pnggccrd.c

Qt/Embedded是一个多平台的C++图形用户界面应用程序框架

            {
               s_start = 0;
               s_end = 6;
               s_inc = 2;
            }
            else
#endif
            {
               s_start = 6;
               s_end = 0;
               s_inc = -2;
            }

            shift = s_start;

            for (i = 0; i < png_ptr->width; i++)
            {
               if (m & mask)
               {
                  value = (*sp >> shift) & 0x3;
                  *dp &= (png_byte)((0x3f3f >> (6 - shift)) & 0xff);
                  *dp |= (png_byte)(value << shift);
               }

               if (shift == s_end)
               {
                  shift = s_start;
                  sp++;
                  dp++;
               }
               else
                  shift += s_inc;
               if (m == 1)
                  m = 0x80;
               else
                  m >>= 1;
            }
            break;
         }

         case 4:        // png_ptr->row_info.pixel_depth
         {
            png_bytep sp;
            png_bytep dp;
            int s_start, s_end, s_inc;
            int m;
            int shift;
            png_uint_32 i;
            int value;

            sp = png_ptr->row_buf + 1;
            dp = row;
            m = 0x80;
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
            if (png_ptr->transformations & PNG_PACKSWAP)
            {
               s_start = 0;
               s_end = 4;
               s_inc = 4;
            }
            else
#endif
            {
               s_start = 4;
               s_end = 0;
               s_inc = -4;
            }
            shift = s_start;

            for (i = 0; i < png_ptr->width; i++)
            {
               if (m & mask)
               {
                  value = (*sp >> shift) & 0xf;
                  *dp &= (png_byte)((0xf0f >> (4 - shift)) & 0xff);
                  *dp |= (png_byte)(value << shift);
               }

               if (shift == s_end)
               {
                  shift = s_start;
                  sp++;
                  dp++;
               }
               else
                  shift += s_inc;
               if (m == 1)
                  m = 0x80;
               else
                  m >>= 1;
            }
            break;
         }

         case 8:        // png_ptr->row_info.pixel_depth
         {
            png_bytep srcptr;
            png_bytep dstptr;

            if (mmx_supported)
            {
               png_uint_32 len;
               int diff;
#ifndef __PIC__
               int unmask = ~mask;
#else
               _unmask = ~mask;            // global variable for -fPIC version
#endif
               srcptr = png_ptr->row_buf + 1;
               dstptr = row;
               len  = png_ptr->width &~7;  // reduce to multiple of 8
               diff = png_ptr->width & 7;  // amount lost

               __asm__ (
#ifdef __PIC__
                  "movd      _unmask, %%mm7  \n\t" // load bit pattern
#else
// preload        "movd      unmask, %%mm7   \n\t" // (unmask is in ebx)
                  "movd      %%ebx, %%mm7    \n\t" // load bit pattern (unmask)
#endif
                  "psubb     %%mm6, %%mm6    \n\t" // zero mm6
                  "punpcklbw %%mm7, %%mm7    \n\t"
                  "punpcklwd %%mm7, %%mm7    \n\t"
                  "punpckldq %%mm7, %%mm7    \n\t" // fill reg with 8 masks

                  "movq      _mask8_0, %%mm0 \n\t"
                  "pand      %%mm7, %%mm0    \n\t" // nonzero if keep byte
                  "pcmpeqb   %%mm6, %%mm0    \n\t" // zeros->1s, v versa

// preload        "movl      len, %%ecx      \n\t" // load length of line
// preload        "movl      srcptr, %%esi   \n\t" // load source
// preload        "movl      dstptr, %%edi   \n\t" // load dest

                  "cmpl      $0, %%ecx       \n\t" // len == 0 ?
                  "je        mainloop8end    \n\t"

                "mainloop8:                  \n\t"
                  "movq      (%%esi), %%mm4  \n\t" // *srcptr
                  "pand      %%mm0, %%mm4    \n\t"
                  "movq      %%mm0, %%mm6    \n\t"
                  "pandn     (%%edi), %%mm6  \n\t" // *dstptr
                  "por       %%mm6, %%mm4    \n\t"
                  "movq      %%mm4, (%%edi)  \n\t"
                  "addl      $8, %%esi       \n\t" // inc by 8 bytes processed
                  "addl      $8, %%edi       \n\t"
                  "subl      $8, %%ecx       \n\t" // dec by 8 pixels processed
                  "ja        mainloop8       \n\t"

                "mainloop8end:               \n\t"
// preload        "movl      diff, %%ecx     \n\t" // (diff is in eax)
                  "movl      %%eax, %%ecx    \n\t"
                  "cmpl      $0, %%ecx       \n\t"
                  "jz        end8            \n\t"
// preload        "movl      mask, %%edx     \n\t"
                  "sall      $24, %%edx      \n\t" // make low byte, high byte

                "secondloop8:                \n\t"
                  "sall      %%edx           \n\t" // move high bit to CF
                  "jnc       skip8           \n\t" // if CF = 0
                  "movb      (%%esi), %%al   \n\t"
                  "movb      %%al, (%%edi)   \n\t"

                "skip8:                      \n\t"
                  "incl      %%esi           \n\t"
                  "incl      %%edi           \n\t"
                  "decl      %%ecx           \n\t"
                  "jnz       secondloop8     \n\t"

                "end8:                       \n\t"
                  "EMMS                      \n\t"  // DONE

                  :                                 // output regs (none)

                  : "S" (srcptr),      // esi       // input regs
                    "D" (dstptr),      // edi
                    "a" (diff),        // eax
#ifndef __PIC__
                    "b" (unmask),      // ebx       // Global Offset Table idx
#endif
                    "c" (len),         // ecx
                    "d" (mask)         // edx

                  : "%esi", "%edi", "%eax",         // clobber list
                    "%ecx", "%edx"
#if 0  /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
                  , "%mm0", "%mm4", "%mm6", "%mm7"
#endif
               );
            }
            else /* mmx _not supported - Use modified C routine */
            {
               register png_uint_32 i;
               png_uint_32 initial_val = png_pass_start[png_ptr->pass];
                 // png.c:  png_pass_start[] = {0, 4, 0, 2, 0, 1, 0};
               register int stride = png_pass_inc[png_ptr->pass];
                 // png.c:  png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
               register int rep_bytes = png_pass_width[png_ptr->pass];
                 // png.c:  png_pass_width[] = {8, 4, 4, 2, 2, 1, 1};
               register png_uint_32 final_val = png_ptr->width;

               srcptr = png_ptr->row_buf + 1 + initial_val;
               dstptr = row + initial_val;

               for (i = initial_val; i < final_val; i += stride)
               {
                  png_memcpy(dstptr, srcptr, rep_bytes);
                  srcptr += stride;
                  dstptr += stride;
               } 
            } /* end of else */

            break;
         }       // end 8 bpp

         case 16:       // png_ptr->row_info.pixel_depth
         {
            png_bytep srcptr;
            png_bytep dstptr;

            if (mmx_supported)
            {
               png_uint_32 len;
               int diff;
#ifndef __PIC__
               int unmask = ~mask;
#else
               _unmask = ~mask;            // global variable for -fPIC version
#endif
               srcptr = png_ptr->row_buf + 1;
               dstptr = row;
               len  = png_ptr->width &~7;  // reduce to multiple of 8
               diff = png_ptr->width & 7;  // amount lost

               __asm__ (
#ifdef __PIC__
                  "movd      _unmask, %%mm7   \n\t" // load bit pattern
#else
// preload        "movd      unmask, %%mm7    \n\t" // (unmask is in ebx)
                  "movd      %%ebx, %%mm7     \n\t" // load bit pattern (unmask)
#endif
                  "psubb     %%mm6, %%mm6     \n\t" // zero mm6
                  "punpcklbw %%mm7, %%mm7     \n\t"
                  "punpcklwd %%mm7, %%mm7     \n\t"
                  "punpckldq %%mm7, %%mm7     \n\t" // fill reg with 8 masks

                  "movq      _mask16_0, %%mm0 \n\t"
                  "movq      _mask16_1, %%mm1 \n\t"

                  "pand      %%mm7, %%mm0     \n\t"
                  "pand      %%mm7, %%mm1     \n\t"

                  "pcmpeqb   %%mm6, %%mm0     \n\t"
                  "pcmpeqb   %%mm6, %%mm1     \n\t"

// preload        "movl      len, %%ecx       \n\t" // load length of line
// preload        "movl      srcptr, %%esi    \n\t" // load source
// preload        "movl      dstptr, %%edi    \n\t" // load dest

                  "cmpl      $0, %%ecx        \n\t"
                  "jz        mainloop16end    \n\t"

                "mainloop16:                  \n\t"
                  "movq      (%%esi), %%mm4   \n\t"
                  "pand      %%mm0, %%mm4     \n\t"
                  "movq      %%mm0, %%mm6     \n\t"
                  "movq      (%%edi), %%mm7   \n\t"
                  "pandn     %%mm7, %%mm6     \n\t"
                  "por       %%mm6, %%mm4     \n\t"
                  "movq      %%mm4, (%%edi)   \n\t"

                  "movq      8(%%esi), %%mm5  \n\t"
                  "pand      %%mm1, %%mm5     \n\t"
                  "movq      %%mm1, %%mm7     \n\t"
                  "movq      8(%%edi), %%mm6  \n\t"
                  "pandn     %%mm6, %%mm7     \n\t"
                  "por       %%mm7, %%mm5     \n\t"
                  "movq      %%mm5, 8(%%edi)  \n\t"

                  "addl      $16, %%esi       \n\t" // inc by 16 bytes processed
                  "addl      $16, %%edi       \n\t"
                  "subl      $8, %%ecx        \n\t" // dec by 8 pixels processed
                  "ja        mainloop16       \n\t"

                "mainloop16end:               \n\t"
// preload        "movl      diff, %%ecx      \n\t" // (diff is in eax)
                  "movl      %%eax, %%ecx     \n\t"
                  "cmpl      $0, %%ecx        \n\t"
                  "jz        end16            \n\t"
// preload        "movl      mask, %%edx      \n\t"
                  "sall      $24, %%edx       \n\t" // make low byte, high byte

                "secondloop16:                \n\t"
                  "sall      %%edx            \n\t" // move high bit to CF
                  "jnc       skip16           \n\t" // if CF = 0
                  "movw      (%%esi), %%ax    \n\t"
                  "movw      %%ax, (%%edi)    \n\t"

                "skip16:                      \n\t"
                  "addl      $2, %%esi        \n\t"
                  "addl      $2, %%edi        \n\t"
                  "decl      %%ecx            \n\t"
                  "jnz       secondloop16     \n\t"

                "end16:                       \n\t"
                  "EMMS                       \n\t" // DONE

                  :                                 // output regs (none)

                  : "S" (srcptr),      // esi       // input regs
                    "D" (dstptr),      // edi
                    "a" (diff),        // eax
#ifndef __PIC__
                    "b" (unmask),      // ebx       // Global Offset Table idx
#endif
                    "c" (len),         // ecx
                    "d" (mask)         // edx

                  : "%esi", "%edi", "%eax",         // clobber list
                    "%ecx", "%edx"
#if 0  /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
                  , "%mm0", "%mm1",
                    "%mm4", "%mm5", "%mm6", "%mm7"
#endif
               );
            }
            else /* mmx _not supported - Use modified C routine */
            {
               register png_uint_32 i;
               png_uint_32 initial_val = 2 * png_pass_start[png_ptr->pass];