FrankNiemeyer

lea         rcx,[rcx-0Ch]  
lea         rax,[rax-4]  
vmovups     xmm0,xmmword ptr [rcx]  
vdpps       xmm0,xmm0,xmm0,71h  
vmovss      dword ptr [rax],xmm0  
sub         edx,1  
jne         benchmark<<lambda_d1ac89d5e59a169233af7a419374e043>,<lambda_c092a5680821d9f5b8bc5a7043f59100> >+0C0h (07FF7B83F2100h)  

FrankNiemeyer

void dot3_aos_vector_dp(const vector<Vec3f>& vs, vector<float>& dp) {
    // 0000 0000 0111 0001: mul lower three components, store sum in lowest component
    static const auto mask = 0x71;
    
    for (auto j = 0; j < reps; ++j) {
        const auto pvs = (float*)vs.data();
        auto pdp = (float*)dp.data();
        auto i = vector_len;
        while (i--) {
            // load 16 bytes (xyz|x)

FrankNiemeyer

lea         rax,[rax-0Ch]  
lea         rdx,[rdx-4]  
vmovss      xmm0,dword ptr [rax-8]  
vmovss      xmm2,dword ptr [rax-4]  
vmovss      xmm3,dword ptr [rax]  
vmulss      xmm1,xmm0,xmm0  
vmulss      xmm0,xmm2,xmm2  
vaddss      xmm2,xmm1,xmm0  
vmulss      xmm1,xmm3,xmm3  
vaddss      xmm2,xmm2,xmm1  

FrankNiemeyer

void dot3_aos_scalar(const vector<Vec3f>& vs, vector<float>& dp) {
    for (auto j = 0; j < reps; ++j) {
        auto i = vector_len;
        while (i--) {
            dp[i] = vs[i].x * vs[i].x + vs[i].y * vs[i].y + vs[i].z * vs[i].z;
        }
    }
}

FrankNiemeyer

lea         ebp,[r11+7]  
cmp         ebp,esi  
jae         00007FF98D06828A  
vmovupd     ymm0,ymmword ptr [rcx+r11*4+10h]  
cmp         ebp,edi  
jae         00007FF98D06828A  
vmovupd     ymm1,ymmword ptr [rdx+r11*4+10h]  
cmp         ebp,ebx  
jae         00007FF98D06828A  
vmovupd     ymm2,ymmword ptr [r8+r11*4+10h]  

FrankNiemeyer

static void Dot3SoaVectorized(float[] xs, float[] ys, float[] zs, float[] dp) {
    for (var j = 0; j < reps; ++j) {
        for (var i = 0; i < dp.Length; i += laneWidth) {
            var x = new Vector<float>(xs, i);
            var y = new Vector<float>(ys, i);
            var z = new Vector<float>(zs, i);
            var d = x * x + y * y + z * z;
            d.CopyTo(dp, i);
        }
    }

FrankNiemeyer

movsxd      rsi,r11d  
vmovss      xmm0,dword ptr [rcx+rsi*4+10h]  
vmulss      xmm0,xmm0,xmm0  
movsxd      rsi,r11d  
vmovss      xmm1,dword ptr [rdx+rsi*4+10h]  
vmulss      xmm1,xmm1,xmm1  
vaddss      xmm0,xmm0,xmm1  
movsxd      rsi,r11d  
vmovss      xmm1,dword ptr [r8+rsi*4+10h]  
vmulss      xmm1,xmm1,xmm1  

FrankNiemeyer

static void Dot3SoaScalar(float[] xs, float[] ys, float[] zs, float[] dp) {
    for (var j = 0; j < reps; ++j) {
        for (var i = 0; i < dp.Length; ++i) {
            dp[i] = xs[i] * xs[i] + ys[i] * ys[i] + zs[i] * zs[i];
        }
    }
}

FrankNiemeyer

xor         r9d,r9d  
mov         r10d,dword ptr [rbx+8]  
movsxd      r10,r10d  
cmp         r10,8  
setge       r10b  
movzx       r10d,r10b  
mov         r11d,dword ptr [rbp+8]  
movsxd      r11,r11d  
cmp         r11,8  
setge       r11b  

FrankNiemeyer

static void Dot3AosGather(Vector3[] vs, float[] dp) {
    var xtmp = new float[laneWidth];
    var ytmp = new float[laneWidth];
    var ztmp = new float[laneWidth];
    for (var j = 0; j < reps; ++j) {
        for (var i = 0; i < dp.Length; i += laneWidth) {
            for (var k = 0; k < laneWidth; ++k) {
                xtmp[k] = vs[i + k].X;
                ytmp[k] = vs[i + k].Y;
                ztmp[k] = vs[i + k].Z;