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

Improve viewcopy benchmark #842

Merged
merged 6 commits into from
Feb 2, 2024

Conversation

bernhardmgruber
Copy link
Member

@bernhardmgruber bernhardmgruber commented Feb 2, 2024

  • Simplify copy implementation
  • Add a fastpath copy for aligned AoSoA
  • Skip single blob SoA in viewcopy
  • Consistenly use mp_for_each_inline inside LLAMA
  • Make mpForEachInline public and more like Mp11 version
  • Parallelize init and hash in viewcopy

Copy link

codecov bot commented Feb 2, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (020a802) 98.73% compared to head (fe83bdf) 98.73%.

Additional details and impacted files
@@             Coverage Diff             @@
##           develop     #842      +/-   ##
===========================================
- Coverage    98.73%   98.73%   -0.01%     
===========================================
  Files           70       70              
  Lines         6902     6897       -5     
===========================================
- Hits          6815     6810       -5     
  Misses          87       87              

* Rename the function to mp_for_each_inline
* Take list as template parameter only
* Hardcode readOpt heuristic
* Drop readOpt parameter from aosoaCommonBlockCopy interface
* Remove aosoaCommonBlockCopy runs from viewcopy
@bernhardmgruber bernhardmgruber merged commit 942680d into alpaka-group:develop Feb 2, 2024
31 checks passed
@bernhardmgruber bernhardmgruber deleted the viewcopy_base branch February 2, 2024 20:22
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.

1 participant