Array VTables Follow Up #7276

Performance Regression: -21.81%

⚡ 2 improved benchmarks
❌ 9 regressed benchmarks
✅ 1111 untouched benchmarks
⏩ 1530 skipped benchmarks¹

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
❌	Simulation	`new_alp_prim_test_between[f64, 2048]`	64 µs	75.6 µs	-15.34%
❌	Simulation	`new_bp_prim_test_between[i64, 2048]`	54.7 µs	64.9 µs	-15.74%
⚡	Simulation	`new_bp_prim_test_between[i64, 32768]`	231.5 µs	179.8 µs	+28.75%
❌	Simulation	`new_bp_prim_test_between[i64, 16384]`	109.6 µs	140.1 µs	-21.81%
❌	Simulation	`new_bp_prim_test_between[i32, 32768]`	138.8 µs	158.7 µs	-12.53%
❌	Simulation	`new_bp_prim_test_between[i32, 16384]`	93.1 µs	104.7 µs	-11.03%
❌	Simulation	`take_10k_random`	192 µs	240 µs	-20%
⚡	Simulation	`patched_take_10k_first_chunk_only`	329.4 µs	274.1 µs	+20.17%
❌	Simulation	`take_10k_contiguous`	269.8 µs	316.5 µs	-14.73%
❌	Simulation	`decompress_rd[f32, (10000, 0.1)]`	82.5 µs	93.2 µs	-11.39%
❌	Simulation	`decompress_rd[f32, (10000, 0.01)]`	82.3 µs	93.2 µs	-11.62%

_{Comparing ngates/vtable-cleanup (7c578bf) with develop (a8351a9)}

1530 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. ↩