Skip to content

refactor: isolate bitpacked v1 serde in the plugin - #9937

Draft
mhk197 wants to merge 2 commits into
developfrom
mk/bitpacked-stack-01-wire-boundary
Draft

mhk197 wants to merge 2 commits into
developfrom
mk/bitpacked-stack-01-wire-boundary

refactor: split bitpacked plugins and preserve v1 serde behavior

349b196
Select commit
Loading
Failed to load commit list.
CodSpeed / CodSpeed Performance Analysis failed Sep 22, 2026

3 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.

Open the report in CodSpeed to investigate

⚡ 5 improved benchmarks
❌ 3 regressed benchmarks
✅ 2200 untouched benchmarks
⏩ 293 skipped benchmarks1

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
Simulation decode_primitives[f32, (1000, 512)] 42.3 µs 64.6 µs -34.56%
Simulation take_fsl_u32_random[128, 100] 208.3 µs 237.2 µs -12.18%
Simulation take_fsl_f16_random[256, 100] 204.9 µs 230.5 µs -11.11%
Simulation take_fsl_u32_random[16, 100] 165.8 µs 125.9 µs +31.66%
WallTime dbp_assemble_kernel_avx512[(I128, 1024)] 546 ns 465 ns +17.42%
Simulation take_fsl_nullable_random[16, 100] 187.7 µs 165.4 µs +13.49%
WallTime dbp_assemble_kernel_avx2[(I128, 1024)] 561 ns 502 ns +11.75%
WallTime dbp_assemble_kernel_narrow_msp_avx2[(I128, 1024)] 699 ns 626 ns +11.66%

Tip

Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.


Comparing mk/bitpacked-stack-01-wire-boundary (349b196) with develop (c3ade49)

Open in CodSpeed

Footnotes

  1. 293 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.