feat: very wide column benchmark#8252
Conversation
Signed-off-by: Joe Isaacs <joe.isaacs@live.co.uk>
Polar Signals Profiling ResultsLatest Run
Previous Runs (1)
Powered by Polar Signals Cloud |
Benchmarks: PolarSignals ProfilingVortex (geomean): 1.012x ➖ How to read Verdict and Engines
datafusion / vortex-file-compressed (1.012x ➖, 1↑ 1↓)
No file size changes detected. |
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.986x ➖, 0↑ 1↓)
datafusion / vortex-compact (0.973x ➖, 0↑ 0↓)
datafusion / parquet (0.953x ➖, 3↑ 1↓)
datafusion / arrow (0.922x ➖, 8↑ 0↓)
duckdb / vortex-file-compressed (0.966x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.960x ➖, 0↑ 0↓)
duckdb / parquet (0.975x ➖, 3↑ 1↓)
duckdb / duckdb (0.965x ➖, 0↑ 0↓)
File Size Changes (10 files changed, -0.2% overall, 4↑ 6↓)
Totals:
Full attributed analysis
|
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.968x ➖, 2↑ 0↓)
datafusion / vortex-compact (0.990x ➖, 0↑ 0↓)
datafusion / parquet (0.987x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.029x ➖, 1↑ 2↓)
duckdb / vortex-compact (0.994x ➖, 0↑ 0↓)
duckdb / parquet (0.996x ➖, 0↑ 0↓)
File Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
Full attributed analysis
|
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.947x ➖, 14↑ 1↓)
datafusion / vortex-compact (0.944x ➖, 16↑ 0↓)
datafusion / parquet (0.920x ➖, 23↑ 0↓)
duckdb / vortex-file-compressed (0.946x ➖, 13↑ 1↓)
duckdb / vortex-compact (0.946x ➖, 15↑ 1↓)
duckdb / parquet (0.958x ➖, 5↑ 0↓)
duckdb / duckdb (0.940x ➖, 8↑ 1↓)
File Size Changes (6 files changed, +0.0% overall, 5↑ 1↓)
Totals:
Full attributed analysis
|
Merging this PR will improve performance by 30.19%
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ⚡ | Simulation | chunked_bool_canonical_into[(1000, 10)] |
45.3 µs | 30.3 µs | +49.41% |
| ⚡ | Simulation | chunked_varbinview_canonical_into[(1000, 10)] |
197.1 µs | 160.8 µs | +22.53% |
| ⚡ | Simulation | chunked_varbinview_into_canonical[(1000, 10)] |
211.7 µs | 175.6 µs | +20.54% |
Tip
Curious why this is faster? Comment @codspeedbot explain why this is faster on this PR, or directly use the CodSpeed MCP with your agent.
Comparing ji/wide-col-projection (9a0f3ba) with develop (3ac6c77)
Benchmarks: FineWeb S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.870x ➖, 1↑ 0↓)
datafusion / vortex-compact (0.985x ➖, 0↑ 0↓)
datafusion / parquet (1.088x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.080x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.019x ➖, 0↑ 0↓)
duckdb / parquet (1.050x ➖, 0↑ 0↓)
Full attributed analysis
|
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) How to read Verdict and Engines
duckdb / vortex-file-compressed (1.007x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.000x ➖, 0↑ 0↓)
duckdb / parquet (1.000x ➖, 0↑ 0↓)
File Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
Full attributed analysis
|
Benchmarks: Random AccessVortex (geomean): 0.978x ➖ How to read Verdict and Engines
unknown / unknown (1.025x ➖, 2↑ 2↓)
|
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.930x ➖, 4↑ 0↓)
datafusion / vortex-compact (0.926x ➖, 4↑ 0↓)
datafusion / parquet (0.926x ➖, 6↑ 0↓)
datafusion / arrow (0.904x ➖, 11↑ 0↓)
duckdb / vortex-file-compressed (0.951x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.964x ➖, 0↑ 0↓)
duckdb / parquet (0.958x ➖, 0↑ 0↓)
duckdb / duckdb (0.976x ➖, 0↑ 0↓)
File Size Changes (27 files changed, -0.0% overall, 12↑ 15↓)
Totals:
Full attributed analysis
|
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.019x ➖, 1↑ 2↓)
datafusion / parquet (0.987x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (1.000x ➖, 5↑ 3↓)
duckdb / parquet (1.006x ➖, 0↑ 1↓)
duckdb / duckdb (0.953x ➖, 10↑ 0↓)
File Size Changes (105 files changed, +0.0% overall, 58↑ 47↓)
Totals:
Full attributed analysis
|
Benchmarks: Appian on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.875x ✅, 7↑ 0↓)
datafusion / parquet (0.871x ✅, 7↑ 0↓)
duckdb / vortex-file-compressed (0.980x ➖, 0↑ 0↓)
duckdb / parquet (0.960x ➖, 0↑ 0↓)
duckdb / duckdb (0.990x ➖, 0↑ 0↓)
File Size Changes (4 files changed, -0.0% overall, 2↑ 2↓)
Totals:
Full attributed analysis
|
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.993x ➖, 1↑ 0↓)
datafusion / vortex-compact (1.123x ➖, 0↑ 4↓)
datafusion / parquet (1.052x ➖, 1↑ 4↓)
duckdb / vortex-file-compressed (1.064x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.033x ➖, 0↑ 1↓)
duckdb / parquet (1.057x ➖, 0↑ 0↓)
Full attributed analysis
|
Benchmarks: CompressionVortex (geomean): 1.006x ➖ How to read Verdict and Engines
unknown / unknown (1.011x ➖, 0↑ 7↓)
|
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.229x ➖, 0↑ 11↓)
datafusion / vortex-compact (1.068x ➖, 1↑ 5↓)
datafusion / parquet (1.253x ➖, 0↑ 9↓)
duckdb / vortex-file-compressed (0.989x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.968x ➖, 0↑ 0↓)
duckdb / parquet (0.985x ➖, 0↑ 0↓)
Full attributed analysis
|
Summary
Closes: #000
Testing