OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nir: add amd shared append/consume

Browse Source 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31075>
This commit is contained in:
Georg Lehmann
2024-09-07 14:22:11 +02:00
committed by Marge Bot
parent 213f5e9152
commit e0bcab953d
5 changed files with 13 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/compiler/nir/nir_divergence_analysis.c
View File

@@ -133,6 +133,8 @@ visit_intrinsic(nir_intrinsic_instr *instr, struct divergence_state *state)
case nir_intrinsic_first_invocation:
case nir_intrinsic_last_invocation:
case nir_intrinsic_load_subgroup_id:
case nir_intrinsic_shared_append_amd:
case nir_intrinsic_shared_consume_amd:
/* VS/TES/GS invocations of the same primitive can be in different
* subgroups, so subgroup ops are always divergent between vertices of
* the same primitive.