[dist-epoch]

Because you are working in the cache.

Also, you should use SIMD.

[lacedeconstruct]

> Also, you should use SIMD. ironically no clang is better at auto vectorizing

[spider-mario]

Better than what? And do you use `-mavx2` or do you let it target baseline x86_64 and miss out on 8-float vectors? How do you make sure its autovectorisation is successful?