perf[runend]: run_end_bool decompress #6229
+745
−61
Open
CodSpeed HQ / CodSpeed Performance Analysis
failed
Feb 2, 2026 in 0s
Performance Regression: -32.46%
⚡ 15 improved benchmarks
❌ 1 regressed benchmark
✅ 1122 untouched benchmarks
🆕 29 new benchmarks
⏩ 1384 skipped benchmarks1
⚠️ Please fix the performance issues or acknowledge them on CodSpeed.
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Simulation | chunked_bool_into_canonical[(1000, 10)] |
43 µs | 63.7 µs | -32.46% |
| ⚡ | Simulation | null_count_run_end[(10000, 16, 0.01)] |
84.7 µs | 48 µs | +76.32% |
| ⚡ | Simulation | null_count_run_end[(10000, 16, 0.5)] |
84.6 µs | 51.7 µs | +63.68% |
| ⚡ | Simulation | null_count_run_end[(10000, 4, 0.01)] |
234.1 µs | 135.2 µs | +73.08% |
| ⚡ | Simulation | null_count_run_end[(100000, 16, 0.01)] |
566.2 µs | 203.4 µs | ×2.8 |
| ⚡ | Simulation | null_count_run_end[(100000, 256, 0.01)] |
78.8 µs | 64.5 µs | +22.03% |
| ⚡ | Simulation | null_count_run_end[(10000, 4, 0.5)] |
190.3 µs | 100.4 µs | +89.59% |
| ⚡ | Simulation | null_count_run_end[(100000, 256, 0.5)] |
78.5 µs | 66.1 µs | +18.75% |
| ⚡ | Simulation | null_count_run_end[(100000, 4, 0.01)] |
1,623.4 µs | 645.7 µs | ×2.5 |
| ⚡ | Simulation | null_count_run_end[(10000, 4, 0.1)] |
190.8 µs | 94.2 µs | ×2 |
| ⚡ | Simulation | null_count_run_end[(100000, 16, 0.1)] |
565.9 µs | 210 µs | ×2.7 |
| ⚡ | Simulation | null_count_run_end[(100000, 4, 0.1)] |
1,623.1 µs | 660.6 µs | ×2.5 |
| ⚡ | Simulation | null_count_run_end[(100000, 16, 0.5)] |
566.5 µs | 242.1 µs | ×2.3 |
| ⚡ | Simulation | null_count_run_end[(10000, 16, 0.1)] |
84.7 µs | 48.8 µs | +73.57% |
| ⚡ | Simulation | null_count_run_end[(100000, 4, 0.5)] |
1,621.7 µs | 737.6 µs | ×2.2 |
| 🆕 | Simulation | decode_bool[10000_1000_mostly_true] |
N/A | 11.5 µs | N/A |
| ⚡ | Simulation | null_count_run_end[(100000, 256, 0.1)] |
78.9 µs | 65.2 µs | +21.11% |
| 🆕 | Simulation | decode_bool[10000_100_mostly_true] |
N/A | 13.8 µs | N/A |
| 🆕 | Simulation | decode_bool[10000_100_mostly_false] |
N/A | 14 µs | N/A |
| 🆕 | Simulation | decode_bool[10000_10_all_false] |
N/A | 32.4 µs | N/A |
| ... | ... | ... | ... | ... | ... |
ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.
Comparing ji/run-end-perf-bool (1beb99c) with develop (2c198c4)
Footnotes
-
1384 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