Issues using the in-line assembler

[solidstate1991]

Seems I found a better solution hidden in the docs:

@nogc protected int[2] transformFunc(int[2] xy){
version(X86){
asm @nogc{
	naked;
	mov			EBX, this;
	movd		XMM1, sX[EBX];
	pslldq		XMM1, 4;
	movss		XMM1, sY[EBX];
	movq		XMM0, xy;
	paddd		XMM0, XMM1;	// [x,y] + [sX,sY]
	movq		XMM3, xy0[EBX];
	psubd		XMM0, XMM3;	// ([x,y] + [sX,sY] - [x_0,y_0])
	movq		XMM1, ac[EBX];
	movq		XMM2, bd[EBX];
	pmuludq		XMM1, XMM0;	// [A,0,C,0] * ([x,y] + [sX,sY] - [x_0,y_0])
	psrlq		XMM1, 16;	// ([A,0,C,0] * ([x,y] + [sX,sY] - 
[x_0,y_0]))>>16
	movups		XMM4, XMM0;
	psrldq		XMM4, 4;
	pslldq		XMM0, 4;
	por			XMM4, XMM0;
	pmuludq		XMM2, XMM4; // [0,B,0,D] * ([x,y] + [sX,sY] - [x_0,y_0])
	psrlq		XMM2, 16;	// ([0,B,0,D] * ([x,y] + [sX,sY] - 
[x_0,y_0]))>>16
	paddq		XMM1, XMM2; // ([A,B,C,D] * ([x,y] + [sX,sY] - 
[x_0,y_0]))>>16
	punpckldq	XMM3, XMM7;
	paddq		XMM1, XMM3;	// ([A,B,C,D] * ([x,y] + [sX,sY] - 
[x_0,y_0]))>>16 + [x_0,y_0]
	movups		XMM0, XMM1;	// Convert 64 bit vectors into 32 bit ones
	psrldq		XMM0, 4;
	por			XMM0, XMM1;	
	ret			;
}
}(...)
}