Accelerate fixed-size-list take for primitive children#8671
Draft
danking wants to merge 1 commit into
Draft
Conversation
Copy selected fixed-size-list rows as contiguous primitive ranges when the child elements are already canonical primitive values, avoiding expanded per-element child take indices. Encoded and non-primitive children continue through the existing child take path instead of being forced to decompress.\n\nExpand take_fsl coverage across list byte widths and add forced strategy comparisons, plus nullable and non-nullable range-path correctness tests.\n\nSigned-off-by: "Daniel King" <dan@spiraldb.com>
github-actions
Bot
removed
the
action/benchmark
Merging this PR will improve performance by 12.77%
Warning Please fix the performance issues or acknowledge them on CodSpeed. Performance Changes
Tip Investigate this regression by commenting Comparing 
Footnotes
|
Contributor
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 0.985x ➖ How to read Verdict and Engines
datafusion / vortex-file-compressed (0.985x ➖, 1↑ 0↓)
No file size changes detected. |
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.014x ➖, 0↑ 1↓)
datafusion / vortex-compact (0.916x ➖, 2↑ 0↓)
datafusion / parquet (0.991x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.014x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.012x ➖, 1↑ 0↓)
duckdb / parquet (0.964x ➖, 2↑ 0↓)
File Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.953x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.951x ➖, 0↑ 0↓)
datafusion / parquet (0.977x ➖, 1↑ 1↓)
datafusion / arrow (0.906x ➖, 10↑ 0↓)
duckdb / vortex-file-compressed (0.977x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.973x ➖, 0↑ 0↓)
duckdb / parquet (0.956x ➖, 2↑ 1↓)
duckdb / duckdb (0.971x ➖, 0↑ 0↓)
File Size Changes (9 files changed, -0.1% overall, 4↑ 5↓)
Totals:
|
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.937x ➖, 11↑ 0↓)
datafusion / vortex-compact (0.961x ➖, 4↑ 1↓)
datafusion / parquet (0.939x ➖, 17↑ 0↓)
duckdb / vortex-file-compressed (0.947x ➖, 11↑ 0↓)
duckdb / vortex-compact (0.958x ➖, 8↑ 0↓)
duckdb / parquet (0.976x ➖, 2↑ 1↓)
duckdb / duckdb (0.964x ➖, 1↑ 1↓)
File Size Changes (6 files changed, +0.0% overall, 4↑ 2↓)
Totals:
|
Contributor
🚨🚨🚨❌❌❌ SQL BENCHMARK FAILED ❌❌❌🚨🚨🚨Benchmark |
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.969x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.004x ➖, 0↑ 1↓)
datafusion / parquet (0.977x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.000x ➖, 0↑ 1↓)
duckdb / vortex-compact (0.892x ➖, 0↑ 0↓)
duckdb / parquet (0.974x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: Clickbench Sorted on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.044x ➖, 1↑ 3↓)
datafusion / parquet (1.046x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.053x ➖, 1↑ 2↓)
duckdb / parquet (1.012x ➖, 0↑ 0↓)
duckdb / duckdb (1.008x ➖, 0↑ 0↓)
File Size Changes (201 files changed, +0.0% overall, 114↑ 87↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.948x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.956x ➖, 0↑ 0↓)
datafusion / parquet (0.952x ➖, 0↑ 0↓)
datafusion / arrow (0.915x ➖, 6↑ 0↓)
duckdb / vortex-file-compressed (0.960x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.966x ➖, 0↑ 0↓)
duckdb / parquet (0.987x ➖, 0↑ 1↓)
duckdb / duckdb (0.973x ➖, 0↑ 0↓)
File Size Changes (27 files changed, -0.0% overall, 11↑ 16↓)
Totals:
|
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.941x ➖, 3↑ 0↓)
datafusion / parquet (0.962x ➖, 2↑ 0↓)
duckdb / vortex-file-compressed (0.952x ➖, 4↑ 1↓)
duckdb / parquet (0.978x ➖, 0↑ 0↓)
duckdb / duckdb (0.985x ➖, 0↑ 0↓)
File Size Changes (105 files changed, +0.0% overall, 43↑ 62↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.025x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.859x ➖, 5↑ 2↓)
datafusion / parquet (0.925x ➖, 3↑ 1↓)
duckdb / vortex-file-compressed (1.039x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.047x ➖, 0↑ 0↓)
duckdb / parquet (0.970x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: Appian on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.913x ➖, 3↑ 0↓)
datafusion / parquet (0.930x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.919x ➖, 2↑ 0↓)
duckdb / parquet (0.917x ➖, 1↑ 0↓)
duckdb / duckdb (0.927x ➖, 0↑ 0↓)
File Size Changes (4 files changed, -0.0% overall, 2↑ 2↓)
Totals:
|
Contributor
Benchmarks: Random AccessVortex (geomean): 1.045x ➖ How to read Verdict and Engines
unknown / unknown (0.986x ➖, 1↑ 1↓)
|
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.080x ➖, 0↑ 3↓)
datafusion / vortex-compact (1.084x ➖, 0↑ 2↓)
datafusion / parquet (1.032x ➖, 0↑ 2↓)
duckdb / vortex-file-compressed (1.225x ➖, 0↑ 4↓)
duckdb / vortex-compact (1.240x ➖, 0↑ 6↓)
duckdb / parquet (1.127x ➖, 0↑ 1↓)
|
Contributor
Benchmarks: CompressionVortex (geomean): 1.002x ➖ How to read Verdict and Engines
unknown / unknown (1.019x ➖, 0↑ 11↓)
|
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.
Summary
takepath so this does not force decompressiontake_fslbenchmark coverage across list byte widths and add forced strategy comparisonsTesting
cargo +nightly fmt --allcargo check -p vortex-array --bench take_fslcargo test -p vortex-array fixed_size_list::tests::takecargo clippy --all-targets --all-featuresgit diff --check