Skip to content

xe: sdpa: fix register overflow warning in prefetch functions #3164

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

umar456
Copy link
Contributor

@umar456 umar456 commented Apr 24, 2025

Description

The micro_sdpa kernel was throwing an overflow warning for when the
PREFETCH_REMAINDER was set to zero. This was caused because the pointer offset
calculation was being done within the function call. Moving the offset
calculation outside of the call fixes the register overflow warning.

Fixes: https://jira.devtools.intel.com/browse/MFDNN-13443

@umar456 umar456 requested a review from a team as a code owner April 24, 2025 22:51
@github-actions github-actions bot added the platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel label Apr 24, 2025
@umar456 umar456 force-pushed the uarshad/sdpa_reg_overflow_fix branch from d65268e to 110c21d Compare April 25, 2025 21:40
umar456 added 2 commits April 25, 2025 14:41
The micro_sdpa kernel was throwing an overflow warning for when the
PREFETCH_REMAINDER was set to zero. This was caused because the pointer offset
calculation was being done within the function call. Moving the offset
calculation outside of the call fixes the register overflow warning.
@umar456 umar456 force-pushed the uarshad/sdpa_reg_overflow_fix branch from 110c21d to 2c16d79 Compare April 25, 2025 21:42
@umar456 umar456 requested a review from a team as a code owner April 25, 2025 22:10
@github-actions github-actions bot added the component:tests Codeowner: @oneapi-src/onednn-arch label Apr 25, 2025
@umar456
Copy link
Contributor Author

umar456 commented Apr 25, 2025

make test
disable test_device_cpu
disable build_cpu_runtime_omp
disable build_cpu_runtime_sycl
disable build_cpu_runtime_tbb
disable benchdnn_all
enable benchdnn_graph
enable test_device_gpu
enable arch_gpu_xe-hpc
enable arch_gpu_xe-hpg-atsm
enable arch_gpu_xe-hpg-dg2
enable arch_gpu_xe-lp
enable arch_gpu_xe-lpg
enable arch_gpu_xe-lpg+
enable arch_gpu_xe2-hpg-bmg
enable arch_gpu_xe2-lpg

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants