Function safe_arch::fused_mul_sub_m128d

#[must_use]pub fn fused_mul_sub_m128d(a: m128d, b: m128d, c: m128d) -> m128d

This is supported with target feature fma only.

Lanewise fused (a * b) - c

let a = m128d::from_array([2.0, 3.0]);
let b = m128d::from_array([4.0, 5.0]);
let c = m128d::from_array([1.0, 1.0]);
let d = fused_mul_sub_m128d(a, b, c).to_array();
assert_eq!(d, [7.0, 14.0]);

• Intrinsic: _mm_fmsub_pd
• Assembly: one of
  • vfmsub132pd xmm, xmm, xmm
  • vfmsub213pd xmm, xmm, xmm
  • vfmsub231pd xmm, xmm, xmm