KEMBAR78
Bug fixes for multi-GPU statevector simulator by 1tnguyen · Pull Request #2313 · NVIDIA/cuda-quantum · GitHub
Skip to content

Conversation

@1tnguyen
Copy link
Collaborator

Description

Changes:

  • Fixed integer overflow when converting CUDAQ_MAX_GPU_MEMORY_GB to bytes.

  • Fixed issues with large CUDAQ_MAX_CPU_MEMORY_GB setting: always cap it based on actual memory availability.

  • Fixed an issue with setting validation: some settings that allow zero was wrongly rejected.

See cuquantum-mgpu MR!30

Changes:

- Fixed integer overflow when converting CUDAQ_MAX_GPU_MEMORY_GB to bytes.

- Fixed issues with large CUDAQ_MAX_CPU_MEMORY_GB setting: always cap it
  based on actual memory availability.

- Fixed an issue with setting validation: some settings that allow zero
  was wrongly rejected.

Signed-off-by: Thien Nguyen <thiennguyen@nvidia.com>
@bmhowe23 bmhowe23 merged commit 156b53b into NVIDIA:main Oct 23, 2024
132 checks passed
@bettinaheim bettinaheim added the bug fix To be listed under Bug Fixes in the release notes label Nov 19, 2024
@bettinaheim bettinaheim added this to the release 0.9.0 milestone Nov 19, 2024
@bettinaheim bettinaheim changed the title Update mgpu commit sha Bug fixes for multi-GPU statevector simulator Nov 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug fix To be listed under Bug Fixes in the release notes

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants