`RowFn` framework and machinery by connortsui20 · Pull Request #9319 · vortex-data/vortex

Performance Gate Passed

⚡ 1 improved benchmark
✅ 1958 untouched benchmarks
🆕 16 new benchmarks
⏩ 89 skipped benchmarks¹

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
⚡	Simulation	`decode_varbin[(1000, 2)]`	78.5 µs	61.9 µs	+26.84%
🆕	Simulation	`handrolled_sink_wrapping_add`	N/A	1.7 ms	N/A
🆕	Simulation	`row_checked_add`	N/A	2.1 ms	N/A
🆕	Simulation	`row_checked_add_constant`	N/A	1.6 ms	N/A
🆕	Simulation	`row_checked_add_nullable`	N/A	2.1 ms	N/A
🆕	Simulation	`row_sink_wrapping_add`	N/A	2.8 ms	N/A
🆕	Simulation	`row_wrapping_add`	N/A	1.8 ms	N/A
🆕	Simulation	`row_wrapping_add_constant`	N/A	1.2 ms	N/A
🆕	Simulation	`row_wrapping_add_nullable`	N/A	1.8 ms	N/A
🆕	Simulation	`eager_chain[1048576]`	N/A	25.2 ms	N/A
🆕	Simulation	`eager_chain[65536]`	N/A	1.9 ms	N/A
🆕	Simulation	`eager[1048576]`	N/A	9.3 ms	N/A
🆕	Simulation	`eager[65536]`	N/A	659.4 µs	N/A
🆕	Simulation	`lazy_chain[1048576]`	N/A	20.5 ms	N/A
🆕	Simulation	`lazy_chain[65536]`	N/A	1.3 ms	N/A
🆕	Simulation	`lazy[1048576]`	N/A	9.2 ms	N/A
🆕	Simulation	`lazy[65536]`	N/A	648.7 µs	N/A

Tip

Curious why this is faster? Comment @codspeedbot explain why this is faster on this PR, or directly use the CodSpeed MCP with your agent.

_{Comparing ct/row-fn-api (f759998) with develop (ff0a26d)}

89 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. ↩