm11 + DB 243,67,15,16,28,139 ; movss (%r11,%r9,4),%xmm3 + DB 102,68,15,58,33,219,48 ; insertps $0x30,%xmm3,%xmm11 + DB 76,139,88,32 ; mov 0x20(%rax),%r11 + DB 243,67,15,16,28,147 ; movss (%r11,%r10,4),%xmm3 + DB 102,65,15,58,33,28,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm3 + DB 243,71,15,16,36,131 ; movss (%r11,%r8,4),%xmm12 + DB 102,65,15,58,33,220,32 ; insertps $0x20,%xmm12,%xmm3 + DB 243,71,15,16,36,139 ; movss (%r11,%r9,4),%xmm12 + DB 102,65,15,58,33,220,48 ; insertps $0x30,%xmm12,%xmm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 243,70,15,16,36,144 ; movss (%rax,%r10,4),%xmm12 + DB 102,68,15,58,33,36,136,16 ; insertps $0x10,(%rax,%rcx,4),%xmm12 + DB 243,70,15,16,44,128 ; movss (%rax,%r8,4),%xmm13 + DB 102,69,15,58,33,229,32 ; insertps $0x20,%xmm13,%xmm12 + DB 243,70,15,16,44,136 ; movss (%rax,%r9,4),%xmm13 + DB 102,69,15,58,33,229,48 ; insertps $0x30,%xmm13,%xmm12 + DB 68,15,89,192 ; mulps %xmm0,%xmm8 + DB 69,15,88,193 ; addps %xmm9,%xmm8 + DB 15,89,200 ; mulps %xmm0,%xmm1 + DB 65,15,88,202 ; addps %xmm10,%xmm1 + DB 15,89,208 ; mulps %xmm0,%xmm2 + DB 65,15,88,211 ; addps %xmm11,%xmm2 + DB 15,89,216 ; mulps %xmm0,%xmm3 + DB 65,15,88,220 ; addps %xmm12,%xmm3 + DB 72,173 ; lods %ds:(%rsi),%rax + DB 65,15,40,192 ; movaps %xmm8,%xmm0 + DB 255,224 ; jmpq *%rax + +PUBLIC _sk_gradient_sse41 +_sk_gradient_sse41 LABEL PROC + DB 72,173 ; lods %ds:(%rsi),%rax + DB 76,139,0 ; mov (%rax),%r8 + DB 102,15,239,201 ; pxor %xmm1,%xmm1 + DB 73,131,248,2 ; cmp $0x2,%r8 + DB 114,50 ; jb 408f <_sk_gradient_sse41+0x41> + DB 72,139,72,72 ; mov 0x48(%rax),%rcx + DB 73,255,200 ; dec %r8 + DB 72,131,193,4 ; add $0x4,%rcx + DB 102,15,239,201 ; pxor %xmm1,%xmm1 + DB 15,40,21,253,20,0,0 ; movaps 0x14fd(%rip),%xmm2 # 5570 <_sk_callback_sse41+0xe9d> + DB 243,15,16,25 ; movss (%rcx),%xmm3 DB 15,198,219,0 ; shufps $0x0,%xmm3,%xmm3 - DB 102,15,56,20,223 ; blendvps %xmm0,%xmm7,%xmm3 - DB 243,68,15,16,80,244 ; movss -0xc(%rax),%xmm10 - DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 - DB 102,69,15,56,20,208 ; blendvps %xmm0,%xmm8,%xmm10 - DB 243,68,15,16,88,248 ; movss -0x8(%rax),%xmm11 - DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 - DB 102,69,15,56,20,222 ; blendvps %xmm0,%xmm14,%xmm11 - DB 243,68,15,16,96,252 ; movss -0x4(%rax),%xmm12 - DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 - DB 102,69,15,56,20,231 ; blendvps %xmm0,%xmm15,%xmm12 - DB 243,68,15,16,40 ; movss (%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 102,68,15,56,20,108,36,64 ; blendvps %xmm0,0x40(%rsp),%xmm13 - DB 15,40,196 ; movaps %xmm4,%xmm0 - DB 72,131,192,36 ; add $0x24,%rax - DB 72,255,201 ; dec %rcx - DB 15,133,65,255,255,255 ; jne 3ee8 <_sk_gradient_sse41+0x66> - DB 15,40,124,36,48 ; movaps 0x30(%rsp),%xmm7 - DB 15,40,116,36,32 ; movaps 0x20(%rsp),%xmm6 - DB 15,40,108,36,16 ; movaps 0x10(%rsp),%xmm5 - DB 15,40,36,36 ; movaps (%rsp),%xmm4 - DB 72,131,196,88 ; add $0x58,%rsp - DB 235,13 ; jmp 3fcd <_sk_gradient_sse41+0x14b> - DB 15,87,201 ; xorps %xmm1,%xmm1 - DB 15,87,210 ; xorps %xmm2,%xmm2 - DB 15,87,219 ; xorps %xmm3,%xmm3 - DB 69,15,87,201 ; xorps %xmm9,%xmm9 - DB 68,15,89,200 ; mulps %xmm0,%xmm9 - DB 69,15,88,202 ; addps %xmm10,%xmm9 + DB 15,194,216,2 ; cmpleps %xmm0,%xmm3 + DB 15,84,218 ; andps %xmm2,%xmm3 + DB 102,15,254,203 ; paddd %xmm3,%xmm1 + DB 72,131,193,4 ; add $0x4,%rcx + DB 73,255,200 ; dec %r8 + DB 117,228 ; jne 4073 <_sk_gradient_sse41+0x25> + DB 65,86 ; push %r14 + DB 83 ; push %rbx + DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 + DB 69,137,200 ; mov %r9d,%r8d + DB 73,193,233,32 ; shr $0x20,%r9 + DB 102,72,15,126,201 ; movq %xmm1,%rcx + DB 65,137,202 ; mov %ecx,%r10d + DB 72,193,233,32 ; shr $0x20,%rcx + DB 76,139,88,8 ; mov 0x8(%rax),%r11 + DB 76,139,112,16 ; mov 0x10(%rax),%r14 + DB 243,71,15,16,4,147 ; movss (%r11,%r10,4),%xmm8 + DB 102,69,15,58,33,4,139,16 ; insertps $0x10,(%r11,%rcx,4),%xmm8 + DB 243,67,15,16,12,131 ; movss (%r11,%r8,4),%xmm1 + DB 102,68,15,58,33,193,32 ; insertps $0x20,%xmm1,%xmm8 + DB 243,67,15,16,12,139 ; movss (%r11,%r9,4),%xmm1 + DB 102,68,15,58,33,193,48 ; insertps $0x30,%xmm1,%xmm8 + DB 72,139,88,40 ; mov 0x28(%rax),%rbx + DB 243,70,15,16,12,147 ; movss (%rbx,%r10,4),%xmm9 + DB 102,68,15,58,33,12,139,16 ; insertps $0x10,(%rbx,%rcx,4),%xmm9 + DB 243,66,15,16,12,131 ; movss (%rbx,%r8,4),%xmm1 + DB 102,68,15,58,33,201,32 ; insertps $0x20,%xmm1,%xmm9 + DB 243,66,15,16,12,139 ; movss (%rbx,%r9,4),%xmm1 + DB 102,68,15,58,33,201,48 ; insertps $0x30,%xmm1,%xmm9 + DB 243,67,15,16,12,150 ; movss (%r14,%r10,4),%xmm1 + DB 102,65,15,58,33,12,142,16 ; insertps $0x10,(%r14,%rcx,4),%xmm1 + DB 243,67,15,16,20,134 ; movss (%r14,%r8,4),%xmm2 + DB 102,15,58,33,202,32 ; insertps $0x20,%xmm2,%xmm1 + DB 243,67,15,16,20,142 ; movss (%r14,%r9,4),%xmm2 + DB 102,15,58,33,202,48 ; insertps $0x30,%xmm2,%xmm1 + DB 72,139,88,48 ; mov 0x30(%rax),%rbx + DB 243,70,15,16,20,147 ; movss (%rbx,%r10,4),%xmm10 + DB 102,68,15,58,33,20,139,16 ; insertps $0x10,(%rbx,%rcx,4),%xmm10 + DB 243,66,15,16,20,131 ; movss (%rbx,%r8,4),%xmm2 + DB 102,68,15,58,33,210,32 ; insertps $0x20,%xmm2,%xmm10 + DB 243,66,15,16,20,139 ; movss (%rbx,%r9,4),%xmm2 + DB 102,68,15,58,33,210,48 ; insertps $0x30,%xmm2,%xmm10 + DB 72,139,88,24 ; mov 0x18(%rax),%rbx + DB 243,66,15,16,20,147 ; movss (%rbx,%r10,4),%xmm2 + DB 102,15,58,33,20,139,16 ; insertps $0x10,(%rbx,%rcx,4),%xmm2 + DB 243,66,15,16,28,131 ; movss (%rbx,%r8,4),%xmm3 + DB 102,15,58,33,211,32 ; insertps $0x20,%xmm3,%xmm2 + DB 243,66,15,16,28,139 ; movss (%rbx,%r9,4),%xmm3 + DB 102,15,58,33,211,48 ; insertps $0x30,%xmm3,%xmm2 + DB 72,139,88,56 ; mov 0x38(%rax),%rbx + DB 243,70,15,16,28,147 ; movss (%rbx,%r10,4),%xmm11 + DB 102,68,15,58,33,28,139,16 ; insertps $0x10,(%rbx,%rcx,4),%xmm11 + DB 243,66,15,16,28,131 ; movss (%rbx,%r8,4),%xmm3 + DB 102,68,15,58,33,219,32 ; insertps $0x20,%xmm3,%xmm11 + DB 243,66,15,16,28,139 ; movss (%rbx,%r9,4),%xmm3 + DB 102,68,15,58,33,219,48 ; insertps $0x30,%xmm3,%xmm11 + DB 72,139,88,32 ; mov 0x20(%rax),%rbx + DB 243,66,15,16,28,147 ; movss (%rbx,%r10,4),%xmm3 + DB 102,15,58,33,28,139,16 ; insertps $0x10,(%rbx,%rcx,4),%xmm3 + DB 243,70,15,16,36,131 ; movss (%rbx,%r8,4),%xmm12 + DB 102,65,15,58,33,220,32 ; insertps $0x20,%xmm12,%xmm3 + DB 243,70,15,16,36,139 ; movss (%rbx,%r9,4),%xmm12 + DB 102,65,15,58,33,220,48 ; insertps $0x30,%xmm12,%xmm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 243,70,15,16,36,144 ; movss (%rax,%r10,4),%xmm12 + DB 102,68,15,58,33,36,136,16 ; insertps $0x10,(%rax,%rcx,4),%xmm12 + DB 243,70,15,16,44,128 ; movss (%rax,%r8,4),%xmm13 + DB 102,69,15,58,33,229,32 ; insertps $0x20,%xmm13,%xmm12 + DB 243,70,15,16,44,136 ; movss (%rax,%r9,4),%xmm13 + DB 102,69,15,58,33,229,48 ; insertps $0x30,%xmm13,%xmm12 + DB 68,15,89,192 ; mulps %xmm0,%xmm8 + DB 69,15,88,193 ; addps %xmm9,%xmm8 DB 15,89,200 ; mulps %xmm0,%xmm1 - DB 65,15,88,203 ; addps %xmm11,%xmm1 + DB 65,15,88,202 ; addps %xmm10,%xmm1 DB 15,89,208 ; mulps %xmm0,%xmm2 - DB 65,15,88,212 ; addps %xmm12,%xmm2 + DB 65,15,88,211 ; addps %xmm11,%xmm2 DB 15,89,216 ; mulps %xmm0,%xmm3 - DB 65,15,88,221 ; addps %xmm13,%xmm3 + DB 65,15,88,220 ; addps %xmm12,%xmm3 DB 72,173 ; lods %ds:(%rsi),%rax - DB 65,15,40,193 ; movaps %xmm9,%xmm0 + DB 65,15,40,192 ; movaps %xmm8,%xmm0 + DB 91 ; pop %rbx + DB 65,94 ; pop %r14 DB 255,224 ; jmpq *%rax PUBLIC _sk_evenly_spaced_2_stop_gradient_sse41 @@ -15007,26 +15489,26 @@ _sk_xy_to_unit_angle_sse41 LABEL PROC DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,40,236 ; movaps %xmm12,%xmm13 DB 69,15,89,237 ; mulps %xmm13,%xmm13 - DB 68,15,40,21,155,18,0,0 ; movaps 0x129b(%rip),%xmm10 # 5340 <_sk_callback_sse41+0xea9> + DB 68,15,40,21,159,18,0,0 ; movaps 0x129f(%rip),%xmm10 # 5580 <_sk_callback_sse41+0xead> DB 69,15,89,213 ; mulps %xmm13,%xmm10 - DB 68,15,88,21,159,18,0,0 ; addps 0x129f(%rip),%xmm10 # 5350 <_sk_callback_sse41+0xeb9> + DB 68,15,88,21,163,18,0,0 ; addps 0x12a3(%rip),%xmm10 # 5590 <_sk_callback_sse41+0xebd> DB 69,15,89,213 ; mulps %xmm13,%xmm10 - DB 68,15,88,21,163,18,0,0 ; addps 0x12a3(%rip),%xmm10 # 5360 <_sk_callback_sse41+0xec9> + DB 68,15,88,21,167,18,0,0 ; addps 0x12a7(%rip),%xmm10 # 55a0 <_sk_callback_sse41+0xecd> DB 69,15,89,213 ; mulps %xmm13,%xmm10 - DB 68,15,88,21,167,18,0,0 ; addps 0x12a7(%rip),%xmm10 # 5370 <_sk_callback_sse41+0xed9> + DB 68,15,88,21,171,18,0,0 ; addps 0x12ab(%rip),%xmm10 # 55b0 <_sk_callback_sse41+0xedd> DB 69,15,89,212 ; mulps %xmm12,%xmm10 DB 65,15,194,195,1 ; cmpltps %xmm11,%xmm0 - DB 68,15,40,29,166,18,0,0 ; movaps 0x12a6(%rip),%xmm11 # 5380 <_sk_callback_sse41+0xee9> + DB 68,15,40,29,170,18,0,0 ; movaps 0x12aa(%rip),%xmm11 # 55c0 <_sk_callback_sse41+0xeed> DB 69,15,92,218 ; subps %xmm10,%xmm11 DB 102,69,15,56,20,211 ; blendvps %xmm0,%xmm11,%xmm10 DB 69,15,194,200,1 ; cmpltps %xmm8,%xmm9 - DB 68,15,40,29,159,18,0,0 ; movaps 0x129f(%rip),%xmm11 # 5390 <_sk_callback_sse41+0xef9> + DB 68,15,40,29,163,18,0,0 ; movaps 0x12a3(%rip),%xmm11 # 55d0 <_sk_callback_sse41+0xefd> DB 69,15,92,218 ; subps %xmm10,%xmm11 DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 102,69,15,56,20,211 ; blendvps %xmm0,%xmm11,%xmm10 DB 15,40,193 ; movaps %xmm1,%xmm0 DB 65,15,194,192,1 ; cmpltps %xmm8,%xmm0 - DB 68,15,40,13,145,18,0,0 ; movaps 0x1291(%rip),%xmm9 # 53a0 <_sk_callback_sse41+0xf09> + DB 68,15,40,13,149,18,0,0 ; movaps 0x1295(%rip),%xmm9 # 55e0 <_sk_callback_sse41+0xf0d> DB 69,15,92,202 ; subps %xmm10,%xmm9 DB 102,69,15,56,20,209 ; blendvps %xmm0,%xmm9,%xmm10 DB 69,15,194,194,7 ; cmpordps %xmm10,%xmm8 @@ -15049,7 +15531,7 @@ _sk_xy_to_radius_sse41 LABEL PROC PUBLIC _sk_save_xy_sse41 _sk_save_xy_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,98,18,0,0 ; movaps 0x1262(%rip),%xmm8 # 53b0 <_sk_callback_sse41+0xf19> + DB 68,15,40,5,102,18,0,0 ; movaps 0x1266(%rip),%xmm8 # 55f0 <_sk_callback_sse41+0xf1d> DB 15,17,0 ; movups %xmm0,(%rax) DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,88,200 ; addps %xmm8,%xmm9 @@ -15089,8 +15571,8 @@ _sk_bilinear_nx_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,228,17,0,0 ; addps 0x11e4(%rip),%xmm0 # 53c0 <_sk_callback_sse41+0xf29> - DB 68,15,40,13,236,17,0,0 ; movaps 0x11ec(%rip),%xmm9 # 53d0 <_sk_callback_sse41+0xf39> + DB 15,88,5,232,17,0,0 ; addps 0x11e8(%rip),%xmm0 # 5600 <_sk_callback_sse41+0xf2d> + DB 68,15,40,13,240,17,0,0 ; movaps 0x11f0(%rip),%xmm9 # 5610 <_sk_callback_sse41+0xf3d> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -15101,7 +15583,7 @@ _sk_bilinear_px_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,219,17,0,0 ; addps 0x11db(%rip),%xmm0 # 53e0 <_sk_callback_sse41+0xf49> + DB 15,88,5,223,17,0,0 ; addps 0x11df(%rip),%xmm0 # 5620 <_sk_callback_sse41+0xf4d> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -15111,8 +15593,8 @@ _sk_bilinear_ny_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,205,17,0,0 ; addps 0x11cd(%rip),%xmm1 # 53f0 <_sk_callback_sse41+0xf59> - DB 68,15,40,13,213,17,0,0 ; movaps 0x11d5(%rip),%xmm9 # 5400 <_sk_callback_sse41+0xf69> + DB 15,88,13,209,17,0,0 ; addps 0x11d1(%rip),%xmm1 # 5630 <_sk_callback_sse41+0xf5d> + DB 68,15,40,13,217,17,0,0 ; movaps 0x11d9(%rip),%xmm9 # 5640 <_sk_callback_sse41+0xf6d> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -15123,7 +15605,7 @@ _sk_bilinear_py_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,195,17,0,0 ; addps 0x11c3(%rip),%xmm1 # 5410 <_sk_callback_sse41+0xf79> + DB 15,88,13,199,17,0,0 ; addps 0x11c7(%rip),%xmm1 # 5650 <_sk_callback_sse41+0xf7d> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -15133,13 +15615,13 @@ _sk_bicubic_n3x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,182,17,0,0 ; addps 0x11b6(%rip),%xmm0 # 5420 <_sk_callback_sse41+0xf89> - DB 68,15,40,13,190,17,0,0 ; movaps 0x11be(%rip),%xmm9 # 5430 <_sk_callback_sse41+0xf99> + DB 15,88,5,186,17,0,0 ; addps 0x11ba(%rip),%xmm0 # 5660 <_sk_callback_sse41+0xf8d> + DB 68,15,40,13,194,17,0,0 ; movaps 0x11c2(%rip),%xmm9 # 5670 <_sk_callback_sse41+0xf9d> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,186,17,0,0 ; mulps 0x11ba(%rip),%xmm9 # 5440 <_sk_callback_sse41+0xfa9> - DB 68,15,88,13,194,17,0,0 ; addps 0x11c2(%rip),%xmm9 # 5450 <_sk_callback_sse41+0xfb9> + DB 68,15,89,13,190,17,0,0 ; mulps 0x11be(%rip),%xmm9 # 5680 <_sk_callback_sse41+0xfad> + DB 68,15,88,13,198,17,0,0 ; addps 0x11c6(%rip),%xmm9 # 5690 <_sk_callback_sse41+0xfbd> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -15150,16 +15632,16 @@ _sk_bicubic_n1x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,177,17,0,0 ; addps 0x11b1(%rip),%xmm0 # 5460 <_sk_callback_sse41+0xfc9> - DB 68,15,40,13,185,17,0,0 ; movaps 0x11b9(%rip),%xmm9 # 5470 <_sk_callback_sse41+0xfd9> + DB 15,88,5,181,17,0,0 ; addps 0x11b5(%rip),%xmm0 # 56a0 <_sk_callback_sse41+0xfcd> + DB 68,15,40,13,189,17,0,0 ; movaps 0x11bd(%rip),%xmm9 # 56b0 <_sk_callback_sse41+0xfdd> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,189,17,0,0 ; movaps 0x11bd(%rip),%xmm8 # 5480 <_sk_callback_sse41+0xfe9> + DB 68,15,40,5,193,17,0,0 ; movaps 0x11c1(%rip),%xmm8 # 56c0 <_sk_callback_sse41+0xfed> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,193,17,0,0 ; addps 0x11c1(%rip),%xmm8 # 5490 <_sk_callback_sse41+0xff9> + DB 68,15,88,5,197,17,0,0 ; addps 0x11c5(%rip),%xmm8 # 56d0 <_sk_callback_sse41+0xffd> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,197,17,0,0 ; addps 0x11c5(%rip),%xmm8 # 54a0 <_sk_callback_sse41+0x1009> + DB 68,15,88,5,201,17,0,0 ; addps 0x11c9(%rip),%xmm8 # 56e0 <_sk_callback_sse41+0x100d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,201,17,0,0 ; addps 0x11c9(%rip),%xmm8 # 54b0 <_sk_callback_sse41+0x1019> + DB 68,15,88,5,205,17,0,0 ; addps 0x11cd(%rip),%xmm8 # 56f0 <_sk_callback_sse41+0x101d> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -15167,17 +15649,17 @@ _sk_bicubic_n1x_sse41 LABEL PROC PUBLIC _sk_bicubic_p1x_sse41 _sk_bicubic_p1x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,195,17,0,0 ; movaps 0x11c3(%rip),%xmm8 # 54c0 <_sk_callback_sse41+0x1029> + DB 68,15,40,5,199,17,0,0 ; movaps 0x11c7(%rip),%xmm8 # 5700 <_sk_callback_sse41+0x102d> DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,72,64 ; movups 0x40(%rax),%xmm9 DB 65,15,88,192 ; addps %xmm8,%xmm0 - DB 68,15,40,21,191,17,0,0 ; movaps 0x11bf(%rip),%xmm10 # 54d0 <_sk_callback_sse41+0x1039> + DB 68,15,40,21,195,17,0,0 ; movaps 0x11c3(%rip),%xmm10 # 5710 <_sk_callback_sse41+0x103d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,195,17,0,0 ; addps 0x11c3(%rip),%xmm10 # 54e0 <_sk_callback_sse41+0x1049> + DB 68,15,88,21,199,17,0,0 ; addps 0x11c7(%rip),%xmm10 # 5720 <_sk_callback_sse41+0x104d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,191,17,0,0 ; addps 0x11bf(%rip),%xmm10 # 54f0 <_sk_callback_sse41+0x1059> + DB 68,15,88,21,195,17,0,0 ; addps 0x11c3(%rip),%xmm10 # 5730 <_sk_callback_sse41+0x105d> DB 68,15,17,144,128,0,0,0 ; movups %xmm10,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -15187,11 +15669,11 @@ _sk_bicubic_p3x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,178,17,0,0 ; addps 0x11b2(%rip),%xmm0 # 5500 <_sk_callback_sse41+0x1069> + DB 15,88,5,182,17,0,0 ; addps 0x11b6(%rip),%xmm0 # 5740 <_sk_callback_sse41+0x106d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,178,17,0,0 ; mulps 0x11b2(%rip),%xmm8 # 5510 <_sk_callback_sse41+0x1079> - DB 68,15,88,5,186,17,0,0 ; addps 0x11ba(%rip),%xmm8 # 5520 <_sk_callback_sse41+0x1089> + DB 68,15,89,5,182,17,0,0 ; mulps 0x11b6(%rip),%xmm8 # 5750 <_sk_callback_sse41+0x107d> + DB 68,15,88,5,190,17,0,0 ; addps 0x11be(%rip),%xmm8 # 5760 <_sk_callback_sse41+0x108d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -15202,13 +15684,13 @@ _sk_bicubic_n3y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,168,17,0,0 ; addps 0x11a8(%rip),%xmm1 # 5530 <_sk_callback_sse41+0x1099> - DB 68,15,40,13,176,17,0,0 ; movaps 0x11b0(%rip),%xmm9 # 5540 <_sk_callback_sse41+0x10a9> + DB 15,88,13,172,17,0,0 ; addps 0x11ac(%rip),%xmm1 # 5770 <_sk_callback_sse41+0x109d> + DB 68,15,40,13,180,17,0,0 ; movaps 0x11b4(%rip),%xmm9 # 5780 <_sk_callback_sse41+0x10ad> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,172,17,0,0 ; mulps 0x11ac(%rip),%xmm9 # 5550 <_sk_callback_sse41+0x10b9> - DB 68,15,88,13,180,17,0,0 ; addps 0x11b4(%rip),%xmm9 # 5560 <_sk_callback_sse41+0x10c9> + DB 68,15,89,13,176,17,0,0 ; mulps 0x11b0(%rip),%xmm9 # 5790 <_sk_callback_sse41+0x10bd> + DB 68,15,88,13,184,17,0,0 ; addps 0x11b8(%rip),%xmm9 # 57a0 <_sk_callback_sse41+0x10cd> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -15219,16 +15701,16 @@ _sk_bicubic_n1y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,162,17,0,0 ; addps 0x11a2(%rip),%xmm1 # 5570 <_sk_callback_sse41+0x10d9> - DB 68,15,40,13,170,17,0,0 ; movaps 0x11aa(%rip),%xmm9 # 5580 <_sk_callback_sse41+0x10e9> + DB 15,88,13,166,17,0,0 ; addps 0x11a6(%rip),%xmm1 # 57b0 <_sk_callback_sse41+0x10dd> + DB 68,15,40,13,174,17,0,0 ; movaps 0x11ae(%rip),%xmm9 # 57c0 <_sk_callback_sse41+0x10ed> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,174,17,0,0 ; movaps 0x11ae(%rip),%xmm8 # 5590 <_sk_callback_sse41+0x10f9> + DB 68,15,40,5,178,17,0,0 ; movaps 0x11b2(%rip),%xmm8 # 57d0 <_sk_callback_sse41+0x10fd> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,178,17,0,0 ; addps 0x11b2(%rip),%xmm8 # 55a0 <_sk_callback_sse41+0x1109> + DB 68,15,88,5,182,17,0,0 ; addps 0x11b6(%rip),%xmm8 # 57e0 <_sk_callback_sse41+0x110d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,182,17,0,0 ; addps 0x11b6(%rip),%xmm8 # 55b0 <_sk_callback_sse41+0x1119> + DB 68,15,88,5,186,17,0,0 ; addps 0x11ba(%rip),%xmm8 # 57f0 <_sk_callback_sse41+0x111d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,186,17,0,0 ; addps 0x11ba(%rip),%xmm8 # 55c0 <_sk_callback_sse41+0x1129> + DB 68,15,88,5,190,17,0,0 ; addps 0x11be(%rip),%xmm8 # 5800 <_sk_callback_sse41+0x112d> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -15236,17 +15718,17 @@ _sk_bicubic_n1y_sse41 LABEL PROC PUBLIC _sk_bicubic_p1y_sse41 _sk_bicubic_p1y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,180,17,0,0 ; movaps 0x11b4(%rip),%xmm8 # 55d0 <_sk_callback_sse41+0x1139> + DB 68,15,40,5,184,17,0,0 ; movaps 0x11b8(%rip),%xmm8 # 5810 <_sk_callback_sse41+0x113d> DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,72,96 ; movups 0x60(%rax),%xmm9 DB 65,15,88,200 ; addps %xmm8,%xmm1 - DB 68,15,40,21,175,17,0,0 ; movaps 0x11af(%rip),%xmm10 # 55e0 <_sk_callback_sse41+0x1149> + DB 68,15,40,21,179,17,0,0 ; movaps 0x11b3(%rip),%xmm10 # 5820 <_sk_callback_sse41+0x114d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,179,17,0,0 ; addps 0x11b3(%rip),%xmm10 # 55f0 <_sk_callback_sse41+0x1159> + DB 68,15,88,21,183,17,0,0 ; addps 0x11b7(%rip),%xmm10 # 5830 <_sk_callback_sse41+0x115d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,175,17,0,0 ; addps 0x11af(%rip),%xmm10 # 5600 <_sk_callback_sse41+0x1169> + DB 68,15,88,21,179,17,0,0 ; addps 0x11b3(%rip),%xmm10 # 5840 <_sk_callback_sse41+0x116d> DB 68,15,17,144,160,0,0,0 ; movups %xmm10,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -15256,11 +15738,11 @@ _sk_bicubic_p3y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,161,17,0,0 ; addps 0x11a1(%rip),%xmm1 # 5610 <_sk_callback_sse41+0x1179> + DB 15,88,13,165,17,0,0 ; addps 0x11a5(%rip),%xmm1 # 5850 <_sk_callback_sse41+0x117d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,161,17,0,0 ; mulps 0x11a1(%rip),%xmm8 # 5620 <_sk_callback_sse41+0x1189> - DB 68,15,88,5,169,17,0,0 ; addps 0x11a9(%rip),%xmm8 # 5630 <_sk_callback_sse41+0x1199> + DB 68,15,89,5,165,17,0,0 ; mulps 0x11a5(%rip),%xmm8 # 5860 <_sk_callback_sse41+0x118d> + DB 68,15,88,5,173,17,0,0 ; addps 0x11ad(%rip),%xmm8 # 5870 <_sk_callback_sse41+0x119d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -15465,11 +15947,11 @@ ALIGN 16 DB 128,191,0,0,128,191,0 ; cmpb $0x0,-0x40800000(%rdi) DB 0,224 ; add %ah,%al DB 64,0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4728 <.literal16+0x1d8> + DB 224,64 ; loopne 4958 <.literal16+0x1d8> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 472c <.literal16+0x1dc> + DB 224,64 ; loopne 495c <.literal16+0x1dc> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4730 <.literal16+0x1e0> + DB 224,64 ; loopne 4960 <.literal16+0x1e0> DB 154 ; (bad) DB 153 ; cltd DB 153 ; cltd @@ -15489,13 +15971,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4751 <.literal16+0x201> + DB 71,225,61 ; rex.RXB loope 4981 <.literal16+0x201> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4755 <.literal16+0x205> + DB 71,225,61 ; rex.RXB loope 4985 <.literal16+0x205> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4759 <.literal16+0x209> + DB 71,225,61 ; rex.RXB loope 4989 <.literal16+0x209> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 475d <.literal16+0x20d> + DB 71,225,61 ; rex.RXB loope 498d <.literal16+0x20d> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -15520,13 +16002,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4791 <.literal16+0x241> + DB 71,225,61 ; rex.RXB loope 49c1 <.literal16+0x241> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4795 <.literal16+0x245> + DB 71,225,61 ; rex.RXB loope 49c5 <.literal16+0x245> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4799 <.literal16+0x249> + DB 71,225,61 ; rex.RXB loope 49c9 <.literal16+0x249> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 479d <.literal16+0x24d> + DB 71,225,61 ; rex.RXB loope 49cd <.literal16+0x24d> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -15551,13 +16033,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 47d1 <.literal16+0x281> + DB 71,225,61 ; rex.RXB loope 4a01 <.literal16+0x281> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 47d5 <.literal16+0x285> + DB 71,225,61 ; rex.RXB loope 4a05 <.literal16+0x285> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 47d9 <.literal16+0x289> + DB 71,225,61 ; rex.RXB loope 4a09 <.literal16+0x289> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 47dd <.literal16+0x28d> + DB 71,225,61 ; rex.RXB loope 4a0d <.literal16+0x28d> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -15582,13 +16064,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4811 <.literal16+0x2c1> + DB 71,225,61 ; rex.RXB loope 4a41 <.literal16+0x2c1> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4815 <.literal16+0x2c5> + DB 71,225,61 ; rex.RXB loope 4a45 <.literal16+0x2c5> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4819 <.literal16+0x2c9> + DB 71,225,61 ; rex.RXB loope 4a49 <.literal16+0x2c9> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 481d <.literal16+0x2cd> + DB 71,225,61 ; rex.RXB loope 4a4d <.literal16+0x2cd> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -15812,13 +16294,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 49e9 <.literal16+0x499> + DB 224,7 ; loopne 4c19 <.literal16+0x499> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 49ed <.literal16+0x49d> + DB 224,7 ; loopne 4c1d <.literal16+0x49d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 49f1 <.literal16+0x4a1> + DB 224,7 ; loopne 4c21 <.literal16+0x4a1> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 49f5 <.literal16+0x4a5> + DB 224,7 ; loopne 4c25 <.literal16+0x4a5> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -15852,10 +16334,10 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004a38 <_sk_callback_sse41+0xa0005a1> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004c68 <_sk_callback_sse41+0xa000595> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3004a40 <_sk_callback_sse41+0x30005a9> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3004c70 <_sk_callback_sse41+0x300059d> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -15910,11 +16392,11 @@ ALIGN 16 DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4b0b <.literal16+0x5bb> + DB 127,67 ; jg 4d3b <.literal16+0x5bb> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4b0f <.literal16+0x5bf> + DB 127,67 ; jg 4d3f <.literal16+0x5bf> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4b13 <.literal16+0x5c3> + DB 127,67 ; jg 4d43 <.literal16+0x5c3> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,129,128,128,59 ; addb $0x3b,-0x7f7f7ec5(%rax) @@ -15929,16 +16411,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4b04 <.literal16+0x5b4> + DB 127,0 ; jg 4d34 <.literal16+0x5b4> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4b08 <.literal16+0x5b8> + DB 127,0 ; jg 4d38 <.literal16+0x5b8> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4b0c <.literal16+0x5bc> + DB 127,0 ; jg 4d3c <.literal16+0x5bc> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4b10 <.literal16+0x5c0> + DB 127,0 ; jg 4d40 <.literal16+0x5c0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -15947,7 +16429,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4b95 <.literal16+0x645> + DB 119,115 ; ja 4dc5 <.literal16+0x645> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -15958,7 +16440,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4af9 <.literal16+0x5a9> + DB 117,191 ; jne 4d29 <.literal16+0x5a9> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -15970,7 +16452,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a38b3a <_sk_callback_sse41+0xffffffffe9a346a3> + DB 233,220,63,163,233 ; jmpq ffffffffe9a38d6a <_sk_callback_sse41+0xffffffffe9a34697> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -16025,16 +16507,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4bd4 <.literal16+0x684> + DB 127,0 ; jg 4e04 <.literal16+0x684> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4bd8 <.literal16+0x688> + DB 127,0 ; jg 4e08 <.literal16+0x688> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4bdc <.literal16+0x68c> + DB 127,0 ; jg 4e0c <.literal16+0x68c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4be0 <.literal16+0x690> + DB 127,0 ; jg 4e10 <.literal16+0x690> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -16043,7 +16525,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4c65 <.literal16+0x715> + DB 119,115 ; ja 4e95 <.literal16+0x715> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -16054,7 +16536,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4bc9 <.literal16+0x679> + DB 117,191 ; jne 4df9 <.literal16+0x679> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -16066,7 +16548,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a38c0a <_sk_callback_sse41+0xffffffffe9a34773> + DB 233,220,63,163,233 ; jmpq ffffffffe9a38e3a <_sk_callback_sse41+0xffffffffe9a34767> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -16121,16 +16603,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4ca4 <.literal16+0x754> + DB 127,0 ; jg 4ed4 <.literal16+0x754> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4ca8 <.literal16+0x758> + DB 127,0 ; jg 4ed8 <.literal16+0x758> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4cac <.literal16+0x75c> + DB 127,0 ; jg 4edc <.literal16+0x75c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4cb0 <.literal16+0x760> + DB 127,0 ; jg 4ee0 <.literal16+0x760> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -16139,7 +16621,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4d35 <.literal16+0x7e5> + DB 119,115 ; ja 4f65 <.literal16+0x7e5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -16150,7 +16632,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4c99 <.literal16+0x749> + DB 117,191 ; jne 4ec9 <.literal16+0x749> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -16162,7 +16644,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a38cda <_sk_callback_sse41+0xffffffffe9a34843> + DB 233,220,63,163,233 ; jmpq ffffffffe9a38f0a <_sk_callback_sse41+0xffffffffe9a34837> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -16217,16 +16699,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4d74 <.literal16+0x824> + DB 127,0 ; jg 4fa4 <.literal16+0x824> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4d78 <.literal16+0x828> + DB 127,0 ; jg 4fa8 <.literal16+0x828> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4d7c <.literal16+0x82c> + DB 127,0 ; jg 4fac <.literal16+0x82c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4d80 <.literal16+0x830> + DB 127,0 ; jg 4fb0 <.literal16+0x830> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -16235,7 +16717,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4e05 <.literal16+0x8b5> + DB 119,115 ; ja 5035 <.literal16+0x8b5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -16246,7 +16728,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4d69 <.literal16+0x819> + DB 117,191 ; jne 4f99 <.literal16+0x819> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -16258,7 +16740,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a38daa <_sk_callback_sse41+0xffffffffe9a34913> + DB 233,220,63,163,233 ; jmpq ffffffffe9a38fda <_sk_callback_sse41+0xffffffffe9a34907> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -16309,13 +16791,13 @@ ALIGN 16 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 - DB 127,67 ; jg 4e87 <.literal16+0x937> + DB 127,67 ; jg 50b7 <.literal16+0x937> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4e8b <.literal16+0x93b> + DB 127,67 ; jg 50bb <.literal16+0x93b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4e8f <.literal16+0x93f> + DB 127,67 ; jg 50bf <.literal16+0x93f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4e93 <.literal16+0x943> + DB 127,67 ; jg 50c3 <.literal16+0x943> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -16362,16 +16844,16 @@ ALIGN 16 DB 128,3,62 ; addb $0x3e,(%rbx) DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4f13 <.literal16+0x9c3> + DB 118,63 ; jbe 5143 <.literal16+0x9c3> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4f17 <.literal16+0x9c7> + DB 118,63 ; jbe 5147 <.literal16+0x9c7> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4f1b <.literal16+0x9cb> + DB 118,63 ; jbe 514b <.literal16+0x9cb> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4f1f <.literal16+0x9cf> + DB 118,63 ; jbe 514f <.literal16+0x9cf> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) @@ -16383,11 +16865,11 @@ ALIGN 16 DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4f5b <.literal16+0xa0b> + DB 127,67 ; jg 518b <.literal16+0xa0b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4f5f <.literal16+0xa0f> + DB 127,67 ; jg 518f <.literal16+0xa0f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4f63 <.literal16+0xa13> + DB 127,67 ; jg 5193 <.literal16+0xa13> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,0,0,128,63 ; addb $0x3f,-0x7fffffc5(%rax) @@ -16416,7 +16898,7 @@ ALIGN 16 DB 5,255,255,255,9 ; add $0x9ffffff,%eax DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3004f90 <_sk_callback_sse41+0x3000af9> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 30051c0 <_sk_callback_sse41+0x3000aed> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -16445,13 +16927,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4fc9 <.literal16+0xa79> + DB 224,7 ; loopne 51f9 <.literal16+0xa79> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4fcd <.literal16+0xa7d> + DB 224,7 ; loopne 51fd <.literal16+0xa7d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4fd1 <.literal16+0xa81> + DB 224,7 ; loopne 5201 <.literal16+0xa81> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4fd5 <.literal16+0xa85> + DB 224,7 ; loopne 5205 <.literal16+0xa85> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -16497,13 +16979,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 5039 <.literal16+0xae9> + DB 224,7 ; loopne 5269 <.literal16+0xae9> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 503d <.literal16+0xaed> + DB 224,7 ; loopne 526d <.literal16+0xaed> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 5041 <.literal16+0xaf1> + DB 224,7 ; loopne 5271 <.literal16+0xaf1> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 5045 <.literal16+0xaf5> + DB 224,7 ; loopne 5275 <.literal16+0xaf5> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -16541,13 +17023,13 @@ ALIGN 16 DB 65,0,0 ; add %al,(%r8) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 50d6 <.literal16+0xb86> + DB 124,66 ; jl 5306 <.literal16+0xb86> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 50da <.literal16+0xb8a> + DB 124,66 ; jl 530a <.literal16+0xb8a> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 50de <.literal16+0xb8e> + DB 124,66 ; jl 530e <.literal16+0xb8e> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 50e2 <.literal16+0xb92> + DB 124,66 ; jl 5312 <.literal16+0xb92> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 0,240 ; add %dh,%al @@ -16637,13 +17119,13 @@ ALIGN 16 DB 136,136,61,137,136,136 ; mov %cl,-0x777776c3(%rax) DB 61,137,136,136,61 ; cmp $0x3d888889,%eax DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 51e5 <.literal16+0xc95> + DB 112,65 ; jo 5415 <.literal16+0xc95> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 51e9 <.literal16+0xc99> + DB 112,65 ; jo 5419 <.literal16+0xc99> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 51ed <.literal16+0xc9d> + DB 112,65 ; jo 541d <.literal16+0xc9d> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 51f1 <.literal16+0xca1> + DB 112,65 ; jo 5421 <.literal16+0xca1> DB 255,0 ; incl (%rax) DB 0,0 ; add %al,(%rax) DB 255,0 ; incl (%rax) @@ -16658,7 +17140,7 @@ ALIGN 16 DB 5,255,255,255,9 ; add $0x9ffffff,%eax DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 30051e0 <_sk_callback_sse41+0x3000d49> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3005410 <_sk_callback_sse41+0x3000d3d> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -16685,7 +17167,7 @@ ALIGN 16 DB 5,255,255,255,9 ; add $0x9ffffff,%eax DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3005220 <_sk_callback_sse41+0x3000d89> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3005450 <_sk_callback_sse41+0x3000d7d> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -16700,11 +17182,11 @@ ALIGN 16 DB 255,0 ; incl (%rax) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 527b <.literal16+0xd2b> + DB 127,67 ; jg 54ab <.literal16+0xd2b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 527f <.literal16+0xd2f> + DB 127,67 ; jg 54af <.literal16+0xd2f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 5283 <.literal16+0xd33> + DB 127,67 ; jg 54b3 <.literal16+0xd33> DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) DB 0,0 ; add %al,(%rax) DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) @@ -16780,13 +17262,13 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 255 ; (bad) - DB 127,71 ; jg 534b <.literal16+0xdfb> + DB 127,71 ; jg 557b <.literal16+0xdfb> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 534f <.literal16+0xdff> + DB 127,71 ; jg 557f <.literal16+0xdff> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 5353 <.literal16+0xe03> + DB 127,71 ; jg 5583 <.literal16+0xe03> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 5357 <.literal16+0xe07> + DB 127,71 ; jg 5587 <.literal16+0xe07> DB 208 ; (bad) DB 179,89 ; mov $0x59,%bl DB 62,208 ; ds (bad) @@ -16815,19 +17297,27 @@ ALIGN 16 DB 221,147,61,152,221,147 ; fstl -0x6c2267c3(%rbx) DB 61,152,221,147,61 ; cmp $0x3d93dd98,%eax DB 152 ; cwtl - DB 221,147,61,111,43,231 ; fstl -0x18d490c3(%rbx) - DB 187,111,43,231,187 ; mov $0xbbe72b6f,%ebx + DB 221,147,61,1,0,0 ; fstl 0x13d(%rbx) + DB 0,1 ; add %al,(%rcx) + DB 0,0 ; add %al,(%rax) + DB 0,1 ; add %al,(%rcx) + DB 0,0 ; add %al,(%rax) + DB 0,1 ; add %al,(%rcx) + DB 0,0 ; add %al,(%rax) + DB 0,111,43 ; add %ch,0x2b(%rdi) + DB 231,187 ; out %eax,$0xbb DB 111 ; outsl %ds:(%rsi),(%dx) DB 43,231 ; sub %edi,%esp DB 187,111,43,231,187 ; mov $0xbbe72b6f,%ebx + DB 111 ; outsl %ds:(%rsi),(%dx) + DB 43,231 ; sub %edi,%esp + DB 187,159,215,202,60 ; mov $0x3ccad79f,%ebx DB 159 ; lahf DB 215 ; xlat %ds:(%rbx) DB 202,60,159 ; lret $0x9f3c DB 215 ; xlat %ds:(%rbx) DB 202,60,159 ; lret $0x9f3c DB 215 ; xlat %ds:(%rbx) - DB 202,60,159 ; lret $0x9f3c - DB 215 ; xlat %ds:(%rbx) DB 202,60,212 ; lret $0xd43c DB 100,84 ; fs push %rsp DB 189,212,100,84,189 ; mov $0xbd5464d4,%ebp @@ -16912,11 +17402,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 5462 <.literal16+0xf12> + DB 62,114,28 ; jb,pt 56a2 <.literal16+0xf22> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5466 <.literal16+0xf16> + DB 62,114,28 ; jb,pt 56a6 <.literal16+0xf26> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 546a <.literal16+0xf1a> + DB 62,114,28 ; jb,pt 56aa <.literal16+0xf2a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -16960,7 +17450,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e2f5 <_sk_callback_sse41+0x3d639e5e> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e535 <_sk_callback_sse41+0x3d639e62> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -16986,7 +17476,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e335 <_sk_callback_sse41+0x3d639e9e> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e575 <_sk_callback_sse41+0x3d639ea2> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -16995,13 +17485,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 552e <.literal16+0xfde> + DB 114,28 ; jb 576e <.literal16+0xfee> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5532 <.literal16+0xfe2> + DB 62,114,28 ; jb,pt 5772 <.literal16+0xff2> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5536 <.literal16+0xfe6> + DB 62,114,28 ; jb,pt 5776 <.literal16+0xff6> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 553a <.literal16+0xfea> + DB 62,114,28 ; jb,pt 577a <.literal16+0xffa> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -17022,11 +17512,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 5572 <.literal16+0x1022> + DB 62,114,28 ; jb,pt 57b2 <.literal16+0x1032> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5576 <.literal16+0x1026> + DB 62,114,28 ; jb,pt 57b6 <.literal16+0x1036> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 557a <.literal16+0x102a> + DB 62,114,28 ; jb,pt 57ba <.literal16+0x103a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -17070,7 +17560,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e405 <_sk_callback_sse41+0x3d639f6e> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e645 <_sk_callback_sse41+0x3d639f72> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -17096,7 +17586,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e445 <_sk_callback_sse41+0x3d639fae> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e685 <_sk_callback_sse41+0x3d639fb2> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -17105,13 +17595,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 563e <.literal16+0x10ee> + DB 114,28 ; jb 587e <.literal16+0x10fe> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5642 <_sk_callback_sse41+0x11ab> + DB 62,114,28 ; jb,pt 5882 <_sk_callback_sse41+0x11af> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5646 <_sk_callback_sse41+0x11af> + DB 62,114,28 ; jb,pt 5886 <_sk_callback_sse41+0x11b3> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 564a <_sk_callback_sse41+0x11b3> + DB 62,114,28 ; jb,pt 588a <_sk_callback_sse41+0x11b7> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -17202,7 +17692,7 @@ _sk_seed_shader_sse2 LABEL PROC DB 102,15,110,199 ; movd %edi,%xmm0 DB 102,15,112,192,0 ; pshufd $0x0,%xmm0,%xmm0 DB 15,91,200 ; cvtdq2ps %xmm0,%xmm1 - DB 15,40,21,241,72,0,0 ; movaps 0x48f1(%rip),%xmm2 # 4a00 <_sk_callback_sse2+0xb2> + DB 15,40,21,225,74,0,0 ; movaps 0x4ae1(%rip),%xmm2 # 4bf0 <_sk_callback_sse2+0xb1> DB 15,88,202 ; addps %xmm2,%xmm1 DB 15,16,2 ; movups (%rdx),%xmm0 DB 15,88,193 ; addps %xmm1,%xmm0 @@ -17211,7 +17701,7 @@ _sk_seed_shader_sse2 LABEL PROC DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 15,88,202 ; addps %xmm2,%xmm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,21,224,72,0,0 ; movaps 0x48e0(%rip),%xmm2 # 4a10 <_sk_callback_sse2+0xc2> + DB 15,40,21,208,74,0,0 ; movaps 0x4ad0(%rip),%xmm2 # 4c00 <_sk_callback_sse2+0xc1> DB 15,87,219 ; xorps %xmm3,%xmm3 DB 15,87,228 ; xorps %xmm4,%xmm4 DB 15,87,237 ; xorps %xmm5,%xmm5 @@ -17232,14 +17722,14 @@ _sk_dither_sse2 LABEL PROC DB 102,68,15,110,1 ; movd (%rcx),%xmm8 DB 102,69,15,112,192,0 ; pshufd $0x0,%xmm8,%xmm8 DB 102,69,15,239,193 ; pxor %xmm9,%xmm8 - DB 102,68,15,111,21,165,72,0,0 ; movdqa 0x48a5(%rip),%xmm10 # 4a20 <_sk_callback_sse2+0xd2> + DB 102,68,15,111,21,149,74,0,0 ; movdqa 0x4a95(%rip),%xmm10 # 4c10 <_sk_callback_sse2+0xd1> DB 102,69,15,111,216 ; movdqa %xmm8,%xmm11 DB 102,69,15,219,218 ; pand %xmm10,%xmm11 DB 102,65,15,114,243,5 ; pslld $0x5,%xmm11 DB 102,69,15,219,209 ; pand %xmm9,%xmm10 DB 102,65,15,114,242,4 ; pslld $0x4,%xmm10 - DB 102,68,15,111,37,145,72,0,0 ; movdqa 0x4891(%rip),%xmm12 # 4a30 <_sk_callback_sse2+0xe2> - DB 102,68,15,111,45,152,72,0,0 ; movdqa 0x4898(%rip),%xmm13 # 4a40 <_sk_callback_sse2+0xf2> + DB 102,68,15,111,37,129,74,0,0 ; movdqa 0x4a81(%rip),%xmm12 # 4c20 <_sk_callback_sse2+0xe1> + DB 102,68,15,111,45,136,74,0,0 ; movdqa 0x4a88(%rip),%xmm13 # 4c30 <_sk_callback_sse2+0xf1> DB 102,69,15,111,240 ; movdqa %xmm8,%xmm14 DB 102,69,15,219,245 ; pand %xmm13,%xmm14 DB 102,65,15,114,246,2 ; pslld $0x2,%xmm14 @@ -17255,8 +17745,8 @@ _sk_dither_sse2 LABEL PROC DB 102,69,15,235,245 ; por %xmm13,%xmm14 DB 102,69,15,235,240 ; por %xmm8,%xmm14 DB 69,15,91,198 ; cvtdq2ps %xmm14,%xmm8 - DB 68,15,89,5,83,72,0,0 ; mulps 0x4853(%rip),%xmm8 # 4a50 <_sk_callback_sse2+0x102> - DB 68,15,88,5,91,72,0,0 ; addps 0x485b(%rip),%xmm8 # 4a60 <_sk_callback_sse2+0x112> + DB 68,15,89,5,67,74,0,0 ; mulps 0x4a43(%rip),%xmm8 # 4c40 <_sk_callback_sse2+0x101> + DB 68,15,88,5,75,74,0,0 ; addps 0x4a4b(%rip),%xmm8 # 4c50 <_sk_callback_sse2+0x111> DB 243,68,15,16,72,8 ; movss 0x8(%rax),%xmm9 DB 69,15,198,201,0 ; shufps $0x0,%xmm9,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 @@ -17312,7 +17802,7 @@ _sk_clear_sse2 LABEL PROC PUBLIC _sk_srcatop_sse2 _sk_srcatop_sse2 LABEL PROC DB 15,89,199 ; mulps %xmm7,%xmm0 - DB 68,15,40,5,222,71,0,0 ; movaps 0x47de(%rip),%xmm8 # 4a70 <_sk_callback_sse2+0x122> + DB 68,15,40,5,206,73,0,0 ; movaps 0x49ce(%rip),%xmm8 # 4c60 <_sk_callback_sse2+0x121> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -17335,7 +17825,7 @@ PUBLIC _sk_dstatop_sse2 _sk_dstatop_sse2 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 DB 68,15,89,196 ; mulps %xmm4,%xmm8 - DB 68,15,40,13,161,71,0,0 ; movaps 0x47a1(%rip),%xmm9 # 4a80 <_sk_callback_sse2+0x132> + DB 68,15,40,13,145,73,0,0 ; movaps 0x4991(%rip),%xmm9 # 4c70 <_sk_callback_sse2+0x131> DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,88,192 ; addps %xmm8,%xmm0 @@ -17376,7 +17866,7 @@ _sk_dstin_sse2 LABEL PROC PUBLIC _sk_srcout_sse2 _sk_srcout_sse2 LABEL PROC - DB 68,15,40,5,69,71,0,0 ; movaps 0x4745(%rip),%xmm8 # 4a90 <_sk_callback_sse2+0x142> + DB 68,15,40,5,53,73,0,0 ; movaps 0x4935(%rip),%xmm8 # 4c80 <_sk_callback_sse2+0x141> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 @@ -17387,7 +17877,7 @@ _sk_srcout_sse2 LABEL PROC PUBLIC _sk_dstout_sse2 _sk_dstout_sse2 LABEL PROC - DB 68,15,40,5,53,71,0,0 ; movaps 0x4735(%rip),%xmm8 # 4aa0 <_sk_callback_sse2+0x152> + DB 68,15,40,5,37,73,0,0 ; movaps 0x4925(%rip),%xmm8 # 4c90 <_sk_callback_sse2+0x151> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 15,89,196 ; mulps %xmm4,%xmm0 @@ -17402,7 +17892,7 @@ _sk_dstout_sse2 LABEL PROC PUBLIC _sk_srcover_sse2 _sk_srcover_sse2 LABEL PROC - DB 68,15,40,5,24,71,0,0 ; movaps 0x4718(%rip),%xmm8 # 4ab0 <_sk_callback_sse2+0x162> + DB 68,15,40,5,8,73,0,0 ; movaps 0x4908(%rip),%xmm8 # 4ca0 <_sk_callback_sse2+0x161> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -17420,7 +17910,7 @@ _sk_srcover_sse2 LABEL PROC PUBLIC _sk_dstover_sse2 _sk_dstover_sse2 LABEL PROC - DB 68,15,40,5,236,70,0,0 ; movaps 0x46ec(%rip),%xmm8 # 4ac0 <_sk_callback_sse2+0x172> + DB 68,15,40,5,220,72,0,0 ; movaps 0x48dc(%rip),%xmm8 # 4cb0 <_sk_callback_sse2+0x171> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -17444,7 +17934,7 @@ _sk_modulate_sse2 LABEL PROC PUBLIC _sk_multiply_sse2 _sk_multiply_sse2 LABEL PROC - DB 68,15,40,5,192,70,0,0 ; movaps 0x46c0(%rip),%xmm8 # 4ad0 <_sk_callback_sse2+0x182> + DB 68,15,40,5,176,72,0,0 ; movaps 0x48b0(%rip),%xmm8 # 4cc0 <_sk_callback_sse2+0x181> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 69,15,40,209 ; movaps %xmm9,%xmm10 @@ -17514,7 +18004,7 @@ _sk_screen_sse2 LABEL PROC PUBLIC _sk_xor__sse2 _sk_xor__sse2 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 - DB 15,40,29,241,69,0,0 ; movaps 0x45f1(%rip),%xmm3 # 4ae0 <_sk_callback_sse2+0x192> + DB 15,40,29,225,71,0,0 ; movaps 0x47e1(%rip),%xmm3 # 4cd0 <_sk_callback_sse2+0x191> DB 68,15,40,203 ; movaps %xmm3,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 @@ -17560,7 +18050,7 @@ _sk_darken_sse2 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,95,209 ; maxps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,92,69,0,0 ; movaps 0x455c(%rip),%xmm2 # 4af0 <_sk_callback_sse2+0x1a2> + DB 15,40,21,76,71,0,0 ; movaps 0x474c(%rip),%xmm2 # 4ce0 <_sk_callback_sse2+0x1a1> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -17592,7 +18082,7 @@ _sk_lighten_sse2 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,1,69,0,0 ; movaps 0x4501(%rip),%xmm2 # 4b00 <_sk_callback_sse2+0x1b2> + DB 15,40,21,241,70,0,0 ; movaps 0x46f1(%rip),%xmm2 # 4cf0 <_sk_callback_sse2+0x1b1> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -17627,7 +18117,7 @@ _sk_difference_sse2 LABEL PROC DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,155,68,0,0 ; movaps 0x449b(%rip),%xmm2 # 4b10 <_sk_callback_sse2+0x1c2> + DB 15,40,21,139,70,0,0 ; movaps 0x468b(%rip),%xmm2 # 4d00 <_sk_callback_sse2+0x1c1> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -17652,7 +18142,7 @@ _sk_exclusion_sse2 LABEL PROC DB 15,89,214 ; mulps %xmm6,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,202 ; subps %xmm2,%xmm9 - DB 15,40,13,92,68,0,0 ; movaps 0x445c(%rip),%xmm1 # 4b20 <_sk_callback_sse2+0x1d2> + DB 15,40,13,76,70,0,0 ; movaps 0x464c(%rip),%xmm1 # 4d10 <_sk_callback_sse2+0x1d1> DB 15,92,203 ; subps %xmm3,%xmm1 DB 15,89,207 ; mulps %xmm7,%xmm1 DB 15,88,217 ; addps %xmm1,%xmm3 @@ -17664,7 +18154,7 @@ _sk_exclusion_sse2 LABEL PROC PUBLIC _sk_colorburn_sse2 _sk_colorburn_sse2 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,40,21,75,68,0,0 ; movaps 0x444b(%rip),%xmm10 # 4b30 <_sk_callback_sse2+0x1e2> + DB 68,15,40,21,59,70,0,0 ; movaps 0x463b(%rip),%xmm10 # 4d20 <_sk_callback_sse2+0x1e1> DB 69,15,40,202 ; movaps %xmm10,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 69,15,40,217 ; movaps %xmm9,%xmm11 @@ -17756,7 +18246,7 @@ _sk_colorburn_sse2 LABEL PROC PUBLIC _sk_colordodge_sse2 _sk_colordodge_sse2 LABEL PROC DB 68,15,40,200 ; movaps %xmm0,%xmm9 - DB 68,15,40,21,1,67,0,0 ; movaps 0x4301(%rip),%xmm10 # 4b40 <_sk_callback_sse2+0x1f2> + DB 68,15,40,21,241,68,0,0 ; movaps 0x44f1(%rip),%xmm10 # 4d30 <_sk_callback_sse2+0x1f1> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 69,15,40,227 ; movaps %xmm11,%xmm12 @@ -17849,7 +18339,7 @@ _sk_hardlight_sse2 LABEL PROC DB 15,41,52,36 ; movaps %xmm6,(%rsp) DB 15,40,245 ; movaps %xmm5,%xmm6 DB 15,40,236 ; movaps %xmm4,%xmm5 - DB 68,15,40,29,179,65,0,0 ; movaps 0x41b3(%rip),%xmm11 # 4b50 <_sk_callback_sse2+0x202> + DB 68,15,40,29,163,67,0,0 ; movaps 0x43a3(%rip),%xmm11 # 4d40 <_sk_callback_sse2+0x201> DB 69,15,40,211 ; movaps %xmm11,%xmm10 DB 68,15,92,215 ; subps %xmm7,%xmm10 DB 69,15,40,194 ; movaps %xmm10,%xmm8 @@ -17936,7 +18426,7 @@ PUBLIC _sk_overlay_sse2 _sk_overlay_sse2 LABEL PROC DB 68,15,40,193 ; movaps %xmm1,%xmm8 DB 68,15,40,232 ; movaps %xmm0,%xmm13 - DB 68,15,40,13,126,64,0,0 ; movaps 0x407e(%rip),%xmm9 # 4b60 <_sk_callback_sse2+0x212> + DB 68,15,40,13,110,66,0,0 ; movaps 0x426e(%rip),%xmm9 # 4d50 <_sk_callback_sse2+0x211> DB 69,15,40,209 ; movaps %xmm9,%xmm10 DB 68,15,92,215 ; subps %xmm7,%xmm10 DB 69,15,40,218 ; movaps %xmm10,%xmm11 @@ -18026,7 +18516,7 @@ _sk_softlight_sse2 LABEL PROC DB 68,15,40,213 ; movaps %xmm5,%xmm10 DB 68,15,94,215 ; divps %xmm7,%xmm10 DB 69,15,84,212 ; andps %xmm12,%xmm10 - DB 68,15,40,13,56,63,0,0 ; movaps 0x3f38(%rip),%xmm9 # 4b70 <_sk_callback_sse2+0x222> + DB 68,15,40,13,40,65,0,0 ; movaps 0x4128(%rip),%xmm9 # 4d60 <_sk_callback_sse2+0x221> DB 69,15,40,249 ; movaps %xmm9,%xmm15 DB 69,15,92,250 ; subps %xmm10,%xmm15 DB 69,15,40,218 ; movaps %xmm10,%xmm11 @@ -18039,10 +18529,10 @@ _sk_softlight_sse2 LABEL PROC DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 15,89,192 ; mulps %xmm0,%xmm0 DB 65,15,88,194 ; addps %xmm10,%xmm0 - DB 68,15,40,53,18,63,0,0 ; movaps 0x3f12(%rip),%xmm14 # 4b80 <_sk_callback_sse2+0x232> + DB 68,15,40,53,2,65,0,0 ; movaps 0x4102(%rip),%xmm14 # 4d70 <_sk_callback_sse2+0x231> DB 69,15,88,222 ; addps %xmm14,%xmm11 DB 68,15,89,216 ; mulps %xmm0,%xmm11 - DB 68,15,40,21,18,63,0,0 ; movaps 0x3f12(%rip),%xmm10 # 4b90 <_sk_callback_sse2+0x242> + DB 68,15,40,21,2,65,0,0 ; movaps 0x4102(%rip),%xmm10 # 4d80 <_sk_callback_sse2+0x241> DB 69,15,89,234 ; mulps %xmm10,%xmm13 DB 69,15,88,235 ; addps %xmm11,%xmm13 DB 15,88,228 ; addps %xmm4,%xmm4 @@ -18187,7 +18677,7 @@ _sk_hue_sse2 LABEL PROC DB 68,15,40,209 ; movaps %xmm1,%xmm10 DB 68,15,40,225 ; movaps %xmm1,%xmm12 DB 68,15,89,211 ; mulps %xmm3,%xmm10 - DB 68,15,40,5,78,61,0,0 ; movaps 0x3d4e(%rip),%xmm8 # 4bd0 <_sk_callback_sse2+0x282> + DB 68,15,40,5,62,63,0,0 ; movaps 0x3f3e(%rip),%xmm8 # 4dc0 <_sk_callback_sse2+0x281> DB 69,15,40,216 ; movaps %xmm8,%xmm11 DB 15,40,207 ; movaps %xmm7,%xmm1 DB 68,15,92,217 ; subps %xmm1,%xmm11 @@ -18233,12 +18723,12 @@ _sk_hue_sse2 LABEL PROC DB 69,15,84,206 ; andps %xmm14,%xmm9 DB 69,15,84,214 ; andps %xmm14,%xmm10 DB 65,15,84,214 ; andps %xmm14,%xmm2 - DB 68,15,40,61,98,60,0,0 ; movaps 0x3c62(%rip),%xmm15 # 4ba0 <_sk_callback_sse2+0x252> + DB 68,15,40,61,82,62,0,0 ; movaps 0x3e52(%rip),%xmm15 # 4d90 <_sk_callback_sse2+0x251> DB 65,15,89,231 ; mulps %xmm15,%xmm4 - DB 15,40,5,103,60,0,0 ; movaps 0x3c67(%rip),%xmm0 # 4bb0 <_sk_callback_sse2+0x262> + DB 15,40,5,87,62,0,0 ; movaps 0x3e57(%rip),%xmm0 # 4da0 <_sk_callback_sse2+0x261> DB 15,89,240 ; mulps %xmm0,%xmm6 DB 15,88,244 ; addps %xmm4,%xmm6 - DB 68,15,40,53,105,60,0,0 ; movaps 0x3c69(%rip),%xmm14 # 4bc0 <_sk_callback_sse2+0x272> + DB 68,15,40,53,89,62,0,0 ; movaps 0x3e59(%rip),%xmm14 # 4db0 <_sk_callback_sse2+0x271> DB 68,15,40,239 ; movaps %xmm7,%xmm13 DB 69,15,89,238 ; mulps %xmm14,%xmm13 DB 68,15,88,238 ; addps %xmm6,%xmm13 @@ -18415,14 +18905,14 @@ _sk_saturation_sse2 LABEL PROC DB 68,15,84,211 ; andps %xmm3,%xmm10 DB 68,15,84,203 ; andps %xmm3,%xmm9 DB 15,84,195 ; andps %xmm3,%xmm0 - DB 68,15,40,5,249,57,0,0 ; movaps 0x39f9(%rip),%xmm8 # 4be0 <_sk_callback_sse2+0x292> + DB 68,15,40,5,233,59,0,0 ; movaps 0x3be9(%rip),%xmm8 # 4dd0 <_sk_callback_sse2+0x291> DB 15,40,214 ; movaps %xmm6,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 - DB 15,40,13,251,57,0,0 ; movaps 0x39fb(%rip),%xmm1 # 4bf0 <_sk_callback_sse2+0x2a2> + DB 15,40,13,235,59,0,0 ; movaps 0x3beb(%rip),%xmm1 # 4de0 <_sk_callback_sse2+0x2a1> DB 15,40,221 ; movaps %xmm5,%xmm3 DB 15,89,217 ; mulps %xmm1,%xmm3 DB 15,88,218 ; addps %xmm2,%xmm3 - DB 68,15,40,37,250,57,0,0 ; movaps 0x39fa(%rip),%xmm12 # 4c00 <_sk_callback_sse2+0x2b2> + DB 68,15,40,37,234,59,0,0 ; movaps 0x3bea(%rip),%xmm12 # 4df0 <_sk_callback_sse2+0x2b1> DB 69,15,89,236 ; mulps %xmm12,%xmm13 DB 68,15,88,235 ; addps %xmm3,%xmm13 DB 65,15,40,210 ; movaps %xmm10,%xmm2 @@ -18467,7 +18957,7 @@ _sk_saturation_sse2 LABEL PROC DB 15,40,223 ; movaps %xmm7,%xmm3 DB 15,40,236 ; movaps %xmm4,%xmm5 DB 15,89,221 ; mulps %xmm5,%xmm3 - DB 68,15,40,5,95,57,0,0 ; movaps 0x395f(%rip),%xmm8 # 4c10 <_sk_callback_sse2+0x2c2> + DB 68,15,40,5,79,59,0,0 ; movaps 0x3b4f(%rip),%xmm8 # 4e00 <_sk_callback_sse2+0x2c1> DB 65,15,40,224 ; movaps %xmm8,%xmm4 DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 15,88,253 ; addps %xmm5,%xmm7 @@ -18568,14 +19058,14 @@ _sk_color_sse2 LABEL PROC DB 68,15,40,213 ; movaps %xmm5,%xmm10 DB 69,15,89,208 ; mulps %xmm8,%xmm10 DB 65,15,40,208 ; movaps %xmm8,%xmm2 - DB 68,15,40,45,247,55,0,0 ; movaps 0x37f7(%rip),%xmm13 # 4c20 <_sk_callback_sse2+0x2d2> + DB 68,15,40,45,231,57,0,0 ; movaps 0x39e7(%rip),%xmm13 # 4e10 <_sk_callback_sse2+0x2d1> DB 68,15,40,198 ; movaps %xmm6,%xmm8 DB 69,15,89,197 ; mulps %xmm13,%xmm8 - DB 68,15,40,53,247,55,0,0 ; movaps 0x37f7(%rip),%xmm14 # 4c30 <_sk_callback_sse2+0x2e2> + DB 68,15,40,53,231,57,0,0 ; movaps 0x39e7(%rip),%xmm14 # 4e20 <_sk_callback_sse2+0x2e1> DB 65,15,40,195 ; movaps %xmm11,%xmm0 DB 65,15,89,198 ; mulps %xmm14,%xmm0 DB 65,15,88,192 ; addps %xmm8,%xmm0 - DB 68,15,40,29,243,55,0,0 ; movaps 0x37f3(%rip),%xmm11 # 4c40 <_sk_callback_sse2+0x2f2> + DB 68,15,40,29,227,57,0,0 ; movaps 0x39e3(%rip),%xmm11 # 4e30 <_sk_callback_sse2+0x2f1> DB 69,15,89,227 ; mulps %xmm11,%xmm12 DB 68,15,88,224 ; addps %xmm0,%xmm12 DB 65,15,40,193 ; movaps %xmm9,%xmm0 @@ -18583,7 +19073,7 @@ _sk_color_sse2 LABEL PROC DB 69,15,40,250 ; movaps %xmm10,%xmm15 DB 69,15,89,254 ; mulps %xmm14,%xmm15 DB 68,15,88,248 ; addps %xmm0,%xmm15 - DB 68,15,40,5,223,55,0,0 ; movaps 0x37df(%rip),%xmm8 # 4c50 <_sk_callback_sse2+0x302> + DB 68,15,40,5,207,57,0,0 ; movaps 0x39cf(%rip),%xmm8 # 4e40 <_sk_callback_sse2+0x301> DB 65,15,40,224 ; movaps %xmm8,%xmm4 DB 15,92,226 ; subps %xmm2,%xmm4 DB 15,89,252 ; mulps %xmm4,%xmm7 @@ -18719,15 +19209,15 @@ _sk_luminosity_sse2 LABEL PROC DB 68,15,40,205 ; movaps %xmm5,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 DB 15,89,222 ; mulps %xmm6,%xmm3 - DB 68,15,40,37,241,53,0,0 ; movaps 0x35f1(%rip),%xmm12 # 4c60 <_sk_callback_sse2+0x312> + DB 68,15,40,37,225,55,0,0 ; movaps 0x37e1(%rip),%xmm12 # 4e50 <_sk_callback_sse2+0x311> DB 68,15,40,199 ; movaps %xmm7,%xmm8 DB 69,15,89,196 ; mulps %xmm12,%xmm8 - DB 68,15,40,45,241,53,0,0 ; movaps 0x35f1(%rip),%xmm13 # 4c70 <_sk_callback_sse2+0x322> + DB 68,15,40,45,225,55,0,0 ; movaps 0x37e1(%rip),%xmm13 # 4e60 <_sk_callback_sse2+0x321> DB 68,15,40,241 ; movaps %xmm1,%xmm14 DB 69,15,89,245 ; mulps %xmm13,%xmm14 DB 69,15,88,240 ; addps %xmm8,%xmm14 - DB 68,15,40,29,237,53,0,0 ; movaps 0x35ed(%rip),%xmm11 # 4c80 <_sk_callback_sse2+0x332> - DB 68,15,40,5,245,53,0,0 ; movaps 0x35f5(%rip),%xmm8 # 4c90 <_sk_callback_sse2+0x342> + DB 68,15,40,29,221,55,0,0 ; movaps 0x37dd(%rip),%xmm11 # 4e70 <_sk_callback_sse2+0x331> + DB 68,15,40,5,229,55,0,0 ; movaps 0x37e5(%rip),%xmm8 # 4e80 <_sk_callback_sse2+0x341> DB 69,15,40,248 ; movaps %xmm8,%xmm15 DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 68,15,92,248 ; subps %xmm0,%xmm15 @@ -18869,7 +19359,7 @@ _sk_clamp_0_sse2 LABEL PROC PUBLIC _sk_clamp_1_sse2 _sk_clamp_1_sse2 LABEL PROC - DB 68,15,40,5,252,51,0,0 ; movaps 0x33fc(%rip),%xmm8 # 4ca0 <_sk_callback_sse2+0x352> + DB 68,15,40,5,236,53,0,0 ; movaps 0x35ec(%rip),%xmm8 # 4e90 <_sk_callback_sse2+0x351> DB 65,15,93,192 ; minps %xmm8,%xmm0 DB 65,15,93,200 ; minps %xmm8,%xmm1 DB 65,15,93,208 ; minps %xmm8,%xmm2 @@ -18879,7 +19369,7 @@ _sk_clamp_1_sse2 LABEL PROC PUBLIC _sk_clamp_a_sse2 _sk_clamp_a_sse2 LABEL PROC - DB 15,93,29,241,51,0,0 ; minps 0x33f1(%rip),%xmm3 # 4cb0 <_sk_callback_sse2+0x362> + DB 15,93,29,225,53,0,0 ; minps 0x35e1(%rip),%xmm3 # 4ea0 <_sk_callback_sse2+0x361> DB 15,93,195 ; minps %xmm3,%xmm0 DB 15,93,203 ; minps %xmm3,%xmm1 DB 15,93,211 ; minps %xmm3,%xmm2 @@ -18952,7 +19442,7 @@ _sk_premul_sse2 LABEL PROC PUBLIC _sk_unpremul_sse2 _sk_unpremul_sse2 LABEL PROC DB 69,15,87,192 ; xorps %xmm8,%xmm8 - DB 68,15,40,13,92,51,0,0 ; movaps 0x335c(%rip),%xmm9 # 4cc0 <_sk_callback_sse2+0x372> + DB 68,15,40,13,76,53,0,0 ; movaps 0x354c(%rip),%xmm9 # 4eb0 <_sk_callback_sse2+0x371> DB 68,15,94,203 ; divps %xmm3,%xmm9 DB 68,15,194,195,4 ; cmpneqps %xmm3,%xmm8 DB 69,15,84,193 ; andps %xmm9,%xmm8 @@ -18964,20 +19454,20 @@ _sk_unpremul_sse2 LABEL PROC PUBLIC _sk_from_srgb_sse2 _sk_from_srgb_sse2 LABEL PROC - DB 68,15,40,5,71,51,0,0 ; movaps 0x3347(%rip),%xmm8 # 4cd0 <_sk_callback_sse2+0x382> + DB 68,15,40,5,55,53,0,0 ; movaps 0x3537(%rip),%xmm8 # 4ec0 <_sk_callback_sse2+0x381> DB 68,15,40,232 ; movaps %xmm0,%xmm13 DB 69,15,89,232 ; mulps %xmm8,%xmm13 DB 68,15,40,216 ; movaps %xmm0,%xmm11 DB 69,15,89,219 ; mulps %xmm11,%xmm11 - DB 68,15,40,13,63,51,0,0 ; movaps 0x333f(%rip),%xmm9 # 4ce0 <_sk_callback_sse2+0x392> + DB 68,15,40,13,47,53,0,0 ; movaps 0x352f(%rip),%xmm9 # 4ed0 <_sk_callback_sse2+0x391> DB 68,15,40,240 ; movaps %xmm0,%xmm14 DB 69,15,89,241 ; mulps %xmm9,%xmm14 - DB 68,15,40,21,63,51,0,0 ; movaps 0x333f(%rip),%xmm10 # 4cf0 <_sk_callback_sse2+0x3a2> + DB 68,15,40,21,47,53,0,0 ; movaps 0x352f(%rip),%xmm10 # 4ee0 <_sk_callback_sse2+0x3a1> DB 69,15,88,242 ; addps %xmm10,%xmm14 DB 69,15,89,243 ; mulps %xmm11,%xmm14 - DB 68,15,40,29,63,51,0,0 ; movaps 0x333f(%rip),%xmm11 # 4d00 <_sk_callback_sse2+0x3b2> + DB 68,15,40,29,47,53,0,0 ; movaps 0x352f(%rip),%xmm11 # 4ef0 <_sk_callback_sse2+0x3b1> DB 69,15,88,243 ; addps %xmm11,%xmm14 - DB 68,15,40,37,67,51,0,0 ; movaps 0x3343(%rip),%xmm12 # 4d10 <_sk_callback_sse2+0x3c2> + DB 68,15,40,37,51,53,0,0 ; movaps 0x3533(%rip),%xmm12 # 4f00 <_sk_callback_sse2+0x3c1> DB 65,15,194,196,1 ; cmpltps %xmm12,%xmm0 DB 68,15,84,232 ; andps %xmm0,%xmm13 DB 65,15,85,198 ; andnps %xmm14,%xmm0 @@ -19014,20 +19504,20 @@ _sk_to_srgb_sse2 LABEL PROC DB 68,15,82,192 ; rsqrtps %xmm0,%xmm8 DB 69,15,83,200 ; rcpps %xmm8,%xmm9 DB 69,15,82,232 ; rsqrtps %xmm8,%xmm13 - DB 68,15,40,5,200,50,0,0 ; movaps 0x32c8(%rip),%xmm8 # 4d20 <_sk_callback_sse2+0x3d2> + DB 68,15,40,5,184,52,0,0 ; movaps 0x34b8(%rip),%xmm8 # 4f10 <_sk_callback_sse2+0x3d1> DB 68,15,40,240 ; movaps %xmm0,%xmm14 DB 69,15,89,240 ; mulps %xmm8,%xmm14 - DB 68,15,40,21,200,50,0,0 ; movaps 0x32c8(%rip),%xmm10 # 4d30 <_sk_callback_sse2+0x3e2> + DB 68,15,40,21,184,52,0,0 ; movaps 0x34b8(%rip),%xmm10 # 4f20 <_sk_callback_sse2+0x3e1> DB 69,15,89,202 ; mulps %xmm10,%xmm9 - DB 68,15,40,29,204,50,0,0 ; movaps 0x32cc(%rip),%xmm11 # 4d40 <_sk_callback_sse2+0x3f2> + DB 68,15,40,29,188,52,0,0 ; movaps 0x34bc(%rip),%xmm11 # 4f30 <_sk_callback_sse2+0x3f1> DB 69,15,88,203 ; addps %xmm11,%xmm9 - DB 68,15,40,37,208,50,0,0 ; movaps 0x32d0(%rip),%xmm12 # 4d50 <_sk_callback_sse2+0x402> + DB 68,15,40,37,192,52,0,0 ; movaps 0x34c0(%rip),%xmm12 # 4f40 <_sk_callback_sse2+0x401> DB 69,15,89,236 ; mulps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,40,13,208,50,0,0 ; movaps 0x32d0(%rip),%xmm9 # 4d60 <_sk_callback_sse2+0x412> + DB 68,15,40,13,192,52,0,0 ; movaps 0x34c0(%rip),%xmm9 # 4f50 <_sk_callback_sse2+0x411> DB 69,15,40,249 ; movaps %xmm9,%xmm15 DB 69,15,93,253 ; minps %xmm13,%xmm15 - DB 68,15,40,45,208,50,0,0 ; movaps 0x32d0(%rip),%xmm13 # 4d70 <_sk_callback_sse2+0x422> + DB 68,15,40,45,192,52,0,0 ; movaps 0x34c0(%rip),%xmm13 # 4f60 <_sk_callback_sse2+0x421> DB 65,15,194,197,1 ; cmpltps %xmm13,%xmm0 DB 68,15,84,240 ; andps %xmm0,%xmm14 DB 65,15,85,199 ; andnps %xmm15,%xmm0 @@ -19075,7 +19565,7 @@ _sk_rgb_to_hsl_sse2 LABEL PROC DB 68,15,93,218 ; minps %xmm2,%xmm11 DB 65,15,40,202 ; movaps %xmm10,%xmm1 DB 65,15,92,203 ; subps %xmm11,%xmm1 - DB 68,15,40,45,41,50,0,0 ; movaps 0x3229(%rip),%xmm13 # 4d80 <_sk_callback_sse2+0x432> + DB 68,15,40,45,25,52,0,0 ; movaps 0x3419(%rip),%xmm13 # 4f70 <_sk_callback_sse2+0x431> DB 68,15,94,233 ; divps %xmm1,%xmm13 DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 65,15,194,192,0 ; cmpeqps %xmm8,%xmm0 @@ -19084,30 +19574,30 @@ _sk_rgb_to_hsl_sse2 LABEL PROC DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,40,241 ; movaps %xmm9,%xmm14 DB 68,15,194,242,1 ; cmpltps %xmm2,%xmm14 - DB 68,15,84,53,15,50,0,0 ; andps 0x320f(%rip),%xmm14 # 4d90 <_sk_callback_sse2+0x442> + DB 68,15,84,53,255,51,0,0 ; andps 0x33ff(%rip),%xmm14 # 4f80 <_sk_callback_sse2+0x441> DB 69,15,88,244 ; addps %xmm12,%xmm14 DB 69,15,40,250 ; movaps %xmm10,%xmm15 DB 69,15,194,249,0 ; cmpeqps %xmm9,%xmm15 DB 65,15,92,208 ; subps %xmm8,%xmm2 DB 65,15,89,213 ; mulps %xmm13,%xmm2 - DB 68,15,40,37,2,50,0,0 ; movaps 0x3202(%rip),%xmm12 # 4da0 <_sk_callback_sse2+0x452> + DB 68,15,40,37,242,51,0,0 ; movaps 0x33f2(%rip),%xmm12 # 4f90 <_sk_callback_sse2+0x451> DB 65,15,88,212 ; addps %xmm12,%xmm2 DB 69,15,92,193 ; subps %xmm9,%xmm8 DB 69,15,89,197 ; mulps %xmm13,%xmm8 - DB 68,15,88,5,254,49,0,0 ; addps 0x31fe(%rip),%xmm8 # 4db0 <_sk_callback_sse2+0x462> + DB 68,15,88,5,238,51,0,0 ; addps 0x33ee(%rip),%xmm8 # 4fa0 <_sk_callback_sse2+0x461> DB 65,15,84,215 ; andps %xmm15,%xmm2 DB 69,15,85,248 ; andnps %xmm8,%xmm15 DB 68,15,86,250 ; orps %xmm2,%xmm15 DB 68,15,84,240 ; andps %xmm0,%xmm14 DB 65,15,85,199 ; andnps %xmm15,%xmm0 DB 65,15,86,198 ; orps %xmm14,%xmm0 - DB 15,89,5,239,49,0,0 ; mulps 0x31ef(%rip),%xmm0 # 4dc0 <_sk_callback_sse2+0x472> + DB 15,89,5,223,51,0,0 ; mulps 0x33df(%rip),%xmm0 # 4fb0 <_sk_callback_sse2+0x471> DB 69,15,40,194 ; movaps %xmm10,%xmm8 DB 69,15,194,195,4 ; cmpneqps %xmm11,%xmm8 DB 65,15,84,192 ; andps %xmm8,%xmm0 DB 69,15,92,226 ; subps %xmm10,%xmm12 DB 69,15,88,211 ; addps %xmm11,%xmm10 - DB 68,15,40,13,226,49,0,0 ; movaps 0x31e2(%rip),%xmm9 # 4dd0 <_sk_callback_sse2+0x482> + DB 68,15,40,13,210,51,0,0 ; movaps 0x33d2(%rip),%xmm9 # 4fc0 <_sk_callback_sse2+0x481> DB 65,15,40,210 ; movaps %xmm10,%xmm2 DB 65,15,89,209 ; mulps %xmm9,%xmm2 DB 68,15,194,202,1 ; cmpltps %xmm2,%xmm9 @@ -19130,7 +19620,7 @@ _sk_hsl_to_rgb_sse2 LABEL PROC DB 15,41,92,36,32 ; movaps %xmm3,0x20(%rsp) DB 68,15,40,218 ; movaps %xmm2,%xmm11 DB 15,40,240 ; movaps %xmm0,%xmm6 - DB 68,15,40,13,157,49,0,0 ; movaps 0x319d(%rip),%xmm9 # 4de0 <_sk_callback_sse2+0x492> + DB 68,15,40,13,141,51,0,0 ; movaps 0x338d(%rip),%xmm9 # 4fd0 <_sk_callback_sse2+0x491> DB 69,15,40,209 ; movaps %xmm9,%xmm10 DB 69,15,194,211,2 ; cmpleps %xmm11,%xmm10 DB 15,40,193 ; movaps %xmm1,%xmm0 @@ -19147,28 +19637,28 @@ _sk_hsl_to_rgb_sse2 LABEL PROC DB 69,15,88,211 ; addps %xmm11,%xmm10 DB 69,15,88,219 ; addps %xmm11,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 15,40,5,103,49,0,0 ; movaps 0x3167(%rip),%xmm0 # 4df0 <_sk_callback_sse2+0x4a2> + DB 15,40,5,87,51,0,0 ; movaps 0x3357(%rip),%xmm0 # 4fe0 <_sk_callback_sse2+0x4a1> DB 15,88,198 ; addps %xmm6,%xmm0 DB 243,15,91,200 ; cvttps2dq %xmm0,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 15,40,216 ; movaps %xmm0,%xmm3 DB 15,194,217,1 ; cmpltps %xmm1,%xmm3 - DB 15,84,29,95,49,0,0 ; andps 0x315f(%rip),%xmm3 # 4e00 <_sk_callback_sse2+0x4b2> + DB 15,84,29,79,51,0,0 ; andps 0x334f(%rip),%xmm3 # 4ff0 <_sk_callback_sse2+0x4b1> DB 15,92,203 ; subps %xmm3,%xmm1 DB 15,92,193 ; subps %xmm1,%xmm0 - DB 68,15,40,45,97,49,0,0 ; movaps 0x3161(%rip),%xmm13 # 4e10 <_sk_callback_sse2+0x4c2> + DB 68,15,40,45,81,51,0,0 ; movaps 0x3351(%rip),%xmm13 # 5000 <_sk_callback_sse2+0x4c1> DB 69,15,40,197 ; movaps %xmm13,%xmm8 DB 68,15,194,192,2 ; cmpleps %xmm0,%xmm8 DB 69,15,40,242 ; movaps %xmm10,%xmm14 DB 69,15,92,243 ; subps %xmm11,%xmm14 DB 65,15,40,217 ; movaps %xmm9,%xmm3 DB 15,194,216,2 ; cmpleps %xmm0,%xmm3 - DB 15,40,21,113,49,0,0 ; movaps 0x3171(%rip),%xmm2 # 4e40 <_sk_callback_sse2+0x4f2> + DB 15,40,21,97,51,0,0 ; movaps 0x3361(%rip),%xmm2 # 5030 <_sk_callback_sse2+0x4f1> DB 68,15,40,250 ; movaps %xmm2,%xmm15 DB 68,15,194,248,2 ; cmpleps %xmm0,%xmm15 - DB 15,40,13,65,49,0,0 ; movaps 0x3141(%rip),%xmm1 # 4e20 <_sk_callback_sse2+0x4d2> + DB 15,40,13,49,51,0,0 ; movaps 0x3331(%rip),%xmm1 # 5010 <_sk_callback_sse2+0x4d1> DB 15,89,193 ; mulps %xmm1,%xmm0 - DB 15,40,45,71,49,0,0 ; movaps 0x3147(%rip),%xmm5 # 4e30 <_sk_callback_sse2+0x4e2> + DB 15,40,45,55,51,0,0 ; movaps 0x3337(%rip),%xmm5 # 5020 <_sk_callback_sse2+0x4e1> DB 15,40,229 ; movaps %xmm5,%xmm4 DB 15,92,224 ; subps %xmm0,%xmm4 DB 65,15,89,230 ; mulps %xmm14,%xmm4 @@ -19191,7 +19681,7 @@ _sk_hsl_to_rgb_sse2 LABEL PROC DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 DB 15,40,222 ; movaps %xmm6,%xmm3 DB 15,194,216,1 ; cmpltps %xmm0,%xmm3 - DB 15,84,29,188,48,0,0 ; andps 0x30bc(%rip),%xmm3 # 4e00 <_sk_callback_sse2+0x4b2> + DB 15,84,29,172,50,0,0 ; andps 0x32ac(%rip),%xmm3 # 4ff0 <_sk_callback_sse2+0x4b1> DB 15,92,195 ; subps %xmm3,%xmm0 DB 68,15,40,230 ; movaps %xmm6,%xmm12 DB 68,15,92,224 ; subps %xmm0,%xmm12 @@ -19221,12 +19711,12 @@ _sk_hsl_to_rgb_sse2 LABEL PROC DB 15,40,60,36 ; movaps (%rsp),%xmm7 DB 15,40,231 ; movaps %xmm7,%xmm4 DB 15,85,227 ; andnps %xmm3,%xmm4 - DB 15,88,53,149,48,0,0 ; addps 0x3095(%rip),%xmm6 # 4e50 <_sk_callback_sse2+0x502> + DB 15,88,53,133,50,0,0 ; addps 0x3285(%rip),%xmm6 # 5040 <_sk_callback_sse2+0x501> DB 243,15,91,198 ; cvttps2dq %xmm6,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 DB 15,40,222 ; movaps %xmm6,%xmm3 DB 15,194,216,1 ; cmpltps %xmm0,%xmm3 - DB 15,84,29,48,48,0,0 ; andps 0x3030(%rip),%xmm3 # 4e00 <_sk_callback_sse2+0x4b2> + DB 15,84,29,32,50,0,0 ; andps 0x3220(%rip),%xmm3 # 4ff0 <_sk_callback_sse2+0x4b1> DB 15,92,195 ; subps %xmm3,%xmm0 DB 15,92,240 ; subps %xmm0,%xmm6 DB 15,89,206 ; mulps %xmm6,%xmm1 @@ -19287,7 +19777,7 @@ _sk_scale_u8_sse2 LABEL PROC DB 102,69,15,96,193 ; punpcklbw %xmm9,%xmm8 DB 102,69,15,97,193 ; punpcklwd %xmm9,%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,186,47,0,0 ; mulps 0x2fba(%rip),%xmm8 # 4e60 <_sk_callback_sse2+0x512> + DB 68,15,89,5,170,49,0,0 ; mulps 0x31aa(%rip),%xmm8 # 5050 <_sk_callback_sse2+0x511> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 65,15,89,208 ; mulps %xmm8,%xmm2 @@ -19324,7 +19814,7 @@ _sk_lerp_u8_sse2 LABEL PROC DB 102,69,15,96,193 ; punpcklbw %xmm9,%xmm8 DB 102,69,15,97,193 ; punpcklwd %xmm9,%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,88,47,0,0 ; mulps 0x2f58(%rip),%xmm8 # 4e70 <_sk_callback_sse2+0x522> + DB 68,15,89,5,72,49,0,0 ; mulps 0x3148(%rip),%xmm8 # 5060 <_sk_callback_sse2+0x521> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -19347,17 +19837,17 @@ _sk_lerp_565_sse2 LABEL PROC DB 243,68,15,126,20,120 ; movq (%rax,%rdi,2),%xmm10 DB 102,69,15,239,192 ; pxor %xmm8,%xmm8 DB 102,69,15,97,208 ; punpcklwd %xmm8,%xmm10 - DB 102,68,15,111,5,30,47,0,0 ; movdqa 0x2f1e(%rip),%xmm8 # 4e80 <_sk_callback_sse2+0x532> + DB 102,68,15,111,5,14,49,0,0 ; movdqa 0x310e(%rip),%xmm8 # 5070 <_sk_callback_sse2+0x531> DB 102,69,15,219,194 ; pand %xmm10,%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,29,47,0,0 ; mulps 0x2f1d(%rip),%xmm8 # 4e90 <_sk_callback_sse2+0x542> - DB 102,68,15,111,13,36,47,0,0 ; movdqa 0x2f24(%rip),%xmm9 # 4ea0 <_sk_callback_sse2+0x552> + DB 68,15,89,5,13,49,0,0 ; mulps 0x310d(%rip),%xmm8 # 5080 <_sk_callback_sse2+0x541> + DB 102,68,15,111,13,20,49,0,0 ; movdqa 0x3114(%rip),%xmm9 # 5090 <_sk_callback_sse2+0x551> DB 102,69,15,219,202 ; pand %xmm10,%xmm9 DB 69,15,91,201 ; cvtdq2ps %xmm9,%xmm9 - DB 68,15,89,13,35,47,0,0 ; mulps 0x2f23(%rip),%xmm9 # 4eb0 <_sk_callback_sse2+0x562> - DB 102,68,15,219,21,42,47,0,0 ; pand 0x2f2a(%rip),%xmm10 # 4ec0 <_sk_callback_sse2+0x572> + DB 68,15,89,13,19,49,0,0 ; mulps 0x3113(%rip),%xmm9 # 50a0 <_sk_callback_sse2+0x561> + DB 102,68,15,219,21,26,49,0,0 ; pand 0x311a(%rip),%xmm10 # 50b0 <_sk_callback_sse2+0x571> DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 - DB 68,15,89,21,46,47,0,0 ; mulps 0x2f2e(%rip),%xmm10 # 4ed0 <_sk_callback_sse2+0x582> + DB 68,15,89,21,30,49,0,0 ; mulps 0x311e(%rip),%xmm10 # 50c0 <_sk_callback_sse2+0x581> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -19386,7 +19876,7 @@ _sk_load_tables_sse2 LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,139,72,8 ; mov 0x8(%rax),%r9 DB 243,69,15,111,12,184 ; movdqu (%r8,%rdi,4),%xmm9 - DB 102,68,15,111,5,222,46,0,0 ; movdqa 0x2ede(%rip),%xmm8 # 4ee0 <_sk_callback_sse2+0x592> + DB 102,68,15,111,5,206,48,0,0 ; movdqa 0x30ce(%rip),%xmm8 # 50d0 <_sk_callback_sse2+0x591> DB 102,65,15,111,193 ; movdqa %xmm9,%xmm0 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,15,112,200,78 ; pshufd $0x4e,%xmm0,%xmm1 @@ -19441,7 +19931,7 @@ _sk_load_tables_sse2 LABEL PROC DB 65,15,20,208 ; unpcklps %xmm8,%xmm2 DB 102,65,15,114,209,24 ; psrld $0x18,%xmm9 DB 65,15,91,217 ; cvtdq2ps %xmm9,%xmm3 - DB 15,89,29,235,45,0,0 ; mulps 0x2deb(%rip),%xmm3 # 4ef0 <_sk_callback_sse2+0x5a2> + DB 15,89,29,219,47,0,0 ; mulps 0x2fdb(%rip),%xmm3 # 50e0 <_sk_callback_sse2+0x5a1> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -19458,7 +19948,7 @@ _sk_load_tables_u16_be_sse2 LABEL PROC DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,97,200 ; punpcklwd %xmm0,%xmm1 DB 102,68,15,105,200 ; punpckhwd %xmm0,%xmm9 - DB 102,68,15,111,21,190,45,0,0 ; movdqa 0x2dbe(%rip),%xmm10 # 4f00 <_sk_callback_sse2+0x5b2> + DB 102,68,15,111,21,174,47,0,0 ; movdqa 0x2fae(%rip),%xmm10 # 50f0 <_sk_callback_sse2+0x5b1> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,194 ; pand %xmm10,%xmm0 DB 102,69,15,239,192 ; pxor %xmm8,%xmm8 @@ -19519,7 +20009,7 @@ _sk_load_tables_u16_be_sse2 LABEL PROC DB 102,65,15,235,217 ; por %xmm9,%xmm3 DB 102,65,15,97,216 ; punpcklwd %xmm8,%xmm3 DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,173,44,0,0 ; mulps 0x2cad(%rip),%xmm3 # 4f10 <_sk_callback_sse2+0x5c2> + DB 15,89,29,157,46,0,0 ; mulps 0x2e9d(%rip),%xmm3 # 5100 <_sk_callback_sse2+0x5c1> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -19539,7 +20029,7 @@ _sk_load_tables_rgb_u16_be_sse2 LABEL PROC DB 102,68,15,97,208 ; punpcklwd %xmm0,%xmm10 DB 102,65,15,111,195 ; movdqa %xmm11,%xmm0 DB 102,65,15,97,194 ; punpcklwd %xmm10,%xmm0 - DB 102,68,15,111,5,109,44,0,0 ; movdqa 0x2c6d(%rip),%xmm8 # 4f20 <_sk_callback_sse2+0x5d2> + DB 102,68,15,111,5,93,46,0,0 ; movdqa 0x2e5d(%rip),%xmm8 # 5110 <_sk_callback_sse2+0x5d1> DB 102,15,112,200,78 ; pshufd $0x4e,%xmm0,%xmm1 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,69,15,239,201 ; pxor %xmm9,%xmm9 @@ -19594,7 +20084,7 @@ _sk_load_tables_rgb_u16_be_sse2 LABEL PROC DB 15,20,211 ; unpcklps %xmm3,%xmm2 DB 65,15,20,208 ; unpcklps %xmm8,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,124,43,0,0 ; movaps 0x2b7c(%rip),%xmm3 # 4f30 <_sk_callback_sse2+0x5e2> + DB 15,40,29,108,45,0,0 ; movaps 0x2d6c(%rip),%xmm3 # 5120 <_sk_callback_sse2+0x5e1> DB 255,224 ; jmpq *%rax PUBLIC _sk_byte_tables_sse2 @@ -19602,7 +20092,7 @@ _sk_byte_tables_sse2 LABEL PROC DB 65,86 ; push %r14 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,125,43,0,0 ; movaps 0x2b7d(%rip),%xmm8 # 4f40 <_sk_callback_sse2+0x5f2> + DB 68,15,40,5,109,45,0,0 ; movaps 0x2d6d(%rip),%xmm8 # 5130 <_sk_callback_sse2+0x5f1> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,91,192 ; cvtps2dq %xmm0,%xmm0 DB 102,72,15,126,193 ; movq %xmm0,%rcx @@ -19629,7 +20119,7 @@ _sk_byte_tables_sse2 LABEL PROC DB 102,65,15,96,193 ; punpcklbw %xmm9,%xmm0 DB 102,65,15,97,193 ; punpcklwd %xmm9,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,21,26,43,0,0 ; movaps 0x2b1a(%rip),%xmm10 # 4f50 <_sk_callback_sse2+0x602> + DB 68,15,40,21,10,45,0,0 ; movaps 0x2d0a(%rip),%xmm10 # 5140 <_sk_callback_sse2+0x601> DB 65,15,89,194 ; mulps %xmm10,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -19743,7 +20233,7 @@ _sk_byte_tables_rgb_sse2 LABEL PROC DB 102,65,15,96,193 ; punpcklbw %xmm9,%xmm0 DB 102,65,15,97,193 ; punpcklwd %xmm9,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,21,109,41,0,0 ; movaps 0x296d(%rip),%xmm10 # 4f60 <_sk_callback_sse2+0x612> + DB 68,15,40,21,93,43,0,0 ; movaps 0x2b5d(%rip),%xmm10 # 5150 <_sk_callback_sse2+0x611> DB 65,15,89,194 ; mulps %xmm10,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -19930,15 +20420,15 @@ _sk_parametric_r_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,172,38,0,0 ; mulps 0x26ac(%rip),%xmm9 # 4f70 <_sk_callback_sse2+0x622> - DB 68,15,84,21,180,38,0,0 ; andps 0x26b4(%rip),%xmm10 # 4f80 <_sk_callback_sse2+0x632> - DB 68,15,86,21,188,38,0,0 ; orps 0x26bc(%rip),%xmm10 # 4f90 <_sk_callback_sse2+0x642> - DB 68,15,88,13,196,38,0,0 ; addps 0x26c4(%rip),%xmm9 # 4fa0 <_sk_callback_sse2+0x652> - DB 68,15,40,37,204,38,0,0 ; movaps 0x26cc(%rip),%xmm12 # 4fb0 <_sk_callback_sse2+0x662> + DB 68,15,89,13,156,40,0,0 ; mulps 0x289c(%rip),%xmm9 # 5160 <_sk_callback_sse2+0x621> + DB 68,15,84,21,164,40,0,0 ; andps 0x28a4(%rip),%xmm10 # 5170 <_sk_callback_sse2+0x631> + DB 68,15,86,21,172,40,0,0 ; orps 0x28ac(%rip),%xmm10 # 5180 <_sk_callback_sse2+0x641> + DB 68,15,88,13,180,40,0,0 ; addps 0x28b4(%rip),%xmm9 # 5190 <_sk_callback_sse2+0x651> + DB 68,15,40,37,188,40,0,0 ; movaps 0x28bc(%rip),%xmm12 # 51a0 <_sk_callback_sse2+0x661> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,204,38,0,0 ; addps 0x26cc(%rip),%xmm10 # 4fc0 <_sk_callback_sse2+0x672> - DB 68,15,40,37,212,38,0,0 ; movaps 0x26d4(%rip),%xmm12 # 4fd0 <_sk_callback_sse2+0x682> + DB 68,15,88,21,188,40,0,0 ; addps 0x28bc(%rip),%xmm10 # 51b0 <_sk_callback_sse2+0x671> + DB 68,15,40,37,196,40,0,0 ; movaps 0x28c4(%rip),%xmm12 # 51c0 <_sk_callback_sse2+0x681> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -19946,22 +20436,22 @@ _sk_parametric_r_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,190,38,0,0 ; movaps 0x26be(%rip),%xmm10 # 4fe0 <_sk_callback_sse2+0x692> + DB 68,15,40,21,174,40,0,0 ; movaps 0x28ae(%rip),%xmm10 # 51d0 <_sk_callback_sse2+0x691> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,178,38,0,0 ; addps 0x26b2(%rip),%xmm9 # 4ff0 <_sk_callback_sse2+0x6a2> - DB 68,15,40,37,186,38,0,0 ; movaps 0x26ba(%rip),%xmm12 # 5000 <_sk_callback_sse2+0x6b2> + DB 68,15,88,13,162,40,0,0 ; addps 0x28a2(%rip),%xmm9 # 51e0 <_sk_callback_sse2+0x6a1> + DB 68,15,40,37,170,40,0,0 ; movaps 0x28aa(%rip),%xmm12 # 51f0 <_sk_callback_sse2+0x6b1> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,186,38,0,0 ; movaps 0x26ba(%rip),%xmm12 # 5010 <_sk_callback_sse2+0x6c2> + DB 68,15,40,37,170,40,0,0 ; movaps 0x28aa(%rip),%xmm12 # 5200 <_sk_callback_sse2+0x6c1> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,190,38,0,0 ; movaps 0x26be(%rip),%xmm13 # 5020 <_sk_callback_sse2+0x6d2> + DB 68,15,40,45,174,40,0,0 ; movaps 0x28ae(%rip),%xmm13 # 5210 <_sk_callback_sse2+0x6d1> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,190,38,0,0 ; mulps 0x26be(%rip),%xmm13 # 5030 <_sk_callback_sse2+0x6e2> + DB 68,15,89,45,174,40,0,0 ; mulps 0x28ae(%rip),%xmm13 # 5220 <_sk_callback_sse2+0x6e1> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -19995,15 +20485,15 @@ _sk_parametric_g_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,62,38,0,0 ; mulps 0x263e(%rip),%xmm9 # 5040 <_sk_callback_sse2+0x6f2> - DB 68,15,84,21,70,38,0,0 ; andps 0x2646(%rip),%xmm10 # 5050 <_sk_callback_sse2+0x702> - DB 68,15,86,21,78,38,0,0 ; orps 0x264e(%rip),%xmm10 # 5060 <_sk_callback_sse2+0x712> - DB 68,15,88,13,86,38,0,0 ; addps 0x2656(%rip),%xmm9 # 5070 <_sk_callback_sse2+0x722> - DB 68,15,40,37,94,38,0,0 ; movaps 0x265e(%rip),%xmm12 # 5080 <_sk_callback_sse2+0x732> + DB 68,15,89,13,46,40,0,0 ; mulps 0x282e(%rip),%xmm9 # 5230 <_sk_callback_sse2+0x6f1> + DB 68,15,84,21,54,40,0,0 ; andps 0x2836(%rip),%xmm10 # 5240 <_sk_callback_sse2+0x701> + DB 68,15,86,21,62,40,0,0 ; orps 0x283e(%rip),%xmm10 # 5250 <_sk_callback_sse2+0x711> + DB 68,15,88,13,70,40,0,0 ; addps 0x2846(%rip),%xmm9 # 5260 <_sk_callback_sse2+0x721> + DB 68,15,40,37,78,40,0,0 ; movaps 0x284e(%rip),%xmm12 # 5270 <_sk_callback_sse2+0x731> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,94,38,0,0 ; addps 0x265e(%rip),%xmm10 # 5090 <_sk_callback_sse2+0x742> - DB 68,15,40,37,102,38,0,0 ; movaps 0x2666(%rip),%xmm12 # 50a0 <_sk_callback_sse2+0x752> + DB 68,15,88,21,78,40,0,0 ; addps 0x284e(%rip),%xmm10 # 5280 <_sk_callback_sse2+0x741> + DB 68,15,40,37,86,40,0,0 ; movaps 0x2856(%rip),%xmm12 # 5290 <_sk_callback_sse2+0x751> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -20011,22 +20501,22 @@ _sk_parametric_g_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,80,38,0,0 ; movaps 0x2650(%rip),%xmm10 # 50b0 <_sk_callback_sse2+0x762> + DB 68,15,40,21,64,40,0,0 ; movaps 0x2840(%rip),%xmm10 # 52a0 <_sk_callback_sse2+0x761> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,68,38,0,0 ; addps 0x2644(%rip),%xmm9 # 50c0 <_sk_callback_sse2+0x772> - DB 68,15,40,37,76,38,0,0 ; movaps 0x264c(%rip),%xmm12 # 50d0 <_sk_callback_sse2+0x782> + DB 68,15,88,13,52,40,0,0 ; addps 0x2834(%rip),%xmm9 # 52b0 <_sk_callback_sse2+0x771> + DB 68,15,40,37,60,40,0,0 ; movaps 0x283c(%rip),%xmm12 # 52c0 <_sk_callback_sse2+0x781> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,76,38,0,0 ; movaps 0x264c(%rip),%xmm12 # 50e0 <_sk_callback_sse2+0x792> + DB 68,15,40,37,60,40,0,0 ; movaps 0x283c(%rip),%xmm12 # 52d0 <_sk_callback_sse2+0x791> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,80,38,0,0 ; movaps 0x2650(%rip),%xmm13 # 50f0 <_sk_callback_sse2+0x7a2> + DB 68,15,40,45,64,40,0,0 ; movaps 0x2840(%rip),%xmm13 # 52e0 <_sk_callback_sse2+0x7a1> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,80,38,0,0 ; mulps 0x2650(%rip),%xmm13 # 5100 <_sk_callback_sse2+0x7b2> + DB 68,15,89,45,64,40,0,0 ; mulps 0x2840(%rip),%xmm13 # 52f0 <_sk_callback_sse2+0x7b1> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -20060,15 +20550,15 @@ _sk_parametric_b_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,208,37,0,0 ; mulps 0x25d0(%rip),%xmm9 # 5110 <_sk_callback_sse2+0x7c2> - DB 68,15,84,21,216,37,0,0 ; andps 0x25d8(%rip),%xmm10 # 5120 <_sk_callback_sse2+0x7d2> - DB 68,15,86,21,224,37,0,0 ; orps 0x25e0(%rip),%xmm10 # 5130 <_sk_callback_sse2+0x7e2> - DB 68,15,88,13,232,37,0,0 ; addps 0x25e8(%rip),%xmm9 # 5140 <_sk_callback_sse2+0x7f2> - DB 68,15,40,37,240,37,0,0 ; movaps 0x25f0(%rip),%xmm12 # 5150 <_sk_callback_sse2+0x802> + DB 68,15,89,13,192,39,0,0 ; mulps 0x27c0(%rip),%xmm9 # 5300 <_sk_callback_sse2+0x7c1> + DB 68,15,84,21,200,39,0,0 ; andps 0x27c8(%rip),%xmm10 # 5310 <_sk_callback_sse2+0x7d1> + DB 68,15,86,21,208,39,0,0 ; orps 0x27d0(%rip),%xmm10 # 5320 <_sk_callback_sse2+0x7e1> + DB 68,15,88,13,216,39,0,0 ; addps 0x27d8(%rip),%xmm9 # 5330 <_sk_callback_sse2+0x7f1> + DB 68,15,40,37,224,39,0,0 ; movaps 0x27e0(%rip),%xmm12 # 5340 <_sk_callback_sse2+0x801> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,240,37,0,0 ; addps 0x25f0(%rip),%xmm10 # 5160 <_sk_callback_sse2+0x812> - DB 68,15,40,37,248,37,0,0 ; movaps 0x25f8(%rip),%xmm12 # 5170 <_sk_callback_sse2+0x822> + DB 68,15,88,21,224,39,0,0 ; addps 0x27e0(%rip),%xmm10 # 5350 <_sk_callback_sse2+0x811> + DB 68,15,40,37,232,39,0,0 ; movaps 0x27e8(%rip),%xmm12 # 5360 <_sk_callback_sse2+0x821> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -20076,22 +20566,22 @@ _sk_parametric_b_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,226,37,0,0 ; movaps 0x25e2(%rip),%xmm10 # 5180 <_sk_callback_sse2+0x832> + DB 68,15,40,21,210,39,0,0 ; movaps 0x27d2(%rip),%xmm10 # 5370 <_sk_callback_sse2+0x831> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,214,37,0,0 ; addps 0x25d6(%rip),%xmm9 # 5190 <_sk_callback_sse2+0x842> - DB 68,15,40,37,222,37,0,0 ; movaps 0x25de(%rip),%xmm12 # 51a0 <_sk_callback_sse2+0x852> + DB 68,15,88,13,198,39,0,0 ; addps 0x27c6(%rip),%xmm9 # 5380 <_sk_callback_sse2+0x841> + DB 68,15,40,37,206,39,0,0 ; movaps 0x27ce(%rip),%xmm12 # 5390 <_sk_callback_sse2+0x851> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,222,37,0,0 ; movaps 0x25de(%rip),%xmm12 # 51b0 <_sk_callback_sse2+0x862> + DB 68,15,40,37,206,39,0,0 ; movaps 0x27ce(%rip),%xmm12 # 53a0 <_sk_callback_sse2+0x861> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,226,37,0,0 ; movaps 0x25e2(%rip),%xmm13 # 51c0 <_sk_callback_sse2+0x872> + DB 68,15,40,45,210,39,0,0 ; movaps 0x27d2(%rip),%xmm13 # 53b0 <_sk_callback_sse2+0x871> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,226,37,0,0 ; mulps 0x25e2(%rip),%xmm13 # 51d0 <_sk_callback_sse2+0x882> + DB 68,15,89,45,210,39,0,0 ; mulps 0x27d2(%rip),%xmm13 # 53c0 <_sk_callback_sse2+0x881> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -20125,15 +20615,15 @@ _sk_parametric_a_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,98,37,0,0 ; mulps 0x2562(%rip),%xmm9 # 51e0 <_sk_callback_sse2+0x892> - DB 68,15,84,21,106,37,0,0 ; andps 0x256a(%rip),%xmm10 # 51f0 <_sk_callback_sse2+0x8a2> - DB 68,15,86,21,114,37,0,0 ; orps 0x2572(%rip),%xmm10 # 5200 <_sk_callback_sse2+0x8b2> - DB 68,15,88,13,122,37,0,0 ; addps 0x257a(%rip),%xmm9 # 5210 <_sk_callback_sse2+0x8c2> - DB 68,15,40,37,130,37,0,0 ; movaps 0x2582(%rip),%xmm12 # 5220 <_sk_callback_sse2+0x8d2> + DB 68,15,89,13,82,39,0,0 ; mulps 0x2752(%rip),%xmm9 # 53d0 <_sk_callback_sse2+0x891> + DB 68,15,84,21,90,39,0,0 ; andps 0x275a(%rip),%xmm10 # 53e0 <_sk_callback_sse2+0x8a1> + DB 68,15,86,21,98,39,0,0 ; orps 0x2762(%rip),%xmm10 # 53f0 <_sk_callback_sse2+0x8b1> + DB 68,15,88,13,106,39,0,0 ; addps 0x276a(%rip),%xmm9 # 5400 <_sk_callback_sse2+0x8c1> + DB 68,15,40,37,114,39,0,0 ; movaps 0x2772(%rip),%xmm12 # 5410 <_sk_callback_sse2+0x8d1> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,130,37,0,0 ; addps 0x2582(%rip),%xmm10 # 5230 <_sk_callback_sse2+0x8e2> - DB 68,15,40,37,138,37,0,0 ; movaps 0x258a(%rip),%xmm12 # 5240 <_sk_callback_sse2+0x8f2> + DB 68,15,88,21,114,39,0,0 ; addps 0x2772(%rip),%xmm10 # 5420 <_sk_callback_sse2+0x8e1> + DB 68,15,40,37,122,39,0,0 ; movaps 0x277a(%rip),%xmm12 # 5430 <_sk_callback_sse2+0x8f1> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -20141,22 +20631,22 @@ _sk_parametric_a_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,116,37,0,0 ; movaps 0x2574(%rip),%xmm10 # 5250 <_sk_callback_sse2+0x902> + DB 68,15,40,21,100,39,0,0 ; movaps 0x2764(%rip),%xmm10 # 5440 <_sk_callback_sse2+0x901> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,104,37,0,0 ; addps 0x2568(%rip),%xmm9 # 5260 <_sk_callback_sse2+0x912> - DB 68,15,40,37,112,37,0,0 ; movaps 0x2570(%rip),%xmm12 # 5270 <_sk_callback_sse2+0x922> + DB 68,15,88,13,88,39,0,0 ; addps 0x2758(%rip),%xmm9 # 5450 <_sk_callback_sse2+0x911> + DB 68,15,40,37,96,39,0,0 ; movaps 0x2760(%rip),%xmm12 # 5460 <_sk_callback_sse2+0x921> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,112,37,0,0 ; movaps 0x2570(%rip),%xmm12 # 5280 <_sk_callback_sse2+0x932> + DB 68,15,40,37,96,39,0,0 ; movaps 0x2760(%rip),%xmm12 # 5470 <_sk_callback_sse2+0x931> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,116,37,0,0 ; movaps 0x2574(%rip),%xmm13 # 5290 <_sk_callback_sse2+0x942> + DB 68,15,40,45,100,39,0,0 ; movaps 0x2764(%rip),%xmm13 # 5480 <_sk_callback_sse2+0x941> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,116,37,0,0 ; mulps 0x2574(%rip),%xmm13 # 52a0 <_sk_callback_sse2+0x952> + DB 68,15,89,45,100,39,0,0 ; mulps 0x2764(%rip),%xmm13 # 5490 <_sk_callback_sse2+0x951> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -20171,29 +20661,29 @@ _sk_parametric_a_sse2 LABEL PROC PUBLIC _sk_lab_to_xyz_sse2 _sk_lab_to_xyz_sse2 LABEL PROC - DB 15,89,5,81,37,0,0 ; mulps 0x2551(%rip),%xmm0 # 52b0 <_sk_callback_sse2+0x962> - DB 68,15,40,5,89,37,0,0 ; movaps 0x2559(%rip),%xmm8 # 52c0 <_sk_callback_sse2+0x972> + DB 15,89,5,65,39,0,0 ; mulps 0x2741(%rip),%xmm0 # 54a0 <_sk_callback_sse2+0x961> + DB 68,15,40,5,73,39,0,0 ; movaps 0x2749(%rip),%xmm8 # 54b0 <_sk_callback_sse2+0x971> DB 65,15,89,200 ; mulps %xmm8,%xmm1 - DB 68,15,40,13,93,37,0,0 ; movaps 0x255d(%rip),%xmm9 # 52d0 <_sk_callback_sse2+0x982> + DB 68,15,40,13,77,39,0,0 ; movaps 0x274d(%rip),%xmm9 # 54c0 <_sk_callback_sse2+0x981> DB 65,15,88,201 ; addps %xmm9,%xmm1 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 65,15,88,209 ; addps %xmm9,%xmm2 - DB 15,88,5,90,37,0,0 ; addps 0x255a(%rip),%xmm0 # 52e0 <_sk_callback_sse2+0x992> - DB 15,89,5,99,37,0,0 ; mulps 0x2563(%rip),%xmm0 # 52f0 <_sk_callback_sse2+0x9a2> - DB 15,89,13,108,37,0,0 ; mulps 0x256c(%rip),%xmm1 # 5300 <_sk_callback_sse2+0x9b2> + DB 15,88,5,74,39,0,0 ; addps 0x274a(%rip),%xmm0 # 54d0 <_sk_callback_sse2+0x991> + DB 15,89,5,83,39,0,0 ; mulps 0x2753(%rip),%xmm0 # 54e0 <_sk_callback_sse2+0x9a1> + DB 15,89,13,92,39,0,0 ; mulps 0x275c(%rip),%xmm1 # 54f0 <_sk_callback_sse2+0x9b1> DB 15,88,200 ; addps %xmm0,%xmm1 - DB 15,89,21,114,37,0,0 ; mulps 0x2572(%rip),%xmm2 # 5310 <_sk_callback_sse2+0x9c2> + DB 15,89,21,98,39,0,0 ; mulps 0x2762(%rip),%xmm2 # 5500 <_sk_callback_sse2+0x9c1> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 68,15,92,202 ; subps %xmm2,%xmm9 DB 68,15,40,225 ; movaps %xmm1,%xmm12 DB 69,15,89,228 ; mulps %xmm12,%xmm12 DB 68,15,89,225 ; mulps %xmm1,%xmm12 - DB 15,40,21,103,37,0,0 ; movaps 0x2567(%rip),%xmm2 # 5320 <_sk_callback_sse2+0x9d2> + DB 15,40,21,87,39,0,0 ; movaps 0x2757(%rip),%xmm2 # 5510 <_sk_callback_sse2+0x9d1> DB 68,15,40,194 ; movaps %xmm2,%xmm8 DB 69,15,194,196,1 ; cmpltps %xmm12,%xmm8 - DB 68,15,40,21,102,37,0,0 ; movaps 0x2566(%rip),%xmm10 # 5330 <_sk_callback_sse2+0x9e2> + DB 68,15,40,21,86,39,0,0 ; movaps 0x2756(%rip),%xmm10 # 5520 <_sk_callback_sse2+0x9e1> DB 65,15,88,202 ; addps %xmm10,%xmm1 - DB 68,15,40,29,106,37,0,0 ; movaps 0x256a(%rip),%xmm11 # 5340 <_sk_callback_sse2+0x9f2> + DB 68,15,40,29,90,39,0,0 ; movaps 0x275a(%rip),%xmm11 # 5530 <_sk_callback_sse2+0x9f1> DB 65,15,89,203 ; mulps %xmm11,%xmm1 DB 69,15,84,224 ; andps %xmm8,%xmm12 DB 68,15,85,193 ; andnps %xmm1,%xmm8 @@ -20217,8 +20707,8 @@ _sk_lab_to_xyz_sse2 LABEL PROC DB 15,84,194 ; andps %xmm2,%xmm0 DB 65,15,85,209 ; andnps %xmm9,%xmm2 DB 15,86,208 ; orps %xmm0,%xmm2 - DB 68,15,89,5,26,37,0,0 ; mulps 0x251a(%rip),%xmm8 # 5350 <_sk_callback_sse2+0xa02> - DB 15,89,21,35,37,0,0 ; mulps 0x2523(%rip),%xmm2 # 5360 <_sk_callback_sse2+0xa12> + DB 68,15,89,5,10,39,0,0 ; mulps 0x270a(%rip),%xmm8 # 5540 <_sk_callback_sse2+0xa01> + DB 15,89,21,19,39,0,0 ; mulps 0x2713(%rip),%xmm2 # 5550 <_sk_callback_sse2+0xa11> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -20232,7 +20722,7 @@ _sk_load_a8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,11,37,0,0 ; mulps 0x250b(%rip),%xmm3 # 5370 <_sk_callback_sse2+0xa22> + DB 15,89,29,251,38,0,0 ; mulps 0x26fb(%rip),%xmm3 # 5560 <_sk_callback_sse2+0xa21> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 102,15,239,201 ; pxor %xmm1,%xmm1 @@ -20275,7 +20765,7 @@ _sk_gather_a8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,122,36,0,0 ; mulps 0x247a(%rip),%xmm3 # 5380 <_sk_callback_sse2+0xa32> + DB 15,89,29,106,38,0,0 ; mulps 0x266a(%rip),%xmm3 # 5570 <_sk_callback_sse2+0xa31> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 102,15,239,201 ; pxor %xmm1,%xmm1 @@ -20286,7 +20776,7 @@ PUBLIC _sk_store_a8_sse2 _sk_store_a8_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,110,36,0,0 ; movaps 0x246e(%rip),%xmm8 # 5390 <_sk_callback_sse2+0xa42> + DB 68,15,40,5,94,38,0,0 ; movaps 0x265e(%rip),%xmm8 # 5580 <_sk_callback_sse2+0xa41> DB 68,15,89,195 ; mulps %xmm3,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 DB 102,65,15,114,240,16 ; pslld $0x10,%xmm8 @@ -20306,9 +20796,9 @@ _sk_load_g8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,53,36,0,0 ; mulps 0x2435(%rip),%xmm0 # 53a0 <_sk_callback_sse2+0xa52> + DB 15,89,5,37,38,0,0 ; mulps 0x2625(%rip),%xmm0 # 5590 <_sk_callback_sse2+0xa51> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,60,36,0,0 ; movaps 0x243c(%rip),%xmm3 # 53b0 <_sk_callback_sse2+0xa62> + DB 15,40,29,44,38,0,0 ; movaps 0x262c(%rip),%xmm3 # 55a0 <_sk_callback_sse2+0xa61> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -20349,9 +20839,9 @@ _sk_gather_g8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,177,35,0,0 ; mulps 0x23b1(%rip),%xmm0 # 53c0 <_sk_callback_sse2+0xa72> + DB 15,89,5,161,37,0,0 ; mulps 0x25a1(%rip),%xmm0 # 55b0 <_sk_callback_sse2+0xa71> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,184,35,0,0 ; movaps 0x23b8(%rip),%xmm3 # 53d0 <_sk_callback_sse2+0xa82> + DB 15,40,29,168,37,0,0 ; movaps 0x25a8(%rip),%xmm3 # 55c0 <_sk_callback_sse2+0xa81> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -20412,11 +20902,11 @@ _sk_gather_i8_sse2 LABEL PROC DB 102,67,15,110,12,136 ; movd (%r8,%r9,4),%xmm1 DB 102,68,15,98,201 ; punpckldq %xmm1,%xmm9 DB 102,68,15,98,200 ; punpckldq %xmm0,%xmm9 - DB 102,15,111,21,215,34,0,0 ; movdqa 0x22d7(%rip),%xmm2 # 53e0 <_sk_callback_sse2+0xa92> + DB 102,15,111,21,199,36,0,0 ; movdqa 0x24c7(%rip),%xmm2 # 55d0 <_sk_callback_sse2+0xa91> DB 102,65,15,111,193 ; movdqa %xmm9,%xmm0 DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,211,34,0,0 ; movaps 0x22d3(%rip),%xmm8 # 53f0 <_sk_callback_sse2+0xaa2> + DB 68,15,40,5,195,36,0,0 ; movaps 0x24c3(%rip),%xmm8 # 55e0 <_sk_callback_sse2+0xaa1> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,114,209,8 ; psrld $0x8,%xmm1 @@ -20441,19 +20931,19 @@ _sk_load_565_sse2 LABEL PROC DB 243,15,126,20,120 ; movq (%rax,%rdi,2),%xmm2 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,208 ; punpcklwd %xmm0,%xmm2 - DB 102,15,111,5,137,34,0,0 ; movdqa 0x2289(%rip),%xmm0 # 5400 <_sk_callback_sse2+0xab2> + DB 102,15,111,5,121,36,0,0 ; movdqa 0x2479(%rip),%xmm0 # 55f0 <_sk_callback_sse2+0xab1> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,139,34,0,0 ; mulps 0x228b(%rip),%xmm0 # 5410 <_sk_callback_sse2+0xac2> - DB 102,15,111,13,147,34,0,0 ; movdqa 0x2293(%rip),%xmm1 # 5420 <_sk_callback_sse2+0xad2> + DB 15,89,5,123,36,0,0 ; mulps 0x247b(%rip),%xmm0 # 5600 <_sk_callback_sse2+0xac1> + DB 102,15,111,13,131,36,0,0 ; movdqa 0x2483(%rip),%xmm1 # 5610 <_sk_callback_sse2+0xad1> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,149,34,0,0 ; mulps 0x2295(%rip),%xmm1 # 5430 <_sk_callback_sse2+0xae2> - DB 102,15,219,21,157,34,0,0 ; pand 0x229d(%rip),%xmm2 # 5440 <_sk_callback_sse2+0xaf2> + DB 15,89,13,133,36,0,0 ; mulps 0x2485(%rip),%xmm1 # 5620 <_sk_callback_sse2+0xae1> + DB 102,15,219,21,141,36,0,0 ; pand 0x248d(%rip),%xmm2 # 5630 <_sk_callback_sse2+0xaf1> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,163,34,0,0 ; mulps 0x22a3(%rip),%xmm2 # 5450 <_sk_callback_sse2+0xb02> + DB 15,89,21,147,36,0,0 ; mulps 0x2493(%rip),%xmm2 # 5640 <_sk_callback_sse2+0xb01> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,170,34,0,0 ; movaps 0x22aa(%rip),%xmm3 # 5460 <_sk_callback_sse2+0xb12> + DB 15,40,29,154,36,0,0 ; movaps 0x249a(%rip),%xmm3 # 5650 <_sk_callback_sse2+0xb11> DB 255,224 ; jmpq *%rax PUBLIC _sk_gather_565_sse2 @@ -20486,31 +20976,31 @@ _sk_gather_565_sse2 LABEL PROC DB 102,15,196,208,3 ; pinsrw $0x3,%eax,%xmm2 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,208 ; punpcklwd %xmm0,%xmm2 - DB 102,15,111,5,51,34,0,0 ; movdqa 0x2233(%rip),%xmm0 # 5470 <_sk_callback_sse2+0xb22> + DB 102,15,111,5,35,36,0,0 ; movdqa 0x2423(%rip),%xmm0 # 5660 <_sk_callback_sse2+0xb21> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,53,34,0,0 ; mulps 0x2235(%rip),%xmm0 # 5480 <_sk_callback_sse2+0xb32> - DB 102,15,111,13,61,34,0,0 ; movdqa 0x223d(%rip),%xmm1 # 5490 <_sk_callback_sse2+0xb42> + DB 15,89,5,37,36,0,0 ; mulps 0x2425(%rip),%xmm0 # 5670 <_sk_callback_sse2+0xb31> + DB 102,15,111,13,45,36,0,0 ; movdqa 0x242d(%rip),%xmm1 # 5680 <_sk_callback_sse2+0xb41> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,63,34,0,0 ; mulps 0x223f(%rip),%xmm1 # 54a0 <_sk_callback_sse2+0xb52> - DB 102,15,219,21,71,34,0,0 ; pand 0x2247(%rip),%xmm2 # 54b0 <_sk_callback_sse2+0xb62> + DB 15,89,13,47,36,0,0 ; mulps 0x242f(%rip),%xmm1 # 5690 <_sk_callback_sse2+0xb51> + DB 102,15,219,21,55,36,0,0 ; pand 0x2437(%rip),%xmm2 # 56a0 <_sk_callback_sse2+0xb61> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,77,34,0,0 ; mulps 0x224d(%rip),%xmm2 # 54c0 <_sk_callback_sse2+0xb72> + DB 15,89,21,61,36,0,0 ; mulps 0x243d(%rip),%xmm2 # 56b0 <_sk_callback_sse2+0xb71> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,84,34,0,0 ; movaps 0x2254(%rip),%xmm3 # 54d0 <_sk_callback_sse2+0xb82> + DB 15,40,29,68,36,0,0 ; movaps 0x2444(%rip),%xmm3 # 56c0 <_sk_callback_sse2+0xb81> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_565_sse2 _sk_store_565_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,85,34,0,0 ; movaps 0x2255(%rip),%xmm8 # 54e0 <_sk_callback_sse2+0xb92> + DB 68,15,40,5,69,36,0,0 ; movaps 0x2445(%rip),%xmm8 # 56d0 <_sk_callback_sse2+0xb91> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 DB 102,65,15,114,241,11 ; pslld $0xb,%xmm9 - DB 68,15,40,21,74,34,0,0 ; movaps 0x224a(%rip),%xmm10 # 54f0 <_sk_callback_sse2+0xba2> + DB 68,15,40,21,58,36,0,0 ; movaps 0x243a(%rip),%xmm10 # 56e0 <_sk_callback_sse2+0xba1> DB 68,15,89,209 ; mulps %xmm1,%xmm10 DB 102,69,15,91,210 ; cvtps2dq %xmm10,%xmm10 DB 102,65,15,114,242,5 ; pslld $0x5,%xmm10 @@ -20532,21 +21022,21 @@ _sk_load_4444_sse2 LABEL PROC DB 243,15,126,28,120 ; movq (%rax,%rdi,2),%xmm3 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,216 ; punpcklwd %xmm0,%xmm3 - DB 102,15,111,5,3,34,0,0 ; movdqa 0x2203(%rip),%xmm0 # 5500 <_sk_callback_sse2+0xbb2> + DB 102,15,111,5,243,35,0,0 ; movdqa 0x23f3(%rip),%xmm0 # 56f0 <_sk_callback_sse2+0xbb1> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,5,34,0,0 ; mulps 0x2205(%rip),%xmm0 # 5510 <_sk_callback_sse2+0xbc2> - DB 102,15,111,13,13,34,0,0 ; movdqa 0x220d(%rip),%xmm1 # 5520 <_sk_callback_sse2+0xbd2> + DB 15,89,5,245,35,0,0 ; mulps 0x23f5(%rip),%xmm0 # 5700 <_sk_callback_sse2+0xbc1> + DB 102,15,111,13,253,35,0,0 ; movdqa 0x23fd(%rip),%xmm1 # 5710 <_sk_callback_sse2+0xbd1> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,15,34,0,0 ; mulps 0x220f(%rip),%xmm1 # 5530 <_sk_callback_sse2+0xbe2> - DB 102,15,111,21,23,34,0,0 ; movdqa 0x2217(%rip),%xmm2 # 5540 <_sk_callback_sse2+0xbf2> + DB 15,89,13,255,35,0,0 ; mulps 0x23ff(%rip),%xmm1 # 5720 <_sk_callback_sse2+0xbe1> + DB 102,15,111,21,7,36,0,0 ; movdqa 0x2407(%rip),%xmm2 # 5730 <_sk_callback_sse2+0xbf1> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,25,34,0,0 ; mulps 0x2219(%rip),%xmm2 # 5550 <_sk_callback_sse2+0xc02> - DB 102,15,219,29,33,34,0,0 ; pand 0x2221(%rip),%xmm3 # 5560 <_sk_callback_sse2+0xc12> + DB 15,89,21,9,36,0,0 ; mulps 0x2409(%rip),%xmm2 # 5740 <_sk_callback_sse2+0xc01> + DB 102,15,219,29,17,36,0,0 ; pand 0x2411(%rip),%xmm3 # 5750 <_sk_callback_sse2+0xc11> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,39,34,0,0 ; mulps 0x2227(%rip),%xmm3 # 5570 <_sk_callback_sse2+0xc22> + DB 15,89,29,23,36,0,0 ; mulps 0x2417(%rip),%xmm3 # 5760 <_sk_callback_sse2+0xc21> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -20580,21 +21070,21 @@ _sk_gather_4444_sse2 LABEL PROC DB 102,15,196,216,3 ; pinsrw $0x3,%eax,%xmm3 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,216 ; punpcklwd %xmm0,%xmm3 - DB 102,15,111,5,174,33,0,0 ; movdqa 0x21ae(%rip),%xmm0 # 5580 <_sk_callback_sse2+0xc32> + DB 102,15,111,5,158,35,0,0 ; movdqa 0x239e(%rip),%xmm0 # 5770 <_sk_callback_sse2+0xc31> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,176,33,0,0 ; mulps 0x21b0(%rip),%xmm0 # 5590 <_sk_callback_sse2+0xc42> - DB 102,15,111,13,184,33,0,0 ; movdqa 0x21b8(%rip),%xmm1 # 55a0 <_sk_callback_sse2+0xc52> + DB 15,89,5,160,35,0,0 ; mulps 0x23a0(%rip),%xmm0 # 5780 <_sk_callback_sse2+0xc41> + DB 102,15,111,13,168,35,0,0 ; movdqa 0x23a8(%rip),%xmm1 # 5790 <_sk_callback_sse2+0xc51> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,186,33,0,0 ; mulps 0x21ba(%rip),%xmm1 # 55b0 <_sk_callback_sse2+0xc62> - DB 102,15,111,21,194,33,0,0 ; movdqa 0x21c2(%rip),%xmm2 # 55c0 <_sk_callback_sse2+0xc72> + DB 15,89,13,170,35,0,0 ; mulps 0x23aa(%rip),%xmm1 # 57a0 <_sk_callback_sse2+0xc61> + DB 102,15,111,21,178,35,0,0 ; movdqa 0x23b2(%rip),%xmm2 # 57b0 <_sk_callback_sse2+0xc71> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,196,33,0,0 ; mulps 0x21c4(%rip),%xmm2 # 55d0 <_sk_callback_sse2+0xc82> - DB 102,15,219,29,204,33,0,0 ; pand 0x21cc(%rip),%xmm3 # 55e0 <_sk_callback_sse2+0xc92> + DB 15,89,21,180,35,0,0 ; mulps 0x23b4(%rip),%xmm2 # 57c0 <_sk_callback_sse2+0xc81> + DB 102,15,219,29,188,35,0,0 ; pand 0x23bc(%rip),%xmm3 # 57d0 <_sk_callback_sse2+0xc91> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,210,33,0,0 ; mulps 0x21d2(%rip),%xmm3 # 55f0 <_sk_callback_sse2+0xca2> + DB 15,89,29,194,35,0,0 ; mulps 0x23c2(%rip),%xmm3 # 57e0 <_sk_callback_sse2+0xca1> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -20602,7 +21092,7 @@ PUBLIC _sk_store_4444_sse2 _sk_store_4444_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,209,33,0,0 ; movaps 0x21d1(%rip),%xmm8 # 5600 <_sk_callback_sse2+0xcb2> + DB 68,15,40,5,193,35,0,0 ; movaps 0x23c1(%rip),%xmm8 # 57f0 <_sk_callback_sse2+0xcb1> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -20632,11 +21122,11 @@ _sk_load_8888_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 68,15,16,12,184 ; movups (%rax,%rdi,4),%xmm9 - DB 15,40,21,100,33,0,0 ; movaps 0x2164(%rip),%xmm2 # 5610 <_sk_callback_sse2+0xcc2> + DB 15,40,21,84,35,0,0 ; movaps 0x2354(%rip),%xmm2 # 5800 <_sk_callback_sse2+0xcc1> DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 15,84,194 ; andps %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,98,33,0,0 ; movaps 0x2162(%rip),%xmm8 # 5620 <_sk_callback_sse2+0xcd2> + DB 68,15,40,5,82,35,0,0 ; movaps 0x2352(%rip),%xmm8 # 5810 <_sk_callback_sse2+0xcd1> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,40,201 ; movaps %xmm9,%xmm1 DB 102,15,114,209,8 ; psrld $0x8,%xmm1 @@ -20683,11 +21173,11 @@ _sk_gather_8888_sse2 LABEL PROC DB 102,67,15,110,12,129 ; movd (%r9,%r8,4),%xmm1 DB 102,68,15,98,201 ; punpckldq %xmm1,%xmm9 DB 102,68,15,98,200 ; punpckldq %xmm0,%xmm9 - DB 102,15,111,21,179,32,0,0 ; movdqa 0x20b3(%rip),%xmm2 # 5630 <_sk_callback_sse2+0xce2> + DB 102,15,111,21,163,34,0,0 ; movdqa 0x22a3(%rip),%xmm2 # 5820 <_sk_callback_sse2+0xce1> DB 102,65,15,111,193 ; movdqa %xmm9,%xmm0 DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,175,32,0,0 ; movaps 0x20af(%rip),%xmm8 # 5640 <_sk_callback_sse2+0xcf2> + DB 68,15,40,5,159,34,0,0 ; movaps 0x229f(%rip),%xmm8 # 5830 <_sk_callback_sse2+0xcf1> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,114,209,8 ; psrld $0x8,%xmm1 @@ -20709,7 +21199,7 @@ PUBLIC _sk_store_8888_sse2 _sk_store_8888_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,114,32,0,0 ; movaps 0x2072(%rip),%xmm8 # 5650 <_sk_callback_sse2+0xd02> + DB 68,15,40,5,98,34,0,0 ; movaps 0x2262(%rip),%xmm8 # 5840 <_sk_callback_sse2+0xd01> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -20746,7 +21236,7 @@ _sk_load_f16_sse2 LABEL PROC DB 102,69,15,239,210 ; pxor %xmm10,%xmm10 DB 102,65,15,111,206 ; movdqa %xmm14,%xmm1 DB 102,65,15,97,202 ; punpcklwd %xmm10,%xmm1 - DB 102,68,15,111,13,226,31,0,0 ; movdqa 0x1fe2(%rip),%xmm9 # 5660 <_sk_callback_sse2+0xd12> + DB 102,68,15,111,13,210,33,0,0 ; movdqa 0x21d2(%rip),%xmm9 # 5850 <_sk_callback_sse2+0xd11> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,193 ; pand %xmm9,%xmm0 DB 102,15,239,200 ; pxor %xmm0,%xmm1 @@ -20754,11 +21244,11 @@ _sk_load_f16_sse2 LABEL PROC DB 102,68,15,111,233 ; movdqa %xmm1,%xmm13 DB 102,65,15,114,245,13 ; pslld $0xd,%xmm13 DB 102,68,15,235,232 ; por %xmm0,%xmm13 - DB 102,68,15,111,29,199,31,0,0 ; movdqa 0x1fc7(%rip),%xmm11 # 5670 <_sk_callback_sse2+0xd22> + DB 102,68,15,111,29,183,33,0,0 ; movdqa 0x21b7(%rip),%xmm11 # 5860 <_sk_callback_sse2+0xd21> DB 102,69,15,254,235 ; paddd %xmm11,%xmm13 - DB 102,68,15,111,37,201,31,0,0 ; movdqa 0x1fc9(%rip),%xmm12 # 5680 <_sk_callback_sse2+0xd32> + DB 102,68,15,111,37,185,33,0,0 ; movdqa 0x21b9(%rip),%xmm12 # 5870 <_sk_callback_sse2+0xd31> DB 102,65,15,239,204 ; pxor %xmm12,%xmm1 - DB 102,15,111,29,204,31,0,0 ; movdqa 0x1fcc(%rip),%xmm3 # 5690 <_sk_callback_sse2+0xd42> + DB 102,15,111,29,188,33,0,0 ; movdqa 0x21bc(%rip),%xmm3 # 5880 <_sk_callback_sse2+0xd41> DB 102,15,111,195 ; movdqa %xmm3,%xmm0 DB 102,15,102,193 ; pcmpgtd %xmm1,%xmm0 DB 102,65,15,223,197 ; pandn %xmm13,%xmm0 @@ -20842,7 +21332,7 @@ _sk_gather_f16_sse2 LABEL PROC DB 102,69,15,239,210 ; pxor %xmm10,%xmm10 DB 102,65,15,111,206 ; movdqa %xmm14,%xmm1 DB 102,65,15,97,202 ; punpcklwd %xmm10,%xmm1 - DB 102,68,15,111,13,90,30,0,0 ; movdqa 0x1e5a(%rip),%xmm9 # 56a0 <_sk_callback_sse2+0xd52> + DB 102,68,15,111,13,74,32,0,0 ; movdqa 0x204a(%rip),%xmm9 # 5890 <_sk_callback_sse2+0xd51> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,193 ; pand %xmm9,%xmm0 DB 102,15,239,200 ; pxor %xmm0,%xmm1 @@ -20850,11 +21340,11 @@ _sk_gather_f16_sse2 LABEL PROC DB 102,68,15,111,233 ; movdqa %xmm1,%xmm13 DB 102,65,15,114,245,13 ; pslld $0xd,%xmm13 DB 102,68,15,235,232 ; por %xmm0,%xmm13 - DB 102,68,15,111,29,63,30,0,0 ; movdqa 0x1e3f(%rip),%xmm11 # 56b0 <_sk_callback_sse2+0xd62> + DB 102,68,15,111,29,47,32,0,0 ; movdqa 0x202f(%rip),%xmm11 # 58a0 <_sk_callback_sse2+0xd61> DB 102,69,15,254,235 ; paddd %xmm11,%xmm13 - DB 102,68,15,111,37,65,30,0,0 ; movdqa 0x1e41(%rip),%xmm12 # 56c0 <_sk_callback_sse2+0xd72> + DB 102,68,15,111,37,49,32,0,0 ; movdqa 0x2031(%rip),%xmm12 # 58b0 <_sk_callback_sse2+0xd71> DB 102,65,15,239,204 ; pxor %xmm12,%xmm1 - DB 102,15,111,29,68,30,0,0 ; movdqa 0x1e44(%rip),%xmm3 # 56d0 <_sk_callback_sse2+0xd82> + DB 102,15,111,29,52,32,0,0 ; movdqa 0x2034(%rip),%xmm3 # 58c0 <_sk_callback_sse2+0xd81> DB 102,15,111,195 ; movdqa %xmm3,%xmm0 DB 102,15,102,193 ; pcmpgtd %xmm1,%xmm0 DB 102,65,15,223,197 ; pandn %xmm13,%xmm0 @@ -20905,17 +21395,17 @@ PUBLIC _sk_store_f16_sse2 _sk_store_f16_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 102,68,15,111,21,108,29,0,0 ; movdqa 0x1d6c(%rip),%xmm10 # 56e0 <_sk_callback_sse2+0xd92> + DB 102,68,15,111,21,92,31,0,0 ; movdqa 0x1f5c(%rip),%xmm10 # 58d0 <_sk_callback_sse2+0xd91> DB 102,68,15,111,224 ; movdqa %xmm0,%xmm12 DB 102,68,15,111,232 ; movdqa %xmm0,%xmm13 DB 102,69,15,219,234 ; pand %xmm10,%xmm13 DB 102,69,15,239,229 ; pxor %xmm13,%xmm12 - DB 102,68,15,111,13,95,29,0,0 ; movdqa 0x1d5f(%rip),%xmm9 # 56f0 <_sk_callback_sse2+0xda2> + DB 102,68,15,111,13,79,31,0,0 ; movdqa 0x1f4f(%rip),%xmm9 # 58e0 <_sk_callback_sse2+0xda1> DB 102,65,15,114,213,16 ; psrld $0x10,%xmm13 DB 102,69,15,111,193 ; movdqa %xmm9,%xmm8 DB 102,69,15,102,196 ; pcmpgtd %xmm12,%xmm8 DB 102,65,15,114,212,13 ; psrld $0xd,%xmm12 - DB 102,68,15,111,29,80,29,0,0 ; movdqa 0x1d50(%rip),%xmm11 # 5700 <_sk_callback_sse2+0xdb2> + DB 102,68,15,111,29,64,31,0,0 ; movdqa 0x1f40(%rip),%xmm11 # 58f0 <_sk_callback_sse2+0xdb1> DB 102,69,15,235,235 ; por %xmm11,%xmm13 DB 102,69,15,254,236 ; paddd %xmm12,%xmm13 DB 102,65,15,114,245,16 ; pslld $0x10,%xmm13 @@ -20992,7 +21482,7 @@ _sk_load_u16_be_sse2 LABEL PROC DB 102,69,15,239,201 ; pxor %xmm9,%xmm9 DB 102,65,15,97,201 ; punpcklwd %xmm9,%xmm1 DB 15,91,193 ; cvtdq2ps %xmm1,%xmm0 - DB 68,15,40,5,238,27,0,0 ; movaps 0x1bee(%rip),%xmm8 # 5710 <_sk_callback_sse2+0xdc2> + DB 68,15,40,5,222,29,0,0 ; movaps 0x1dde(%rip),%xmm8 # 5900 <_sk_callback_sse2+0xdc1> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -21043,7 +21533,7 @@ _sk_load_rgb_u16_be_sse2 LABEL PROC DB 102,69,15,239,192 ; pxor %xmm8,%xmm8 DB 102,65,15,97,192 ; punpcklwd %xmm8,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,13,42,27,0,0 ; movaps 0x1b2a(%rip),%xmm9 # 5720 <_sk_callback_sse2+0xdd2> + DB 68,15,40,13,26,29,0,0 ; movaps 0x1d1a(%rip),%xmm9 # 5910 <_sk_callback_sse2+0xdd1> DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -21060,14 +21550,14 @@ _sk_load_rgb_u16_be_sse2 LABEL PROC DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,209 ; mulps %xmm9,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,241,26,0,0 ; movaps 0x1af1(%rip),%xmm3 # 5730 <_sk_callback_sse2+0xde2> + DB 15,40,29,225,28,0,0 ; movaps 0x1ce1(%rip),%xmm3 # 5920 <_sk_callback_sse2+0xde1> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_u16_be_sse2 _sk_store_u16_be_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,13,242,26,0,0 ; movaps 0x1af2(%rip),%xmm9 # 5740 <_sk_callback_sse2+0xdf2> + DB 68,15,40,13,226,28,0,0 ; movaps 0x1ce2(%rip),%xmm9 # 5930 <_sk_callback_sse2+0xdf1> DB 68,15,40,192 ; movaps %xmm0,%xmm8 DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 @@ -21203,7 +21693,7 @@ _sk_repeat_x_sse2 LABEL PROC DB 243,69,15,91,209 ; cvttps2dq %xmm9,%xmm10 DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 DB 69,15,194,202,1 ; cmpltps %xmm10,%xmm9 - DB 68,15,84,13,242,24,0,0 ; andps 0x18f2(%rip),%xmm9 # 5750 <_sk_callback_sse2+0xe02> + DB 68,15,84,13,226,26,0,0 ; andps 0x1ae2(%rip),%xmm9 # 5940 <_sk_callback_sse2+0xe01> DB 69,15,92,209 ; subps %xmm9,%xmm10 DB 69,15,89,208 ; mulps %xmm8,%xmm10 DB 65,15,92,194 ; subps %xmm10,%xmm0 @@ -21221,7 +21711,7 @@ _sk_repeat_y_sse2 LABEL PROC DB 243,69,15,91,209 ; cvttps2dq %xmm9,%xmm10 DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 DB 69,15,194,202,1 ; cmpltps %xmm10,%xmm9 - DB 68,15,84,13,196,24,0,0 ; andps 0x18c4(%rip),%xmm9 # 5760 <_sk_callback_sse2+0xe12> + DB 68,15,84,13,180,26,0,0 ; andps 0x1ab4(%rip),%xmm9 # 5950 <_sk_callback_sse2+0xe11> DB 69,15,92,209 ; subps %xmm9,%xmm10 DB 69,15,89,208 ; mulps %xmm8,%xmm10 DB 65,15,92,202 ; subps %xmm10,%xmm1 @@ -21243,7 +21733,7 @@ _sk_mirror_x_sse2 LABEL PROC DB 243,69,15,91,218 ; cvttps2dq %xmm10,%xmm11 DB 69,15,91,219 ; cvtdq2ps %xmm11,%xmm11 DB 69,15,194,211,1 ; cmpltps %xmm11,%xmm10 - DB 68,15,84,21,132,24,0,0 ; andps 0x1884(%rip),%xmm10 # 5770 <_sk_callback_sse2+0xe22> + DB 68,15,84,21,116,26,0,0 ; andps 0x1a74(%rip),%xmm10 # 5960 <_sk_callback_sse2+0xe21> DB 69,15,87,228 ; xorps %xmm12,%xmm12 DB 69,15,92,218 ; subps %xmm10,%xmm11 DB 69,15,89,216 ; mulps %xmm8,%xmm11 @@ -21269,7 +21759,7 @@ _sk_mirror_y_sse2 LABEL PROC DB 243,69,15,91,218 ; cvttps2dq %xmm10,%xmm11 DB 69,15,91,219 ; cvtdq2ps %xmm11,%xmm11 DB 69,15,194,211,1 ; cmpltps %xmm11,%xmm10 - DB 68,15,84,21,52,24,0,0 ; andps 0x1834(%rip),%xmm10 # 5780 <_sk_callback_sse2+0xe32> + DB 68,15,84,21,36,26,0,0 ; andps 0x1a24(%rip),%xmm10 # 5970 <_sk_callback_sse2+0xe31> DB 69,15,87,228 ; xorps %xmm12,%xmm12 DB 69,15,92,218 ; subps %xmm10,%xmm11 DB 69,15,89,216 ; mulps %xmm8,%xmm11 @@ -21284,10 +21774,10 @@ _sk_mirror_y_sse2 LABEL PROC PUBLIC _sk_luminance_to_alpha_sse2 _sk_luminance_to_alpha_sse2 LABEL PROC DB 15,40,218 ; movaps %xmm2,%xmm3 - DB 15,89,5,22,24,0,0 ; mulps 0x1816(%rip),%xmm0 # 5790 <_sk_callback_sse2+0xe42> - DB 15,89,13,31,24,0,0 ; mulps 0x181f(%rip),%xmm1 # 57a0 <_sk_callback_sse2+0xe52> + DB 15,89,5,6,26,0,0 ; mulps 0x1a06(%rip),%xmm0 # 5980 <_sk_callback_sse2+0xe41> + DB 15,89,13,15,26,0,0 ; mulps 0x1a0f(%rip),%xmm1 # 5990 <_sk_callback_sse2+0xe51> DB 15,88,200 ; addps %xmm0,%xmm1 - DB 15,89,29,37,24,0,0 ; mulps 0x1825(%rip),%xmm3 # 57b0 <_sk_callback_sse2+0xe62> + DB 15,89,29,21,26,0,0 ; mulps 0x1a15(%rip),%xmm3 # 59a0 <_sk_callback_sse2+0xe61> DB 15,88,217 ; addps %xmm1,%xmm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 @@ -21497,86 +21987,94 @@ _sk_matrix_perspective_sse2 LABEL PROC DB 65,15,40,201 ; movaps %xmm9,%xmm1 DB 255,224 ; jmpq *%rax -PUBLIC _sk_gradient_sse2 -_sk_gradient_sse2 LABEL PROC +PUBLIC _sk_evenly_spaced_gradient_sse2 +_sk_evenly_spaced_gradient_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 243,68,15,16,72,16 ; movss 0x10(%rax),%xmm9 - DB 69,15,198,201,0 ; shufps $0x0,%xmm9,%xmm9 - DB 243,68,15,16,80,20 ; movss 0x14(%rax),%xmm10 - DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 - DB 243,68,15,16,88,24 ; movss 0x18(%rax),%xmm11 - DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 - DB 243,68,15,16,96,28 ; movss 0x1c(%rax),%xmm12 - DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 DB 72,139,8 ; mov (%rax),%rcx - DB 72,133,201 ; test %rcx,%rcx - DB 15,132,15,1,0,0 ; je 443e <_sk_gradient_sse2+0x149> - DB 72,139,64,8 ; mov 0x8(%rax),%rax - DB 72,131,192,32 ; add $0x20,%rax - DB 69,15,87,192 ; xorps %xmm8,%xmm8 - DB 15,87,219 ; xorps %xmm3,%xmm3 - DB 15,87,210 ; xorps %xmm2,%xmm2 - DB 15,87,201 ; xorps %xmm1,%xmm1 - DB 243,68,15,16,112,224 ; movss -0x20(%rax),%xmm14 - DB 243,68,15,16,104,228 ; movss -0x1c(%rax),%xmm13 - DB 69,15,198,246,0 ; shufps $0x0,%xmm14,%xmm14 - DB 69,15,40,252 ; movaps %xmm12,%xmm15 - DB 68,15,40,224 ; movaps %xmm0,%xmm12 - DB 69,15,194,230,1 ; cmpltps %xmm14,%xmm12 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 69,15,84,196 ; andps %xmm12,%xmm8 - DB 69,15,86,198 ; orps %xmm14,%xmm8 - DB 243,68,15,16,104,232 ; movss -0x18(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 65,15,84,204 ; andps %xmm12,%xmm1 - DB 65,15,86,206 ; orps %xmm14,%xmm1 - DB 243,68,15,16,104,236 ; movss -0x14(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 65,15,84,212 ; andps %xmm12,%xmm2 - DB 65,15,86,214 ; orps %xmm14,%xmm2 - DB 243,68,15,16,104,240 ; movss -0x10(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 65,15,84,220 ; andps %xmm12,%xmm3 - DB 65,15,86,222 ; orps %xmm14,%xmm3 - DB 243,68,15,16,104,244 ; movss -0xc(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 69,15,84,204 ; andps %xmm12,%xmm9 - DB 69,15,86,206 ; orps %xmm14,%xmm9 - DB 243,68,15,16,104,248 ; movss -0x8(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 69,15,84,212 ; andps %xmm12,%xmm10 - DB 69,15,86,214 ; orps %xmm14,%xmm10 - DB 243,68,15,16,104,252 ; movss -0x4(%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 69,15,85,245 ; andnps %xmm13,%xmm14 - DB 69,15,84,220 ; andps %xmm12,%xmm11 - DB 69,15,86,222 ; orps %xmm14,%xmm11 - DB 243,68,15,16,40 ; movss (%rax),%xmm13 - DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 - DB 69,15,84,252 ; andps %xmm12,%xmm15 - DB 69,15,85,229 ; andnps %xmm13,%xmm12 - DB 69,15,86,231 ; orps %xmm15,%xmm12 - DB 72,131,192,36 ; add $0x24,%rax + DB 76,139,88,8 ; mov 0x8(%rax),%r11 DB 72,255,201 ; dec %rcx - DB 15,133,8,255,255,255 ; jne 4344 <_sk_gradient_sse2+0x4f> - DB 235,13 ; jmp 444b <_sk_gradient_sse2+0x156> - DB 15,87,201 ; xorps %xmm1,%xmm1 - DB 15,87,210 ; xorps %xmm2,%xmm2 - DB 15,87,219 ; xorps %xmm3,%xmm3 - DB 69,15,87,192 ; xorps %xmm8,%xmm8 + DB 120,7 ; js 430a <_sk_evenly_spaced_gradient_sse2+0x15> + DB 243,72,15,42,201 ; cvtsi2ss %rcx,%xmm1 + DB 235,21 ; jmp 431f <_sk_evenly_spaced_gradient_sse2+0x2a> + DB 73,137,200 ; mov %rcx,%r8 + DB 73,209,232 ; shr %r8 + DB 131,225,1 ; and $0x1,%ecx + DB 76,9,193 ; or %r8,%rcx + DB 243,72,15,42,201 ; cvtsi2ss %rcx,%xmm1 + DB 243,15,88,201 ; addss %xmm1,%xmm1 + DB 15,198,201,0 ; shufps $0x0,%xmm1,%xmm1 + DB 15,89,200 ; mulps %xmm0,%xmm1 + DB 243,15,91,201 ; cvttps2dq %xmm1,%xmm1 + DB 102,15,112,209,78 ; pshufd $0x4e,%xmm1,%xmm2 + DB 102,73,15,126,210 ; movq %xmm2,%r10 + DB 69,137,208 ; mov %r10d,%r8d + DB 73,193,234,32 ; shr $0x20,%r10 + DB 102,72,15,126,201 ; movq %xmm1,%rcx + DB 65,137,201 ; mov %ecx,%r9d + DB 72,193,233,32 ; shr $0x20,%rcx + DB 243,65,15,16,12,139 ; movss (%r11,%rcx,4),%xmm1 + DB 243,67,15,16,20,147 ; movss (%r11,%r10,4),%xmm2 + DB 15,20,202 ; unpcklps %xmm2,%xmm1 + DB 243,71,15,16,4,139 ; movss (%r11,%r9,4),%xmm8 + DB 243,67,15,16,20,131 ; movss (%r11,%r8,4),%xmm2 + DB 68,15,20,194 ; unpcklps %xmm2,%xmm8 + DB 68,15,20,193 ; unpcklps %xmm1,%xmm8 + DB 76,139,88,40 ; mov 0x28(%rax),%r11 + DB 243,65,15,16,12,139 ; movss (%r11,%rcx,4),%xmm1 + DB 243,67,15,16,20,147 ; movss (%r11,%r10,4),%xmm2 + DB 15,20,202 ; unpcklps %xmm2,%xmm1 + DB 243,71,15,16,12,139 ; movss (%r11,%r9,4),%xmm9 + DB 243,67,15,16,20,131 ; movss (%r11,%r8,4),%xmm2 + DB 68,15,20,202 ; unpcklps %xmm2,%xmm9 + DB 68,15,20,201 ; unpcklps %xmm1,%xmm9 + DB 76,139,88,16 ; mov 0x10(%rax),%r11 + DB 243,65,15,16,20,139 ; movss (%r11,%rcx,4),%xmm2 + DB 243,67,15,16,12,147 ; movss (%r11,%r10,4),%xmm1 + DB 15,20,209 ; unpcklps %xmm1,%xmm2 + DB 243,67,15,16,12,139 ; movss (%r11,%r9,4),%xmm1 + DB 243,67,15,16,28,131 ; movss (%r11,%r8,4),%xmm3 + DB 15,20,203 ; unpcklps %xmm3,%xmm1 + DB 15,20,202 ; unpcklps %xmm2,%xmm1 + DB 76,139,88,48 ; mov 0x30(%rax),%r11 + DB 243,65,15,16,20,139 ; movss (%r11,%rcx,4),%xmm2 + DB 243,67,15,16,28,147 ; movss (%r11,%r10,4),%xmm3 + DB 15,20,211 ; unpcklps %xmm3,%xmm2 + DB 243,71,15,16,20,139 ; movss (%r11,%r9,4),%xmm10 + DB 243,67,15,16,28,131 ; movss (%r11,%r8,4),%xmm3 + DB 68,15,20,211 ; unpcklps %xmm3,%xmm10 + DB 68,15,20,210 ; unpcklps %xmm2,%xmm10 + DB 76,139,88,24 ; mov 0x18(%rax),%r11 + DB 243,69,15,16,28,139 ; movss (%r11,%rcx,4),%xmm11 + DB 243,67,15,16,20,147 ; movss (%r11,%r10,4),%xmm2 + DB 68,15,20,218 ; unpcklps %xmm2,%xmm11 + DB 243,67,15,16,20,139 ; movss (%r11,%r9,4),%xmm2 + DB 243,67,15,16,28,131 ; movss (%r11,%r8,4),%xmm3 + DB 15,20,211 ; unpcklps %xmm3,%xmm2 + DB 65,15,20,211 ; unpcklps %xmm11,%xmm2 + DB 76,139,88,56 ; mov 0x38(%rax),%r11 + DB 243,69,15,16,36,139 ; movss (%r11,%rcx,4),%xmm12 + DB 243,67,15,16,28,147 ; movss (%r11,%r10,4),%xmm3 + DB 68,15,20,227 ; unpcklps %xmm3,%xmm12 + DB 243,71,15,16,28,139 ; movss (%r11,%r9,4),%xmm11 + DB 243,67,15,16,28,131 ; movss (%r11,%r8,4),%xmm3 + DB 68,15,20,219 ; unpcklps %xmm3,%xmm11 + DB 69,15,20,220 ; unpcklps %xmm12,%xmm11 + DB 76,139,88,32 ; mov 0x20(%rax),%r11 + DB 243,69,15,16,36,139 ; movss (%r11,%rcx,4),%xmm12 + DB 243,67,15,16,28,147 ; movss (%r11,%r10,4),%xmm3 + DB 68,15,20,227 ; unpcklps %xmm3,%xmm12 + DB 243,67,15,16,28,139 ; movss (%r11,%r9,4),%xmm3 + DB 243,71,15,16,44,131 ; movss (%r11,%r8,4),%xmm13 + DB 65,15,20,221 ; unpcklps %xmm13,%xmm3 + DB 65,15,20,220 ; unpcklps %xmm12,%xmm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 243,68,15,16,36,136 ; movss (%rax,%rcx,4),%xmm12 + DB 243,70,15,16,44,144 ; movss (%rax,%r10,4),%xmm13 + DB 69,15,20,229 ; unpcklps %xmm13,%xmm12 + DB 243,70,15,16,44,136 ; movss (%rax,%r9,4),%xmm13 + DB 243,70,15,16,52,128 ; movss (%rax,%r8,4),%xmm14 + DB 69,15,20,238 ; unpcklps %xmm14,%xmm13 + DB 69,15,20,236 ; unpcklps %xmm12,%xmm13 DB 68,15,89,192 ; mulps %xmm0,%xmm8 DB 69,15,88,193 ; addps %xmm9,%xmm8 DB 15,89,200 ; mulps %xmm0,%xmm1 @@ -21584,9 +22082,116 @@ _sk_gradient_sse2 LABEL PROC DB 15,89,208 ; mulps %xmm0,%xmm2 DB 65,15,88,211 ; addps %xmm11,%xmm2 DB 15,89,216 ; mulps %xmm0,%xmm3 - DB 65,15,88,220 ; addps %xmm12,%xmm3 + DB 65,15,88,221 ; addps %xmm13,%xmm3 + DB 72,173 ; lods %ds:(%rsi),%rax + DB 65,15,40,192 ; movaps %xmm8,%xmm0 + DB 255,224 ; jmpq *%rax + +PUBLIC _sk_gradient_sse2 +_sk_gradient_sse2 LABEL PROC + DB 72,173 ; lods %ds:(%rsi),%rax + DB 76,139,0 ; mov (%rax),%r8 + DB 102,15,239,201 ; pxor %xmm1,%xmm1 + DB 73,131,248,2 ; cmp $0x2,%r8 + DB 114,50 ; jb 44e2 <_sk_gradient_sse2+0x41> + DB 72,139,72,72 ; mov 0x48(%rax),%rcx + DB 73,255,200 ; dec %r8 + DB 72,131,193,4 ; add $0x4,%rcx + DB 102,15,239,201 ; pxor %xmm1,%xmm1 + DB 15,40,21,234,20,0,0 ; movaps 0x14ea(%rip),%xmm2 # 59b0 <_sk_callback_sse2+0xe71> + DB 243,15,16,25 ; movss (%rcx),%xmm3 + DB 15,198,219,0 ; shufps $0x0,%xmm3,%xmm3 + DB 15,194,216,2 ; cmpleps %xmm0,%xmm3 + DB 15,84,218 ; andps %xmm2,%xmm3 + DB 102,15,254,203 ; paddd %xmm3,%xmm1 + DB 72,131,193,4 ; add $0x4,%rcx + DB 73,255,200 ; dec %r8 + DB 117,228 ; jne 44c6 <_sk_gradient_sse2+0x25> + DB 65,86 ; push %r14 + DB 83 ; push %rbx + DB 102,15,112,209,78 ; pshufd $0x4e,%xmm1,%xmm2 + DB 102,73,15,126,210 ; movq %xmm2,%r10 + DB 69,137,208 ; mov %r10d,%r8d + DB 73,193,234,32 ; shr $0x20,%r10 + DB 102,72,15,126,201 ; movq %xmm1,%rcx + DB 65,137,201 ; mov %ecx,%r9d + DB 72,193,233,32 ; shr $0x20,%rcx + DB 76,139,88,8 ; mov 0x8(%rax),%r11 + DB 76,139,112,16 ; mov 0x10(%rax),%r14 + DB 243,65,15,16,12,139 ; movss (%r11,%rcx,4),%xmm1 + DB 243,67,15,16,20,147 ; movss (%r11,%r10,4),%xmm2 + DB 15,20,202 ; unpcklps %xmm2,%xmm1 + DB 243,71,15,16,4,139 ; movss (%r11,%r9,4),%xmm8 + DB 243,67,15,16,20,131 ; movss (%r11,%r8,4),%xmm2 + DB 68,15,20,194 ; unpcklps %xmm2,%xmm8 + DB 68,15,20,193 ; unpcklps %xmm1,%xmm8 + DB 72,139,88,40 ; mov 0x28(%rax),%rbx + DB 243,15,16,12,139 ; movss (%rbx,%rcx,4),%xmm1 + DB 243,66,15,16,20,147 ; movss (%rbx,%r10,4),%xmm2 + DB 15,20,202 ; unpcklps %xmm2,%xmm1 + DB 243,70,15,16,12,139 ; movss (%rbx,%r9,4),%xmm9 + DB 243,66,15,16,20,131 ; movss (%rbx,%r8,4),%xmm2 + DB 68,15,20,202 ; unpcklps %xmm2,%xmm9 + DB 68,15,20,201 ; unpcklps %xmm1,%xmm9 + DB 243,65,15,16,20,142 ; movss (%r14,%rcx,4),%xmm2 + DB 243,67,15,16,12,150 ; movss (%r14,%r10,4),%xmm1 + DB 15,20,209 ; unpcklps %xmm1,%xmm2 + DB 243,67,15,16,12,142 ; movss (%r14,%r9,4),%xmm1 + DB 243,67,15,16,28,134 ; movss (%r14,%r8,4),%xmm3 + DB 15,20,203 ; unpcklps %xmm3,%xmm1 + DB 15,20,202 ; unpcklps %xmm2,%xmm1 + DB 72,139,88,48 ; mov 0x30(%rax),%rbx + DB 243,15,16,20,139 ; movss (%rbx,%rcx,4),%xmm2 + DB 243,66,15,16,28,147 ; movss (%rbx,%r10,4),%xmm3 + DB 15,20,211 ; unpcklps %xmm3,%xmm2 + DB 243,70,15,16,20,139 ; movss (%rbx,%r9,4),%xmm10 + DB 243,66,15,16,28,131 ; movss (%rbx,%r8,4),%xmm3 + DB 68,15,20,211 ; unpcklps %xmm3,%xmm10 + DB 68,15,20,210 ; unpcklps %xmm2,%xmm10 + DB 72,139,88,24 ; mov 0x18(%rax),%rbx + DB 243,68,15,16,28,139 ; movss (%rbx,%rcx,4),%xmm11 + DB 243,66,15,16,20,147 ; movss (%rbx,%r10,4),%xmm2 + DB 68,15,20,218 ; unpcklps %xmm2,%xmm11 + DB 243,66,15,16,20,139 ; movss (%rbx,%r9,4),%xmm2 + DB 243,66,15,16,28,131 ; movss (%rbx,%r8,4),%xmm3 + DB 15,20,211 ; unpcklps %xmm3,%xmm2 + DB 65,15,20,211 ; unpcklps %xmm11,%xmm2 + DB 72,139,88,56 ; mov 0x38(%rax),%rbx + DB 243,68,15,16,36,139 ; movss (%rbx,%rcx,4),%xmm12 + DB 243,66,15,16,28,147 ; movss (%rbx,%r10,4),%xmm3 + DB 68,15,20,227 ; unpcklps %xmm3,%xmm12 + DB 243,70,15,16,28,139 ; movss (%rbx,%r9,4),%xmm11 + DB 243,66,15,16,28,131 ; movss (%rbx,%r8,4),%xmm3 + DB 68,15,20,219 ; unpcklps %xmm3,%xmm11 + DB 69,15,20,220 ; unpcklps %xmm12,%xmm11 + DB 72,139,88,32 ; mov 0x20(%rax),%rbx + DB 243,68,15,16,36,139 ; movss (%rbx,%rcx,4),%xmm12 + DB 243,66,15,16,28,147 ; movss (%rbx,%r10,4),%xmm3 + DB 68,15,20,227 ; unpcklps %xmm3,%xmm12 + DB 243,66,15,16,28,139 ; movss (%rbx,%r9,4),%xmm3 + DB 243,70,15,16,44,131 ; movss (%rbx,%r8,4),%xmm13 + DB 65,15,20,221 ; unpcklps %xmm13,%xmm3 + DB 65,15,20,220 ; unpcklps %xmm12,%xmm3 + DB 72,139,64,64 ; mov 0x40(%rax),%rax + DB 243,68,15,16,36,136 ; movss (%rax,%rcx,4),%xmm12 + DB 243,70,15,16,44,144 ; movss (%rax,%r10,4),%xmm13 + DB 69,15,20,229 ; unpcklps %xmm13,%xmm12 + DB 243,70,15,16,44,136 ; movss (%rax,%r9,4),%xmm13 + DB 243,70,15,16,52,128 ; movss (%rax,%r8,4),%xmm14 + DB 69,15,20,238 ; unpcklps %xmm14,%xmm13 + DB 69,15,20,236 ; unpcklps %xmm12,%xmm13 + DB 68,15,89,192 ; mulps %xmm0,%xmm8 + DB 69,15,88,193 ; addps %xmm9,%xmm8 + DB 15,89,200 ; mulps %xmm0,%xmm1 + DB 65,15,88,202 ; addps %xmm10,%xmm1 + DB 15,89,208 ; mulps %xmm0,%xmm2 + DB 65,15,88,211 ; addps %xmm11,%xmm2 + DB 15,89,216 ; mulps %xmm0,%xmm3 + DB 65,15,88,221 ; addps %xmm13,%xmm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 + DB 91 ; pop %rbx + DB 65,94 ; pop %r14 DB 255,224 ; jmpq *%rax PUBLIC _sk_evenly_spaced_2_stop_gradient_sse2 @@ -21637,29 +22242,29 @@ _sk_xy_to_unit_angle_sse2 LABEL PROC DB 69,15,94,220 ; divps %xmm12,%xmm11 DB 69,15,40,227 ; movaps %xmm11,%xmm12 DB 69,15,89,228 ; mulps %xmm12,%xmm12 - DB 68,15,40,45,157,18,0,0 ; movaps 0x129d(%rip),%xmm13 # 57c0 <_sk_callback_sse2+0xe72> + DB 68,15,40,45,172,18,0,0 ; movaps 0x12ac(%rip),%xmm13 # 59c0 <_sk_callback_sse2+0xe81> DB 69,15,89,236 ; mulps %xmm12,%xmm13 - DB 68,15,88,45,161,18,0,0 ; addps 0x12a1(%rip),%xmm13 # 57d0 <_sk_callback_sse2+0xe82> + DB 68,15,88,45,176,18,0,0 ; addps 0x12b0(%rip),%xmm13 # 59d0 <_sk_callback_sse2+0xe91> DB 69,15,89,236 ; mulps %xmm12,%xmm13 - DB 68,15,88,45,165,18,0,0 ; addps 0x12a5(%rip),%xmm13 # 57e0 <_sk_callback_sse2+0xe92> + DB 68,15,88,45,180,18,0,0 ; addps 0x12b4(%rip),%xmm13 # 59e0 <_sk_callback_sse2+0xea1> DB 69,15,89,236 ; mulps %xmm12,%xmm13 - DB 68,15,88,45,169,18,0,0 ; addps 0x12a9(%rip),%xmm13 # 57f0 <_sk_callback_sse2+0xea2> + DB 68,15,88,45,184,18,0,0 ; addps 0x12b8(%rip),%xmm13 # 59f0 <_sk_callback_sse2+0xeb1> DB 69,15,89,235 ; mulps %xmm11,%xmm13 DB 69,15,194,202,1 ; cmpltps %xmm10,%xmm9 - DB 68,15,40,21,168,18,0,0 ; movaps 0x12a8(%rip),%xmm10 # 5800 <_sk_callback_sse2+0xeb2> + DB 68,15,40,21,183,18,0,0 ; movaps 0x12b7(%rip),%xmm10 # 5a00 <_sk_callback_sse2+0xec1> DB 69,15,92,213 ; subps %xmm13,%xmm10 DB 69,15,84,209 ; andps %xmm9,%xmm10 DB 69,15,85,205 ; andnps %xmm13,%xmm9 DB 69,15,86,202 ; orps %xmm10,%xmm9 DB 68,15,194,192,1 ; cmpltps %xmm0,%xmm8 - DB 68,15,40,21,155,18,0,0 ; movaps 0x129b(%rip),%xmm10 # 5810 <_sk_callback_sse2+0xec2> + DB 68,15,40,21,170,18,0,0 ; movaps 0x12aa(%rip),%xmm10 # 5a10 <_sk_callback_sse2+0xed1> DB 69,15,92,209 ; subps %xmm9,%xmm10 DB 69,15,84,208 ; andps %xmm8,%xmm10 DB 69,15,85,193 ; andnps %xmm9,%xmm8 DB 69,15,86,194 ; orps %xmm10,%xmm8 DB 68,15,40,201 ; movaps %xmm1,%xmm9 DB 68,15,194,200,1 ; cmpltps %xmm0,%xmm9 - DB 68,15,40,21,138,18,0,0 ; movaps 0x128a(%rip),%xmm10 # 5820 <_sk_callback_sse2+0xed2> + DB 68,15,40,21,153,18,0,0 ; movaps 0x1299(%rip),%xmm10 # 5a20 <_sk_callback_sse2+0xee1> DB 69,15,92,208 ; subps %xmm8,%xmm10 DB 69,15,84,209 ; andps %xmm9,%xmm10 DB 69,15,85,200 ; andnps %xmm8,%xmm9 @@ -21683,7 +22288,7 @@ _sk_xy_to_radius_sse2 LABEL PROC PUBLIC _sk_save_xy_sse2 _sk_save_xy_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,89,18,0,0 ; movaps 0x1259(%rip),%xmm8 # 5830 <_sk_callback_sse2+0xee2> + DB 68,15,40,5,104,18,0,0 ; movaps 0x1268(%rip),%xmm8 # 5a30 <_sk_callback_sse2+0xef1> DB 15,17,0 ; movups %xmm0,(%rax) DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,88,200 ; addps %xmm8,%xmm9 @@ -21691,7 +22296,7 @@ _sk_save_xy_sse2 LABEL PROC DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 DB 69,15,40,217 ; movaps %xmm9,%xmm11 DB 69,15,194,218,1 ; cmpltps %xmm10,%xmm11 - DB 68,15,40,37,68,18,0,0 ; movaps 0x1244(%rip),%xmm12 # 5840 <_sk_callback_sse2+0xef2> + DB 68,15,40,37,83,18,0,0 ; movaps 0x1253(%rip),%xmm12 # 5a40 <_sk_callback_sse2+0xf01> DB 69,15,84,220 ; andps %xmm12,%xmm11 DB 69,15,92,211 ; subps %xmm11,%xmm10 DB 69,15,92,202 ; subps %xmm10,%xmm9 @@ -21734,8 +22339,8 @@ _sk_bilinear_nx_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,189,17,0,0 ; addps 0x11bd(%rip),%xmm0 # 5850 <_sk_callback_sse2+0xf02> - DB 68,15,40,13,197,17,0,0 ; movaps 0x11c5(%rip),%xmm9 # 5860 <_sk_callback_sse2+0xf12> + DB 15,88,5,204,17,0,0 ; addps 0x11cc(%rip),%xmm0 # 5a50 <_sk_callback_sse2+0xf11> + DB 68,15,40,13,212,17,0,0 ; movaps 0x11d4(%rip),%xmm9 # 5a60 <_sk_callback_sse2+0xf21> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -21746,7 +22351,7 @@ _sk_bilinear_px_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,180,17,0,0 ; addps 0x11b4(%rip),%xmm0 # 5870 <_sk_callback_sse2+0xf22> + DB 15,88,5,195,17,0,0 ; addps 0x11c3(%rip),%xmm0 # 5a70 <_sk_callback_sse2+0xf31> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -21756,8 +22361,8 @@ _sk_bilinear_ny_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,166,17,0,0 ; addps 0x11a6(%rip),%xmm1 # 5880 <_sk_callback_sse2+0xf32> - DB 68,15,40,13,174,17,0,0 ; movaps 0x11ae(%rip),%xmm9 # 5890 <_sk_callback_sse2+0xf42> + DB 15,88,13,181,17,0,0 ; addps 0x11b5(%rip),%xmm1 # 5a80 <_sk_callback_sse2+0xf41> + DB 68,15,40,13,189,17,0,0 ; movaps 0x11bd(%rip),%xmm9 # 5a90 <_sk_callback_sse2+0xf51> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -21768,7 +22373,7 @@ _sk_bilinear_py_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,156,17,0,0 ; addps 0x119c(%rip),%xmm1 # 58a0 <_sk_callback_sse2+0xf52> + DB 15,88,13,171,17,0,0 ; addps 0x11ab(%rip),%xmm1 # 5aa0 <_sk_callback_sse2+0xf61> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -21778,13 +22383,13 @@ _sk_bicubic_n3x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,143,17,0,0 ; addps 0x118f(%rip),%xmm0 # 58b0 <_sk_callback_sse2+0xf62> - DB 68,15,40,13,151,17,0,0 ; movaps 0x1197(%rip),%xmm9 # 58c0 <_sk_callback_sse2+0xf72> + DB 15,88,5,158,17,0,0 ; addps 0x119e(%rip),%xmm0 # 5ab0 <_sk_callback_sse2+0xf71> + DB 68,15,40,13,166,17,0,0 ; movaps 0x11a6(%rip),%xmm9 # 5ac0 <_sk_callback_sse2+0xf81> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,147,17,0,0 ; mulps 0x1193(%rip),%xmm9 # 58d0 <_sk_callback_sse2+0xf82> - DB 68,15,88,13,155,17,0,0 ; addps 0x119b(%rip),%xmm9 # 58e0 <_sk_callback_sse2+0xf92> + DB 68,15,89,13,162,17,0,0 ; mulps 0x11a2(%rip),%xmm9 # 5ad0 <_sk_callback_sse2+0xf91> + DB 68,15,88,13,170,17,0,0 ; addps 0x11aa(%rip),%xmm9 # 5ae0 <_sk_callback_sse2+0xfa1> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -21795,16 +22400,16 @@ _sk_bicubic_n1x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,138,17,0,0 ; addps 0x118a(%rip),%xmm0 # 58f0 <_sk_callback_sse2+0xfa2> - DB 68,15,40,13,146,17,0,0 ; movaps 0x1192(%rip),%xmm9 # 5900 <_sk_callback_sse2+0xfb2> + DB 15,88,5,153,17,0,0 ; addps 0x1199(%rip),%xmm0 # 5af0 <_sk_callback_sse2+0xfb1> + DB 68,15,40,13,161,17,0,0 ; movaps 0x11a1(%rip),%xmm9 # 5b00 <_sk_callback_sse2+0xfc1> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,150,17,0,0 ; movaps 0x1196(%rip),%xmm8 # 5910 <_sk_callback_sse2+0xfc2> + DB 68,15,40,5,165,17,0,0 ; movaps 0x11a5(%rip),%xmm8 # 5b10 <_sk_callback_sse2+0xfd1> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,154,17,0,0 ; addps 0x119a(%rip),%xmm8 # 5920 <_sk_callback_sse2+0xfd2> + DB 68,15,88,5,169,17,0,0 ; addps 0x11a9(%rip),%xmm8 # 5b20 <_sk_callback_sse2+0xfe1> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,158,17,0,0 ; addps 0x119e(%rip),%xmm8 # 5930 <_sk_callback_sse2+0xfe2> + DB 68,15,88,5,173,17,0,0 ; addps 0x11ad(%rip),%xmm8 # 5b30 <_sk_callback_sse2+0xff1> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,162,17,0,0 ; addps 0x11a2(%rip),%xmm8 # 5940 <_sk_callback_sse2+0xff2> + DB 68,15,88,5,177,17,0,0 ; addps 0x11b1(%rip),%xmm8 # 5b40 <_sk_callback_sse2+0x1001> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -21812,17 +22417,17 @@ _sk_bicubic_n1x_sse2 LABEL PROC PUBLIC _sk_bicubic_p1x_sse2 _sk_bicubic_p1x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,156,17,0,0 ; movaps 0x119c(%rip),%xmm8 # 5950 <_sk_callback_sse2+0x1002> + DB 68,15,40,5,171,17,0,0 ; movaps 0x11ab(%rip),%xmm8 # 5b50 <_sk_callback_sse2+0x1011> DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,72,64 ; movups 0x40(%rax),%xmm9 DB 65,15,88,192 ; addps %xmm8,%xmm0 - DB 68,15,40,21,152,17,0,0 ; movaps 0x1198(%rip),%xmm10 # 5960 <_sk_callback_sse2+0x1012> + DB 68,15,40,21,167,17,0,0 ; movaps 0x11a7(%rip),%xmm10 # 5b60 <_sk_callback_sse2+0x1021> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,156,17,0,0 ; addps 0x119c(%rip),%xmm10 # 5970 <_sk_callback_sse2+0x1022> + DB 68,15,88,21,171,17,0,0 ; addps 0x11ab(%rip),%xmm10 # 5b70 <_sk_callback_sse2+0x1031> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,152,17,0,0 ; addps 0x1198(%rip),%xmm10 # 5980 <_sk_callback_sse2+0x1032> + DB 68,15,88,21,167,17,0,0 ; addps 0x11a7(%rip),%xmm10 # 5b80 <_sk_callback_sse2+0x1041> DB 68,15,17,144,128,0,0,0 ; movups %xmm10,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -21832,11 +22437,11 @@ _sk_bicubic_p3x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,139,17,0,0 ; addps 0x118b(%rip),%xmm0 # 5990 <_sk_callback_sse2+0x1042> + DB 15,88,5,154,17,0,0 ; addps 0x119a(%rip),%xmm0 # 5b90 <_sk_callback_sse2+0x1051> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,139,17,0,0 ; mulps 0x118b(%rip),%xmm8 # 59a0 <_sk_callback_sse2+0x1052> - DB 68,15,88,5,147,17,0,0 ; addps 0x1193(%rip),%xmm8 # 59b0 <_sk_callback_sse2+0x1062> + DB 68,15,89,5,154,17,0,0 ; mulps 0x119a(%rip),%xmm8 # 5ba0 <_sk_callback_sse2+0x1061> + DB 68,15,88,5,162,17,0,0 ; addps 0x11a2(%rip),%xmm8 # 5bb0 <_sk_callback_sse2+0x1071> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -21847,13 +22452,13 @@ _sk_bicubic_n3y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,129,17,0,0 ; addps 0x1181(%rip),%xmm1 # 59c0 <_sk_callback_sse2+0x1072> - DB 68,15,40,13,137,17,0,0 ; movaps 0x1189(%rip),%xmm9 # 59d0 <_sk_callback_sse2+0x1082> + DB 15,88,13,144,17,0,0 ; addps 0x1190(%rip),%xmm1 # 5bc0 <_sk_callback_sse2+0x1081> + DB 68,15,40,13,152,17,0,0 ; movaps 0x1198(%rip),%xmm9 # 5bd0 <_sk_callback_sse2+0x1091> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,133,17,0,0 ; mulps 0x1185(%rip),%xmm9 # 59e0 <_sk_callback_sse2+0x1092> - DB 68,15,88,13,141,17,0,0 ; addps 0x118d(%rip),%xmm9 # 59f0 <_sk_callback_sse2+0x10a2> + DB 68,15,89,13,148,17,0,0 ; mulps 0x1194(%rip),%xmm9 # 5be0 <_sk_callback_sse2+0x10a1> + DB 68,15,88,13,156,17,0,0 ; addps 0x119c(%rip),%xmm9 # 5bf0 <_sk_callback_sse2+0x10b1> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -21864,16 +22469,16 @@ _sk_bicubic_n1y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,123,17,0,0 ; addps 0x117b(%rip),%xmm1 # 5a00 <_sk_callback_sse2+0x10b2> - DB 68,15,40,13,131,17,0,0 ; movaps 0x1183(%rip),%xmm9 # 5a10 <_sk_callback_sse2+0x10c2> + DB 15,88,13,138,17,0,0 ; addps 0x118a(%rip),%xmm1 # 5c00 <_sk_callback_sse2+0x10c1> + DB 68,15,40,13,146,17,0,0 ; movaps 0x1192(%rip),%xmm9 # 5c10 <_sk_callback_sse2+0x10d1> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,135,17,0,0 ; movaps 0x1187(%rip),%xmm8 # 5a20 <_sk_callback_sse2+0x10d2> + DB 68,15,40,5,150,17,0,0 ; movaps 0x1196(%rip),%xmm8 # 5c20 <_sk_callback_sse2+0x10e1> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,139,17,0,0 ; addps 0x118b(%rip),%xmm8 # 5a30 <_sk_callback_sse2+0x10e2> + DB 68,15,88,5,154,17,0,0 ; addps 0x119a(%rip),%xmm8 # 5c30 <_sk_callback_sse2+0x10f1> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,143,17,0,0 ; addps 0x118f(%rip),%xmm8 # 5a40 <_sk_callback_sse2+0x10f2> + DB 68,15,88,5,158,17,0,0 ; addps 0x119e(%rip),%xmm8 # 5c40 <_sk_callback_sse2+0x1101> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,147,17,0,0 ; addps 0x1193(%rip),%xmm8 # 5a50 <_sk_callback_sse2+0x1102> + DB 68,15,88,5,162,17,0,0 ; addps 0x11a2(%rip),%xmm8 # 5c50 <_sk_callback_sse2+0x1111> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -21881,17 +22486,17 @@ _sk_bicubic_n1y_sse2 LABEL PROC PUBLIC _sk_bicubic_p1y_sse2 _sk_bicubic_p1y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,141,17,0,0 ; movaps 0x118d(%rip),%xmm8 # 5a60 <_sk_callback_sse2+0x1112> + DB 68,15,40,5,156,17,0,0 ; movaps 0x119c(%rip),%xmm8 # 5c60 <_sk_callback_sse2+0x1121> DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,72,96 ; movups 0x60(%rax),%xmm9 DB 65,15,88,200 ; addps %xmm8,%xmm1 - DB 68,15,40,21,136,17,0,0 ; movaps 0x1188(%rip),%xmm10 # 5a70 <_sk_callback_sse2+0x1122> + DB 68,15,40,21,151,17,0,0 ; movaps 0x1197(%rip),%xmm10 # 5c70 <_sk_callback_sse2+0x1131> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,140,17,0,0 ; addps 0x118c(%rip),%xmm10 # 5a80 <_sk_callback_sse2+0x1132> + DB 68,15,88,21,155,17,0,0 ; addps 0x119b(%rip),%xmm10 # 5c80 <_sk_callback_sse2+0x1141> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,136,17,0,0 ; addps 0x1188(%rip),%xmm10 # 5a90 <_sk_callback_sse2+0x1142> + DB 68,15,88,21,151,17,0,0 ; addps 0x1197(%rip),%xmm10 # 5c90 <_sk_callback_sse2+0x1151> DB 68,15,17,144,160,0,0,0 ; movups %xmm10,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -21901,11 +22506,11 @@ _sk_bicubic_p3y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,122,17,0,0 ; addps 0x117a(%rip),%xmm1 # 5aa0 <_sk_callback_sse2+0x1152> + DB 15,88,13,137,17,0,0 ; addps 0x1189(%rip),%xmm1 # 5ca0 <_sk_callback_sse2+0x1161> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,122,17,0,0 ; mulps 0x117a(%rip),%xmm8 # 5ab0 <_sk_callback_sse2+0x1162> - DB 68,15,88,5,130,17,0,0 ; addps 0x1182(%rip),%xmm8 # 5ac0 <_sk_callback_sse2+0x1172> + DB 68,15,89,5,137,17,0,0 ; mulps 0x1189(%rip),%xmm8 # 5cb0 <_sk_callback_sse2+0x1171> + DB 68,15,88,5,145,17,0,0 ; addps 0x1191(%rip),%xmm8 # 5cc0 <_sk_callback_sse2+0x1181> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -22110,11 +22715,11 @@ ALIGN 16 DB 128,191,0,0,128,191,0 ; cmpb $0x0,-0x40800000(%rdi) DB 0,224 ; add %ah,%al DB 64,0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4bd8 <.literal16+0x1d8> + DB 224,64 ; loopne 4dc8 <.literal16+0x1d8> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4bdc <.literal16+0x1dc> + DB 224,64 ; loopne 4dcc <.literal16+0x1dc> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4be0 <.literal16+0x1e0> + DB 224,64 ; loopne 4dd0 <.literal16+0x1e0> DB 154 ; (bad) DB 153 ; cltd DB 153 ; cltd @@ -22134,13 +22739,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c01 <.literal16+0x201> + DB 71,225,61 ; rex.RXB loope 4df1 <.literal16+0x201> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c05 <.literal16+0x205> + DB 71,225,61 ; rex.RXB loope 4df5 <.literal16+0x205> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c09 <.literal16+0x209> + DB 71,225,61 ; rex.RXB loope 4df9 <.literal16+0x209> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c0d <.literal16+0x20d> + DB 71,225,61 ; rex.RXB loope 4dfd <.literal16+0x20d> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -22165,13 +22770,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c41 <.literal16+0x241> + DB 71,225,61 ; rex.RXB loope 4e31 <.literal16+0x241> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c45 <.literal16+0x245> + DB 71,225,61 ; rex.RXB loope 4e35 <.literal16+0x245> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c49 <.literal16+0x249> + DB 71,225,61 ; rex.RXB loope 4e39 <.literal16+0x249> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c4d <.literal16+0x24d> + DB 71,225,61 ; rex.RXB loope 4e3d <.literal16+0x24d> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -22196,13 +22801,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c81 <.literal16+0x281> + DB 71,225,61 ; rex.RXB loope 4e71 <.literal16+0x281> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c85 <.literal16+0x285> + DB 71,225,61 ; rex.RXB loope 4e75 <.literal16+0x285> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c89 <.literal16+0x289> + DB 71,225,61 ; rex.RXB loope 4e79 <.literal16+0x289> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4c8d <.literal16+0x28d> + DB 71,225,61 ; rex.RXB loope 4e7d <.literal16+0x28d> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -22227,13 +22832,13 @@ ALIGN 16 DB 10,23 ; or (%rdi),%dl DB 63 ; (bad) DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4cc1 <.literal16+0x2c1> + DB 71,225,61 ; rex.RXB loope 4eb1 <.literal16+0x2c1> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4cc5 <.literal16+0x2c5> + DB 71,225,61 ; rex.RXB loope 4eb5 <.literal16+0x2c5> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4cc9 <.literal16+0x2c9> + DB 71,225,61 ; rex.RXB loope 4eb9 <.literal16+0x2c9> DB 174 ; scas %es:(%rdi),%al - DB 71,225,61 ; rex.RXB loope 4ccd <.literal16+0x2cd> + DB 71,225,61 ; rex.RXB loope 4ebd <.literal16+0x2cd> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -22462,13 +23067,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4ea9 <.literal16+0x4a9> + DB 224,7 ; loopne 5099 <.literal16+0x4a9> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4ead <.literal16+0x4ad> + DB 224,7 ; loopne 509d <.literal16+0x4ad> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4eb1 <.literal16+0x4b1> + DB 224,7 ; loopne 50a1 <.literal16+0x4b1> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4eb5 <.literal16+0x4b5> + DB 224,7 ; loopne 50a5 <.literal16+0x4b5> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -22533,11 +23138,11 @@ ALIGN 16 DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4f8b <.literal16+0x58b> + DB 127,67 ; jg 517b <.literal16+0x58b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4f8f <.literal16+0x58f> + DB 127,67 ; jg 517f <.literal16+0x58f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4f93 <.literal16+0x593> + DB 127,67 ; jg 5183 <.literal16+0x593> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,129,128,128,59 ; addb $0x3b,-0x7f7f7ec5(%rax) @@ -22552,16 +23157,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4f84 <.literal16+0x584> + DB 127,0 ; jg 5174 <.literal16+0x584> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4f88 <.literal16+0x588> + DB 127,0 ; jg 5178 <.literal16+0x588> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4f8c <.literal16+0x58c> + DB 127,0 ; jg 517c <.literal16+0x58c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4f90 <.literal16+0x590> + DB 127,0 ; jg 5180 <.literal16+0x590> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -22570,7 +23175,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 5015 <.literal16+0x615> + DB 119,115 ; ja 5205 <.literal16+0x615> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -22581,7 +23186,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4f79 <.literal16+0x579> + DB 117,191 ; jne 5169 <.literal16+0x579> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -22593,7 +23198,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a38fba <_sk_callback_sse2+0xffffffffe9a3466c> + DB 233,220,63,163,233 ; jmpq ffffffffe9a391aa <_sk_callback_sse2+0xffffffffe9a3466b> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -22647,16 +23252,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 5054 <.literal16+0x654> + DB 127,0 ; jg 5244 <.literal16+0x654> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 5058 <.literal16+0x658> + DB 127,0 ; jg 5248 <.literal16+0x658> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 505c <.literal16+0x65c> + DB 127,0 ; jg 524c <.literal16+0x65c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 5060 <.literal16+0x660> + DB 127,0 ; jg 5250 <.literal16+0x660> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -22665,7 +23270,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 50e5 <.literal16+0x6e5> + DB 119,115 ; ja 52d5 <.literal16+0x6e5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -22676,7 +23281,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 5049 <.literal16+0x649> + DB 117,191 ; jne 5239 <.literal16+0x649> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -22688,7 +23293,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a3908a <_sk_callback_sse2+0xffffffffe9a3473c> + DB 233,220,63,163,233 ; jmpq ffffffffe9a3927a <_sk_callback_sse2+0xffffffffe9a3473b> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -22742,16 +23347,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 5124 <.literal16+0x724> + DB 127,0 ; jg 5314 <.literal16+0x724> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 5128 <.literal16+0x728> + DB 127,0 ; jg 5318 <.literal16+0x728> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 512c <.literal16+0x72c> + DB 127,0 ; jg 531c <.literal16+0x72c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 5130 <.literal16+0x730> + DB 127,0 ; jg 5320 <.literal16+0x730> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -22760,7 +23365,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 51b5 <.literal16+0x7b5> + DB 119,115 ; ja 53a5 <.literal16+0x7b5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -22771,7 +23376,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 5119 <.literal16+0x719> + DB 117,191 ; jne 5309 <.literal16+0x719> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -22783,7 +23388,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a3915a <_sk_callback_sse2+0xffffffffe9a3480c> + DB 233,220,63,163,233 ; jmpq ffffffffe9a3934a <_sk_callback_sse2+0xffffffffe9a3480b> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -22837,16 +23442,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 51f4 <.literal16+0x7f4> + DB 127,0 ; jg 53e4 <.literal16+0x7f4> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 51f8 <.literal16+0x7f8> + DB 127,0 ; jg 53e8 <.literal16+0x7f8> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 51fc <.literal16+0x7fc> + DB 127,0 ; jg 53ec <.literal16+0x7fc> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 5200 <.literal16+0x800> + DB 127,0 ; jg 53f0 <.literal16+0x800> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -22855,7 +23460,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 5285 <.literal16+0x885> + DB 119,115 ; ja 5475 <.literal16+0x885> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -22866,7 +23471,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 51e9 <.literal16+0x7e9> + DB 117,191 ; jne 53d9 <.literal16+0x7e9> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -22878,7 +23483,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a3922a <_sk_callback_sse2+0xffffffffe9a348dc> + DB 233,220,63,163,233 ; jmpq ffffffffe9a3941a <_sk_callback_sse2+0xffffffffe9a348db> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -22928,13 +23533,13 @@ ALIGN 16 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 - DB 127,67 ; jg 5307 <.literal16+0x907> + DB 127,67 ; jg 54f7 <.literal16+0x907> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 530b <.literal16+0x90b> + DB 127,67 ; jg 54fb <.literal16+0x90b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 530f <.literal16+0x90f> + DB 127,67 ; jg 54ff <.literal16+0x90f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 5313 <.literal16+0x913> + DB 127,67 ; jg 5503 <.literal16+0x913> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -22981,16 +23586,16 @@ ALIGN 16 DB 128,3,62 ; addb $0x3e,(%rbx) DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 5393 <.literal16+0x993> + DB 118,63 ; jbe 5583 <.literal16+0x993> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 5397 <.literal16+0x997> + DB 118,63 ; jbe 5587 <.literal16+0x997> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 539b <.literal16+0x99b> + DB 118,63 ; jbe 558b <.literal16+0x99b> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 539f <.literal16+0x99f> + DB 118,63 ; jbe 558f <.literal16+0x99f> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) @@ -23002,11 +23607,11 @@ ALIGN 16 DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 53db <.literal16+0x9db> + DB 127,67 ; jg 55cb <.literal16+0x9db> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 53df <.literal16+0x9df> + DB 127,67 ; jg 55cf <.literal16+0x9df> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 53e3 <.literal16+0x9e3> + DB 127,67 ; jg 55d3 <.literal16+0x9e3> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,0,0,128,63 ; addb $0x3f,-0x7fffffc5(%rax) @@ -23046,13 +23651,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 5429 <.literal16+0xa29> + DB 224,7 ; loopne 5619 <.literal16+0xa29> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 542d <.literal16+0xa2d> + DB 224,7 ; loopne 561d <.literal16+0xa2d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 5431 <.literal16+0xa31> + DB 224,7 ; loopne 5621 <.literal16+0xa31> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 5435 <.literal16+0xa35> + DB 224,7 ; loopne 5625 <.literal16+0xa35> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -23098,13 +23703,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 5499 <.literal16+0xa99> + DB 224,7 ; loopne 5689 <.literal16+0xa99> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 549d <.literal16+0xa9d> + DB 224,7 ; loopne 568d <.literal16+0xa9d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 54a1 <.literal16+0xaa1> + DB 224,7 ; loopne 5691 <.literal16+0xaa1> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 54a5 <.literal16+0xaa5> + DB 224,7 ; loopne 5695 <.literal16+0xaa5> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -23142,13 +23747,13 @@ ALIGN 16 DB 65,0,0 ; add %al,(%r8) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 5536 <.literal16+0xb36> + DB 124,66 ; jl 5726 <.literal16+0xb36> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 553a <.literal16+0xb3a> + DB 124,66 ; jl 572a <.literal16+0xb3a> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 553e <.literal16+0xb3e> + DB 124,66 ; jl 572e <.literal16+0xb3e> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 5542 <.literal16+0xb42> + DB 124,66 ; jl 5732 <.literal16+0xb42> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 0,240 ; add %dh,%al @@ -23238,13 +23843,13 @@ ALIGN 16 DB 136,136,61,137,136,136 ; mov %cl,-0x777776c3(%rax) DB 61,137,136,136,61 ; cmp $0x3d888889,%eax DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 5645 <.literal16+0xc45> + DB 112,65 ; jo 5835 <.literal16+0xc45> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 5649 <.literal16+0xc49> + DB 112,65 ; jo 5839 <.literal16+0xc49> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 564d <.literal16+0xc4d> + DB 112,65 ; jo 583d <.literal16+0xc4d> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 5651 <.literal16+0xc51> + DB 112,65 ; jo 5841 <.literal16+0xc51> DB 255,0 ; incl (%rax) DB 0,0 ; add %al,(%rax) DB 255,0 ; incl (%rax) @@ -23266,11 +23871,11 @@ ALIGN 16 DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,0,0,127,67 ; addb $0x43,0x7f00003b(%rax) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 569b <.literal16+0xc9b> + DB 127,67 ; jg 588b <.literal16+0xc9b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 569f <.literal16+0xc9f> + DB 127,67 ; jg 588f <.literal16+0xc9f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 56a3 <.literal16+0xca3> + DB 127,67 ; jg 5893 <.literal16+0xca3> DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) DB 0,0 ; add %al,(%rax) DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) @@ -23346,13 +23951,13 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 255 ; (bad) - DB 127,71 ; jg 578b <.literal16+0xd8b> + DB 127,71 ; jg 597b <.literal16+0xd8b> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 578f <.literal16+0xd8f> + DB 127,71 ; jg 597f <.literal16+0xd8f> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 5793 <.literal16+0xd93> + DB 127,71 ; jg 5983 <.literal16+0xd93> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 5797 <.literal16+0xd97> + DB 127,71 ; jg 5987 <.literal16+0xd97> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -23402,19 +24007,27 @@ ALIGN 16 DB 221,147,61,152,221,147 ; fstl -0x6c2267c3(%rbx) DB 61,152,221,147,61 ; cmp $0x3d93dd98,%eax DB 152 ; cwtl - DB 221,147,61,111,43,231 ; fstl -0x18d490c3(%rbx) - DB 187,111,43,231,187 ; mov $0xbbe72b6f,%ebx + DB 221,147,61,1,0,0 ; fstl 0x13d(%rbx) + DB 0,1 ; add %al,(%rcx) + DB 0,0 ; add %al,(%rax) + DB 0,1 ; add %al,(%rcx) + DB 0,0 ; add %al,(%rax) + DB 0,1 ; add %al,(%rcx) + DB 0,0 ; add %al,(%rax) + DB 0,111,43 ; add %ch,0x2b(%rdi) + DB 231,187 ; out %eax,$0xbb DB 111 ; outsl %ds:(%rsi),(%dx) DB 43,231 ; sub %edi,%esp DB 187,111,43,231,187 ; mov $0xbbe72b6f,%ebx + DB 111 ; outsl %ds:(%rsi),(%dx) + DB 43,231 ; sub %edi,%esp + DB 187,159,215,202,60 ; mov $0x3ccad79f,%ebx DB 159 ; lahf DB 215 ; xlat %ds:(%rbx) DB 202,60,159 ; lret $0x9f3c DB 215 ; xlat %ds:(%rbx) DB 202,60,159 ; lret $0x9f3c DB 215 ; xlat %ds:(%rbx) - DB 202,60,159 ; lret $0x9f3c - DB 215 ; xlat %ds:(%rbx) DB 202,60,212 ; lret $0xd43c DB 100,84 ; fs push %rsp DB 189,212,100,84,189 ; mov $0xbd5464d4,%ebp @@ -23505,11 +24118,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 58f2 <.literal16+0xef2> + DB 62,114,28 ; jb,pt 5af2 <.literal16+0xf02> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 58f6 <.literal16+0xef6> + DB 62,114,28 ; jb,pt 5af6 <.literal16+0xf06> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 58fa <.literal16+0xefa> + DB 62,114,28 ; jb,pt 5afa <.literal16+0xf0a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -23553,7 +24166,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e785 <_sk_callback_sse2+0x3d639e37> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e985 <_sk_callback_sse2+0x3d639e46> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -23579,7 +24192,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e7c5 <_sk_callback_sse2+0x3d639e77> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e9c5 <_sk_callback_sse2+0x3d639e86> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -23588,13 +24201,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 59be <.literal16+0xfbe> + DB 114,28 ; jb 5bbe <.literal16+0xfce> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 59c2 <.literal16+0xfc2> + DB 62,114,28 ; jb,pt 5bc2 <.literal16+0xfd2> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 59c6 <.literal16+0xfc6> + DB 62,114,28 ; jb,pt 5bc6 <.literal16+0xfd6> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 59ca <.literal16+0xfca> + DB 62,114,28 ; jb,pt 5bca <.literal16+0xfda> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -23615,11 +24228,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 5a02 <.literal16+0x1002> + DB 62,114,28 ; jb,pt 5c02 <.literal16+0x1012> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5a06 <.literal16+0x1006> + DB 62,114,28 ; jb,pt 5c06 <.literal16+0x1016> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5a0a <.literal16+0x100a> + DB 62,114,28 ; jb,pt 5c0a <.literal16+0x101a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -23663,7 +24276,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e895 <_sk_callback_sse2+0x3d639f47> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63ea95 <_sk_callback_sse2+0x3d639f56> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -23689,7 +24302,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63e8d5 <_sk_callback_sse2+0x3d639f87> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63ead5 <_sk_callback_sse2+0x3d639f96> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -23698,13 +24311,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 5ace <.literal16+0x10ce> + DB 114,28 ; jb 5cce <.literal16+0x10de> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5ad2 <_sk_callback_sse2+0x1184> + DB 62,114,28 ; jb,pt 5cd2 <_sk_callback_sse2+0x1193> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5ad6 <_sk_callback_sse2+0x1188> + DB 62,114,28 ; jb,pt 5cd6 <_sk_callback_sse2+0x1197> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 5ada <_sk_callback_sse2+0x118c> + DB 62,114,28 ; jb,pt 5cda <_sk_callback_sse2+0x119b> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) diff --git a/src/jumper/SkJumper_misc.h b/src/jumper/SkJumper_misc.h index bc7fd22..de74789 100644 --- a/src/jumper/SkJumper_misc.h +++ b/src/jumper/SkJumper_misc.h @@ -13,7 +13,12 @@ // Miscellany used by SkJumper_stages.cpp and SkJumper_vectors.h. // Every function in this file should be marked static and inline using SI. -#define SI static inline +#if defined(JUMPER) + #define SI __attribute__((always_inline)) static inline +#else + #define SI static inline +#endif + template SI T unaligned_load(const P* p) { // const void* would work too, but const P* helps ARMv7 codegen. diff --git a/src/jumper/SkJumper_stages.cpp b/src/jumper/SkJumper_stages.cpp index 9b6cfa8..5dd84e2 100644 --- a/src/jumper/SkJumper_stages.cpp +++ b/src/jumper/SkJumper_stages.cpp @@ -1055,32 +1055,56 @@ STAGE(matrix_perspective) { g = G * rcp(Z); } -STAGE(gradient) { - struct Stop { float pos; float f[4], b[4]; }; - struct Ctx { size_t n; Stop *stops; float start[4]; }; +SI void gradient_lookup(const SkJumper_GradientCtx* c, U32 idx, F t, + F* r, F* g, F* b, F* a) { + F fr, br, fg, bg, fb, bb, fa, ba; +#if defined(JUMPER) && defined(__AVX2__) + if (c->stopCount <=8) { + fr = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->fs[0]), idx); + br = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->bs[0]), idx); + fg = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->fs[1]), idx); + bg = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->bs[1]), idx); + fb = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->fs[2]), idx); + bb = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->bs[2]), idx); + fa = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->fs[3]), idx); + ba = _mm256_permutevar8x32_ps(_mm256_loadu_ps(c->bs[3]), idx); + } else +#endif + { + fr = gather(c->fs[0], idx); + br = gather(c->bs[0], idx); + fg = gather(c->fs[1], idx); + bg = gather(c->bs[1], idx); + fb = gather(c->fs[2], idx); + bb = gather(c->bs[2], idx); + fa = gather(c->fs[3], idx); + ba = gather(c->bs[3], idx); + } - auto c = (const Ctx*)ctx; - F fr = 0, fg = 0, fb = 0, fa = 0; - F br = c->start[0], - bg = c->start[1], - bb = c->start[2], - ba = c->start[3]; + *r = mad(t, fr, br); + *g = mad(t, fg, bg); + *b = mad(t, fb, bb); + *a = mad(t, fa, ba); +} + +STAGE(evenly_spaced_gradient) { + auto c = (const SkJumper_GradientCtx*)ctx; + auto t = r; + auto idx = trunc_(t * (c->stopCount-1)); + gradient_lookup(c, idx, t, &r, &g, &b, &a); +} + +STAGE(gradient) { + auto c = (const SkJumper_GradientCtx*)ctx; auto t = r; - for (size_t i = 0; i < c->n; i++) { - fr = if_then_else(t < c->stops[i].pos, fr, c->stops[i].f[0]); - fg = if_then_else(t < c->stops[i].pos, fg, c->stops[i].f[1]); - fb = if_then_else(t < c->stops[i].pos, fb, c->stops[i].f[2]); - fa = if_then_else(t < c->stops[i].pos, fa, c->stops[i].f[3]); - br = if_then_else(t < c->stops[i].pos, br, c->stops[i].b[0]); - bg = if_then_else(t < c->stops[i].pos, bg, c->stops[i].b[1]); - bb = if_then_else(t < c->stops[i].pos, bb, c->stops[i].b[2]); - ba = if_then_else(t < c->stops[i].pos, ba, c->stops[i].b[3]); + U32 idx = 0; + + // N.B. The loop starts at 1 because idx 0 is the color to use before the first stop. + for (size_t i = 1; i < c->stopCount; i++) { + idx += if_then_else(t >= c->ts[i], U32(1), U32(0)); } - r = mad(t, fr, br); - g = mad(t, fg, bg); - b = mad(t, fb, bb); - a = mad(t, fa, ba); + gradient_lookup(c, idx, t, &r, &g, &b, &a); } STAGE(evenly_spaced_2_stop_gradient) {