feat: add experimental onpair string encoding#8144
Open
joseph-isaacs wants to merge 30 commits into
Open
Conversation
Adds the vortex-onpair array encoding under encodings/experimental/onpair, sourcing the compression algorithm from the standalone `onpair` crate (local path dependency) rather than vendored code. - vortex-onpair: Vortex array wrapping, serialisation, and cast/filter pushdown only; train/encode/decode live in the onpair crate. - btrblocks: register OnPairScheme alongside FSSTScheme so the sample-based selector keeps the smaller per column; delta-encode the monotonic dict_offsets/codes_offsets children (>= 2048 rows) when it wins. - vortex-file: register the OnPair encoding and allow it in the write strategy. Note: onpair is a local path dependency for now (to be published to crates.io). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>
joseph-isaacs
commented
May 29, 2026
- Remove unused public DEFAULT_BITS const and config_with_bits fn (plus their public-api.lock entries). - Drop stale "C++" references in comments; the algorithm is the pure-Rust onpair crate, not the old FFI shim. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>
joseph-isaacs
changed the title
onpair string encoding
Merging this PR will not alter performance
|
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Previous Runs (11)
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 1.114x ❌ How to read Verdict and Engines
datafusion / vortex-file-compressed (1.114x ❌, 0↑ 5↓)
File Size Changes (1 files changed, +0.5% overall, 1↑ 0↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.035x ➖, 0↑ 2↓)
datafusion / vortex-compact (1.039x ➖, 0↑ 2↓)
datafusion / parquet (0.988x ➖, 1↑ 0↓)
datafusion / arrow (1.006x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.004x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.006x ➖, 0↑ 0↓)
duckdb / parquet (1.026x ➖, 0↑ 3↓)
duckdb / duckdb (1.002x ➖, 0↑ 0↓)
File Size Changes (18 files changed, -5.3% overall, 9↑ 9↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.997x ➖, 1↑ 1↓)
datafusion / vortex-compact (1.000x ➖, 3↑ 2↓)
datafusion / parquet (0.991x ➖, 2↑ 1↓)
duckdb / vortex-file-compressed (0.997x ➖, 1↑ 2↓)
duckdb / vortex-compact (0.989x ➖, 0↑ 1↓)
duckdb / parquet (1.000x ➖, 1↑ 1↓)
duckdb / duckdb (0.992x ➖, 0↑ 1↓)
File Size Changes (48 files changed, -0.2% overall, 43↑ 5↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) How to read Verdict and Engines
duckdb / vortex-file-compressed (1.011x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.009x ➖, 0↑ 0↓)
duckdb / parquet (1.006x ➖, 0↑ 0↓)
File Size Changes (2 files changed, -0.2% overall, 1↑ 1↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.045x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.031x ➖, 0↑ 0↓)
datafusion / parquet (1.022x ➖, 0↑ 0↓)
datafusion / arrow (1.055x ➖, 0↑ 1↓)
duckdb / vortex-file-compressed (1.043x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.037x ➖, 0↑ 0↓)
duckdb / parquet (1.014x ➖, 0↑ 0↓)
duckdb / duckdb (1.020x ➖, 0↑ 0↓)
File Size Changes (48 files changed, -5.2% overall, 22↑ 26↓)
Totals:
Full attributed analysis
|
Replace the hand-rolled SIMD decoder (DecodeView::decode_rows_unchecked, build_dict_table) with onpair::decompress_into / decompress_row_into / decompressed_len. OwnedDecodeInputs is now just four flat host buffers plus a Parts<'_, u32> view; the hot loop lives upstream where the aarch64 NEON intrinsic path also lives. Bench (UrlLog, 1M rows): decompress_into median 8.4 ms, canonicalize_to_varbinview 14.7 ms. Adds num-traits as a direct dep to support the generic widen helpers (AsPrimitive::as_() side-steps clippy::cast_* lints on the match_each_integer_ptype! arms). Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>
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 (0.935x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.967x ➖, 0↑ 0↓)
datafusion / parquet (0.918x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (0.883x ➖, 1↑ 0↓)
duckdb / vortex-compact (0.850x ➖, 1↑ 0↓)
duckdb / parquet (0.875x ➖, 0↑ 0↓)
Full attributed analysis
|
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 (0.828x ➖, 2↑ 0↓)
datafusion / vortex-compact (0.809x ➖, 3↑ 0↓)
datafusion / parquet (0.924x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (0.861x ➖, 1↑ 0↓)
duckdb / vortex-compact (0.859x ➖, 1↑ 0↓)
duckdb / parquet (0.792x ➖, 2↑ 0↓)
Full attributed analysis
|
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.075x ➖, 1↑ 3↓)
datafusion / vortex-compact (0.984x ➖, 0↑ 0↓)
datafusion / parquet (0.991x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.171x ❌, 0↑ 4↓)
duckdb / vortex-compact (0.988x ➖, 0↑ 0↓)
duckdb / parquet (0.997x ➖, 0↑ 0↓)
File Size Changes (2 files changed, -12.0% overall, 1↑ 1↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.789x ➖, 1↑ 0↓)
datafusion / vortex-compact (0.947x ➖, 1↑ 0↓)
datafusion / parquet (0.907x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.775x ➖, 2↑ 0↓)
duckdb / vortex-compact (0.914x ➖, 0↑ 0↓)
duckdb / parquet (0.858x ➖, 0↑ 0↓)
Full attributed analysis
|
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
Contributor
Author
|
fineweb regression are quite small due to like contains and prefix. |
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.
Adds the
vortex-onpairarray encoding underencodings/experimental/onpair, sourcing the compression algorithm from the standaloneonpaircrate (local path dependency) rather than vendored code.