archive/blender-archive
Archived
1
1
Fork 0
Code Pull Requests Packages Activity

Cycles: remove SSE3 and AVX kernel optimization levels

Browse Source 
While keeping SSE2, SSE4.1 and AVX2. This does not affect hardware support, it
only slightly reduces performance for some older CPUs.

To reduce maintenance cost and improve compile times.

Differential Revision: https://developer.blender.org/D16978
This commit is contained in:
Brecht Van Lommel
2023-01-11 16:16:21 +01:00
parent debd912bef
commit a84a8a528d
16 changed files with 5 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
intern/cycles/blender/python.cpp
View File

@@ -63,9 +63,7 @@ static void debug_flags_sync_from_scene(BL::Scene b_scene)
PointerRNA cscene = RNA_pointer_get(&b_scene.ptr, "cycles");
/* Synchronize CPU flags. */
flags.cpu.avx2 = get_boolean(cscene, "debug_use_cpu_avx2");
flags.cpu.avx = get_boolean(cscene, "debug_use_cpu_avx");
flags.cpu.sse41 = get_boolean(cscene, "debug_use_cpu_sse41");
flags.cpu.sse3 = get_boolean(cscene, "debug_use_cpu_sse3");
flags.cpu.sse2 = get_boolean(cscene, "debug_use_cpu_sse2");
flags.cpu.bvh_layout = (BVHLayout)get_enum(cscene, "debug_bvh_layout");
/* Synchronize CUDA flags. */