From c2c639ecf667b4b7cf17cfe33dfe710432f2c43a Mon Sep 17 00:00:00 2001 From: Matt Turner Date: Thu, 22 May 2014 09:39:13 -0700 Subject: [PATCH] Revert "i965/fs: Change fs_visitor::emit_lrp to use MAC for gen<6" This reverts commit a6860100b87415ab510d0d210cabfeeccebc9a0a. Why this code didn't work in all circumstances is unknown and without a working Ironlake simulator (which uses a different AUB format) we'll probably never know, short of a lot of experimentation, and spending a bunch of time to try to optimize a few instructions on Ironlake is not time well spent. Moreover, for mix(vec4, vec4, vec4) using the accumulator introduces a dependence between the otherwise independent per-component calculations. Not using the accumulator, even if it means an extra instruction per component might be preferable. We don't know, we don't have data, and we don't have the necessary register on Ironlake for shader_time to tell us. Cc: "10.2" Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=77707 Acked-by: Kenneth Graunke --- src/mesa/drivers/dri/i965/brw_fs_visitor.cpp | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp index dcc8441..ff3d0f7 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp @@ -224,15 +224,18 @@ fs_visitor::emit_lrp(const fs_reg &dst, const fs_reg &x, const fs_reg &y, !y.is_valid_3src() || !a.is_valid_3src()) { /* We can't use the LRP instruction. Emit x*(1-a) + y*a. */ + fs_reg y_times_a = fs_reg(this, glsl_type::float_type); fs_reg one_minus_a = fs_reg(this, glsl_type::float_type); + fs_reg x_times_one_minus_a = fs_reg(this, glsl_type::float_type); + + emit(MUL(y_times_a, y, a)); fs_reg negative_a = a; negative_a.negate = !a.negate; - emit(ADD(one_minus_a, negative_a, fs_reg(1.0f))); - fs_inst *mul = emit(MUL(reg_null_f, y, a)); - mul->writes_accumulator = true; - emit(MAC(dst, x, one_minus_a)); + emit(MUL(x_times_one_minus_a, x, one_minus_a)); + + emit(ADD(dst, x_times_one_minus_a, y_times_a)); } else { /* The LRP instruction actually does op1 * op0 + op2 * (1 - op0), so * we need to reorder the operands. -- 2.7.4