diff options
| author | Rhys Perry <pendingchaos02@gmail.com> | 2022-02-23 17:29:25 +0000 |
|---|---|---|
| committer | Marge Bot <emma+marge@anholt.net> | 2022-03-08 12:49:59 +0000 |
| commit | d068eb53e84ca1e44ad96c31dab63476880b3c72 (patch) | |
| tree | b8c933592201ca9e9fab99d477715da46d619517 /src/amd/compiler/aco_insert_exec_mask.cpp | |
| parent | 42a5be975adc51d1029f25719b979bf2b3bae8a9 (diff) | |
| download | mesa-d068eb53e84ca1e44ad96c31dab63476880b3c72.tar.gz | |
aco/insert_exec_mask: optimize top-level transition to exact before demote
fossil-db (Sienna Cichlid):
Totals from 5767 (3.55% of 162293) affected shaders:
Instrs: 3264949 -> 3257527 (-0.23%); split: -0.23%, +0.00%
CodeSize: 17835692 -> 17806004 (-0.17%); split: -0.17%, +0.00%
Latency: 45990060 -> 45987924 (-0.00%); split: -0.00%, +0.00%
InvThroughput: 7643850 -> 7643835 (-0.00%); split: -0.00%, +0.00%
Copies: 193641 -> 186219 (-3.83%); split: -3.84%, +0.01%
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/15244>
Diffstat (limited to 'src/amd/compiler/aco_insert_exec_mask.cpp')
| -rw-r--r-- | src/amd/compiler/aco_insert_exec_mask.cpp | 13 |
1 files changed, 10 insertions, 3 deletions
diff --git a/src/amd/compiler/aco_insert_exec_mask.cpp b/src/amd/compiler/aco_insert_exec_mask.cpp index 04928c3c722..e1dd3929910 100644 --- a/src/amd/compiler/aco_insert_exec_mask.cpp +++ b/src/amd/compiler/aco_insert_exec_mask.cpp @@ -585,8 +585,7 @@ process_instructions(exec_ctx& ctx, Block* block, std::vector<aco_ptr<Instructio } } else if (instr->opcode == aco_opcode::p_demote_to_helper) { /* turn demote into discard_if with only exact masks */ - assert((ctx.info[block->index].exec[0].second & (mask_type_exact | mask_type_global)) == - (mask_type_exact | mask_type_global)); + assert(ctx.info[block->index].exec[0].second == (mask_type_exact | mask_type_global)); int num; Temp cond, exit_cond; @@ -605,7 +604,15 @@ process_instructions(exec_ctx& ctx, Block* block, std::vector<aco_ptr<Instructio } } else { /* demote_if: transition to exact */ - transition_to_Exact(ctx, bld, block->index); + if (block->kind & block_kind_top_level && ctx.info[block->index].exec.size() == 2 && + ctx.info[block->index].exec.back().second & mask_type_global) { + /* We don't need to actually copy anything into exact, since the s_andn2 + * instructions later will do that. + */ + ctx.info[block->index].exec.pop_back(); + } else { + transition_to_Exact(ctx, bld, block->index); + } assert(instr->operands[0].isTemp()); cond = instr->operands[0].getTemp(); num = ctx.info[block->index].exec.size() - 1; |