Add TakeSlices for fixed-size-list take by danking · Pull Request #8674 · vortex-data/vortex

1 benchmark regressed

⚡ 3 improved benchmarks
❌ 1 regressed benchmark
✅ 1636 untouched benchmarks
🆕 76 new benchmarks
⏩ 67 skipped benchmarks¹

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
❌	Simulation	`varbinview_large`	389.3 µs	439.1 µs	-11.35%
⚡	Simulation	`list_i32_large`	213.8 µs	162.4 µs	+31.65%
⚡	Simulation	`struct_large`	431.3 µs	344 µs	+25.36%
⚡	Simulation	`i32_large`	278.7 µs	229.4 µs	+21.49%
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[1, 10]`	N/A	19.2 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[1024, 10]`	N/A	34.6 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[128, 10]`	N/A	17.3 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[16, 10]`	N/A	14.6 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[2, 10]`	N/A	14.6 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[2048, 10]`	N/A	54 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[256, 10]`	N/A	19.9 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[4, 10]`	N/A	14.3 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[4096, 10]`	N/A	93.2 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[512, 10]`	N/A	24.7 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[64, 10]`	N/A	16.1 µs	N/A
🆕	Simulation	`take_fsl_f16_force_manual_range_copy[8, 10]`	N/A	14.2 µs	N/A
🆕	Simulation	`take_fsl_f16_force_per_index[1, 10]`	N/A	27.9 µs	N/A
🆕	Simulation	`take_fsl_f16_force_per_index[1024, 10]`	N/A	148.7 µs	N/A
🆕	Simulation	`take_fsl_f16_force_per_index[128, 10]`	N/A	41.1 µs	N/A
🆕	Simulation	`take_fsl_f16_force_per_index[16, 10]`	N/A	29 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 codex/take-slices-fsl (a95022a) with develop (cdaa5a5)}

67 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. ↩