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.

Sign up for GitHub

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

Jump to bottom

Implement parallel_scan with ThreadVectorRange and Reducer #3861

Merged
merged 8 commits into from
Apr 8, 2021
Merged

Implement parallel_scan with ThreadVectorRange and Reducer #3861

merged 8 commits into from
Apr 8, 2021

Conversation

masterleinad
Copy link
Contributor

A rebased version of #3602 also including a SYCL implementation and adding the test.

@masterleinad masterleinad added Enhancement Improve existing capability; will potentially require voting and removed [WIP] labels Mar 22, 2021
@masterleinad
Copy link
Contributor Author

@Char-Aznable Can you please check if this works for you?

@masterleinad masterleinad marked this pull request as ready for review March 22, 2021 18:42
@Char-Aznable
Copy link
Contributor

@masterleinad Thank you for working on this. This works great as far as the tests go.
Just curious, have you noticed any performance difference on the CUDA backend? This seems slightly bit faster than the existing develop branch's sum scan just timing some of my existing scan kernels.

@masterleinad masterleinad mentioned this pull request Mar 23, 2021
Closed
@masterleinad
Copy link
Contributor Author

No, I didn't benchmark anything but I wouldn't expect a big difference in performance between the old and the new implementation.

dalg24
dalg24 previously requested changes Mar 24, 2021
View reviewed changes
core/src/Cuda/Kokkos_Cuda_Team.hpp Show resolved Hide resolved
core/src/Cuda/Kokkos_Cuda_Team.hpp Outdated Show resolved Hide resolved
core/unit_test/TestTeamVector.hpp Outdated Show resolved Hide resolved
core/unit_test/TestTeamVector.hpp Outdated Show resolved Hide resolved
core/unit_test/TestTeamVector.hpp Outdated Show resolved Hide resolved
core/unit_test/TestTeamVector.hpp Outdated Show resolved Hide resolved
core/unit_test/TestTeamVector.hpp Outdated Show resolved Hide resolved
@dalg24 dalg24 dismissed their stale review April 7, 2021 18:13

Not blocking

@masterleinad masterleinad added the Blocks Promotion Overview issue for release-blocking bugs label Apr 7, 2021
@masterleinad masterleinad added this to the Tentative 3.4 Release milestone Apr 7, 2021
@crtrott crtrott merged commit 0e13061 into kokkos:develop Apr 8, 2021
@ndellingwood ndellingwood mentioned this pull request Apr 9, 2021
Closed
@masterleinad masterleinad deleted the vector_scan_reducer branch July 22, 2021 14:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@crtrott crtrott crtrott approved these changes

@dalg24 dalg24 Awaiting requested review from dalg24

Assignees
No one assigned
Labels
Blocks Promotion Overview issue for release-blocking bugs Enhancement Improve existing capability; will potentially require voting
Projects
None yet
Milestone
Tentative 3.4 Release
Development

Successfully merging this pull request may close these issues.

None yet
4 participants
@masterleinad @Char-Aznable @dalg24 @crtrott