diff options
| author | Takoroka <137927095+Takoroka@users.noreply.github.com> | 2026-10-29 08:04:42 -0400 |
|---|---|---|
| committer | Takoroka <137927095+Takoroka@users.noreply.github.com> | 2026-10-29 20:49:47 -0400 |
| commit | 6cefcce15f821cd0e65459173cf217bb7e622f43 (patch) | |
| tree | 293629f633fed276a5fee9d658d2ab0bfa807da5 /src/video_core/gpu_thread.cpp | |
| parent | 15eef40dd12c2b751d5b1cac57dd8f3602e2d133 (diff) | |
kepler_compute: store plain native register writes directly
Most native compute register writes (QMD fields its macros replay for thousands of
dispatches a second) only store the value; they went through ProcessNativeMethod's
macro, QMD, upload and semaphore checks. CallMethod now stores them through a table of
plain methods. ProcessNativeMethod's own time 2.2% -> 1.6% of the GPU thread.
Diffstat (limited to 'src/video_core/gpu_thread.cpp')
0 files changed, 0 insertions, 0 deletions