Implement the new tuning API for DeviceSegmentedReduce#7334
Merged
bernhardmgruber merged 11 commits intoNVIDIA:mainfrom Jan 29, 2026
Merged
Implement the new tuning API for DeviceSegmentedReduce#7334bernhardmgruber merged 11 commits intoNVIDIA:mainfrom
bernhardmgruber merged 11 commits intoNVIDIA:mainfrom
Conversation
Contributor
|
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. |
30 tasks
bernhardmgruber
force-pushed
the
tuning_segmented_reduce
branch
from
4c33932 to
074fd13
Compare
Contributor
Author
|
/ok to test 074fd13 |
Contributor
Author
|
/ok to test 5863ec6 |
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
miscco
reviewed
Jan 26, 2026
Comment on lines
108
to
110
| CUB_DETAIL_KERNEL_ATTRIBUTES __launch_bounds__(int( | ||
| PolicySelector{}(::cuda::arch_id{CUB_PTX_ARCH / 10}) | ||
| .segmented_reduce.block_threads)) void DeviceSegmentedReduceKernel(InputIteratorT d_in, |
Contributor
There was a problem hiding this comment.
That is some cursed formatting
4 tasks
bernhardmgruber
force-pushed
the
tuning_segmented_reduce
branch
from
93a5e32 to
df71698
Compare
This comment has been minimized.
This comment has been minimized.
bernhardmgruber
force-pushed
the
tuning_segmented_reduce
branch
from
df71698 to
7d2dcdc
Compare
Contributor
🥳 CI Workflow Results🟩 Finished in 5h 18m: Pass: 100%/93 | Total: 4d 07h | Max: 5h 15m | Hits: 72%/92292See results here. |
NaderAlAwar
approved these changes
Jan 29, 2026
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I started with this prompt to Cursor+codex:
Except CCCL.C, all worked, but it was not particularly clean. I would say it got 85% there. I am still positively surprised.
I added a lot of refactoring and cleanup on top. And I debugged some segfaults in CCCL.C myself.
cub.bench.segmented_reduce.sum.baseon SM75/SM100