Skip to content
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.

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

Implement cuda::mr::cuda_memory_resource #1578

Merged
merged 9 commits into from
Apr 12, 2024

Conversation

miscco
Copy link
Collaborator

@miscco miscco commented Apr 2, 2024

Fixes #1512

I managed to close #1513 because I did not change the target branch before merging

Stacked PRs are "fun"

@miscco miscco requested review from a team as code owners April 2, 2024 18:36
@miscco miscco requested review from griwes, elstehle and harrism April 2, 2024 18:36
@miscco miscco added feature request New feature or request. libcu++ For all items related to libcu++ labels Apr 2, 2024
@harrism
Copy link
Contributor

harrism commented Apr 2, 2024

So my review is gone. Let's avoid "stacked PRs". Losing reviewer history is a big loss in productivity.

@miscco
Copy link
Collaborator Author

miscco commented Apr 2, 2024

So my review is gone. Let's avoid "stacked PRs". Losing reviewer history is a big loss in productivity.

It was more my bad. I forgot to change the target branch before I merged the first PR

@miscco
Copy link
Collaborator Author

miscco commented Apr 3, 2024

Also the review is still there #1513

@miscco miscco force-pushed the cuda_memory_resource branch from 2b30982 to c701e83 Compare April 3, 2024 15:22
@harrism
Copy link
Contributor

harrism commented Apr 4, 2024

Also the review is still there #1513

Please respond to this unanswered comment: #1513 (comment)

@miscco
Copy link
Collaborator Author

miscco commented Apr 4, 2024

Also the review is still there #1513

Please respond to this unanswered comment: #1513 (comment)

Addressed the comment

@miscco miscco requested a review from a team as a code owner April 5, 2024 07:08
@miscco miscco requested a review from wmaxey April 5, 2024 07:08
@miscco miscco force-pushed the cuda_memory_resource branch 6 times, most recently from 5df98a1 to 7c86598 Compare April 5, 2024 20:40
* @throw cuda::cuda_error of the returned error code
* @return Pointer to the newly allocated memory
*/
void* allocate(const size_t __bytes, const size_t __alignment = default_cuda_malloc_alignment) const
Copy link
Collaborator

Choose a reason for hiding this comment

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

question: Should allocate in all our resources always be nodiscard?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Yes

@miscco miscco force-pushed the cuda_memory_resource branch from b367f31 to 83a2dd5 Compare April 11, 2024 09:26
@miscco miscco requested a review from a team as a code owner April 11, 2024 09:26
@miscco miscco enabled auto-merge (squash) April 12, 2024 06:19
@miscco miscco merged commit 0739bc6 into NVIDIA:main Apr 12, 2024
586 checks passed
@miscco miscco deleted the cuda_memory_resource branch June 12, 2024 09:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature request New feature or request. libcu++ For all items related to libcu++
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

[FEA]: Implement a memory_resource using cudaMalloc and cudaFree
4 participants