chore[array]: add filter bool bench

[joseph-isaacs]

Add filter bool benchmarks to later optimize

[codspeed-hq]

Merging this PR will not alter performance

✅ 1016 untouched benchmarks
🆕 109 new benchmarks
⏩ 1522 skipped benchmarks¹

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
🆕	Simulation	density_sweep_dense_runs[0.001]	N/A	1.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.02]	N/A	1.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.005]	N/A	1.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.5]	N/A	1.4 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.05]	N/A	1.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.95]	N/A	2.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.1]	N/A	1.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.9999]	N/A	328.5 µs	N/A
🆕	Simulation	density_sweep_dense_runs[0.999]	N/A	342.2 µs	N/A
🆕	Simulation	density_sweep_dense_runs[0.01]	N/A	1.1 ms	N/A
🆕	Simulation	density_sweep_dense_runs[0.99]	N/A	636.9 µs	N/A
🆕	Simulation	density_sweep_dense_runs[0.9]	N/A	3.7 ms	N/A
🆕	Simulation	density_sweep_random[0.001]	N/A	35.9 µs	N/A
🆕	Simulation	density_sweep_random[0.005]	N/A	50.4 µs	N/A
🆕	Simulation	density_sweep_random[0.01]	N/A	64.1 µs	N/A
🆕	Simulation	density_sweep_random[0.99]	N/A	655.9 µs	N/A
🆕	Simulation	density_sweep_random[0.02]	N/A	90.6 µs	N/A
🆕	Simulation	density_sweep_random[0.05]	N/A	171 µs	N/A
🆕	Simulation	density_sweep_random[0.95]	N/A	2 ms	N/A
🆕	Simulation	density_sweep_random[0.9999]	N/A	320.3 µs	N/A
...	...	...	...	...	...

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

---

_{Comparing ji/bool-filter-bench (f0ed8c4) with develop (cbc8ad1)}

Footnotes

1. 1522 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. ↩

[0ax1]

why not compute both in with inputs rather than calc true count upfront?

let true_count = make_density_mask(DENSITY_SWEEP_SIZE, density, &mut mask_rng()).true_count()

[0ax1]

shall we black box all bench inputs here, and elsewhere