Add tuning policies to CUB API docs#9745
Merged
bernhardmgruber merged 7 commits intoJul 13, 2026
Merged
Conversation
17 tasks
Contributor
|
Caution Review failedAn error occurred during the review process. Please try again later. 📝 WalkthroughSummary by CodeRabbit
WalkthroughMoves lookback-delay types into ChangesLookback Delay API Relocation
Friend Operator Qualifier Reformatting
Doxyfile Configuration Updates
Suggested reviewers: Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 916f0b3b-12af-4578-abf3-6b3a5efaf8f4
📒 Files selected for processing (31)
cub/cub/detail/delay_constructor.cuhcub/cub/device/dispatch/tuning/common.cuhcub/cub/device/dispatch/tuning/tuning_adjacent_difference.cuhcub/cub/device/dispatch/tuning/tuning_batch_memcpy.cuhcub/cub/device/dispatch/tuning/tuning_batched_topk.cuhcub/cub/device/dispatch/tuning/tuning_find.cuhcub/cub/device/dispatch/tuning/tuning_find_bound_sorted_values.cuhcub/cub/device/dispatch/tuning/tuning_for.cuhcub/cub/device/dispatch/tuning/tuning_histogram.cuhcub/cub/device/dispatch/tuning/tuning_merge.cuhcub/cub/device/dispatch/tuning/tuning_merge_sort.cuhcub/cub/device/dispatch/tuning/tuning_radix_sort.cuhcub/cub/device/dispatch/tuning/tuning_reduce.cuhcub/cub/device/dispatch/tuning/tuning_reduce_by_key.cuhcub/cub/device/dispatch/tuning/tuning_rle_encode.cuhcub/cub/device/dispatch/tuning/tuning_rle_non_trivial_runs.cuhcub/cub/device/dispatch/tuning/tuning_scan.cuhcub/cub/device/dispatch/tuning/tuning_scan_by_key.cuhcub/cub/device/dispatch/tuning/tuning_segmented_radix_sort.cuhcub/cub/device/dispatch/tuning/tuning_segmented_reduce.cuhcub/cub/device/dispatch/tuning/tuning_segmented_scan.cuhcub/cub/device/dispatch/tuning/tuning_segmented_sort.cuhcub/cub/device/dispatch/tuning/tuning_select_if.cuhcub/cub/device/dispatch/tuning/tuning_three_way_partition.cuhcub/cub/device/dispatch/tuning/tuning_topk.cuhcub/cub/device/dispatch/tuning/tuning_transform.cuhcub/cub/device/dispatch/tuning/tuning_unique_by_key.cuhdocs/cub/Doxyfiledocs/cudax/Doxyfiledocs/libcudacxx/Doxyfiledocs/thrust/Doxyfile
Jacobfaib
reviewed
Jul 8, 2026
Comment on lines
+263
to
+265
| LookbackDelayAlgorithm kind; //!< The algorithm used for delaying during decoupled lookback | ||
| unsigned int delay; //!< The delay in nanoseconds | ||
| unsigned int l2_write_latency; //!< The write latency of the L2 cache in nanoseconds |
Contributor
There was a problem hiding this comment.
Important: should provide default values for these, otherwise
LookbackDelayPolicy pol;produces garbage.
Contributor
Author
There was a problem hiding this comment.
Why is that a problem? And what are good default values?
Contributor
There was a problem hiding this comment.
If there are no good defaults, then we should declare a constructor to force the user to populate everything.
Contributor
Author
There was a problem hiding this comment.
This will suppress designated initializers, which are a major help when defining those kind of structs.
Still, I don't see the problem of having uninitialized members upon construction. It's erroneous behavior to use that and will also fail during constant evaluation, if you forget to set a value.
| //! The delay algorithm used by decoupled lookback | ||
| enum class LookbackDelayAlgorithm | ||
| { | ||
| no_delay, |
Contributor
There was a problem hiding this comment.
Important: should document what these enum values represent exactly. For example, what does exponential_back_jitter mean? How big is the delay for fixed_delay?
Contributor
Author
There was a problem hiding this comment.
exponential_back_jitter is one of the algorithm for handling the delay of lookback-based algorithms. I have no idea what it does.
How big is the delay for fixed_delay?
The value specified in LookbackDelayPolicy::delay
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
bernhardmgruber
force-pushed
the
tuning_policies_docs
branch
from
14f3324 to
df301fb
Compare
Contributor
🥳 CI Workflow Results🟩 Finished in 2h 34m: Pass: 100%/287 | Total: 12d 10h | Max: 2h 33m | Hits: 15%/1163679See results here. |
bernhardmgruber
commented
Jul 13, 2026
| BlockStoreAlgorithm store_algorithm; //!< The @ref BlockStoreAlgorithm used for storing items to global memory | ||
|
|
||
| [[nodiscard]] _CCCL_HOST_DEVICE_API constexpr friend bool | ||
| [[nodiscard]] _CCCL_HOST_DEVICE_API friend constexpr bool |
Contributor
Author
There was a problem hiding this comment.
Note: These changes are needed for Breathe to avoid a parsing issue.
davebayer
approved these changes
Jul 13, 2026
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.
Fixes part of: #9378