diff options
| author | Rhys Perry <[email protected]> | 2020-02-27 19:56:22 +0000 |
|---|---|---|
| committer | Marge Bot <[email protected]> | 2020-03-05 19:37:24 +0000 |
| commit | c6e0c062daa55269661b190deaec40e9749198bc (patch) | |
| tree | 73fcf1b9822a6113c16add3191c52d793ff012fa /src/amd | |
| parent | 47b7f104a0aa3692e9fb202741406a0c6d9ac8ad (diff) | |
aco: improve control flow handling in GFX6-9 NOP pass
Fixes Detroit: Become Human hang. Also affects World of Warships.
pipeline-db (Tahiti):
Totals from affected shaders:
SGPRS: 0 -> 0 (0.00 %)
VGPRS: 0 -> 0 (0.00 %)
Spilled SGPRs: 0 -> 0 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 0 -> 0 (0.00 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 0 -> 0 (0.00 %)
pipeline-db (Polaris):
Totals from affected shaders:
SGPRS: 17168 -> 17168 (0.00 %)
VGPRS: 11296 -> 11296 (0.00 %)
Spilled SGPRs: 1870 -> 1870 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 1472628 -> 1473292 (0.05 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 628 -> 628 (0.00 %)
pipeline-db (Vega):
Totals from affected shaders:
SGPRS: 17168 -> 17168 (0.00 %)
VGPRS: 11296 -> 11296 (0.00 %)
Spilled SGPRs: 1870 -> 1870 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 1409716 -> 1410380 (0.05 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 0 -> 0 (0.00 %)
Max Waves is lower than it should be because of a null winsys bug.
Signed-off-by: Rhys Perry <[email protected]>
Reviewed-by: Daniel Schürmann <[email protected]>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4004>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4004>
Diffstat (limited to 'src/amd')
| -rw-r--r-- | src/amd/compiler/aco_insert_NOPs.cpp | 21 |
1 files changed, 13 insertions, 8 deletions
diff --git a/src/amd/compiler/aco_insert_NOPs.cpp b/src/amd/compiler/aco_insert_NOPs.cpp index 4302711ba81..75dbe852174 100644 --- a/src/amd/compiler/aco_insert_NOPs.cpp +++ b/src/amd/compiler/aco_insert_NOPs.cpp @@ -225,7 +225,16 @@ int handle_raw_hazard_internal(Program *program, Block *block, return 0; } - return 0; + int res = 0; + + /* Loops require branch instructions, which count towards the wait + * states. So even with loops this should finish unless nops_needed is some + * huge value. */ + for (unsigned lin_pred : block->linear_preds) { + res = std::max(res, handle_raw_hazard_internal<Valu, Vintrp, Salu>( + program, &program->blocks[lin_pred], nops_needed, reg, mask)); + } + return res; } template <bool Valu, bool Vintrp, bool Salu> @@ -763,14 +772,10 @@ void mitigate_hazards(Program *program) void insert_NOPs(Program* program) { - if (program->chip_class >= GFX10) { + if (program->chip_class >= GFX10) mitigate_hazards<NOP_ctx_gfx10, handle_instruction_gfx10>(program); - } else { - for (Block& block : program->blocks) { - NOP_ctx_gfx6 ctx; - handle_block<NOP_ctx_gfx6, handle_instruction_gfx6>(program, ctx, block); - } - } + else + mitigate_hazards<NOP_ctx_gfx6, handle_instruction_gfx6>(program); } } |