Add portable_simd support

[farnoy]

Fixes #33

Does not have acceleration for trigonometric functions due to https://github.com/rust-lang/portable-simd/issues/6

Follows the packed_simd implementation closely, but masks are called mask<$elt>x<$lanes> not m<$elt>x<$lanes>

Has a few more things than packed_simd like native recip, floor, ceil, trunc, but crucially it's missing trigonometry accelration.