Replies: 1 comment 2 replies
-
We don't have anything metal-specific. I recommend using the native profiling tools available in the instruments app. You can also do somewhat crude profiling by adding the target feature "-debug", which adds synchronization to GPU API calls and causes a lot of debugging spew, including how long each kernel launch took. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi, I'm trying to test halide metal backend on apple silicon. Could you tell me the correct way to profile a python testing example using halide python binding? Is there something like nsight system for NVIDIA we can use to profile? Thanks
Beta Was this translation helpful? Give feedback.
All reactions