Skip to content

Increase alignment requirement for parquet bloom filter to 256 - #19573

Merged
rapids-bot[bot] merged 11 commits into
NVIDIA:branch-25.10from
mhaseeb123:fix/bloom-filter-alignment
Aug 5, 2025
Merged

Increase alignment requirement for parquet bloom filter to 256#19573
rapids-bot[bot] merged 11 commits into
NVIDIA:branch-25.10from
mhaseeb123:fix/bloom-filter-alignment

Conversation

@mhaseeb123

@mhaseeb123 mhaseeb123 commented Aug 2, 2025

Copy link
Copy Markdown
Contributor

Description

Closes #19539. Related to rapidsai/rmm#2002

This PR increases the alignment requirement for parquet bloom filters from 32 to 256(== cuda allocation alignment) to avoid allocating invalid sized buffers and/or data corruption with aligned mr adapter. Doing so, doesn't really affect anything as 256 byte aligned addresses are also 32 byte aligned.

Checklist

  • I am familiar with the Contributing Guidelines.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.

@copy-pr-bot

copy-pr-bot Bot commented Aug 2, 2025

Copy link
Copy Markdown

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-actions github-actions Bot added libcudf Affects libcudf (C++/CUDA) code. Python Affects Python cuDF API. labels Aug 2, 2025
@GPUtester GPUtester moved this to In Progress in cuDF Python Aug 2, 2025
Comment thread python/cudf/cudf/tests/test_parquet.py
@mhaseeb123
mhaseeb123 requested a review from Matt711 August 2, 2025 00:17
@mhaseeb123
mhaseeb123 marked this pull request as ready for review August 2, 2025 00:17
@mhaseeb123
mhaseeb123 requested review from a team as code owners August 2, 2025 00:17
@mhaseeb123 mhaseeb123 added bug Something isn't working 3 - Ready for Review Ready for review by team non-breaking Non-breaking change 4 - Needs Review Waiting for reviewer to review or respond ! - Hotfix Hotfix is a bug that affects the majority of users for which there is no reasonable workaround and removed 3 - Ready for Review Ready for review by team labels Aug 2, 2025
Comment thread cpp/src/io/parquet/bloom_filter_reader.cu
Comment thread python/cudf/cudf/tests/test_parquet.py Outdated
@mhaseeb123
mhaseeb123 requested a review from Matt711 August 4, 2025 19:47

@Matt711 Matt711 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Thanks!

Comment thread python/cudf/cudf/tests/test_parquet.py Outdated
Co-authored-by: Matthew Murray <41342305+Matt711@users.noreply.github.com>
@mhaseeb123 mhaseeb123 added 5 - Ready to Merge Testing and reviews complete, ready to merge and removed 4 - Needs Review Waiting for reviewer to review or respond labels Aug 4, 2025
Comment thread python/cudf/cudf/tests/test_parquet.py Outdated
@mhaseeb123

Copy link
Copy Markdown
Contributor Author

/merge

@rapids-bot
rapids-bot Bot merged commit e5fd4e6 into NVIDIA:branch-25.10 Aug 5, 2025
171 of 173 checks passed
@github-project-automation github-project-automation Bot moved this from In Progress to Done in cuDF Python Aug 5, 2025
@mhaseeb123
mhaseeb123 deleted the fix/bloom-filter-alignment branch August 5, 2025 18:56
AyodeAwe pushed a commit that referenced this pull request Aug 5, 2025
## Description
This PR cherry picks minor changes from PR #19573 to hotfix bloom filter
alignment requirement in libcudf.

## Checklist
- [x] I am familiar with the [Contributing
Guidelines](https://github.com/rapidsai/cudf/blob/HEAD/CONTRIBUTING.md).
- [x] New or existing tests cover these changes.
- [x] The documentation is up to date with these changes.

---------

Co-authored-by: Matthew Murray <41342305+Matt711@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

5 - Ready to Merge Testing and reviews complete, ready to merge ! - Hotfix Hotfix is a bug that affects the majority of users for which there is no reasonable workaround bug Something isn't working libcudf Affects libcudf (C++/CUDA) code. non-breaking Non-breaking change Python Affects Python cuDF API.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] Predicate pushdown on DuckDB-generated Parquet crashes w/OOM or empty result

6 participants