Cover occupancy calculator APIs

Open leofang opened this issue 10 months ago • 2 comments

We have them in the bindings:

driver: https://nvidia.github.io/cuda-python/cuda-bindings/latest/module/driver.html#occupancy
runtime: https://nvidia.github.io/cuda-python/cuda-bindings/latest/module/runtime.html#occupancy

and this issue is about cuda.core exposure.

Mar 10 '25 03:03 leofang

Based on my learning from the CUTLASS team, we should be able to support this API easily (by passing Kernel and LaunchConfig): cuOccupancyMaxActiveClusters.

Mar 14 '25 03:03 leofang

Greate if it's possible that the process could be simplified with the help from cuda-python!

Mar 25 '25 01:03 dongxiao92