// -------------------------------------------------------------- //
//
// More Efficient SAD Calculation 
//
// -------------------------------------------------------------- //
int sad(unsigned char* blk1, unsigned char* blk2, int distlim) {
	
	int j, k, v;
	int s = 0;
	
	for (j=0; j<16; j++)
	{
		if( (v=blk1[j*16+0] -blk2[j*16+0])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+1] -blk2[j*16+1])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+2] -blk2[j*16+2])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+3] -blk2[j*16+3])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+4] -blk2[j*16+4])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+5] -blk2[j*16+6])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+6] -blk2[j*16+6])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+7] -blk2[j*16+7])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+8] -blk2[j*16+8])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+9] -blk2[j*16+9])  < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+10]-blk2[j*16+10]) < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+11]-blk2[j*16+11]) < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+12]-blk2[j*16+12]) < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+13]-blk2[j*16+13]) < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+14]-blk2[j*16+14]) < 0 ) { v = -v; s+= v } 
		if( (v=blk1[j*16+15]-blk2[j*16+15]) < 0 ) { v = -v; s+= v } 
		if (s >= distlim) break;
	}
	
	return s;
}