Repository navigation
perf: speed up runtime pruning and run-end execution - #10416
joseph-isaacs wants to merge 6 commits into
2 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.
⚠️ 15 benchmarks spent significant time in system calls
System calls cannot be consistently instrumented, so they are not included in the measure, which understates the real cost. Please switch to the Walltime instrument to accurately measure system calls.
chunked_into_canonical[(20, 100, 16, 4)]take_varbinfilter_list_primitive_short[Repeated]pcodec_compress_f64density_sweep_dense_runs[0.001]optimize_lookup_predicate[ids=256, shape=in_list]case_when_fragmented[400]random_i128[0.01]chunked_dict_primitive_into_canonical[f64, (1000, 1000, 10)]decompress[u16, (4000, 256)]- …and 5 more
⚠️ Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.
⚡ 11 improved benchmarks
❌ 2 regressed benchmarks
✅ 2164 untouched benchmarks
🆕 167 new benchmarks
⏩ 365 skipped benchmarks1
Warning
Please fix the performance issues or acknowledge them on CodSpeed.
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | WallTime | bitpack_blocked_compress_avx2 |
6.7 µs | 7.6 µs | -11.34% |
| ❌ | Simulation | and_false_constant |
18.5 µs | 20.6 µs | -10.21% |
| ⚡ | Simulation | i64_random_chunked[256] |
15,817.7 µs | 738.8 µs | ×21 |
| ⚡ | Simulation | i64_random[256] |
4,360.6 µs | 247.3 µs | ×18 |
| ⚡ | Simulation | decode_bool[10000_2_all_true] |
175.7 µs | 15.3 µs | ×11 |
| ⚡ | Simulation | decode_bool[10000_2_all_false] |
176.1 µs | 15.8 µs | ×11 |
| ⚡ | Simulation | decode_bool[10000_10_all_true] |
47.5 µs | 14.7 µs | ×3.2 |
| ⚡ | Simulation | decode_bool[10000_10_all_false] |
47.9 µs | 15.2 µs | ×3.1 |
| ⚡ | Simulation | copy_nullable[16384] |
424.4 µs | 313.6 µs | +35.3% |
| ⚡ | Simulation | decode_bool[10000_100_all_true] |
17.9 µs | 13.8 µs | +29.45% |
| ⚡ | Simulation | decode_bool[10000_100_all_false] |
18.4 µs | 14.4 µs | +27.48% |
| ⚡ | Simulation | sum_i64 |
225.1 µs | 194.1 µs | +15.98% |
| ⚡ | Simulation | sum_v2_i64 |
224.8 µs | 194.2 µs | +15.76% |
| 🆕 | Simulation | decode_primitive_array[i64, 1] |
N/A | 2.9 ms | N/A |
| 🆕 | Simulation | decode_primitive_array[i64, 128] |
N/A | 530.3 µs | N/A |
| 🆕 | Simulation | decode_primitive_array[i64, 16] |
N/A | 693.5 µs | N/A |
| 🆕 | Simulation | decode_primitive_array[i64, 2] |
N/A | 1.8 ms | N/A |
| 🆕 | Simulation | decode_primitive_array[i64, 4096] |
N/A | 509.8 µs | N/A |
| 🆕 | Simulation | decode_primitive_array[u16, 1] |
N/A | 2.3 ms | N/A |
| 🆕 | Simulation | decode_primitive_array[u16, 128] |
N/A | 150.8 µs | N/A |
| ... | ... | ... | ... | ... | ... |
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 ji/tpcds-runtime-pruning-20261009 (3850f40) with develop (731a231)
Footnotes
-
365 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. ↩