entry:
%shuffle = shufflevector <16 x i16> %a, <16 x i16> undef, <16 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
ret <16 x i16> %shuffle
-}\r
-\r
-; CHECK: vmovq\r
-; CHECK-NEXT: vmovddup %xmm\r
-; CHECK-NEXT: vinsertf128 $1\r
-define <4 x i64> @funcC(i64 %q) nounwind uwtable readnone ssp {\r
-entry:\r
+}
+
+; CHECK: vmovq
+; CHECK-NEXT: vmovddup %xmm
+; CHECK-NEXT: vinsertf128 $1
+define <4 x i64> @funcC(i64 %q) nounwind uwtable readnone ssp {
+entry:
%vecinit.i = insertelement <4 x i64> undef, i64 %q, i32 0
%vecinit2.i = insertelement <4 x i64> %vecinit.i, i64 %q, i32 1
%vecinit4.i = insertelement <4 x i64> %vecinit2.i, i64 %q, i32 2
%vecinit6.i = insertelement <4 x i64> %vecinit4.i, i64 %q, i32 3
- ret <4 x i64> %vecinit6.i\r
-}\r
-\r
-; CHECK: vmovddup %xmm\r
-; CHECK-NEXT: vinsertf128 $1\r
-define <4 x double> @funcD(double %q) nounwind uwtable readnone ssp {\r
-entry:\r
+ ret <4 x i64> %vecinit6.i
+}
+
+; CHECK: vmovddup %xmm
+; CHECK-NEXT: vinsertf128 $1
+define <4 x double> @funcD(double %q) nounwind uwtable readnone ssp {
+entry:
%vecinit.i = insertelement <4 x double> undef, double %q, i32 0
%vecinit2.i = insertelement <4 x double> %vecinit.i, double %q, i32 1
%vecinit4.i = insertelement <4 x double> %vecinit2.i, double %q, i32 2
%vecinit6.i = insertelement <4 x double> %vecinit4.i, double %q, i32 3
ret <4 x double> %vecinit6.i
}
-\r
-; Test this turns into a broadcast:\r
-; shuffle (scalar_to_vector (load (ptr + 4))), undef, <0, 0, 0, 0>\r
-;\r
-; CHECK: vbroadcastss\r
-define <8 x float> @funcE() nounwind {\r
-allocas:\r
+
+; Test this turns into a broadcast:
+; shuffle (scalar_to_vector (load (ptr + 4))), undef, <0, 0, 0, 0>
+;
+; CHECK: vbroadcastss
+define <8 x float> @funcE() nounwind {
+allocas:
%udx495 = alloca [18 x [18 x float]], align 32
br label %for_test505.preheader
define <4 x double> @_inreg4xdouble(<4 x double> %a) {
%b = shufflevector <4 x double> %a, <4 x double> undef, <4 x i32> zeroinitializer
ret <4 x double> %b
-}\r
-\r
-;CHECK-LABEL: _inreg2xdouble:\r
-;CHECK: vmovddup\r
-;CHECK: ret\r
-define <2 x double> @_inreg2xdouble(<2 x double> %a) {\r
- %b = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> zeroinitializer\r
+}
+
+;CHECK-LABEL: _inreg2xdouble:
+;CHECK: vmovddup
+;CHECK: ret
+define <2 x double> @_inreg2xdouble(<2 x double> %a) {
+ %b = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> zeroinitializer
ret <2 x double> %b
}
; GNU_SINCOS: callq sincosf
; GNU_SINCOS: movss 4(%rsp), %xmm0
; GNU_SINCOS: addss (%rsp), %xmm0
-\r
-; OSX_SINCOS-LABEL: test1:\r
-; OSX_SINCOS: callq ___sincosf_stret\r
-; OSX_SINCOS: movshdup {{.*}} xmm1 = xmm0[1,1,3,3]\r
-; OSX_SINCOS: addss %xmm1, %xmm0\r
-\r
-; OSX_NOOPT: test1\r
-; OSX_NOOPT: callq _sinf\r
+
+; OSX_SINCOS-LABEL: test1:
+; OSX_SINCOS: callq ___sincosf_stret
+; OSX_SINCOS: movshdup {{.*}} xmm1 = xmm0[1,1,3,3]
+; OSX_SINCOS: addss %xmm1, %xmm0
+
+; OSX_NOOPT: test1
+; OSX_NOOPT: callq _sinf
; OSX_NOOPT: callq _cosf
%call = tail call float @sinf(float %x) nounwind readnone
%call1 = tail call float @cosf(float %x) nounwind readnone
; This used to compile to insertps $0 + insertps $16. insertps $0 is always
; pointless.
-define <2 x float> @buildvector(<2 x float> %A, <2 x float> %B) nounwind {\r
-; X32-LABEL: buildvector:\r
-; X32: ## BB#0: ## %entry\r
-; X32-NEXT: movshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]\r
-; X32-NEXT: movshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]\r
-; X32-NEXT: addss %xmm1, %xmm0\r
-; X32-NEXT: addss %xmm2, %xmm3\r
-; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[2,3]\r
-; X32-NEXT: retl\r
-;\r
-; X64-LABEL: buildvector:\r
-; X64: ## BB#0: ## %entry\r
-; X64-NEXT: movshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]\r
-; X64-NEXT: movshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]\r
-; X64-NEXT: addss %xmm1, %xmm0\r
-; X64-NEXT: addss %xmm2, %xmm3\r
-; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[2,3]\r
-; X64-NEXT: retq\r
-entry:\r
- %tmp7 = extractelement <2 x float> %A, i32 0\r
+define <2 x float> @buildvector(<2 x float> %A, <2 x float> %B) nounwind {
+; X32-LABEL: buildvector:
+; X32: ## BB#0: ## %entry
+; X32-NEXT: movshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; X32-NEXT: movshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]
+; X32-NEXT: addss %xmm1, %xmm0
+; X32-NEXT: addss %xmm2, %xmm3
+; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[2,3]
+; X32-NEXT: retl
+;
+; X64-LABEL: buildvector:
+; X64: ## BB#0: ## %entry
+; X64-NEXT: movshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; X64-NEXT: movshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]
+; X64-NEXT: addss %xmm1, %xmm0
+; X64-NEXT: addss %xmm2, %xmm3
+; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[2,3]
+; X64-NEXT: retq
+entry:
+ %tmp7 = extractelement <2 x float> %A, i32 0
%tmp5 = extractelement <2 x float> %A, i32 1
%tmp3 = extractelement <2 x float> %B, i32 0
%tmp1 = extractelement <2 x float> %B, i32 1
; RUN: llc < %s -mcpu=yonah -march=x86 -mtriple=i386-linux-gnu -o - | FileCheck %s --check-prefix=X32
; PR7518
-define void @test1(<2 x float> %Q, float *%P2) nounwind {\r
-; X64-LABEL: test1:\r
-; X64: # BB#0:\r
-; X64-NEXT: movshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]\r
-; X64-NEXT: addss %xmm0, %xmm1\r
-; X64-NEXT: movss %xmm1, (%rdi)\r
-; X64-NEXT: retq\r
-;\r
-; X32-LABEL: test1:\r
-; X32: # BB#0:\r
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax\r
-; X32-NEXT: movshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]\r
-; X32-NEXT: addss %xmm0, %xmm1\r
-; X32-NEXT: movss %xmm1, (%eax)\r
-; X32-NEXT: retl\r
+define void @test1(<2 x float> %Q, float *%P2) nounwind {
+; X64-LABEL: test1:
+; X64: # BB#0:
+; X64-NEXT: movshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; X64-NEXT: addss %xmm0, %xmm1
+; X64-NEXT: movss %xmm1, (%rdi)
+; X64-NEXT: retq
+;
+; X32-LABEL: test1:
+; X32: # BB#0:
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: movshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; X32-NEXT: addss %xmm0, %xmm1
+; X32-NEXT: movss %xmm1, (%eax)
+; X32-NEXT: retl
%a = extractelement <2 x float> %Q, i32 0
%b = extractelement <2 x float> %Q, i32 1
%c = fadd float %a, %b
; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %eax
; CHECK-WIDE-NEXT: shll $8, %eax
; CHECK-WIDE-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
-; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %ecx\r
-; CHECK-WIDE-NEXT: movzbl %cl, %ecx\r
-; CHECK-WIDE-NEXT: orl %eax, %ecx\r
-; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]\r
-; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %eax\r
-; CHECK-WIDE-NEXT: shll $8, %eax\r
-; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %edx\r
-; CHECK-WIDE-NEXT: movzbl %dl, %edx\r
-; CHECK-WIDE-NEXT: orl %eax, %edx\r
-; CHECK-WIDE-NEXT: vpinsrw $0, %edx, %xmm0, %xmm1\r
-; CHECK-WIDE-NEXT: vpinsrw $1, %ecx, %xmm1, %xmm1\r
-; CHECK-WIDE-NEXT: vextractf128 $1, %ymm0, %xmm0\r
-; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]\r
-; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax\r
-; CHECK-WIDE-NEXT: shll $8, %eax\r
-; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %ecx\r
+; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %ecx
+; CHECK-WIDE-NEXT: movzbl %cl, %ecx
+; CHECK-WIDE-NEXT: orl %eax, %ecx
+; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %eax
+; CHECK-WIDE-NEXT: shll $8, %eax
+; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %edx
+; CHECK-WIDE-NEXT: movzbl %dl, %edx
+; CHECK-WIDE-NEXT: orl %eax, %edx
+; CHECK-WIDE-NEXT: vpinsrw $0, %edx, %xmm0, %xmm1
+; CHECK-WIDE-NEXT: vpinsrw $1, %ecx, %xmm1, %xmm1
+; CHECK-WIDE-NEXT: vextractf128 $1, %ymm0, %xmm0
+; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax
+; CHECK-WIDE-NEXT: shll $8, %eax
+; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %ecx
; CHECK-WIDE-NEXT: movzbl %cl, %ecx
; CHECK-WIDE-NEXT: orl %eax, %ecx
; CHECK-WIDE-NEXT: vpinsrw $2, %ecx, %xmm1, %xmm1
; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %eax
; CHECK-WIDE-NEXT: shll $8, %eax
; CHECK-WIDE-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
-; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %ecx\r
-; CHECK-WIDE-NEXT: movzbl %cl, %ecx\r
-; CHECK-WIDE-NEXT: orl %eax, %ecx\r
-; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]\r
-; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %eax\r
-; CHECK-WIDE-NEXT: shll $8, %eax\r
-; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %edx\r
+; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %ecx
+; CHECK-WIDE-NEXT: movzbl %cl, %ecx
+; CHECK-WIDE-NEXT: orl %eax, %ecx
+; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; CHECK-WIDE-NEXT: vcvttss2si %xmm1, %eax
+; CHECK-WIDE-NEXT: shll $8, %eax
+; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %edx
; CHECK-WIDE-NEXT: movzbl %dl, %edx
; CHECK-WIDE-NEXT: orl %eax, %edx
; CHECK-WIDE-NEXT: vpinsrw $0, %edx, %xmm0, %xmm0
ret <8 x float> %shuffle
}
-define <8 x float> @shuffle_v8f32_01014545(<8 x float> %a, <8 x float> %b) {\r
-; ALL-LABEL: shuffle_v8f32_01014545:\r
-; ALL: # BB#0:\r
-; ALL-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]\r
-; ALL-NEXT: retq\r
- %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 4, i32 5, i32 4, i32 5>\r
- ret <8 x float> %shuffle\r
+define <8 x float> @shuffle_v8f32_01014545(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_01014545:
+; ALL: # BB#0:
+; ALL-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 4, i32 5, i32 4, i32 5>
+ ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_00112233(<8 x float> %a, <8 x float> %b) {
define <8 x float> @shuffle_v8f32_08080808(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_08080808:
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]\r
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1\r
-; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]\r
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0\r
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]\r
-; AVX1-NEXT: retq\r
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
+; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_08080808:
; AVX2: # BB#0:
ret <8 x float> %shuffle
}
-define <8 x float> @shuffle_v8f32_09ab1def(<8 x float> %a, <8 x float> %b) {\r
-; AVX1-LABEL: shuffle_v8f32_09ab1def:\r
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]\r
-; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0\r
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]\r
-; AVX1-NEXT: retq\r
+define <8 x float> @shuffle_v8f32_09ab1def(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_09ab1def:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_09ab1def:
; AVX2: # BB#0:
ret <8 x float> %shuffle
}
-define <8 x float> @shuffle_v8f32_00224466(<8 x float> %a, <8 x float> %b) {\r
-; ALL-LABEL: shuffle_v8f32_00224466:\r
-; ALL: # BB#0:\r
-; ALL-NEXT: vmovsldup {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]\r
-; ALL-NEXT: retq\r
- %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>\r
- ret <8 x float> %shuffle\r
+define <8 x float> @shuffle_v8f32_00224466(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_00224466:
+; ALL: # BB#0:
+; ALL-NEXT: vmovsldup {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
+ ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_10325476(<8 x float> %a, <8 x float> %b) {
ret <8 x float> %shuffle
}
-define <8 x float> @shuffle_v8f32_11335577(<8 x float> %a, <8 x float> %b) {\r
-; ALL-LABEL: shuffle_v8f32_11335577:\r
-; ALL: # BB#0:\r
-; ALL-NEXT: vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]\r
-; ALL-NEXT: retq\r
- %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>\r
- ret <8 x float> %shuffle\r
+define <8 x float> @shuffle_v8f32_11335577(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_11335577:
+; ALL: # BB#0:
+; ALL-NEXT: vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
+ ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_10235467(<8 x float> %a, <8 x float> %b) {
ret <8 x i32> %shuffle
}
-define <8 x i32> @shuffle_v8i32_01014545(<8 x i32> %a, <8 x i32> %b) {\r
-; AVX1-LABEL: shuffle_v8i32_01014545:\r
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]\r
-; AVX1-NEXT: retq\r
-;\r
-; AVX2-LABEL: shuffle_v8i32_01014545:\r
+define <8 x i32> @shuffle_v8i32_01014545(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_01014545:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_01014545:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5]
; AVX2-NEXT: retq
define <8 x i32> @shuffle_v8i32_08080808(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_08080808:
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]\r
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1\r
-; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]\r
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0\r
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]\r
-; AVX1-NEXT: retq\r
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
+; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_08080808:
; AVX2: # BB#0:
ret <8 x i32> %shuffle
}
-define <8 x i32> @shuffle_v8i32_09ab1def(<8 x i32> %a, <8 x i32> %b) {\r
-; AVX1-LABEL: shuffle_v8i32_09ab1def:\r
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]\r
-; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0\r
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]\r
-; AVX1-NEXT: retq\r
+define <8 x i32> @shuffle_v8i32_09ab1def(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_09ab1def:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_09ab1def:
; AVX2: # BB#0:
ret <8 x i32> %shuffle
}
-define <8 x i32> @shuffle_v8i32_00224466(<8 x i32> %a, <8 x i32> %b) {\r
-; AVX1-LABEL: shuffle_v8i32_00224466:\r
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vmovsldup {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]\r
-; AVX1-NEXT: retq\r
-;\r
-; AVX2-LABEL: shuffle_v8i32_00224466:\r
+define <8 x i32> @shuffle_v8i32_00224466(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_00224466:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovsldup {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_00224466:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
; AVX2-NEXT: retq
ret <8 x i32> %shuffle
}
-define <8 x i32> @shuffle_v8i32_11335577(<8 x i32> %a, <8 x i32> %b) {\r
-; AVX1-LABEL: shuffle_v8i32_11335577:\r
-; AVX1: # BB#0:\r
-; AVX1-NEXT: vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]\r
-; AVX1-NEXT: retq\r
-;\r
-; AVX2-LABEL: shuffle_v8i32_11335577:\r
+define <8 x i32> @shuffle_v8i32_11335577(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_11335577:
+; AVX1: # BB#0:
+; AVX1-NEXT: vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_11335577:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
; AVX2-NEXT: retq