Luna::Simd::add_f4

float4 add_f4(float4 a, float4 b)

Adds packed single-precision (32-bit) floating-point elements in a and b, and stores the results in dst.

dst.x = a.x + b.x
dst.y = a.y + b.y
dst.z = a.z + b.z
dst.w = a.w + b.w