diff options
| author | Marek Olšák <marek.olsak@amd.com> | 2023-02-25 17:52:24 -0500 |
|---|---|---|
| committer | Marge Bot <emma+marge@anholt.net> | 2023-03-08 07:29:09 +0000 |
| commit | 461ccb00e15a234dcca8c035e1303260a42a1393 (patch) | |
| tree | 6c468f9460152072db3ae3145438fa081c7c49f5 /src/gallium/drivers/radeonsi/si_pipe.h | |
| parent | 43fd5528728ec8c04267749debfa1e66f84316d6 (diff) | |
radeonsi: increase NGG workgroup size to 256 for VS/TES with streamout and GS
NGG streamout performance is limited by the workgroup size, so make it as
large as possible.
Since this uses si_get_max_workgroup_size() to set the NGG workgroup size,
the side effect is that all GS is also getting an increase to 256, which
is OK.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21403>
Diffstat (limited to 'src/gallium/drivers/radeonsi/si_pipe.h')
| -rw-r--r-- | src/gallium/drivers/radeonsi/si_pipe.h | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/src/gallium/drivers/radeonsi/si_pipe.h b/src/gallium/drivers/radeonsi/si_pipe.h index 368e3abc795..3c3ad6af7cd 100644 --- a/src/gallium/drivers/radeonsi/si_pipe.h +++ b/src/gallium/drivers/radeonsi/si_pipe.h @@ -694,8 +694,6 @@ struct si_screen { * We want to minimize the impact on multithreaded Mesa. */ struct ac_llvm_compiler compiler_lowp[10]; - unsigned ngg_subgroup_size; - struct util_idalloc_mt buffer_ids; struct util_vertex_state_cache vertex_state_cache; |