Add GPU architecture BLACKWELL #488
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@koarakawaii Do you think we need to install cuda13 and nvidia hpc to spock:/software? So that the config no longer need to depend to your own file. |
Contributor
Author
|
@xuanweishan : I think that will be great. I guess we will need it in the future anyway~ |
|
It seems good to me.
|
Contributor
Author
|
@xuanweishan : conflicts have been solved~ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
cudaDevicePropare deprecated inCUDA 13.0; I did not check all of them, but only modified those affecting the compilation. See https://docs.nvidia.com/cuda/cuda-runtime-api/structcudaDeviceProp.html#structcudaDeviceProp for details.cudaDeviceGetAttributeAPI; but again, I did not check whether it covers all the properties we queried forcudaDevicePropspock_intel_RTX5090.configfor RTX5090 onspock26, which uses privateNVIDIA HPC SDKmodules instead of publicCUDAon the log-in node. The path should be directing to publicCUDA 13.0when available, if we want to install it.CUDA 12.1also works for current driver version580.95.05, but I am not sure we want to fall back toCUDA 12.1if a more advanced version has been released.