Skip to content

Use the new tuning API internally for detail::reduce[_nd]::dispatch[_nd]#8826

Open
bernhardmgruber wants to merge 4 commits intoNVIDIA:mainfrom
bernhardmgruber:tune_reduce
Open

Use the new tuning API internally for detail::reduce[_nd]::dispatch[_nd]#8826
bernhardmgruber wants to merge 4 commits intoNVIDIA:mainfrom
bernhardmgruber:tune_reduce

Conversation

@bernhardmgruber
Copy link
Copy Markdown
Contributor

@bernhardmgruber bernhardmgruber commented May 5, 2026

Fixes: #7948
Fixes: #7951

@copy-pr-bot
Copy link
Copy Markdown
Contributor

copy-pr-bot Bot commented May 5, 2026

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

@github-project-automation github-project-automation Bot moved this to Todo in CCCL May 5, 2026
@cccl-authenticator-app cccl-authenticator-app Bot moved this from Todo to In Progress in CCCL May 5, 2026
@bernhardmgruber
Copy link
Copy Markdown
Contributor Author

/ok to test 4781524

@github-actions

This comment has been minimized.

@bernhardmgruber bernhardmgruber marked this pull request as ready for review May 7, 2026 07:26
@bernhardmgruber bernhardmgruber requested review from a team as code owners May 7, 2026 07:26
@cccl-authenticator-app cccl-authenticator-app Bot moved this from In Progress to In Review in CCCL May 7, 2026
@github-actions

This comment has been minimized.

@github-actions

This comment has been minimized.

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented May 8, 2026

😬 CI Workflow Results

🟥 Finished in 2h 26m: Pass: 97%/283 | Total: 9d 12h | Max: 2h 26m | Hits: 29%/731124

See results here.

Comment on lines +152 to +155
# if _CCCL_CUDA_COMPILER(NVCC, >=, 12, 1)
// some rare combinations, like nvcc 12.0 + clang-14 in C++20, or nvcc 12.0 + GCC12 fail with:
// pod_tuple.h(130): error: Internal Compiler Error (codegen): "internal error during structure layout!"
// if we pass more than two policy selectors
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The per-PR CI only founds this for nvcc 12.0 and not for nvcc 12.9. It could happen for some versions in-between, but I want to not disable too many runs and will let the nightly CI catch this.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Status: In Review

Development

Successfully merging this pull request may close these issues.

Use the new tuning API internally for detail::reduce::dispatch_nondeterministic Use the new tuning API internally for detail::reduce::dispatch

1 participant