batched_memset to use a host_span arg instead of std::vector - #19020
Merged
rapids-bot[bot] merged 4 commits intoMay 29, 2025
Conversation
mhaseeb123
added
3 - Ready for Review
mhaseeb123
commented
May 28, 2025
| /** | ||
| * @brief A helper function that copies a vector of vectors from source to destination addresses in | ||
| * a batched manner. | ||
| * @brief Helper to batched memcpy specified numbers of bytes from source device iterators to |
Contributor
Author
There was a problem hiding this comment.
Minor improvement to docstring here
| bool has_lists = false; | ||
| // Casting to std::byte since data buffer pointer is void * | ||
| std::vector<cudf::device_span<std::byte>> memset_bufs; | ||
| std::vector<cudf::device_span<cuda::std::byte>> memset_bufs; |
Contributor
Author
There was a problem hiding this comment.
Using cuda::std::byte for proper device compatibility
| TEST(MultiBufferTestIntegral, BasicTest1) | ||
| { | ||
| std::vector<size_t> const BUF_SIZES{ | ||
| std::vector<size_t> const buffer_sizes{ |
davidwendt
approved these changes
May 28, 2025
mhaseeb123
added
4 - Needs Review
bdice
approved these changes
May 28, 2025
mhaseeb123
added
5 - Ready to Merge
Contributor
Author
|
/merge |
copy-pr-bot Bot
pushed a commit
that referenced
this pull request
May 30, 2025
…19020) Related to #18968 (comment) This PR updates the `batched_memset` cuIO utility to take in a `host_span` type argument instead of a `std::vector` to allow using `cudf::host_vectors` or `cudf::pinned_vectors` in the future as input. Authors: - Muhammad Haseeb (https://github.com/mhaseeb123) Approvers: - David Wendt (https://github.com/davidwendt) - Bradley Dice (https://github.com/bdice) URL: #19020
This was referenced Aug 2, 2025
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.
Description
Related to #18968 (comment)
This PR updates the
batched_memsetcuIO utility to take in ahost_spantype argument instead of astd::vectorto allow usingcudf::host_vectorsorcudf::pinned_vectorsin the future as input.Checklist