Skip to content

Reduce lazy masks into arrays with all-valid metadata - #10016

Merged
connortsui20 merged 3 commits into
developfrom
ct/all-valid-mask-reduction
Sep 24, 2026
Merged

Reduce lazy masks into arrays with all-valid metadata#10016
connortsui20 merged 3 commits into
developfrom
ct/all-valid-mask-reduction

Use validity helper in mask reduction

a8d283b
Select commit
Loading
Failed to load commit list.
CodSpeed / CodSpeed Performance Analysis failed Sep 23, 2026 in 0s

4 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.

⚠️ 3 benchmarks measured no execution time

Nothing ran under measurement, usually because the compiler removed the code under test. These results are not comparable, so they count as unchanged.

Preventing compiler optimizations

⚡ 12 improved benchmarks
❌ 4 regressed benchmarks
✅ 2160 untouched benchmarks
⏩ 385 skipped benchmarks1

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
❌ Simulation take_chunked_fsl_sorted[32, 64] 195.7 µs 269.6 µs -27.42%
❌ WallTime decode_avx2[8192, (Inline, OneNullInEight)] 86 µs 104.7 µs -17.86%
❌ WallTime filtered_owned_i64_avx512[OneNullInEight] 22.2 µs 26.2 µs -15.14%
❌ WallTime filtered_owned_i64_avx2[OneNullInEight] 22 µs 25.5 µs -13.88%
⚡ WallTime deferred_bool_avx2[16384, (ConstantLhs, PartialAccepted)] 205.8 µs 33.2 µs ×6.2
⚡ WallTime deferred_bool_avx512[16384, (ConstantLhs, PartialAccepted)] 206.2 µs 38.2 µs ×5.4
⚡ WallTime deferred_bool_neon[16384, (ConstantLhs, PartialAccepted)] 169.5 µs 54.3 µs ×3.1
⚡ WallTime deferred_bool_avx2[16384, (Columns, PartialAccepted)] 109.8 µs 42.2 µs ×2.6
⚡ WallTime deferred_bool_avx512[16384, (ConstantLhs, NullOnlyFailure)] 470.8 µs 286.3 µs +64.45%
⚡ WallTime deferred_bool_avx2[16384, (ConstantLhs, NullOnlyFailure)] 454.5 µs 281.4 µs +61.5%
⚡ Simulation take_fsl_f16_force_per_index[256, 10] 57 µs 38.8 µs +46.85%
⚡ WallTime mul_u64_nonnull_neon 40.4 µs 29.1 µs +38.76%
⚡ WallTime deferred_bool_neon[16384, (ConstantLhs, NullOnlyFailure)] 478.6 µs 377.5 µs +26.79%
⚡ WallTime deferred_bool_avx2[16384, (Columns, NullOnlyFailure)] 344.3 µs 278.7 µs +23.53%
⚡ WallTime multiply_shapes_neon[(32768, PerRowPerRow)] 39 µs 32.7 µs +19.03%
⚡ WallTime mul_i64_nonnull_neon 38.9 µs 32.9 µs +18.38%
⚠️ Simulation fixed_16_advancing_ptr_safe[100] < 1 ns < 1 ns N/A
⚠️ Simulation preverify_advancing_ptr_unchecked[1000] < 1 ns < 1 ns N/A
⚠️ Simulation preverify_advancing_ptr_unchecked[10000] < 1 ns < 1 ns N/A

Tip

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

Comparing ct/all-valid-mask-reduction (a8d283b) with develop (26231bb)2

Open in CodSpeed

Footnotes

  1. 385 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. ↩

  2. No successful run was found on develop (da48008) during the generation of this report, so 26231bb was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

View more details on CodSpeed