Conversation
sort_by_keys only had host side implementations, so every call round tripped the buffers through host memory, and the only device sort in the tree, sort_by_key_pow2_len, requires a power of two length. Add a device tiled merge sort: every work item first sorts a tile of Vt consecutive elements with a fully unrolled odd-even transpose network held in thread private arrays, then adjacent sorted runs are merged pairwise, doubling the run length each round. A merge round is one kernel where a work item owns a fixed size chunk of the output and finds its own input sub-ranges with a Merge Path co-rank search. The total work is O(n log n), and the length does not need to be a power of two. A trailing partial tile is padded up to Vt with shambase::get_max. Since the network only swaps on a strictly smaller key, the padding never overtakes a real key comparing equal to the sentinel. - shambase: odd_even_transpose_sort_by_key, the key/value twin of the existing keys only OddEvenTransposeSortT - shamalgs: co_rank, a device and host compatible Merge Path partition search, alongside lower_bound and upper_bound - shamalgs: tiled_merge_sort.hpp for the device implementation, and tiled_merge_sort_host.hpp for the host serial reference, kept free of any SYCL dependency so the algorithm can be checked without a device - sort_by_keys: new tiled_merge_sort and tiled_merge_host_serial implementation variants, the default stays std_sort Assisted-by: Claude Code
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: trueThanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
|
Thanks @tdavidcl for opening this PR! You can do multiple things directly here: Once the workflow completes a message will appear displaying informations related to the run. Also the PR gets automatically reviewed by gemini, you can: |
Contributor
Workflow reportworkflow report corresponding to commit 2bc3669 Light CI is enabled (the default for pull requests). This will only run the basic tests and not the full tests. Pre-commit check reportPre-commit check: ✅ Test pipeline can run. Clang-tidy diff reportDoxygen diff with
|
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
1 participant
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.
No description provided.