Add sm_90a to enable use of accelerated wgmma and setmaxnreg instructions #913
Conversation
sm_90a adds support for accelerated wgmma and setmaxnreg instructions. https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#ptx-module-directives-target
|
Thank you, this is good to know that wgmma is now added. I think Hopper supports both sm_90 and sm_90a. Since we do not make use of wgmma or setmaxnreg for now we would not need sm_90a. I would want to not add it at the moment to keep the binary a bit smaller. I am currently having troubles with the binary size since all binaries must be smaller than 100MB for PyPi uploads. |
TimDettmers
added
low priority
|
Thanks for raising this. We'll keep this in mind and implement it once we have figured out the current cross-platform + build + distribution topics. |
|
For PyPI, you can request a quota increase for the project via https://github.com/pypi/support :) |
Nice, that would unblock us on this before we've figured out the cross-platform compilation and distribution stuff. I'll look into that today. Valuable input, thanks! |
Titus-von-Koeller
force-pushed
the
main
branch
2 times, most recently
from
9b72679 to
7800734
Compare
sm_90a adds support for accelerated wgmma and setmaxnreg instructions.
https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#ptx-module-directives-target