Skip to content

Support i128 and i256 decimals in DecimalByteParts encoding - #9834

Merged
mhk197 merged 5 commits into
developfrom
mk/dbp-v2-feature
Sep 18, 2026
Merged

Support i128 and i256 decimals in DecimalByteParts encoding #9834
mhk197 merged 5 commits into
developfrom
mk/dbp-v2-feature

Do not link the private lower-part limit from public docs

026bb26
Select commit
Loading
Failed to load commit list.
CodSpeed / CodSpeed Performance Analysis failed Sep 17, 2026 in 0s

2 benchmarks regressed

⚠️ 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

⚡ 5 improved benchmarks
❌ 2 regressed benchmarks
✅ 2240 untouched benchmarks
🆕 48 new benchmarks
⏩ 176 skipped benchmarks1
🗄️ 1 archived benchmark run2

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
❌ Simulation decode_primitives[f32, (1000, 512)] 42.2 µs 64.6 µs -34.67%
❌ WallTime words_gather_scalar_avx2[65536] 8.2 µs 9.3 µs -11.82%
⚡ WallTime arrow_checked_add_u32_neon[16384] 20.5 µs 12.9 µs +58.74%
⚡ WallTime filtered_sink_i64_avx2[OneNullInEight] 26.4 µs 22.2 µs +18.81%
⚡ Simulation allocate_drop_vortex_minimal_alignment[0] 1,077.2 ns 968.9 ns +11.18%
⚡ Simulation allocate_drop_vortex[0] 1.1 µs 1 µs +10.57%
⚡ Simulation allocate_drop_bytes[0] 581.3 ns 527.2 ns +10.27%
🆕 WallTime dbp_assemble_kernel_avx2[(I128, 1024)] N/A 552 ns N/A
🆕 WallTime dbp_assemble_kernel_avx2[(I128, 8192)] N/A 4.4 µs N/A
🆕 WallTime dbp_assemble_kernel_avx2[(I256, 1024)] N/A 1.1 µs N/A
🆕 WallTime dbp_assemble_kernel_avx2[(I256, 8192)] N/A 8.6 µs N/A
🆕 WallTime dbp_assemble_kernel_narrow_msp_avx2[(I128, 1024)] N/A 612 ns N/A
🆕 WallTime dbp_assemble_kernel_narrow_msp_avx2[(I128, 8192)] N/A 4.9 µs N/A
🆕 WallTime dbp_assemble_kernel_narrow_msp_avx2[(I256, 1024)] N/A 1.2 µs N/A
🆕 WallTime dbp_assemble_kernel_narrow_msp_avx2[(I256, 8192)] N/A 9.1 µs N/A
🆕 WallTime dbp_split_kernel_all_valid_avx2[(I128, 1024)] N/A 897 ns N/A
🆕 WallTime dbp_split_kernel_all_valid_avx2[(I128, 8192)] N/A 6.6 µs N/A
🆕 WallTime dbp_split_kernel_all_valid_avx2[(I256, 1024)] N/A 2.1 µs N/A
🆕 WallTime dbp_split_kernel_all_valid_avx2[(I256, 8192)] N/A 54.2 µs N/A
🆕 WallTime dbp_split_kernel_mixed_null_avx2[(I128, 1024)] N/A 1.2 µs N/A
... ... ... ... ... ...

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 mk/dbp-v2-feature (026bb26) with develop (ae00d7a)

Open in CodSpeed

Footnotes

  1. 176 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. 1 benchmark was run, but is now archived. If it was deleted in another branch, consider rebasing to remove it from the report. Instead if it was added back, click here to restore it. ↩

View more details on CodSpeed