feat: select bitpacked widths independently per chunk

[mhk197]

Choose a cost-model width for each 1024-value chunk, accounting for padded packed bytes and exceptions. Add the per-chunk encoder with separate planning, packing, and patch-gathering passes, plus kernel, nullable/signed, and conformance coverage. The existing BtrBlocks scheme continues to use its global-width encoder.

Part 7/9 of the bitpacked-v2 stack (435 added + removed lines). Merge in order; each draft targets the preceding branch, starting from develop.

1 → 2 → 3 → 4 → 5 → 6 → 7 → 8 → 9

Validation: All 48 focused plugin, serde, and chunk-layout tests passed on this commit, including the regression that rejects direct vtable serde. Changed Rust files were formatted with nightly; git diff --check passed.

[codspeed]

Merging this PR will regress 4 benchmarks

⚠️ 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

⚡ 4 improved benchmarks
❌ 4 regressed benchmarks
✅ 2245 untouched benchmarks
⏩ 218 skipped benchmarks¹

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	Simulation	random_i16[0.8]	79.4 µs	97.8 µs	-18.81%
❌	Simulation	allocate_drop_bytes[0]	527.2 ns	635.5 ns	-17.05%
❌	WallTime	dbp_assemble_kernel_avx2[(I256, 8192)]	8.2 µs	9.9 µs	-17.01%
❌	WallTime	dbp_split_kernel_all_valid_neon[(I256, 1024)]	1.3 µs	1.5 µs	-16.25%
⚡	WallTime	arrow_checked_add_u32_neon[16384]	20.3 µs	12.2 µs	+66.38%
⚡	Simulation	random_i8[0.5]	96 µs	72.4 µs	+32.64%
⚡	WallTime	filtered_sink_i64_avx2[OneNullInEight]	26.1 µs	22.6 µs	+15.28%
⚡	WallTime	dbp_split_kernel_mixed_null_neon[(I256, 1024)]	2.2 µs	1.9 µs	+13.62%

Tip

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

---

_{Comparing mk/bitpacked-stack-07-width-selection (3e5dc30) with mk/bitpacked-stack-06-v2-wire (db2c61b)}

Footnotes

1. 218 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. ↩