arch:: x86:: _mm_fmaddsub_pd
pub unsafe fn _mm_fmaddsub_pd(a: __m128d, b: __m128d, c: __m128d) -> __m128d
This is supported on x86 and target feature
Multiplies packed double-precision (64-bit) floating-point elements in
b, and alternatively add and subtract packed elements in
the intermediate result.