Vector similarity search scan benchmarks#7499
Merged
connortsui20 merged 1 commit intodevelopfrom Apr 17, 2026
Merged
Conversation
connortsui20
force-pushed
the
ct/vector-search-scan
branch
from
7123283 to
95480de
Compare
Merging this PR will not alter performance
Comparing 
Footnotes
|
connortsui20
force-pushed
the
ct/vector-search-scan
branch
from
95480de to
064f059
Compare
This was referenced Apr 17, 2026
Merged
connortsui20
added a commit
that referenced
this pull request
Apr 17, 2026
## Summary We want to merge #7499 soon, but it is not a fair comparison because we do not normalize the uncompressed vectors flavor, but we do normalize the TurboQuant-encoded vectors. This just makes the comparison fair. I've marked this as semi-unstable (there is no `with_turboquant` equivalent on the compressor builder, but the ID is clearly unstable) just so we can get the benchmark in #7499 over the line in a reasonable state. ## Testing It already works for the TurboQuant scheme, this is just a reduction of that so we don't need to test this. Signed-off-by: Connor Tsui <connor.tsui20@gmail.com>
connortsui20
force-pushed
the
ct/vector-search-scan
branch
2 times, most recently
from
b340119 to
a4c6350
Compare
connortsui20
changed the title
connortsui20
force-pushed
the
ct/vector-search-scan
branch
from
a4c6350 to
7ce60d2
Compare
connortsui20
force-pushed
the
ct/vector-search-scan
branch
2 times, most recently
from
ca526bd to
40c97f2
Compare
a10y
approved these changes
Apr 17, 2026
Signed-off-by: Connor Tsui <connor.tsui20@gmail.com>
connortsui20
force-pushed
the
ct/vector-search-scan
branch
from
40c97f2 to
aa3f3d5
Compare
connortsui20
added
the
action/benchmark
github-actions
bot
removed
the
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 1.076x ➖ datafusion / vortex-file-compressed (1.076x ➖, 0↑ 3↓)
|
Contributor
File Sizes: PolarSignals ProfilingNo file size changes detected. |
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.000x ➖, 1↑ 0↓)
datafusion / vortex-compact (0.995x ➖, 0↑ 0↓)
datafusion / parquet (1.015x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.018x ➖, 0↑ 2↓)
duckdb / vortex-compact (1.038x ➖, 0↑ 1↓)
duckdb / parquet (1.038x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: FineWeb NVMeNo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.070x ➖, 0↑ 1↓)
datafusion / vortex-compact (1.063x ➖, 0↑ 2↓)
datafusion / parquet (1.049x ➖, 0↑ 5↓)
datafusion / arrow (1.078x ➖, 0↑ 4↓)
duckdb / vortex-file-compressed (1.049x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.031x ➖, 0↑ 0↓)
duckdb / parquet (1.027x ➖, 0↑ 1↓)
duckdb / duckdb (1.047x ➖, 0↑ 1↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.002x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.994x ➖, 0↑ 0↓)
datafusion / parquet (1.031x ➖, 0↑ 11↓)
duckdb / vortex-file-compressed (1.056x ➖, 0↑ 26↓)
duckdb / vortex-compact (1.023x ➖, 0↑ 6↓)
duckdb / parquet (1.012x ➖, 0↑ 2↓)
duckdb / duckdb (0.998x ➖, 4↑ 5↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-DS SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.705x ➖, 4↑ 1↓)
datafusion / vortex-compact (1.093x ➖, 0↑ 1↓)
datafusion / parquet (1.049x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.974x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.024x ➖, 0↑ 0↓)
duckdb / parquet (1.004x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) duckdb / vortex-file-compressed (1.020x ➖, 0↑ 1↓)
duckdb / vortex-compact (0.991x ➖, 0↑ 0↓)
duckdb / parquet (0.984x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.932x ➖, 3↑ 0↓)
datafusion / vortex-compact (0.929x ➖, 1↑ 0↓)
datafusion / parquet (0.960x ➖, 0↑ 0↓)
datafusion / arrow (0.941x ➖, 3↑ 0↓)
duckdb / vortex-file-compressed (0.931x ➖, 4↑ 0↓)
duckdb / vortex-compact (0.961x ➖, 0↑ 0↓)
duckdb / parquet (0.969x ➖, 0↑ 0↓)
duckdb / duckdb (0.989x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: Statistical and Population GeneticsNo file size changes detected. |
Contributor
File Sizes: TPC-H SF=10 on NVMENo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (1.027x ➖, 0↑ 3↓)
datafusion / vortex-compact (1.022x ➖, 0↑ 1↓)
datafusion / parquet (1.105x ➖, 1↑ 6↓)
duckdb / vortex-file-compressed (0.983x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.009x ➖, 0↑ 1↓)
duckdb / parquet (1.003x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.113x ❌, 0↑ 25↓)
datafusion / parquet (1.085x ➖, 0↑ 20↓)
duckdb / vortex-file-compressed (1.080x ➖, 0↑ 20↓)
duckdb / parquet (1.080x ➖, 0↑ 14↓)
duckdb / duckdb (1.067x ➖, 0↑ 12↓)
Full attributed analysis
|
Contributor
File Sizes: Clickbench on NVMEFile Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
|
Contributor
Benchmarks: Random AccessVortex (geomean): 0.901x ➖ unknown / unknown (1.001x ➖, 6↑ 9↓)
|
Contributor
Benchmarks: CompressionVortex (geomean): 0.999x ➖ unknown / unknown (0.997x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (0.995x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.013x ➖, 0↑ 1↓)
datafusion / parquet (1.083x ➖, 0↑ 2↓)
duckdb / vortex-file-compressed (1.063x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.046x ➖, 0↑ 0↓)
duckdb / parquet (1.080x ➖, 0↑ 0↓)
Full attributed analysis
|
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
2 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.
Summary
Tracking Issue: #7297
Adds a basic vector similarity search benchmark to the Vortex benchmark suite as a binary.
Here is an example of how to run this:
The main scan logic is in
scan_one_fileinbenchmarks/vector-search-bench/src/scan.rs, and everything else is just setup for that.Future Work
Testing
The benchmark running successfully for all datasets is sufficient.