VarBinViewBuilder: support appending buffers directly into the builder storage - #9235
VarBinViewBuilder: support appending buffers directly into the builder storage#9235robert3005 wants to merge 2 commits into
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.
⚡ 11 improved benchmarks
❌ 5 regressed benchmarks
✅ 1952 untouched benchmarks
⏩ 8 skipped benchmarks1
Warning
Please fix the performance issues or acknowledge them on CodSpeed.
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Simulation | decompress[u32, (10000, 1024)] |
78.5 µs | 95.2 µs | -17.55% |
| ❌ | Simulation | fsst_decompress_string |
7.2 ms | 8.3 ms | -12.77% |
| ❌ | Simulation | decompress_fsst[(10000, 4, 4)] |
794.2 µs | 901 µs | -11.85% |
| ❌ | Simulation | decompress_fsst[(10000, 4, 8)] |
815.5 µs | 922.1 µs | -11.56% |
| ❌ | Simulation | canonicalize_compare[(10000, 4, 4)] |
955.9 µs | 1,064.1 µs | -10.17% |
| ⚡ | Simulation | chunked_varbin_to_varbinview_builder[(10, 100)] |
509.3 µs | 329.1 µs | +54.76% |
| ⚡ | Simulation | chunked_varbin_opt_to_varbinview_builder[(10, 100)] |
794.1 µs | 554.8 µs | +43.14% |
| ⚡ | Simulation | chunked_varbin_to_varbinview_builder[(500, 2)] |
164.5 µs | 119.1 µs | +38.13% |
| ⚡ | Simulation | chunked_varbin_into_canonical[(10, 100)] |
670.9 µs | 488 µs | +37.47% |
| ⚡ | Simulation | chunked_varbin_into_canonical[(500, 2)] |
175.4 µs | 130.9 µs | +33.94% |
| ⚡ | Simulation | chunked_varbin_opt_to_varbinview_builder[(500, 2)] |
162.4 µs | 122.5 µs | +32.57% |
| ⚡ | Simulation | chunked_into_canonical[(1000, 50, 8, 4)] |
17.9 ms | 15.7 ms | +14.22% |
| ⚡ | Simulation | chunked_canonicalize_into[(1000, 50, 8, 4)] |
15.1 ms | 13.2 ms | +13.66% |
| ⚡ | Simulation | chunked_canonicalize_into[(1000, 50, 8, 16)] |
16.2 ms | 14.3 ms | +12.98% |
| ⚡ | Simulation | chunked_into_canonical[(1000, 50, 8, 16)] |
19 ms | 16.8 ms | +12.83% |
| ⚡ | Simulation | decompress[u64, (1000, 16)] |
73 µs | 65.2 µs | +11.87% |
Tip
Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.
Comparing rk/varbinview-append-buffer (a0bec35) with develop (a1057db)
Footnotes
-
8 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. ↩