diff options
author | Rhys Perry <pendingchaos02@gmail.com> | 2021-01-27 14:04:10 +0000 |
---|---|---|
committer | Dylan Baker <dylan.c.baker@intel.com> | 2021-02-10 15:11:02 -0800 |
commit | bb2aea8ded661a0481e5845689870a5cddb07937 (patch) | |
tree | 939bdf78b3fdf793ae60eb033911ea21e30c5de2 | |
parent | 00b62f387c7977d9fcbc8222f2ca83d47041d4f5 (diff) |
aco: always set exec_live=false
Register demand calculation for exec masks doesn't always match
get_live_changes() and get_temp_registers(). For now, just set
exec_live=false.
fossil-db (GFX10.3):
Totals from 108230 (77.64% of 139391) affected shaders:
SGPRs: 5759658 -> 5756818 (-0.05%); split: -0.08%, +0.03%
VGPRs: 4061104 -> 4061248 (+0.00%); split: -0.00%, +0.01%
SpillSGPRs: 14114 -> 15198 (+7.68%); split: -0.10%, +7.78%
CodeSize: 266548396 -> 266603288 (+0.02%); split: -0.01%, +0.03%
MaxWaves: 1390885 -> 1390855 (-0.00%); split: +0.00%, -0.00%
Instrs: 50983353 -> 50992972 (+0.02%); split: -0.02%, +0.04%
Cycles: 1733042048 -> 1735443264 (+0.14%); split: -0.02%, +0.16%
VMEM: 41933625 -> 41914722 (-0.05%); split: +0.04%, -0.09%
SMEM: 7197675 -> 7197789 (+0.00%); split: +0.16%, -0.16%
VClause: 1050885 -> 1050978 (+0.01%); split: -0.02%, +0.03%
SClause: 2074913 -> 2071844 (-0.15%); split: -0.23%, +0.08%
Copies: 3181464 -> 3188125 (+0.21%); split: -0.38%, +0.59%
Branches: 1127526 -> 1127716 (+0.02%); split: -0.10%, +0.12%
PreSGPRs: 3376687 -> 3586076 (+6.20%); split: -0.00%, +6.20%
PreVGPRs: 3339740 -> 3339811 (+0.00%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8807>
(cherry picked from commit d1f93261b17d73eceb16b7081000b5bb8f6608f2)
-rw-r--r-- | .pick_status.json | 2 | ||||
-rw-r--r-- | src/amd/compiler/aco_live_var_analysis.cpp | 21 |
2 files changed, 2 insertions, 21 deletions
diff --git a/.pick_status.json b/.pick_status.json index fd4af7035a8..45f0153d665 100644 --- a/.pick_status.json +++ b/.pick_status.json @@ -2227,7 +2227,7 @@ "description": "aco: always set exec_live=false", "nominated": true, "nomination_type": 0, - "resolution": 0, + "resolution": 1, "master_sha": null, "because_sha": null }, diff --git a/src/amd/compiler/aco_live_var_analysis.cpp b/src/amd/compiler/aco_live_var_analysis.cpp index bc713a1a188..44f47cab118 100644 --- a/src/amd/compiler/aco_live_var_analysis.cpp +++ b/src/amd/compiler/aco_live_var_analysis.cpp @@ -91,13 +91,6 @@ void process_live_temps_per_block(Program *program, live& lives, Block* block, block->register_demand = RegisterDemand(); IDSet live = lives.live_out[block->index]; - /* add the live_out_exec to live */ - bool exec_live = false; - if (block->live_out_exec != Temp()) { - live.insert(block->live_out_exec.id()); - exec_live = true; - } - /* initialize register demand */ for (unsigned t : live) new_demand += Temp(t, program->temp_rc[t]); @@ -110,10 +103,7 @@ void process_live_temps_per_block(Program *program, live& lives, Block* block, if (is_phi(insn)) break; - /* substract the 1 or 2 sgprs from exec */ - if (exec_live) - assert(new_demand.sgpr >= (int16_t) program->lane_mask.size()); - register_demand[idx] = RegisterDemand(new_demand.vgpr, new_demand.sgpr - (exec_live ? program->lane_mask.size() : 0)); + register_demand[idx] = RegisterDemand(new_demand.vgpr, new_demand.sgpr); /* KILL */ for (Definition& definition : insn->definitions) { @@ -133,9 +123,6 @@ void process_live_temps_per_block(Program *program, live& lives, Block* block, register_demand[idx] += temp; definition.setKill(true); } - - if (definition.isFixed() && definition.physReg() == exec) - exec_live = false; } /* GEN */ @@ -169,9 +156,6 @@ void process_live_temps_per_block(Program *program, live& lives, Block* block, register_demand[idx] += temp; new_demand += temp; } - - if (operand.isFixed() && operand.physReg() == exec) - exec_live = true; } } @@ -179,9 +163,6 @@ void process_live_temps_per_block(Program *program, live& lives, Block* block, } /* update block's register demand for a last time */ - if (exec_live) - assert(new_demand.sgpr >= (int16_t) program->lane_mask.size()); - new_demand.sgpr -= exec_live ? program->lane_mask.size() : 0; block->register_demand.update(new_demand); /* handle phi definitions */ |