AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

aco: use -1.0*x and 1.0*|x| for fneg/fabs

Browse Source 
Besides -1.0*x being 1 dword smaller than x^0x80000000, this commit also
improves generated code when the application requires that denormals are
flushed.

Future versions of DXVK will require that 32-bit denormals are flushed.

fossil-db (GFX8):
Totals from 21021 (14.22% of 147787) affected shaders:
SGPRs: 1288960 -> 1288944 (-0.00%); split: -0.01%, +0.01%
VGPRs: 792672 -> 792848 (+0.02%); split: -0.01%, +0.03%
CodeSize: 62439228 -> 62403552 (-0.06%); split: -0.11%, +0.05%
MaxWaves: 136182 -> 136181 (-0.00%); split: +0.00%, -0.00%
Instrs: 12230882 -> 12239927 (+0.07%); split: -0.01%, +0.08%

fossil-db (GFX10.3):
Totals from 20191 (13.80% of 146267) affected shaders:
VGPRs: 799992 -> 800032 (+0.01%)
CodeSize: 59763656 -> 59715484 (-0.08%); split: -0.12%, +0.03%
MaxWaves: 525378 -> 525376 (-0.00%)
Instrs: 11511082 -> 11517419 (+0.06%); split: -0.00%, +0.06%

fossil-db (GFX8, d3d float controls):
Totals from 87160 (58.98% of 147787) affected shaders:
SGPRs: 5395072 -> 5408480 (+0.25%); split: -0.06%, +0.31%
VGPRs: 3596716 -> 3581592 (-0.42%); split: -0.55%, +0.13%
CodeSize: 271347396 -> 266814460 (-1.67%); split: -1.67%, +0.00%
MaxWaves: 539669 -> 540400 (+0.14%); split: +0.15%, -0.02%
Instrs: 53395194 -> 52257505 (-2.13%); split: -2.13%, +0.00%

fossil-db (GFX10.3, d3d float controls):
Totals from 82306 (56.27% of 146267) affected shaders:
VGPRs: 3572312 -> 3558848 (-0.38%); split: -0.44%, +0.06%
CodeSize: 273494748 -> 269648968 (-1.41%); split: -1.41%, +0.00%
MaxWaves: 2007156 -> 2009950 (+0.14%); split: +0.15%, -0.01%
Instrs: 52251568 -> 51356424 (-1.71%); split: -1.71%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9079>
This commit is contained in:
Rhys Perry
2020-06-25 11:44:26 +01:00
committed by Marge Bot
parent 561fcfb50f
commit e3c283e0bc
3 changed files with 174 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/amd/compiler/aco_instruction_selection.cpp
+6 -12
View File
@@ -2073,13 +2073,9 @@ void visit_alu_instr(isel_context *ctx, nir_alu_instr *instr)
}
Temp src = get_alu_src(ctx, instr->src[0]);
if (dst.regClass() == v2b) {
if (ctx->block->fp_mode.must_flush_denorms16_64)
src = bld.vop2(aco_opcode::v_mul_f16, bld.def(v2b), Operand((uint16_t)0x3C00), as_vgpr(ctx, src));
bld.vop2(aco_opcode::v_xor_b32, Definition(dst), Operand(0x8000u), as_vgpr(ctx, src));
bld.vop2(aco_opcode::v_mul_f16, Definition(dst), Operand((uint16_t)0xbc00u), as_vgpr(ctx, src));
} else if (dst.regClass() == v1) {
if (ctx->block->fp_mode.must_flush_denorms32)
src = bld.vop2(aco_opcode::v_mul_f32, bld.def(v1), Operand(0x3f800000u), as_vgpr(ctx, src));
bld.vop2(aco_opcode::v_xor_b32, Definition(dst), Operand(0x80000000u), as_vgpr(ctx, src));
bld.vop2(aco_opcode::v_mul_f32, Definition(dst), Operand(0xbf800000u), as_vgpr(ctx, src));
} else if (dst.regClass() == v2) {
if (ctx->block->fp_mode.must_flush_denorms16_64)
src = bld.vop3(aco_opcode::v_mul_f64, bld.def(v2), Operand(UINT64_C(0x3FF0000000000000)), as_vgpr(ctx, src));
@@ -2095,13 +2091,11 @@ void visit_alu_instr(isel_context *ctx, nir_alu_instr *instr)
case nir_op_fabs: {
Temp src = get_alu_src(ctx, instr->src[0]);
if (dst.regClass() == v2b) {
if (ctx->block->fp_mode.must_flush_denorms16_64)
src = bld.vop2(aco_opcode::v_mul_f16, bld.def(v2b), Operand((uint16_t)0x3C00), as_vgpr(ctx, src));
bld.vop2(aco_opcode::v_and_b32, Definition(dst), Operand(0x7FFFu), as_vgpr(ctx, src));
Instruction *mul = bld.vop2_e64(aco_opcode::v_mul_f16, Definition(dst), Operand((uint16_t)0x3c00), as_vgpr(ctx, src)).instr;
mul->vop3().abs[1] = true;
} else if (dst.regClass() == v1) {
if (ctx->block->fp_mode.must_flush_denorms32)
src = bld.vop2(aco_opcode::v_mul_f32, bld.def(v1), Operand(0x3f800000u), as_vgpr(ctx, src));
bld.vop2(aco_opcode::v_and_b32, Definition(dst), Operand(0x7FFFFFFFu), as_vgpr(ctx, src));
Instruction *mul = bld.vop2_e64(aco_opcode::v_mul_f32, Definition(dst), Operand(0x3f800000u), as_vgpr(ctx, src)).instr;
mul->vop3().abs[1] = true;
} else if (dst.regClass() == v2) {
if (ctx->block->fp_mode.must_flush_denorms16_64)
src = bld.vop3(aco_opcode::v_mul_f64, bld.def(v2), Operand(UINT64_C(0x3FF0000000000000)), as_vgpr(ctx, src));