Reduce vortex-fastlanes debug symbols by halving unchecked_unpack_cmp monomorphization

[AdamGS]

Summary

vortex-fastlanes is currently a pretty big crate, due to its underlying structure/generics.

When running cargo clean; cargo build -p vortex-fastlanes

Currently on `develop:

• vortex-fastlanes dev build with debug: 229MB rlib 105s
• vortex-fastlanes dev build no debug: 119MB rlib 57s

We currently disable debug symbols for it to improve our development experience, but underlying crates can't enjoy that without explicitly adding the same or similar configuration.

With this branch, the build takes 50s and generates a 133MB rlib, with no performance impact for release builds.
For a release build, this change saves about 2.5MB (out of 7.4MB).

[codspeed-hq]

Merging this PR will not alter performance

⚠️ 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.

⚡ 9 improved benchmarks
❌ 7 regressed benchmarks
✅ 1565 untouched benchmarks

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	Simulation	decompress_rd[f64, (10000, 0.01)]	108.7 µs	139.1 µs	-21.86%
❌	Simulation	decompress_rd[f64, (10000, 0.1)]	109 µs	139.4 µs	-21.82%
❌	Simulation	decompress_rd[f64, (10000, 0.0)]	108.7 µs	139 µs	-21.79%
❌	Simulation	decompress_rd[f32, (100000, 0.0)]	496 µs	583.7 µs	-15.04%
❌	Simulation	decompress_rd[f32, (10000, 0.1)]	78.1 µs	91.2 µs	-14.38%
❌	Simulation	decompress_rd[f32, (10000, 0.01)]	78.1 µs	90.9 µs	-14.14%
❌	Simulation	decompress_rd[f32, (10000, 0.0)]	78.5 µs	91.1 µs	-13.82%
⚡	Simulation	bitwise_not_vortex_buffer_mut[128]	244.4 ns	186.1 ns	+31.34%
⚡	Simulation	bitwise_not_vortex_buffer_mut[1024]	304.7 ns	246.4 ns	+23.68%
⚡	Simulation	take_10k_random	241.1 µs	196 µs	+23.02%
⚡	Simulation	chunked_varbinview_opt_canonical_into[(1000, 10)]	206.8 µs	170.2 µs	+21.45%
⚡	Simulation	take_10k_contiguous	261.7 µs	216.8 µs	+20.75%
⚡	Simulation	bitwise_not_vortex_buffer_mut[2048]	427.8 ns	369.4 ns	+15.79%
⚡	Simulation	patched_take_10k_contiguous_patches	260.6 µs	230.2 µs	+13.24%
⚡	Simulation	chunked_varbinview_into_canonical[(100, 100)]	307.1 µs	272.5 µs	+12.71%
⚡	Simulation	patched_take_10k_random	273.1 µs	242.6 µs	+12.55%

Tip

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

---

_{Comparing adamg/cmp-experiment (ff7d356) with develop (5d55fbc)}