[Mesa3d-dev] RE: Texutil optimizations - an interesting story

[<ad...@hu...>]

i will just include the code here so that no conversions are necessary...

#include <stdio.h>

#define GLubyte  char
#define GLushort short
#define GLint    int

int main(void){
    char whatever1[]={"sakjdhsskhjasjashaskdsakjasjas"};
    char whatever2[]={"lhlkgjlkajdsflkfjlkjklfdaskfaf"};
//const GLubyte *src=_mesa_image_address(packing, srcImage, srcWidth,
//                                       srcHeight,srcFormat,srcType);
// GLubyte  *src=(GLubyte *)malloc(1024);
 GLubyte  *src=(GLubyte *)whatever1;
//      GLushort *dst=(GLushort *)dstImage;
// GLushort *dst=(GLushort *)malloc(1024);
 GLushort *dst=(GLushort *)whatever2;
      int f;
      GLushort val;
      GLint    val32;
      GLint row;
//      for(row=0; row < dstHeight; row++){
//          GLint col, col4;
          GLint col=4, col4=4;  //rig some values so we don't over/underflow
//          for(col=col4=0; col < dstWidth; col++, col4 +=4){

//original
///*
              GLubyte r = src[col4 + 0];
              GLubyte g = src[col4 + 1];
              GLubyte b = src[col4 + 2];
              GLubyte a = src[col4 + 3];
              //printf("Datazzzz: (lsb)RGBA(msb)= 0x%x%x%x%x \n",a,b,g,r);
              dst[col] = ((a & 0xf0) << 8) | ((r & 0xf0) << 4) | ((g & 0xf0) 
) | ((b & 0xf0) >> 4);
              //printf("Method 0: 0x%x \n",dst[col]);
//*/
              f++; f++; f++; f++; f++; f++; f++; f++; f++; // segment the 
assembler code for easier reading :))
//new1
///*
              *(dst+col)=                   \
              (((*(src+col4+3))&0xf0)<<8) | \
              (((*(src+col4+2))&0xf0)>>4) | \
              (((*(src+col4+1))&0xf0)   ) | \
              (((*(src+col4+0))&0xf0)<<4);
              //printf("Method 1: 0x%x \n",dst[col]);
//*/
              f++; f++; f++; f++; f++; f++; f++; f++; f++; // segment the 
assembler code for easier reading :))
//new2
///*
              src+=col4;
              val =((*src)&0xf0)<<4;
              src++;
              val|=((*src)&0xf0);
              src++;
              val|=((*src)&0xf0)>>4;
              src++;
              val|=((*src)&0xf0)<<8;
              *(dst+col)=val;                //save converted thing
              //printf("Method 2: 0x%x \n",dst[col]);
              src-=col4+3;                   //re-adjust src, this can be 
skipped outside this forloop by adjusting srcStride...
//*/
              f++; f++; f++; f++; f++; f++; f++; f++; f++; // segment the 
assembler code for easier reading :))
//new3
///*
              val32=*( (GLint*)(src+col));
              *(dst+col)=                   \
              (( val32 & 0xf0000000)>>16) | \
              (( val32 & 0x00f00000)>>20) | \
              (( val32 & 0x0000f000)>>8 ) | \
              (( val32 & 0x000000f0)<<4);
              //printf("Method 3: 0x%x \n",dst[col]);
//*/




//          }//inner
//          src +=srcStride;
//          dst  =(GLushort *) ((GLubyte*) dst+dstRowStride);
//      }//outter


return 0;
};//end main