fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-07 07:08:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

aco: ignore exec and literals when mitigating VALUMaskWriteHazard

Browse source 
LLVM ignores exec and literals don't seem to work in some cases.

fossil-db (navi31):
Totals from 2676 (3.37% of 79395) affected shaders:
Instrs: 10638979 -> 10646019 (+0.07%); split: -0.00%, +0.07%
CodeSize: 55929640 -> 55959416 (+0.05%); split: -0.00%, +0.06%
Latency: 107707408 -> 107712893 (+0.01%); split: -0.00%, +0.01%
InvThroughput: 18119843 -> 18120442 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Backport-to: 24.1
Backport-to: 24.2
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30818>
(cherry picked from commit ee648326d9)
This commit is contained in:
Rhys Perry 2024-08-22 15:37:20 +01:00 • committed by Eric Engestrom
parent cbee9e7a88
commit e0e7bfadee
3 changed files with 5 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.pick_status.json
View file

@ -1094,7 +1094,7 @@
"description": "aco: ignore exec and literals when mitigating VALUMaskWriteHazard", "description": "aco: ignore exec and literals when mitigating VALUMaskWriteHazard",
"nominated": false, "nominated": false,
"nomination_type": 3, "nomination_type": 3,
"resolution": 4, "resolution": 1,
"main_sha": null, "main_sha": null,
"because_sha": null, "because_sha": null,
"notes": null "notes": null

3
src/amd/compiler/README-ISA.md
View file

@ -375,4 +375,5 @@ Triggered by:
SALU writing then reading a SGPR that was previously used as a lane mask for a VALU. SALU writing then reading a SGPR that was previously used as a lane mask for a VALU.
Mitigated by: Mitigated by:
A VALU instruction reading a SGPR or with literal, or a sa_sdst=0 wait: `s_waitcnt_depctr 0xfffe` A VALU instruction reading a non-exec SGPR before the SALU write, or a sa_sdst=0 wait:
`s_waitcnt_depctr 0xfffe`

3
src/amd/compiler/aco_insert_NOPs.cpp
View file

@ -1498,7 +1498,8 @@ handle_instruction_gfx11(State& state, NOP_ctx_gfx11& ctx, aco_ptr<Instruction>&
if (state.program->wave_size == 64) { if (state.program->wave_size == 64) {
for (Operand& op : instr->operands) { for (Operand& op : instr->operands) {
if (op.isLiteral() || (!op.isConstant() && op.physReg().reg() < 128)) /* This should ignore exec reads */
if (!op.isConstant() && op.physReg().reg() < 126)
ctx.sgpr_read_by_valu_as_lanemask.reset(); ctx.sgpr_read_by_valu_as_lanemask.reset();
} }
switch (instr->opcode) { switch (instr->opcode) {