chore[array]: remove CanonicalVTable and move append_to_builder to main VTable #6045
CodSpeed HQ / CodSpeed Performance Analysis
failed
Jan 19, 2026 in 0s
Performance Regression: -56.1%
⚡ 75 improved benchmarks
❌ 56 regressed benchmarks
✅ 1123 untouched benchmarks
⏩ 1254 skipped benchmarks1
⚠️ Please fix the performance issues or acknowledge them on CodSpeed.
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Simulation | chunked_bool_canonical_into[(10, 1000)] |
605.3 µs | 711.5 µs | -14.93% |
| ❌ | Simulation | chunked_bool_canonical_into[(100, 100)] |
89.7 µs | 100.9 µs | -11.02% |
| ❌ | Simulation | chunked_bool_into_canonical[(10, 1000)] |
605.4 µs | 712.2 µs | -14.99% |
| ❌ | Simulation | chunked_bool_into_canonical[(100, 100)] |
90.4 µs | 101.4 µs | -10.85% |
| ❌ | Simulation | chunked_opt_bool_canonical_into[(10, 1000)] |
710.9 µs | 818.4 µs | -13.13% |
| ❌ | Simulation | bench_compare_primitive[(10000, 2048)] |
204.1 µs | 229.7 µs | -11.17% |
| ❌ | Simulation | chunked_opt_bool_into_canonical[(10, 1000)] |
712.6 µs | 819.9 µs | -13.09% |
| ❌ | Simulation | bench_compare_primitive[(100000, 2048)] |
821.4 µs | 1,083.3 µs | -24.17% |
| ❌ | Simulation | bench_compare_primitive[(100000, 2)] |
742.5 µs | 979.9 µs | -24.23% |
| ❌ | Simulation | bench_compare_primitive[(100000, 128)] |
744.7 µs | 984.3 µs | -24.34% |
| ❌ | Simulation | bench_compare_primitive[(100000, 4)] |
742.7 µs | 978.8 µs | -24.12% |
| ❌ | Simulation | bench_compare_primitive[(100000, 8)] |
742.4 µs | 979.8 µs | -24.23% |
| ❌ | Simulation | bench_compare_primitive[(100000, 512)] |
797.6 µs | 1,042 µs | -23.46% |
| ❌ | Simulation | bench_compare_primitive[(100000, 32)] |
742.6 µs | 980.7 µs | -24.29% |
| ⚡ | Simulation | bench_compare_sliced_dict_varbinview[(1000, 10000)] |
288.2 µs | 255.7 µs | +12.7% |
| ❌ | Simulation | bench_compare_varbin[(100000, 2048)] |
1 ms | 1.3 ms | -20.07% |
| ⚡ | Simulation | chunked_dict_primitive_canonical_into[f32, (1000, 10, 10)] |
104.3 µs | 89.2 µs | +16.92% |
| ❌ | Simulation | bench_compare_varbin[(100000, 32)] |
753 µs | 988.6 µs | -23.83% |
| ⚡ | Simulation | chunked_dict_primitive_canonical_into[f32, (1000, 10, 100)] |
833.4 µs | 732.8 µs | +13.72% |
| ⚡ | Simulation | chunked_dict_primitive_canonical_into[f32, (1000, 100, 10)] |
106.1 µs | 91.7 µs | +15.73% |
| ... | ... | ... | ... | ... | ... |
ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.
Comparing ji/remoev-canonical-vtable (52bed2f) with develop (cb31e1c)
Footnotes
-
1254 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. ↩
Loading