This repository has been archived on 2023-10-09. You can view files and clone it. You cannot open issues or pull requests or push a commit.

Michael Jones (Apple) 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: blender/blender#106217

2023-03-29 21:46:11 +02:00

..

image.h

Cycles: add NanoVDB support for Metal on Apple Silicon

2023-02-21 15:03:52 +01:00

kernel.h

Cycles: Exploit non-uniform threadgroup sizes on Metal

2023-03-29 21:46:11 +02:00

parallel_active_index.h

Cycles: Use local atomics for faster shader sorting (enabled on Metal)

2023-02-06 11:18:26 +00:00

parallel_prefix_sum.h

Cycles: use SPDX license headers

2022-02-11 17:47:34 +01:00

parallel_sorted_index.h

Cycles: Fix Metal API validation error (use uint instead of ushort)

2023-03-14 22:05:55 +01:00

work_stealing.h

Cycles: use SPDX license headers

2022-02-11 17:47:34 +01:00