fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-20 16:00:08 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

aco/optimizer: reassociate rcp(mul(a, const)) into rcp_omod(a)

Browse source 
Foz-DB Navi48:
Totals from 2484 (2.54% of 97637) affected shaders:
Instrs: 10368279 -> 10361892 (-0.06%); split: -0.06%, +0.00%
CodeSize: 55161104 -> 55150752 (-0.02%); split: -0.02%, +0.00%
SpillSGPRs: 14665 -> 14666 (+0.01%)
Latency: 87694014 -> 87689324 (-0.01%); split: -0.01%, +0.00%
InvThroughput: 16595764 -> 16594448 (-0.01%); split: -0.01%, +0.00%
VClause: 209922 -> 209918 (-0.00%); split: -0.01%, +0.00%
SClause: 205195 -> 205251 (+0.03%); split: -0.01%, +0.04%
Copies: 843771 -> 843765 (-0.00%); split: -0.01%, +0.01%
Branches: 275985 -> 275962 (-0.01%); split: -0.01%, +0.00%
PreVGPRs: 170608 -> 170494 (-0.07%)
VALU: 5840893 -> 5838038 (-0.05%); split: -0.05%, +0.00%
SALU: 1481388 -> 1479037 (-0.16%); split: -0.16%, +0.00%
VOPD: 7496 -> 7485 (-0.15%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38730>
This commit is contained in:
Georg Lehmann 2025-11-30 14:57:14 +01:00 • committed by Marge Bot
parent a8f5ced670
commit 0478021fdc
1 changed files with 16 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
src/amd/compiler/aco_optimizer.cpp
View file

@ -4372,6 +4372,22 @@ combine_instruction(opt_ctx& ctx, aco_ptr<Instruction>& instr)
add_opt(v_mul_f64, v_mul_f64, 0x3, "120", reassoc_omod_cb<false>, true); add_opt(v_mul_f64, v_mul_f64, 0x3, "120", reassoc_omod_cb<false>, true);
} else if (info.opcode == aco_opcode::v_mul_f64_e64 && can_reassoc_omod(ctx, info, 64)) { } else if (info.opcode == aco_opcode::v_mul_f64_e64 && can_reassoc_omod(ctx, info, 64)) {
add_opt(v_mul_f64_e64, v_mul_f64_e64, 0x3, "120", reassoc_omod_cb<false>, true); add_opt(v_mul_f64_e64, v_mul_f64_e64, 0x3, "120", reassoc_omod_cb<false>, true);
} else if (info.opcode == aco_opcode::v_rcp_f32 && can_reassoc_omod(ctx, info, 32)) {
add_opt(v_mul_f32, v_rcp_f32, 0x1, "01", reassoc_omod_cb<true>);
add_opt(v_mul_legacy_f32, v_rcp_f32, 0x1, "01", reassoc_omod_cb<true>);
add_opt(s_mul_f32, v_rcp_f32, 0x1, "01", reassoc_omod_cb<true>);
} else if (info.opcode == aco_opcode::v_s_rcp_f32 && can_reassoc_omod(ctx, info, 32)) {
add_opt(s_mul_f32, v_s_rcp_f32, 0x1, "01", reassoc_omod_cb<true>);
} else if (info.opcode == aco_opcode::v_rcp_f16 && can_reassoc_omod(ctx, info, 16)) {
add_opt(v_mul_f16, v_rcp_f16, 0x1, "01", reassoc_omod_cb<true>);
add_opt(s_mul_f16, v_rcp_f16, 0x1, "01", reassoc_omod_cb<true>);
} else if (info.opcode == aco_opcode::v_s_rcp_f16 && can_reassoc_omod(ctx, info, 16)) {
add_opt(s_mul_f16, v_s_rcp_f16, 0x1, "01", reassoc_omod_cb<true>);
} else if (info.opcode == aco_opcode::v_rcp_f64 && can_reassoc_omod(ctx, info, 64)) {
if (ctx.program->gfx_level < GFX12)
add_opt(v_mul_f64_e64, v_rcp_f64, 0x1, "01", reassoc_omod_cb<true>);
else
add_opt(v_mul_f64, v_rcp_f64, 0x1, "01", reassoc_omod_cb<true>);
} else if (info.opcode == aco_opcode::v_add_u16 && !info.clamp) { } else if (info.opcode == aco_opcode::v_add_u16 && !info.clamp) {
if (ctx.program->gfx_level < GFX9) { if (ctx.program->gfx_level < GFX9) {
add_opt(v_mul_lo_u16, v_mad_legacy_u16, 0x3, "120"); add_opt(v_mul_lo_u16, v_mad_legacy_u16, 0x3, "120");