Skip to content

Add pco-inspired lightweight numeric schemes - #9544

Draft
lwwmanning wants to merge 82 commits into
developfrom
wm/pcodec-fixed-bin-experiment
Draft

Add pco-inspired lightweight numeric schemes#9544
lwwmanning wants to merge 82 commits into
developfrom
wm/pcodec-fixed-bin-experiment

bench: configure preview numeric schemes explicitly

67afb3b
Select commit
Loading
Failed to load commit list.
CodSpeed HQ / CodSpeed Performance Analysis failed Aug 24, 2026

1 benchmark 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

⚡ 3 improved benchmarks
❌ 1 regressed benchmark
✅ 1977 untouched benchmarks
🆕 172 new benchmarks
⏩ 54 skipped benchmarks1

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
❌ Simulation compress_fsst[(500, 64, 8)] 530.5 µs 595 µs -10.85%
⚡ Simulation fsst_decompress_string 520.3 µs 206.8 µs ×2.5
⚡ Simulation decompress[alp_for_bp_f64] 169.7 µs 116.9 µs +45.12%
⚡ Simulation zstd_decompress_string 135.8 µs 115.5 µs +17.58%
🆕 Simulation block_local_block_residual_compress[i16] N/A 221.4 µs N/A
🆕 Simulation block_local_block_residual_compress[i32] N/A 267.2 µs N/A
🆕 Simulation block_local_block_residual_compress[i64] N/A 280.8 µs N/A
🆕 Simulation block_local_block_residual_compress[i8] N/A 220.1 µs N/A
🆕 Simulation block_local_block_residual_compress[u16] N/A 219.2 µs N/A
🆕 Simulation block_local_block_residual_compress[u32] N/A 267 µs N/A
🆕 Simulation block_local_block_residual_compress[u64] N/A 401.8 µs N/A
🆕 Simulation block_local_block_residual_compress[u8] N/A 218.7 µs N/A
🆕 Simulation block_local_block_residual_decompress[i16] N/A 47 µs N/A
🆕 Simulation block_local_block_residual_decompress[i32] N/A 69.4 µs N/A
🆕 Simulation block_local_block_residual_decompress[i64] N/A 101.5 µs N/A
🆕 Simulation block_local_block_residual_decompress[i8] N/A 39.1 µs N/A
🆕 Simulation block_local_block_residual_decompress[u16] N/A 46.9 µs N/A
🆕 Simulation block_local_block_residual_decompress[u32] N/A 67.2 µs N/A
🆕 Simulation block_local_block_residual_decompress[u64] N/A 97.4 µs N/A
🆕 Simulation block_local_block_residual_decompress[u8] N/A 38.3 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 wm/pcodec-fixed-bin-experiment (67afb3b) with develop (e4b3421)

Open in CodSpeed

Footnotes

  1. 54 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. ↩

View more details on CodSpeed HQ