Add BlockedFoR encoding backed by BitPackedV2

[joseph-isaacs]

Summary

• add BlockedFoR with one frame-of-reference base per 1,024 values
• encode BlockedFoR residuals with BitPackedV2
• allow BlockedFoR to subsume global FoR while retaining a fallback
• register the encoding in a draft core edition
• route benchmark writers through explicit write options so BlockedFoR can be opted into

Stack

This PR is intentionally based on ji/bitpacked-v2-patches. Its delta contains no PatchesV2 or FloatQuantV2 implementation changes.

Validation

• cargo +nightly fmt --all -- --check
• cargo check -p vortex-btrblocks
• cargo check -p vortex-btrblocks --features unstable_encodings
• cargo check -p vortex-bench --features unstable_encodings
• cargo test -p vortex-btrblocks --features unstable_encodings test_blocked_for
• cargo clippy -p vortex-btrblocks -p vortex-bench --all-targets --features unstable_encodings -- -D warnings

The focused test verifies that the residual child selected by BlockedFoR is actually BitPackedV2.

Compression note

In the controlled TPC-H SF10 ablation on the earlier combined branch, BlockedFoR produced 2,416,147,124 bytes versus 2,415,156,692 bytes with global FoR: +990,432 bytes (+0.041%). This draft therefore does not claim an SF10 compression saving; it is separated so its workload trade-offs can be reviewed and benchmarked independently.

[codspeed-hq]

Merging this PR will degrade performance by 0.22%

⚠️ 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
❌ 1 regressed benchmark
✅ 2137 untouched benchmarks
⏩ 106 skipped benchmarks¹
🗄️ 4 archived benchmarks run²

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	Simulation	compress_fsst[(500, 64, 8)]	481.1 µs	537.8 µs	-10.56%
⚡	WallTime	mul_u32_nonnull_avx512	6.3 µs	5.7 µs	+11.32%

Tip

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

---

_{Comparing ji/blocked-for-v2-stack (ada4bbf) with develop (ba90f3d)³}

Footnotes

1. 106 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. ↩

3. No successful run was found on ji/bitpacked-v2-patches (f4d3659) during the generation of this report, so develop (ba90f3d) was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩