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

[EXP][CMDBUF] Improve CUDA Fill op implementation #1319

Merged
merged 2 commits into from
Mar 14, 2024

Conversation

mfrancepillois
Copy link
Contributor

Adjustment of value pointer size according to pattern size.
Large patterns are now broken into 1-byte chunks, as in the regular implementation.

@mfrancepillois
Copy link
Contributor Author

Linked DPC++ PR: intel/llvm#12605

@EwanC EwanC added the ready to merge Added to PR's which are ready to merge label Feb 8, 2024
@codecov-commenter
Copy link

codecov-commenter commented Feb 13, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 12.49%. Comparing base (78ef1ca) to head (81f142c).
Report is 144 commits behind head on main.

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1319      +/-   ##
==========================================
- Coverage   14.82%   12.49%   -2.33%     
==========================================
  Files         250      239      -11     
  Lines       36220    36003     -217     
  Branches     4094     4086       -8     
==========================================
- Hits         5369     4498     -871     
- Misses      30800    31501     +701     
+ Partials       51        4      -47     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

EwanC added a commit to Bensuo/unified-runtime that referenced this pull request Feb 19, 2024
Match the CUDA change from
oneapi-src#1319
in HIP.
EwanC added a commit to Bensuo/unified-runtime that referenced this pull request Feb 19, 2024
Match the CUDA change from
oneapi-src#1319
in HIP.
@EwanC EwanC force-pushed the maxime/cuda-large-fill-pattern branch from 4861b40 to 6545b72 Compare March 11, 2024 15:40
@EwanC EwanC added the v0.9.x Include in the v0.9.x release label Mar 11, 2024
@EwanC EwanC force-pushed the maxime/cuda-large-fill-pattern branch from 6545b72 to ee408be Compare March 12, 2024 15:43
@EwanC EwanC force-pushed the maxime/cuda-large-fill-pattern branch from ee408be to 81f142c Compare March 14, 2024 14:15
EwanC added a commit to reble/llvm that referenced this pull request Mar 14, 2024
mfrancepillois and others added 2 commits March 14, 2024 16:40
Adjustment of value pointer size according to pattern size.
Large patterns are now broken into 1-byte chunks, as in the regular implementation.
@EwanC EwanC force-pushed the maxime/cuda-large-fill-pattern branch from 81f142c to ef72b3f Compare March 14, 2024 16:40
@kbenzie kbenzie merged commit bb589ca into oneapi-src:main Mar 14, 2024
50 checks passed
bader pushed a commit to intel/llvm that referenced this pull request Mar 14, 2024
Graph support in the CUDA backend for graph buffer fill nodes has been
improved in UR PR
oneapi-src/unified-runtime#1319

---------

Co-authored-by: Ewan Crawford <ewan@codeplay.com>
Co-authored-by: Kenneth Benzie (Benie) <k.benzie@codeplay.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready to merge Added to PR's which are ready to merge v0.9.x Include in the v0.9.x release
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants