mov eax, 6
movd xmm5, eax
pshufd xmm5, xmm5, 0
cvtpi2ps xmm5, xmm5     ;xmm5 == 6.0
mov eax, 15
movd xmm6, eax
pshufd xmm6, xmm6, 0
cvtpi2ps xmm6, xmm6     ;xmm6 == 15.0
mov eax, 10
movd xmm7, eax
pshufd xmm7, xmm7, 0
cvtpi2ps xmm7, xmm7     ;xmm7 == 10.0

lea ecx, [result]
mov eax, dword [sx]
mul dword [sy]
loop_top:
    movaps xmm1, qword [x + ecx]

    movaps xmm2, xmm1 ;start out with t
    mulps xmm2, xmm5  ;multiply by 6
    subps xmm2, xmm6  ;subtract 15
    mulps xmm2, xmm1  ;multiply by t
    addps xmm2, xmm7  ;add 10
    mulps xmm2, xmm1
    mulps xmm2, xmm1
    mulps xmm2, xmm1  ;multiply by t^3

    movaps xmm0, qword [x0y0 + ecx]
    movaps xmm1, qword [x1y0 + ecx]
    subps xmm1, xmm0
    mulps xmm1, xmm2
    addps xmm0, xmm1     ;xmm0 = u

    movaps xmm4, qword [x0y1 + ecx]
    movaps xmm1, qword [x1y1 + ecx]
    subps xmm1, xmm4
    mulps xmm1, xmm2
    addps xmm4, xmm1     ;xmm4 = v

    movaps xmm1, qword [y + ecx]

    movaps xmm2, xmm1
    mulps xmm2, xmm5
    subps xmm2, xmm6
    mulps xmm2, xmm1
    addps xmm2, xmm7
    mulps xmm2, xmm1
    mulps xmm2, xmm1
    mulps xmm2, xmm1  ;xmm2 = ty
    subps xmm4, xmm0
    mulps xmm4, xmm2
    addps xmm0, xmm4

    movaps qword [result + ecx], xmm0
    add ecx, 10h
dec eax
jne loop_top