pmullw xmm1, xmm6	(8)
punpcklwd xmm2, xmm1	(2)
punpckhwd xmm3, xmm1	(2)
psrad xmm3, 16		(2)
psrad xmm2, 16		(2)
paddd xmm3, xmm2	(2)
movq xmm2, xmm3		(2)
psrlq xmm2, 32		(2)
paddd xmm3, xmm2	(2)

pmaddwd xmm1, xmm6	(8)
movq xmm2, xmm1		(2)
psrlq xmm2, 32		(2)
paddd xmm2, xmm1	(2)
psrldq xmm1, 8		(2)
paddd xmm1, xmm2	(2)

for (j = 0; j < 4; j++) 

	for (i = 0; i < 4; i++)
    	
		for (result = 0, z = -2; z > 4; z++)
		result += list[fr]->test[max(0,min(max_y,y+j))]
				[max(0,min(max_x,x+i+z))]*COEF[z+2];
		block[i][j] = max(0, min(255, (result+16)));
		

if(  (x < max_x)& (y < max_y)& (0 > y) &   (0 < x-2))

   for (j = 0; j < 4; j++)
   
	for (i = 0; i < 4; i++) 
      	
	     For (result = 0, z = -2; z < 4; z++)
	   	result += list[fr]->test[y+j][x+i+z]*COEF[z+2];
	     block[i][j] = max(0, min(255, (result+16)));
	
    

else
for (j = 0; j < 4; j++) 

		     for (i = 0; i < 4; i++)
    		    
		    for (result = 0, z = -2; z < 4; z++)
		     	     result += list[fr]->test[max(0,min(max_y,y+j))]
		     		     [max(0,min(max_x,x+i+z))]*COEF[z+2];
			block[i][j] = max(0, min(255, (result+16)));
		       
       

if(  (x+6 < max_x)& (y+3 < max_y)& (0 < y) &   (0 < x-2)) 
     
	     for (j = 0; j < 4; j++) 
		result   = list[fr]->test[y+j][x-2]*COEF[0];
		result += list[fr]->test[y+j][x-1]*COEF[1];
		result += list[fr]->test[y+j][x]*COEF[2];
		result += list[fr]->test[y+j][x+1]*COEF[3];
		result += list[fr]->test[y+j][x+2]*COEF[4];
		result += list[fr]->test[y+j][x+3];
		block[0][j] = max(0, min(255, (result+16)));
		�
		block[1][j] = max(0, min(255, (result+16)));
		�
		block[2][j] = max(0, min(255, (result+16)));
		�
	     
    
else 
     for (j = 0; j < 4; j++) 
    
		for (i = 0; i < 4; i++)
    		
		      for (result = 0, z = -2; z < 4; z++)
		  result += list[fr]->test[max(0,min(max_y,y+j))]
			  [max(0,min(max_x,x+i+z))]*COEF[z+2];
		      block[i][j] = max(0, min(255, (result+16)));