Inline Kleene boolean kernels#8478
5 benchmarks regressed
⚠️ 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.
⚡ 21 improved benchmarks
❌ 5 regressed benchmarks
✅ 1555 untouched benchmarks
Warning
Please fix the performance issues or acknowledge them on CodSpeed.
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Simulation | take_10k_random |
197.9 µs | 255.8 µs | -22.63% |
| ❌ | Simulation | take_10k_contiguous |
218.3 µs | 276.3 µs | -21% |
| ❌ | Simulation | patched_take_10k_contiguous_patches |
232.3 µs | 290.9 µs | -20.16% |
| ❌ | Simulation | patched_take_10k_random |
244.2 µs | 303 µs | -19.38% |
| ❌ | WallTime | cuda/bitpacked_u8/unpack/3bw[100M] |
299 µs | 347.7 µs | -14% |
| ⚡ | Simulation | or_false_constant |
69.8 µs | 15 µs | ×4.7 |
| ⚡ | Simulation | and_true_constant |
69.3 µs | 15 µs | ×4.6 |
| ⚡ | Simulation | or_true_constant |
69.4 µs | 16.1 µs | ×4.3 |
| ⚡ | Simulation | and_false_constant |
69.5 µs | 17.5 µs | ×4 |
| ⚡ | Simulation | or_bool_constant |
69 µs | 33.9 µs | ×2 |
| ⚡ | Simulation | or_null_constant |
92.3 µs | 49.8 µs | +85.23% |
| ⚡ | Simulation | or_null_constant_aligned |
92.4 µs | 49.9 µs | +85.16% |
| ⚡ | Simulation | and_null_constant |
92.5 µs | 50.1 µs | +84.71% |
| ⚡ | Simulation | and_null_constant_aligned |
92.5 µs | 50.2 µs | +84.18% |
| ⚡ | Simulation | chunked_bool_canonical_into[(1000, 10)] |
35.3 µs | 20.3 µs | +73.73% |
| ⚡ | Simulation | and_null_constant_shifted |
99.4 µs | 69.5 µs | +43.06% |
| ⚡ | Simulation | or_null_constant_shifted |
98.6 µs | 69.3 µs | +42.36% |
| ⚡ | Simulation | or_bool_nonnull_arrays |
40.8 µs | 32.7 µs | +24.79% |
| ⚡ | Simulation | and_bool_nonnull_arrays |
40.9 µs | 33 µs | +24.12% |
| ⚡ | Simulation | or_bool_nullable_arrays_shifted |
108.2 µs | 90.1 µs | +20.06% |
| ... | ... | ... | ... | ... | ... |
ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.
Tip
Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.
Comparing ngates/kleene-bool-kernels (225076f) with develop (c2119d9)
