Repository navigation
Optimise bitpacked filtering for valid runs and buffer filtering - #10281
robert3005 wants to merge 9 commits into
Performance Gate Passed
⚠️ Unknown Walltime execution environment detected
Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.
For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.
⚠️ Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.
⚡ 8 improved benchmarks
✅ 2167 untouched benchmarks
🆕 4 new benchmarks
⏩ 534 skipped benchmarks1
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ⚡ | Simulation | density_sweep_dense_runs[0.001] |
48 µs | 30.3 µs | +58.49% |
| ⚡ | Simulation | random_i128[0.01] |
7 µs | 4.6 µs | +53.49% |
| ⚡ | Simulation | filter_powerlaw_by_mostly_true[250000] |
150 µs | 103.8 µs | +44.52% |
| ⚡ | Simulation | random_i128[0.5] |
116.6 µs | 101.8 µs | +14.57% |
| ⚡ | Simulation | patterns_i128[Random] |
116.5 µs | 101.8 µs | +14.39% |
| ⚡ | Simulation | random_i128[0.8] |
174.8 µs | 153.2 µs | +14.06% |
| ⚡ | Simulation | patterns_i128[Runs] |
117.2 µs | 103 µs | +13.81% |
| ⚡ | Simulation | random_i256[0.8] |
123.4 µs | 111.8 µs | +10.34% |
| 🆕 | Simulation | fsl_i32[16, 0.1] |
N/A | 591.4 µs | N/A |
| 🆕 | Simulation | fsl_i32[4, 0.1] |
N/A | 813 µs | N/A |
| 🆕 | Simulation | primitive_i32[0.01] |
N/A | 179.1 µs | N/A |
| 🆕 | Simulation | primitive_i32[0.1] |
N/A | 518.9 µs | N/A |
Tip
Curious why performance improved? Comment @codspeedbot explain why performance improved on this PR, or directly use the CodSpeed MCP with your agent.
Comparing rk/bitpacked-filter (e00d694) with develop (c93ffa3)
Footnotes
-
534 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩