Fast round

[NamorNiradnug]

.round() function is very slow compared to platform-native intrinsic on AVX (https://godbolt.org/z/3sdd9jrvW) because it provides a platform-agnostic behavior. Although there are many use cases when the exact behavior on half-way values or INFs and NaNs doesn't matter.

I think adding somewhat like round_fast function is reasonable.

[programmerjake]

what you want is usually round_ties_even (not yet available on Simd), since that usually compiles to a single instruction

e.g.: https://godbolt.org/z/Tb8xvzqo7

[NamorNiradnug]

what you want is usually round_ties_even (not yet available on Simd), since that usually compiles to a single instruction

Yet still there are maybe platforms where it's not the case. Or may be such an instruction is slower than another rounding instruction.

Although at least NEON, AVX and SSE all have round_ties_even instructions.

[NamorNiradnug]

e.g.: https://godbolt.org/z/Tb8xvzqo7

Thanks for a workaround!