New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Workflow] Update workflow to use the stable version of pytorch #145

Merged

yaoyaoding merged 1 commit into hidet-org:main from yaoyaoding:update-workflow

Mar 24, 2023

Member

yaoyaoding commented Mar 24, 2023

No description provided.


          update workflow to use the stable version of pytorch

ae551a8

yaoyaoding merged commit 5b3ab00 into hidet-org:main

2 checks passed

yaoyaoding deleted the update-workflow branch

March 24, 2023 06:36

KTong821 added a commit to KTong821/hidet that referenced this pull request


          [IR] [Primitives] Add thread cluster on sm_90 (hidet-org#145)

1444c20

Allow access to cluster attributes inside Hidet kernels. Launch kernels
with distributed shared memory.

See docs:


https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#distributed-shared-memory

https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#thread-block-clusters

API:
https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#cluster-group-cg

Towards supporting hidet-org#102 by adding cluster rank primitive in Hidet.

See `test_cluster.py` for example usage. To run test on Hopper machines
use `pytest --hopper`

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment