break: clean up compute #6572

Performance Regression: -21.5%

⚡ 21 improved benchmarks
❌ 20 regressed benchmarks
✅ 936 untouched benchmarks
⏩ 1426 skipped benchmarks¹

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

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
❌	Simulation	`bench_dict_mask[(0.01, 0.1)]`	1.8 ms	2.1 ms	-17.59%
❌	Simulation	`bench_dict_mask[(0.01, 0.01)]`	1.7 ms	2.2 ms	-21.49%
⚡	Simulation	`bench_dict_mask[(0.01, 0.9)]`	2.2 ms	1.7 ms	+24.06%
⚡	Simulation	`bench_dict_mask[(0.5, 0.9)]`	2.2 ms	1.9 ms	+16.53%
❌	Simulation	`bench_dict_mask[(0.5, 0.1)]`	1.8 ms	2.1 ms	-17.56%
❌	Simulation	`bench_dict_mask[(0.1, 0.1)]`	1.8 ms	2.1 ms	-17.54%
❌	Simulation	`bench_dict_mask[(0.1, 0.01)]`	1.7 ms	2.2 ms	-21.5%
❌	Simulation	`bench_dict_mask[(0.5, 0.01)]`	1.7 ms	2.2 ms	-21.24%
❌	Simulation	`bench_dict_mask[(0.9, 0.1)]`	1.8 ms	2.1 ms	-17.74%
❌	Simulation	`bench_dict_mask[(0.9, 0.01)]`	1.7 ms	2.2 ms	-21.36%
⚡	Simulation	`bench_dict_mask[(0.1, 0.9)]`	2.2 ms	1.9 ms	+16.53%
⚡	Simulation	`bench_dict_mask[(0.9, 0.9)]`	2.3 ms	1.9 ms	+22.28%
⚡	Simulation	`old_raw_prim_test_between[f64, 2048]`	146.9 µs	125.5 µs	+17.05%
⚡	Simulation	`old_raw_prim_test_between[i32, 2048]`	143.8 µs	121.1 µs	+18.74%
⚡	Simulation	`old_raw_prim_test_between[i64, 2048]`	149 µs	126.8 µs	+17.51%
⚡	Simulation	`old_raw_prim_test_between[u64, 2048]`	149.1 µs	127.2 µs	+17.18%
⚡	Simulation	`old_raw_prim_test_between[u32, 2048]`	143.6 µs	120.5 µs	+19.19%
❌	Simulation	`pushdown_compare[(1000, 16, 4)]`	371 µs	455.2 µs	-18.5%
❌	Simulation	`pushdown_compare[(1000, 16, 8)]`	393.5 µs	477.3 µs	-17.55%
❌	Simulation	`pushdown_compare[(10000, 16, 4)]`	531.5 µs	615.7 µs	-13.67%
...	...	...	...	...	...

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

_{Comparing ji/compute-cleanup (8f83b6f) with develop (9aa98d1)²}

1426 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. ↩
No successful run was found on develop (2e74b8a) during the generation of this report, so 9aa98d1 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩