NiallHornFX

// Scalar Trilinear Interoplation Lambda using SSE. 
auto trilerp_v = [&](int i0, int j0, int k0, float z, float y, float x) -> auto
{

	vec4 aa(this->getdata(i0, j0, k0), this->getdata(i0, j0 + 1, k0), this->getdata(i0 + 1, j0, k0), this->getdata(i0 + 1, j0 + 1, k0));
	vec4 bb(this->getdata(i0, j0, k0 + 1), this->getdata(i0, j0 + 1, k0 + 1), this->getdata(i0 + 1, j0, k0 + 1), this->getdata(i0 + 1, j0 + 1, k0 + 1));
	vec4 coeff_z(z); vec4 ccoeff_z(1.0f - z);
	__m128 L_a = _mm_fmadd_ps(ccoeff_z.sa, aa.sa, _mm_mul_ps(coeff_z.sa, bb.sa));

	__m128 cc = _mm_shuffle_ps(L_a, L_a, _MM_SHUFFLE(1, 0, 1, 0));  // (z0,z1,|z0,z1)

NiallHornFX

	
	// SSE Cross Product Test Implementations Test - 
	temp_vec3<float> a(1.0f, 2.0f, 3.0f); temp_vec3<float> b(4.0f, 5.0f, 6.0f);

	for (std::size_t j = 0; j < 5; ++j)
	{
		std::cout << "\nITER = " << j << "\n";
		// Version A) \\

		auto start = std::chrono::system_clock::now();