Skip to content

[AsyncAlloc][CUDA] Don't set pool maxSize if CUDA version < 12.2 #17733

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

Merged
merged 4 commits into from
Mar 31, 2025

Conversation

Seanst98
Copy link
Contributor

CUDA did not introduce the maxSize property to CUmemPoolProps until version 12.2. In the case where the user has set a maxSize > 0, and their CUDA version is < 12.2, return an error.

This commit fixes the compilation error associated with setting this property in older CUDA versions.

Also fix incorrect error reporting when creating a memory pool.

CUDA did not introduce the maxSize property to CUmemPoolProps until
version 12.2. In the case where the user has set a maxSize > 0, and
their CUDA version is < 12.2, return an error.

This commit fixes the compilation error associated with setting this
property in older CUDA versions.

Also fix incorrect error reporting when creating a memory pool.
@Seanst98
Copy link
Contributor Author

@intel/llvm-gatekeepers can we merge this please. Thanks!

@sarnex sarnex merged commit c0bff06 into intel:sycl Mar 31, 2025
42 of 43 checks passed
@Seanst98 Seanst98 deleted the sean/async-alloc-maxSize-ifdef branch April 4, 2025 16:39
KornevNikita pushed a commit that referenced this pull request May 28, 2025
)

CUDA did not introduce the maxSize property to CUmemPoolProps until
version 12.2. In the case where the user has set a maxSize > 0, and
their CUDA version is < 12.2, return an error.

This commit fixes the compilation error associated with setting this
property in older CUDA versions.

Also fix incorrect error reporting when creating a memory pool.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants