Skip to content

fsst decompress optimize try 2#7001

Closed
joseph-isaacs wants to merge 17 commits into
developfrom
claude/fsst-decompress-optimize-TylL2
Closed

fsst decompress optimize try 2#7001
joseph-isaacs wants to merge 17 commits into
developfrom
claude/fsst-decompress-optimize-TylL2

Optimize FSST inline view construction and escape handling

7fd4e7c
Select commit
Loading
Failed to load commit list.
CodSpeed HQ / CodSpeed Performance Analysis failed Mar 17, 2026 in 0s

Performance Regression: -12.23%

⚡ 48 improved benchmarks
❌ 2 regressed benchmarks
✅ 959 untouched benchmarks
🆕 40 new benchmarks
⏩ 1515 skipped benchmarks1

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
⚡ Simulation chunked_dict_fsst_canonical_into[(1000, 100, 100)] 30.1 ms 27 ms +11.34%
⚡ Simulation chunked_dict_fsst_canonical_into[(1000, 100, 10)] 3.1 ms 2.8 ms +10.78%
⚡ Simulation chunked_dict_fsst_canonical_into[(1000, 10, 100)] 28.9 ms 25.9 ms +11.82%
⚡ Simulation chunked_dict_fsst_into_canonical[(1000, 10, 100)] 29 ms 25.9 ms +11.95%
⚡ Simulation chunked_dict_fsst_canonical_into[(1000, 1000, 10)] 3.1 ms 2.8 ms +10.37%
⚡ Simulation chunked_dict_fsst_canonical_into[(1000, 1000, 100)] 30.5 ms 27.5 ms +10.84%
⚡ Simulation chunked_dict_fsst_canonical_into[(1000, 10, 10)] 3 ms 2.7 ms +11.11%
⚡ Simulation chunked_dict_fsst_into_canonical[(1000, 100, 10)] 3.1 ms 2.8 ms +10.95%
⚡ Simulation chunked_dict_fsst_into_canonical[(1000, 1000, 100)] 30.6 ms 27.6 ms +10.79%
⚡ Simulation chunked_dict_fsst_into_canonical[(1000, 100, 100)] 30.1 ms 27 ms +11.23%
⚡ Simulation chunked_dict_fsst_into_canonical[(1000, 10, 10)] 3 ms 2.7 ms +11.28%
⚡ Simulation chunked_dict_fsst_into_canonical[(1000, 1000, 10)] 3.1 ms 2.8 ms +10.27%
⚡ Simulation canonicalize_compare[(1000, 64, 4)] 373.1 µs 337.3 µs +10.63%
⚡ Simulation canonicalize_compare[(1000, 64, 8)] 415.8 µs 375.1 µs +10.86%
⚡ Simulation canonicalize_compare[(10000, 16, 8)] 1.5 ms 1.3 ms +17.19%
⚡ Simulation chunked_canonicalize_into[(10, 10000, 64, 4)] 28.1 ms 24.2 ms +16.08%
⚡ Simulation chunked_canonicalize_into[(10, 10000, 4, 4)] 7.8 ms 5.9 ms +33.11%
⚡ Simulation canonicalize_compare[(10000, 16, 4)] 1.4 ms 1.2 ms +17.23%
⚡ Simulation chunked_canonicalize_into[(1000, 100, 16, 16)] 20.5 ms 18.5 ms +11.12%
⚡ Simulation canonicalize_compare[(10000, 4, 8)] 1,173.5 µs 979.3 µs +19.83%
... ... ... ... ... ...

ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.

Comparing claude/fsst-decompress-optimize-TylL2 (7fd4e7c) with develop (50868db)

Open in CodSpeed

Footnotes

  1. 1515 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