SIMD float subtraction

simd.c

#include <array>
#include <xmmintrin.h>

int main()
{
    alignas(32) std::array<float, 8> A = {1, 2, 3, 4, 5, 6, 7, 8};
    alignas(32) std::array<float, 8> B = {10, 11, 12, 13, 14, 15, 16, 0.0f};
    alignas(32) std::array<float, 8> C;

    const __m256 A_vec = _mm256_load_ps(A.data());
    const __m256 B_vec = _mm256_load_ps(B.data());
    const __m256 Sub = _mm256_sub_ps(A_vec, B_vec);
    _mm256_store_ps(C.data(), Sub);
}