add bp with patches benchmark

[a10y]

We have a benchmark for unpatched bitpacking but I wanted a baseline as I'm refining #6708

[a10y]

Results on A100

Benchmarking bitunpack_cuda_patched_u8/bitunpack_patched/0.1%: Collecting 10 samples in estimated 5.5364 s
bitunpack_cuda_patched_u8/bitunpack_patched/0.1%
                        time:   [419.09 µs 419.24 µs 419.47 µs]
                        thrpt:  [222.03 GiB/s 222.14 GiB/s 222.22 GiB/s]
Found 2 outliers among 10 measurements (20.00%)
  1 (10.00%) low mild
  1 (10.00%) high severe
Benchmarking bitunpack_cuda_patched_u8/bitunpack_patched/1%: Collecting 10 samples in estimated 5.1481 s (3
bitunpack_cuda_patched_u8/bitunpack_patched/1%
                        time:   [746.30 µs 746.73 µs 747.27 µs]
                        thrpt:  [124.63 GiB/s 124.72 GiB/s 124.79 GiB/s]
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) high mild
Benchmarking bitunpack_cuda_patched_u8/bitunpack_patched/5%: Collecting 10 samples in estimated 5.9989 s (3
bitunpack_cuda_patched_u8/bitunpack_patched/5%
                        time:   [1.5585 ms 1.5594 ms 1.5604 ms]
                        thrpt:  [59.683 GiB/s 59.725 GiB/s 59.758 GiB/s]
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) high mild
Benchmarking bitunpack_cuda_patched_u8/bitunpack_patched/10%: Collecting 10 samples in estimated 5.8198 s (
bitunpack_cuda_patched_u8/bitunpack_patched/10%
                        time:   [2.0051 ms 2.0056 ms 2.0061 ms]
                        thrpt:  [46.424 GiB/s 46.435 GiB/s 46.447 GiB/s]
Found 2 outliers among 10 measurements (20.00%)

[codspeed-hq]

Merging this PR will improve performance by 17.64%

⚡ 1 improved benchmark
✅ 953 untouched benchmarks
⏩ 1466 skipped benchmarks¹

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
⚡	Simulation	chunked_opt_bool_canonical_into[(10, 1000)]	1.6 ms	1.4 ms	+17.64%

---

_{Comparing aduffy/bp-patches-ench (047280c) with develop (fc3af37)}

Footnotes

1. 1466 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. ↩