Skip to content

Thread scope dtype through stats rewrites #7958

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gatesn wants to merge 2 commits into
base: ngates/stats-7707/min-max-aggregate-fns
Choose a base branch
from

Rename stats rewrite session

dd555d9
Select commit
Loading
Failed to load commit list.
Open

Thread scope dtype through stats rewrites #7958

Rename stats rewrite session
dd555d9
Select commit
Loading
Failed to load commit list.
CodSpeed HQ / CodSpeed Performance Analysis failed May 17, 2026 in 0s

Performance Regression: -14.75%

⚠️ 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

⚡ 10 improved benchmarks
❌ 69 regressed benchmarks
✅ 1137 untouched benchmarks
⏩ 5 skipped benchmarks1

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
❌ WallTime cuda/bitpacked_u8/unpack/3bw[100M] 299.5 µs 353.9 µs -15.36%
❌ Simulation chunked_varbinview_canonical_into[(100, 100)] 308.1 µs 400.7 µs -23.11%
❌ Simulation chunked_varbinview_canonical_into[(1000, 10)] 197.9 µs 284.7 µs -30.49%
❌ Simulation chunked_varbinview_into_canonical[(10, 1000)] 1.9 ms 2.2 ms -12.45%
❌ Simulation chunked_varbinview_into_canonical[(100, 100)] 358.6 µs 461.6 µs -22.31%
❌ Simulation chunked_varbinview_into_canonical[(1000, 10)] 212.1 µs 300.6 µs -29.44%
❌ Simulation chunked_varbinview_opt_canonical_into[(100, 100)] 411.4 µs 501.5 µs -17.96%
❌ Simulation chunked_varbinview_opt_canonical_into[(1000, 10)] 188.2 µs 307.3 µs -38.78%
❌ Simulation chunked_varbinview_opt_into_canonical[(100, 100)] 467.2 µs 565.2 µs -17.34%
❌ Simulation chunked_varbinview_opt_into_canonical[(1000, 10)] 240.4 µs 324.7 µs -25.95%
❌ Simulation encode_primitives[u8, (10000, 2)] 313.9 µs 358.6 µs -12.45%
❌ Simulation encode_primitives[u8, (10000, 32)] 318.4 µs 360.8 µs -11.75%
❌ Simulation encode_primitives[u8, (10000, 4)] 314.3 µs 358 µs -12.2%
❌ Simulation encode_primitives[u8, (10000, 512)] 335.2 µs 377.1 µs -11.11%
❌ Simulation encode_primitives[u8, (10000, 8)] 315.2 µs 358.1 µs -11.98%
❌ Simulation varbinview_large 130.1 µs 174.5 µs -25.46%
❌ Simulation execute_scalar_struct_simple 407.6 µs 464.3 µs -12.2%
❌ Simulation binary_search_vortex 485 ns 727.2 ns -33.31%
❌ Simulation take_search[(0.005, 0.05)] 131 µs 168.5 µs -22.26%
❌ Simulation take_search[(0.005, 0.1)] 246.6 µs 320.5 µs -23.07%
... ... ... ... ... ...

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 ngates/stats-7707/typed-stats-rewrite-api (dd555d9) with ngates/stats-7707/min-max-aggregate-fns (30b42c6)

Open in CodSpeed

Footnotes

  1. 5 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