Faster true count using AVX2 and AVX512 instructions #6931

Performance Regression: -50.39%

⚡ 8 improved benchmarks
❌ 2 regressed benchmarks
✅ 999 untouched benchmarks
⏩ 1515 skipped benchmarks¹

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

	Mode	Benchmark	`BASE`	`HEAD`	Efficiency
⚡	Simulation	`null_count_run_end[(100000, 1024, 0.5)]`	65.1 µs	57.5 µs	+13.21%
⚡	Simulation	`null_count_run_end[(100000, 256, 0.01)]`	72 µs	64.3 µs	+12.03%
⚡	Simulation	`null_count_run_end[(100000, 1024, 0.1)]`	64.7 µs	57.1 µs	+13.3%
⚡	Simulation	`null_count_run_end[(100000, 256, 0.5)]`	74.4 µs	66.7 µs	+11.57%
⚡	Simulation	`null_count_run_end[(100000, 256, 0.1)]`	72.3 µs	64.6 µs	+11.98%
⚡	Simulation	`true_count_vortex_buffer[128]`	955.6 ns	597.5 ns	+59.93%
❌	Simulation	`true_count_vortex_buffer[2048]`	1.2 µs	1.4 µs	-12.92%
⚡	Simulation	`true_count_vortex_buffer[65536]`	11.7 µs	6.7 µs	+74.02%
❌	Simulation	`true_count_vortex_buffer[1024]`	1 µs	2.1 µs	-50.39%
⚡	Simulation	`true_count_vortex_buffer[16384]`	3.6 µs	2.6 µs	+39.45%

_{Comparing rk/truecount (8720068) with develop (b825593)}

1515 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. ↩