blender/intern/cycles
Michael Jones 5f61eca7af Cycles: Exploit non-uniform threadgroup sizes on Metal
This patch replaces `dispatchThreadgroups` with `dispatchThreads` which takes care of non-uniform threadgroup bounds. This allows us to remove the bounds guards in the integrator kernel entry points.

Pull Request: https://projects.blender.org/blender/blender/pulls/106217
2023-03-29 21:46:11 +02:00
..
app Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
blender Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
bvh Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
cmake Revert release branch only commit after merge 2023-02-20 11:51:16 +01:00
device Cycles: Exploit non-uniform threadgroup sizes on Metal 2023-03-29 21:46:11 +02:00
doc Cleanup: cmake formatting 2022-12-17 13:33:27 +11:00
graph Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
hydra Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
integrator Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
kernel Cycles: Exploit non-uniform threadgroup sizes on Metal 2023-03-29 21:46:11 +02:00
scene Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
session Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
subd Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
test Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
util Clang-Format: Allow empty functions to be single-line 2023-03-29 16:50:54 +02:00
CMakeLists.txt Cycles: remove SSE3 and AVX kernel optimization levels 2023-01-16 17:53:36 +01:00