So I spent a fair amount of time yesterday and this morning trying to get around the fact that it appeared that I needed to do a lot of data shuffling to multiply two 4x4 matricies using SIMD instructions. I didn't want to accept that because shuffling data around is a waste of time to me unless it absolutely HAS to be done, so I looked up some things on Intel's web site and I was right unfortunately. I have to do a ridiculous amount of data shuffling, OMG its horrible, so ugly it makes me want to [bawling]. Oh well it HAS to be done so I'll have to live with it.

Here is the unedited Intel code:

multiply_4x4_matrix: ;multiplies two 4 x 4 matricies

mov edx, dword ptr [esp+4] ; src1
mov eax, dword ptr [esp+0Ch] ; dst
mov ecx, dword ptr [esp+8] ; src2
movss xmm0, dword ptr [edx]
movaps xmm1, xmmword ptr [ecx]
shufps xmm0, xmm0, 0
movss xmm2, dword ptr [edx+4]
mulps xmm0, xmm1
shufps xmm2, xmm2, 0
movaps xmm3, xmmword ptr [ecx+10h]
movss xmm7, dword ptr [edx+8]
mulps xmm2, xmm3
shufps xmm7, xmm7, 0
addps xmm0, xmm2
movaps xmm4, xmmword ptr [ecx+20h]
movss xmm2, dword ptr [edx+0Ch]
mulps xmm7, xmm4
shufps xmm2, xmm2, 0
addps xmm0, xmm7
movaps xmm5, xmmword ptr [ecx+30h]
movss xmm6, dword ptr [edx+10h]
mulps xmm2, xmm5
movss xmm7, dword ptr [edx+14h]
shufps xmm6, xmm6, 0
addps xmm0, xmm2
shufps xmm7, xmm7, 0
movlps qword ptr [eax], xmm0
movhps qword ptr [eax+8], xmm0
mulps xmm7, xmm3
movss xmm0, dword ptr [edx+18h]
mulps xmm6, xmm1
shufps xmm0, xmm0, 0
addps xmm6, xmm7
mulps xmm0, xmm4
movss xmm2, dword ptr [edx+24h]
addps xmm6, xmm0
movss xmm0, dword ptr [edx+1Ch]
movss xmm7, dword ptr [edx+20h]
shufps xmm0, xmm0, 0
shufps xmm7, xmm7, 0
mulps xmm0, xmm5
mulps xmm7, xmm1
addps xmm6, xmm0
shufps xmm2, xmm2, 0
movlps qword ptr [eax+10h], xmm6
movhps qword ptr [eax+18h], xmm6
mulps xmm2, xmm3
movss xmm6, dword ptr [edx+28h]
addps xmm7, xmm2
shufps xmm6, xmm6, 0
movss xmm2, dword ptr [edx+2Ch]
mulps xmm6, xmm4
shufps xmm2, xmm2, 0
addps xmm7, xmm6
mulps xmm2, xmm5
movss xmm0, dword ptr [edx+34h]
addps xmm7, xmm2
shufps xmm0, xmm0, 0
movlps qword ptr [eax+20h], xmm7
movss xmm2, dword ptr [edx+30h]
movhps qword ptr [eax+28h], xmm7
mulps xmm0, xmm3
shufps xmm2, xmm2, 0
movss xmm6, dword ptr [edx+38h]
mulps xmm2, xmm1
shufps xmm6, xmm6, 0
addps xmm2, xmm0
mulps xmm6, xmm4
movss xmm7, dword ptr [edx+3Ch]
shufps xmm7, xmm7, 0
addps xmm2, xmm6
mulps xmm7, xmm5
addps xmm2, xmm7
movaps xmmword ptr [eax+30h], xmm2