MMX intrinsic to inline assembly

void tom::Transform(void* btr)
{   
    short* block =(short*)btr;
    __declspec(align(8)) __m64*block1 = (__m64*)block;  
		 int j;   
	
	/// Only do IT modes = 0 & 1.
	if(_mode != QuantOnly)	//< 2 = Q only.
	{
            __m64 s0,s1,s2,s3,f0,f1,f2,f3,temp4,temp5,temp6,temp7;
            j=0;
	    // transpose input
	    temp4 = _mm_unpacklo_pi16(block1[j],block1[j+1]);
	    temp5 = _mm_unpacklo_pi16(block1[j+2],block1[j+3]);
	    temp6 = _mm_unpackhi_pi16(block1[j],block1[j+1]);
	    temp7 = _mm_unpackhi_pi16(block1[j+2],block1[j+3]);
	    f0 = _mm_unpacklo_pi32(temp4,temp5);
	    f2 = _mm_unpacklo_pi32(temp6,temp7);
	    f1 = _mm_unpackhi_pi32(temp4,temp5);
	    f3 = _mm_unpackhi_pi32(temp6,temp7);
	    // stage one
	    s0 =_mm_add_pi16(f0,f3);
	    s3 =_mm_sub_pi16(f0,f3);
	    s1 =_mm_add_pi16(f1,f2);
	    s2 =_mm_sub_pi16(f1,f2); 
	    //stage 2
            block1[j] =_mm_add_pi16(s0,s1);
            block1[j+2] =_mm_sub_pi16(s0,s1);
            block1[j+1] =_mm_add_pi16(s2,_mm_slli_pi16(s3, 1));
            block1[j+3] =_mm_sub_pi16(s3,_mm_slli_pi16(s2, 1));