diff options
| author | Daniel Schürmann <daniel@schuermann.dev> | 2020-08-13 10:13:49 +0200 |
|---|---|---|
| committer | Daniel Schürmann <daniel@schuermann.dev> | 2020-12-22 15:08:40 +0100 |
| commit | 0287ebeef3bfcd12fce665d9f92a6e90d8c8a9ac (patch) | |
| tree | 3b4bb8e0f7fced1f2de0183eccde576fc08e4ffa | |
| parent | 3f14140f484b4af5c25ef9b23b7f23def4a32ed7 (diff) | |
aco: fix def-use distance calculation when scheduling.
This change also increases the VMEM_MAX_MOVES
to mitigate some of the scheduling changes.
Totals from 34301 (24.61% of 139391) affected shaders:
SGPRs: 2515440 -> 2552304 (+1.47%); split: -1.25%, +2.71%
VGPRs: 1786676 -> 1794724 (+0.45%); split: -0.31%, +0.76%
CodeSize: 151079856 -> 151209828 (+0.09%); split: -0.06%, +0.15%
MaxWaves: 392454 -> 388966 (-0.89%); split: +0.39%, -1.28%
Instrs: 28870746 -> 28895907 (+0.09%); split: -0.09%, +0.17%
Cycles: 960450680 -> 961315796 (+0.09%); split: -0.09%, +0.18%
VMEM: 19027987 -> 19796223 (+4.04%); split: +7.49%, -3.45%
SMEM: 2434691 -> 2394829 (-1.64%); split: +2.80%, -4.43%
VClause: 551776 -> 543051 (-1.58%); split: -1.73%, +0.15%
SClause: 1230147 -> 1227637 (-0.20%); split: -1.40%, +1.20%
Copies: 1957640 -> 1963617 (+0.31%); split: -1.11%, +1.41%
Branches: 611747 -> 612504 (+0.12%); split: -0.11%, +0.23%
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7903>
| -rw-r--r-- | src/amd/compiler/aco_scheduler.cpp | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/src/amd/compiler/aco_scheduler.cpp b/src/amd/compiler/aco_scheduler.cpp index d7e7f1edabd..18b28d4499a 100644 --- a/src/amd/compiler/aco_scheduler.cpp +++ b/src/amd/compiler/aco_scheduler.cpp @@ -33,7 +33,7 @@ #define VMEM_WINDOW_SIZE (1024 - ctx.num_waves * 64) #define POS_EXP_WINDOW_SIZE 512 #define SMEM_MAX_MOVES (64 - ctx.num_waves * 4) -#define VMEM_MAX_MOVES (128 - ctx.num_waves * 8) +#define VMEM_MAX_MOVES (256 - ctx.num_waves * 16) /* creating clauses decreases def-use distances, so make it less aggressive the lower num_waves is */ #define VMEM_CLAUSE_MAX_GRAB_DIST ((ctx.num_waves - 1) * 8) #define POS_EXP_MAX_MOVES 512 @@ -733,7 +733,8 @@ void schedule_VMEM(sched_ctx& ctx, Block* block, } if (part_of_clause) add_to_hazard_query(&indep_hq, candidate_ptr); - k++; + else + k++; if (candidate_idx < ctx.last_SMEM_dep_idx) ctx.last_SMEM_stall++; } @@ -782,6 +783,8 @@ void schedule_VMEM(sched_ctx& ctx, Block* block, if (is_dependency || !found_dependency) { if (found_dependency) add_to_hazard_query(&indep_hq, candidate.get()); + else + k++; ctx.mv.upwards_skip(); continue; } |