Resolve bitpacking functions once for bitwidth

[robert3005]

Instead of using unchecked_* variants of bitpacking functions resolve the functions once. Avoids finding the right generic function for given bitwidth on every call

[codspeed-hq]

Merging this PR will degrade performance by 14.44%

⚠️ 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

⚡ 1 improved benchmark
❌ 32 regressed benchmarks
✅ 2057 untouched benchmarks
⏩ 206 skipped benchmarks¹
🗄️ 4 archived benchmarks run²

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	WallTime	arrow_checked_add_u32_neon[16384]	13.5 µs	20.4 µs	-33.79%
❌	Simulation	decompress[datetime_for_bp]	220.1 µs	310 µs	-29.01%
❌	Simulation	new_bp_prim_test_between[i64, 2048]	90.2 µs	120 µs	-24.83%
❌	Simulation	new_alp_prim_test_between[f64, 2048]	107.1 µs	137.5 µs	-22.14%
❌	Simulation	decompress_rd[f64, (2000, 0.0)]	121.9 µs	152.6 µs	-20.13%
❌	Simulation	decompress_rd[f64, (2000, 0.1)]	121.9 µs	152.6 µs	-20.13%
❌	Simulation	decompress_rd[f64, (2000, 0.01)]	121.9 µs	152.6 µs	-20.09%
❌	Simulation	decompress[alp_for_bp_f64]	145 µs	177 µs	-18.08%
❌	WallTime	arrow_checked_add_u32_avx2[16384]	17.7 µs	21.4 µs	-17.34%
❌	Simulation	alp_rd_decompress_f64	169.6 µs	200.7 µs	-15.51%
❌	Simulation	new_bp_prim_test_between[i64, 16384]	170.8 µs	201.3 µs	-15.12%
❌	Simulation	new_alp_prim_test_between[f64, 16384]	193.9 µs	224.8 µs	-13.73%
❌	Simulation	compare[1]	206.8 µs	237.9 µs	-13.09%
❌	Simulation	compare[2]	212.3 µs	243.2 µs	-12.71%
❌	Simulation	compare[2]	215.8 µs	246.4 µs	-12.44%
❌	Simulation	compare[1]	210.8 µs	240.4 µs	-12.34%
❌	Simulation	compare[3]	219.7 µs	250.4 µs	-12.26%
❌	Simulation	compare[3]	223.1 µs	254 µs	-12.16%
❌	Simulation	compare[4]	225.5 µs	256.2 µs	-11.98%
❌	Simulation	compare[4]	228.7 µs	259.5 µs	-11.85%
...	...	...	...	...	...

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 claude/bitpacked-fastlanes-function-pointers-ckpnee (117a5ce) with develop (50cd6d7)}

Footnotes

1. 206 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. 4 benchmarks were run, but are now archived. If they were deleted in another branch, consider rebasing to remove them from the report. Instead if they were added back, click here to restore them. ↩