diff options
| author | Marek Olšák <[email protected]> | 2018-09-01 03:10:27 -0400 |
|---|---|---|
| committer | Marek Olšák <[email protected]> | 2018-09-04 14:31:56 -0400 |
| commit | 28e542dcdbb8a1187007b588c2b8f91f92870a24 (patch) | |
| tree | 190cf1ff850df640ef48557e227b83826a2014ed /src | |
| parent | ebd5806e0fce2bc351255dc50bcb9afa607f35d2 (diff) | |
gallium/u_threaded: increase batch size to increase performance
This reduces mutex overhead.
radeonsi: +4.4% performance with piglit/drawoverhead, DrawElements, Ryzen X1700
iris_dri.so: +14% with piglit/drawoverhead, DrawArrays, i7 7700HQ.
Acked-by: Kenneth Graunke <[email protected]>
Diffstat (limited to 'src')
| -rw-r--r-- | src/gallium/auxiliary/util/u_threaded_context.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/gallium/auxiliary/util/u_threaded_context.h b/src/gallium/auxiliary/util/u_threaded_context.h index 53c5a7e8c4c..be6933d05a4 100644 --- a/src/gallium/auxiliary/util/u_threaded_context.h +++ b/src/gallium/auxiliary/util/u_threaded_context.h @@ -220,7 +220,7 @@ struct tc_unflushed_batch_token; * The idea is to have batches as small as possible but large enough so that * the queuing and mutex overhead is negligible. */ -#define TC_CALLS_PER_BATCH 192 +#define TC_CALLS_PER_BATCH 768 /* Threshold for when to use the queue or sync. */ #define TC_MAX_STRING_MARKER_BYTES 512 |