Skip to content

Conversation

@wenduwan
Copy link
Contributor

Fix a couple minor typos to make compiler happy

@wenduwan
Copy link
Contributor Author

Running AWS CI

@wenduwan
Copy link
Contributor Author

Had to made a couple more adjustments. Requesting review from @devreal

@wenduwan wenduwan requested a review from devreal June 13, 2024 15:40
Comment on lines 501 to 502
result = cuMemcpyAsync((CUdeviceptr) dest, (CUdeviceptr) src, size,
GET_STREAM(&opal_accelerator_cuda_memcpy_stream.base));
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@devreal Does this change do what you intended it for?

Copy link
Member

@edgargabriel edgargabriel Jun 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why do you need the GET_STREAM macro in this particular scenario? I think you can just use the opal_accelerator_cuda_memcpy_stream here, there is no ambiguity with the default stream (which is what the GET_STREAM macro was designed to do), isn't it?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@edgargabriel I think you are right. Updated the PR.

Fix a couple minor typos to make compiler happy

Signed-off-by: Wenduo Wang <[email protected]>
Copy link
Member

@edgargabriel edgargabriel left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@wenduwan
Copy link
Contributor Author

Merging the change for now. This is currently blocking CI on main branch.

@wenduwan wenduwan merged commit 55c0bda into open-mpi:main Jun 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants