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

radv: Skip and for node_to_addr with bvh_base.

Browse Source 
Cause the bvh base is always 64 byte aligned.

Totals from 7 (0.01% of 134913) affected shaders:

CodeSize: 209216 -> 209076 (-0.07%)
Instrs: 38402 -> 38374 (-0.07%)
Latency: 804537 -> 803899 (-0.08%)
InvThroughput: 165663 -> 165530 (-0.08%)
Copies: 4919 -> 4912 (-0.14%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19706>
This commit is contained in:
Bas Nieuwenhuizen
2022-11-12 02:13:17 +01:00
committed by Marge Bot
parent 0a26975840
commit 3884210902
2 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/amd/vulkan/radv_rt_common.h
View File

@@ -47,8 +47,6 @@ nir_ssa_def *intersect_ray_amd_software_tri(struct radv_device *device, nir_buil
nir_ssa_def *build_addr_to_node(nir_builder *b, nir_ssa_def *addr);
nir_ssa_def *build_node_to_addr(struct radv_device *device, nir_builder *b, nir_ssa_def *node);
nir_ssa_def *nir_build_vec3_mat_mult(nir_builder *b, nir_ssa_def *vec, nir_ssa_def *matrix[],
bool translation);