Skip to content

Conversation

@AD2605
Copy link
Contributor

@AD2605 AD2605 commented Apr 3, 2025

The CPY operation tests occasionally fail on both nvptx and intel targets of the SYCL backend, which stem from using lesser precise instructions. Setting the environment SYCL_PROGRAM_COMPILE_OPTION to -cl-fp32-correctly-rounded-divide-sqrt resolves this issue. On the nvptx backends, passing -fno-fast-math resolves the same.

This PR adds the environment variables, and conveys the same via the SYCL.md file.

@AD2605 AD2605 requested a review from ggerganov as a code owner April 3, 2025 11:43
@github-actions github-actions bot added documentation Improvements or additions to documentation devops improvements to build systems and github actions SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels Apr 3, 2025
@ggerganov ggerganov merged commit 2004644 into ggml-org:master Apr 3, 2025
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

devops improvements to build systems and github actions documentation Improvements or additions to documentation SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants