feat[array]: move over to a expr based cast #6404

Performance Regression: -12.54%

⚡ 19 improved benchmarks
❌ 2 regressed benchmarks
✅ 1114 untouched benchmarks
⏩ 1268 skipped benchmarks¹

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

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
⚡	Simulation	`decode_varbinview[(1000, 2)]`	37.7 µs	33.9 µs	+11.27%
⚡	Simulation	`take_200k_first_chunk_only`	4.2 ms	3.3 ms	+26.41%
⚡	Simulation	`take_200k_dispersed`	4.5 ms	3.6 ms	+24.38%
⚡	Simulation	`pushdown_compare[(1000, 64, 4)]`	443.8 µs	354.1 µs	+25.32%
⚡	Simulation	`pushdown_compare[(1000, 16, 4)]`	444.2 µs	354 µs	+25.45%
⚡	Simulation	`pushdown_compare[(1000, 4, 8)]`	445.6 µs	356.2 µs	+25.08%
⚡	Simulation	`pushdown_compare[(1000, 64, 8)]`	455.4 µs	366.2 µs	+24.37%
⚡	Simulation	`pushdown_compare[(1000, 16, 8)]`	466.4 µs	377.8 µs	+23.44%
⚡	Simulation	`pushdown_compare[(1000, 4, 4)]`	443.5 µs	353.8 µs	+25.37%
⚡	Simulation	`pushdown_compare[(10000, 4, 8)]`	614 µs	525.6 µs	+16.81%
⚡	Simulation	`pushdown_compare[(10000, 16, 4)]`	606.3 µs	516.2 µs	+17.44%
⚡	Simulation	`pushdown_compare[(10000, 64, 4)]`	604.6 µs	515.9 µs	+17.2%
⚡	Simulation	`pushdown_compare[(10000, 64, 8)]`	615.9 µs	527.4 µs	+16.77%
⚡	Simulation	`pushdown_compare[(10000, 16, 8)]`	653.8 µs	565.1 µs	+15.7%
⚡	Simulation	`pushdown_compare[(10000, 4, 4)]`	605.2 µs	515.8 µs	+17.33%
⚡	Simulation	`old_bp_prim_test_between[i16, 2048]`	163.3 µs	147.1 µs	+11.01%
⚡	Simulation	`new_bp_prim_test_between[i16, 32768]`	125.2 µs	113.2 µs	+10.69%
⚡	Simulation	`old_bp_prim_test_between[i32, 2048]`	163 µs	146 µs	+11.63%
⚡	Simulation	`old_bp_prim_test_between[i64, 2048]`	172.3 µs	156.4 µs	+10.15%
❌	Simulation	`compress[(1000, 256)]`	53.2 µs	60.8 µs	-12.54%
...	...	...	...	...	...

ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.

_{Comparing ji/remove-cast-compute (2b99941) with develop (c7f9549)}

1268 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. ↩