Process parquet bools with microkernels #17157
Open
Conversation
This file contains 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
…lable column code
…attione-nvidia/cudf into mukernels_fixedwidth_optimize
Co-authored-by: nvdbaranec <[email protected]>
Co-authored-by: nvdbaranec <[email protected]>
Co-authored-by: nvdbaranec <[email protected]>
…attione-nvidia/cudf into mukernels_fixedwidth_optimize
Co-authored-by: Vukasin Milovanovic <[email protected]>
…attione-nvidia/cudf into mukernels_fixedwidth_optimize
pmattione-nvidia
added
improvement
pmattione-nvidia
requested review from
vyasr,
PointKernel,
nvdbaranec and
vuule
PointKernel
reviewed
Oct 30, 2024
Co-authored-by: Yunsong Wang <[email protected]>
nvdbaranec
approved these changes
Nov 6, 2024
Co-authored-by: nvdbaranec <[email protected]>
vuule
approved these changes
Nov 6, 2024
| int s_idx = 0; | ||
|
|
||
| auto decode_data = [&](decode_kernel_mask decoder_mask) { |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This adds support for the bool type to reading parquet microkernels. Both plain (bit-packed) and RLE-encoded bool decode is supported, using separate code paths. This PR also massively reduces boilerplate code, as most of the template info needed is already encoded in the kernel mask. Also the superfluous level_t template parameter on rle_run has been removed. And bools have been added to the parquet benchmarks.
Performance: register count drops from 62 -> 56, both plain and RLE-encoded bool decoding are now 46% faster (uncompressed). Reading sample customer data shows no change. NDS tests show no change.
Checklist