FrankNiemeyer

lea         rax,[rax-20h]  
vmovups     ymm0,ymmword ptr [rbx+rax]  
vmovups     ymm2,ymmword ptr [rax]  
vmovups     ymm3,ymmword ptr [rdi+rax]  
vmulps      ymm0,ymm0,ymm0  
vfmadd231ps ymm0,ymm2,ymm2  
vfmadd231ps ymm0,ymm3,ymm3  
vmovups     ymmword ptr [rsi+rax],ymm0  
sub         r11d,1  
jne         dot3_soa_vectorized+52h (07FF7DF9913D2h) 

FrankNiemeyer

void dot3_soa_vectorized_fma(const vector<float>& xs, const vector<float>& ys, const vector<float>& zs, vector<float>& dp) {
    for (auto j = 0; j < reps; ++j) {
        const auto px = (__m256*)xs.data();
        const auto py = (__m256*)ys.data();
        const auto pz = (__m256*)zs.data();
        auto pd = (__m256*)dp.data();
        auto i = vector_len / lane_width;
        while (i--) {
            pd[i] = _mm256_fmadd_ps(pz[i], pz[i], _mm256_fmadd_ps(py[i], py[i], _mm256_mul_ps(px[i], px[i])));
        }

FrankNiemeyer

lea         rax,[rax-20h]  
vmovups     ymm0,ymmword ptr [rbx+rax]  
vmovups     ymm2,ymmword ptr [rax]  
vmovups     ymm3,ymmword ptr [rdi+rax]  
vmulps      ymm1,ymm0,ymm0  
vmulps      ymm0,ymm2,ymm2  
vaddps      ymm2,ymm1,ymm0  
vmulps      ymm1,ymm3,ymm3  
vaddps      ymm2,ymm2,ymm1  
vmovups     ymmword ptr [rsi+rax],ymm2  

FrankNiemeyer

void dot3_soa_vectorized(const vector<float>& xs, const vector<float>& ys, const vector<float>& zs, vector<float>& dp) {
    for (auto j = 0; j < reps; ++j) {
        const auto px = (__m256*)xs.data();
        const auto py = (__m256*)ys.data();
        const auto pz = (__m256*)zs.data();
        auto pd = (__m256*)dp.data();
        auto i = vector_len / lane_width;
        while (i--) {
            pd[i] = _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(px[i], px[i]), _mm256_mul_ps(py[i], py[i])), _mm256_mul_ps(pz[i], pz[i]));
        }

FrankNiemeyer

lea         rax,[rcx+rbx]  
vmovups     ymm2,ymmword ptr [r10+rcx]  
vmovups     ymm3,ymmword ptr [rcx]  
vmovups     ymm0,ymmword ptr [r11+rcx]  
lea         rcx,[rcx+20h]  
vmulps      ymm1,ymm2,ymm2  
vfmadd231ps ymm1,ymm3,ymm3  
vfmadd231ps ymm1,ymm0,ymm0  
vmovups     ymmword ptr [rax+r8],ymm1  
sub         r9,1  

FrankNiemeyer

void dot3_soa_autovec(const vector<float>& xs, const vector<float>& ys, const vector<float>& zs, vector<float>& dp) {
    for (auto j = 0; j < reps; ++j) {
        for (auto i = 0; i < vector_len; ++i) {
            dp[i] = xs[i] * xs[i] + ys[i] * ys[i] + zs[i] * zs[i];
        }
    }
}

FrankNiemeyer

lea         rax,[rax-4]  
vmovss      xmm0,dword ptr [rax]  
vmovss      xmm2,dword ptr [rdx+rax]  
vmovss      xmm3,dword ptr [r8+rax]  
vmulss      xmm1,xmm0,xmm0  
vmulss      xmm0,xmm2,xmm2  
vaddss      xmm2,xmm1,xmm0  
vmulss      xmm1,xmm3,xmm3  
vaddss      xmm2,xmm2,xmm1  
vmovss      dword ptr [r9+rax],xmm2  

FrankNiemeyer

void dot3_soa_scalar(const vector<float>& xs, const vector<float>& ys, const vector<float>& zs, vector<float>& dp) {
    for (auto j = 0; j < reps; ++j) {
        auto i = vector_len;
        while(i--) {
            dp[i] = xs[i] * xs[i] + ys[i] * ys[i] + zs[i] * zs[i];
        }
    }
}

FrankNiemeyer

lea         rax,[rax-60h]  
lea         r8,[r8-20h]  
vpcmpeqb    ymm2,ymm2,ymm2  
vmovups     ymm5,ymm0  
vgatherdps  ymm5,dword ptr [rax+ymm6*4],ymm2  
vpcmpeqb    ymm2,ymm2,ymm2  
vmovups     ymm4,ymm0  
vgatherdps  ymm4,dword ptr [rax+ymm7*4],ymm2  
vpcmpeqb    ymm2,ymm2,ymm2  
vmovups     ymm1,ymm0  

FrankNiemeyer

void dot3_aos_vector_gather(const vector<Vec3f>& vs, vector<float>& dp) {
    static const auto epi32_one = _mm256_set1_epi32(1);
    static const auto x_offsets = _mm256_setr_epi32(0, 3, 6, 9, 12, 15, 18, 21);
    static const auto y_offsets = _mm256_add_epi32(x_offsets, epi32_one);
    static const auto z_offsets = _mm256_add_epi32(y_offsets, epi32_one);

    for (auto j = 0; j < reps; ++j) {
        const auto pvs = (float*)vs.data();
        auto pdp = (__m256*)dp.data();
        auto i = vector_len / lane_width;