pnggccrd.c

Qt/Embedded是一个多平台的C++图形用户界面应用程序框架

            png_uint_32 i;

            sp = row + (png_size_t)((row_info->width - 1) >> 2);
            dp = row + (png_size_t)((final_width - 1) >> 2);
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
            if (transformations & PNG_PACKSWAP)
            {
               sshift = (png_size_t)(((row_info->width + 3) & 3) << 1);
               dshift = (png_size_t)(((final_width + 3) & 3) << 1);
               s_start = 6;
               s_end = 0;
               s_inc = -2;
            }
            else
#endif
            {
               sshift = (png_size_t)((3 - ((row_info->width + 3) & 3)) << 1);
               dshift = (png_size_t)((3 - ((final_width + 3) & 3)) << 1);
               s_start = 0;
               s_end = 6;
               s_inc = 2;
            }

            for (i = row_info->width; i; i--)
            {
               png_byte v;
               int j;

               v = (png_byte)((*sp >> sshift) & 0x3);
               for (j = 0; j < png_pass_inc[pass]; j++)
               {
                  *dp &= (png_byte)((0x3f3f >> (6 - dshift)) & 0xff);
                  *dp |= (png_byte)(v << dshift);
                  if (dshift == s_end)
                  {
                     dshift = s_start;
                     dp--;
                  }
                  else
                     dshift += s_inc;
               }
               if (sshift == s_end)
               {
                  sshift = s_start;
                  sp--;
               }
               else
                  sshift += s_inc;
            }
            break;
         }

         case 4:
         {
            png_bytep sp, dp;
            int sshift, dshift;
            int s_start, s_end, s_inc;
            png_uint_32 i;

            sp = row + (png_size_t)((row_info->width - 1) >> 1);
            dp = row + (png_size_t)((final_width - 1) >> 1);
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
            if (transformations & PNG_PACKSWAP)
            {
               sshift = (png_size_t)(((row_info->width + 1) & 1) << 2);
               dshift = (png_size_t)(((final_width + 1) & 1) << 2);
               s_start = 4;
               s_end = 0;
               s_inc = -4;
            }
            else
#endif
            {
               sshift = (png_size_t)((1 - ((row_info->width + 1) & 1)) << 2);
               dshift = (png_size_t)((1 - ((final_width + 1) & 1)) << 2);
               s_start = 0;
               s_end = 4;
               s_inc = 4;
            }

            for (i = row_info->width; i; i--)
            {
               png_byte v;
               int j;

               v = (png_byte)((*sp >> sshift) & 0xf);
               for (j = 0; j < png_pass_inc[pass]; j++)
               {
                  *dp &= (png_byte)((0xf0f >> (4 - dshift)) & 0xff);
                  *dp |= (png_byte)(v << dshift);
                  if (dshift == s_end)
                  {
                     dshift = s_start;
                     dp--;
                  }
                  else
                     dshift += s_inc;
               }
               if (sshift == s_end)
               {
                  sshift = s_start;
                  sp--;
               }
               else
                  sshift += s_inc;
            }
            break;
         }

         //====================================================================

         default:  // 8-bit or larger (this is where the routine is modified)
         {
//          static unsigned long long _const4 = 0x0000000000FFFFFFLL;  no good
//          static unsigned long long const4 = 0x0000000000FFFFFFLL;   no good
//          unsigned long long _const4 = 0x0000000000FFFFFFLL;         no good
//          unsigned long long const4 = 0x0000000000FFFFFFLL;          no good
            png_bytep sptr, dp;
            png_uint_32 i;
            png_size_t pixel_bytes;
            int width = row_info->width;

            pixel_bytes = (row_info->pixel_depth >> 3);

            // point sptr at the last pixel in the pre-expanded row:
            sptr = row + (width - 1) * pixel_bytes;

            // point dp at the last pixel position in the expanded row:
            dp = row + (final_width - 1) * pixel_bytes;

            // New code by Nirav Chhatrapati - Intel Corporation

            if (mmx_supported)  // use MMX code if machine supports it
            {
               //--------------------------------------------------------------
               if (pixel_bytes == 3)
               {
                  if (((pass == 0) || (pass == 1)) && width)
                  {
                     __asm__ (
                        "subl $21, %%edi         \n\t"
                                     // (png_pass_inc[pass] - 1)*pixel_bytes

                     ".loop3_pass0:              \n\t"
                        "movd (%%esi), %%mm0     \n\t" // x x x x x 2 1 0
                        "pand _const4, %%mm0     \n\t" // z z z z z 2 1 0
                        "movq %%mm0, %%mm1       \n\t" // z z z z z 2 1 0
                        "psllq $16, %%mm0        \n\t" // z z z 2 1 0 z z
                        "movq %%mm0, %%mm2       \n\t" // z z z 2 1 0 z z
                        "psllq $24, %%mm0        \n\t" // 2 1 0 z z z z z
                        "psrlq $8, %%mm1         \n\t" // z z z z z z 2 1
                        "por %%mm2, %%mm0        \n\t" // 2 1 0 2 1 0 z z
                        "por %%mm1, %%mm0        \n\t" // 2 1 0 2 1 0 2 1
                        "movq %%mm0, %%mm3       \n\t" // 2 1 0 2 1 0 2 1
                        "psllq $16, %%mm0        \n\t" // 0 2 1 0 2 1 z z
                        "movq %%mm3, %%mm4       \n\t" // 2 1 0 2 1 0 2 1
                        "punpckhdq %%mm0, %%mm3  \n\t" // 0 2 1 0 2 1 0 2
                        "movq %%mm4, 16(%%edi)   \n\t"
                        "psrlq $32, %%mm0        \n\t" // z z z z 0 2 1 0
                        "movq %%mm3, 8(%%edi)    \n\t"
                        "punpckldq %%mm4, %%mm0  \n\t" // 1 0 2 1 0 2 1 0
                        "subl $3, %%esi          \n\t"
                        "movq %%mm0, (%%edi)     \n\t"
                        "subl $24, %%edi         \n\t"
                        "decl %%ecx              \n\t"
                        "jnz .loop3_pass0        \n\t"
                        "EMMS                    \n\t" // DONE

                        :                              // output regs (none)

                        : "S" (sptr),      // esi      // input regs
                          "D" (dp),        // edi
                          "c" (width)      // ecx
// doesn't work           "i" (0x0000000000FFFFFFLL)   // %1 (a.k.a. _const4)

                        : "%esi", "%edi", "%ecx"       // clobber list
#if 0  /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */
                        , "%mm0", "%mm1", "%mm2", "%mm3", "%mm4"
#endif
                     );
                  }
                  else if (((pass == 2) || (pass == 3)) && width)
                  {
                     __asm__ (
                        "subl $9, %%edi          \n\t"
                                     // (png_pass_inc[pass] - 1)*pixel_bytes

                     ".loop3_pass2:              \n\t"
                        "movd (%%esi), %%mm0     \n\t" // x x x x x 2 1 0
                        "pand _const4, %%mm0     \n\t" // z z z z z 2 1 0
                        "movq %%mm0, %%mm1       \n\t" // z z z z z 2 1 0
                        "psllq $16, %%mm0        \n\t" // z z z 2 1 0 z z
                        "movq %%mm0, %%mm2       \n\t" // z z z 2 1 0 z z
                        "psllq $24, %%mm0        \n\t" // 2 1 0 z z z z z
                        "psrlq $8, %%mm1         \n\t" // z z z z z z 2 1
                        "por %%mm2, %%mm0        \n\t" // 2 1 0 2 1 0 z z
                        "por %%mm1, %%mm0        \n\t" // 2 1 0 2 1 0 2 1
                        "movq %%mm0, 4(%%edi)    \n\t"
                        "psrlq $16, %%mm0        \n\t" // z z 2 1 0 2 1 0
                        "subl $3, %%esi          \n\t"
                        "movd %%mm0, (%%edi)     \n\t"
                        "subl $12, %%edi         \n\t"
                        "decl %%ecx              \n\t"
                        "jnz .loop3_pass2        \n\t"
                        "EMMS                    \n\t" // DONE

                        :                              // output regs (none)

                        : "S" (sptr),      // esi      // input regs
                          "D" (dp),        // edi
                          "c" (width)      // ecx

                        : "%esi", "%edi", "%ecx"       // clobber list
#if 0  /* %mm0, ..., %mm2 not supported by gcc 2.7.2.3 or egcs 1.1 */
                        , "%mm0", "%mm1", "%mm2"
#endif
                     );
                  }
                  else if (width) /* && ((pass == 4) || (pass == 5)) */
                  {
                     int width_mmx = ((width >> 1) << 1) - 8;   // GRR:  huh?
                     if (width_mmx < 0)
                         width_mmx = 0;
                     width -= width_mmx;        // 8 or 9 pix, 24 or 27 bytes
                     if (width_mmx)
                     {
                        // png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
                        // sptr points at last pixel in pre-expanded row
                        // dp points at last pixel position in expanded row
                        __asm__ (
                           "subl $3, %%esi          \n\t"
                           "subl $9, %%edi          \n\t"
                                        // (png_pass_inc[pass] + 1)*pixel_bytes

                        ".loop3_pass4:              \n\t"
                           "movq (%%esi), %%mm0     \n\t" // x x 5 4 3 2 1 0
                           "movq %%mm0, %%mm1       \n\t" // x x 5 4 3 2 1 0
                           "movq %%mm0, %%mm2       \n\t" // x x 5 4 3 2 1 0
                           "psllq $24, %%mm0        \n\t" // 4 3 2 1 0 z z z
                           "pand _const4, %%mm1     \n\t" // z z z z z 2 1 0
                           "psrlq $24, %%mm2        \n\t" // z z z x x 5 4 3
                           "por %%mm1, %%mm0        \n\t" // 4 3 2 1 0 2 1 0
                           "movq %%mm2, %%mm3       \n\t" // z z z x x 5 4 3
                           "psllq $8, %%mm2         \n\t" // z z x x 5 4 3 z
                           "movq %%mm0, (%%edi)     \n\t"
                           "psrlq $16, %%mm3        \n\t" // z z z z z x x 5
                           "pand _const6, %%mm3     \n\t" // z z z z z z z 5
                           "por %%mm3, %%mm2        \n\t" // z z x x 5 4 3 5
                           "subl $6, %%esi          \n\t"
                           "movd %%mm2, 8(%%edi)    \n\t"
                           "subl $12, %%edi         \n\t"
                           "subl $2, %%ecx          \n\t"
                           "jnz .loop3_pass4        \n\t"
                           "EMMS                    \n\t" // DONE

                           :                              // output regs (none)

                           : "S" (sptr),      // esi      // input regs
                             "D" (dp),        // edi
                             "c" (width_mmx)  // ecx

                           : "%esi", "%edi", "%ecx"       // clobber list
#if 0  /* %mm0, ..., %mm3 not supported by gcc 2.7.2.3 or egcs 1.1 */
                           , "%mm0", "%mm1", "%mm2", "%mm3"
#endif
                        );
                     }

                     sptr -= width_mmx*3;
                     dp -= width_mmx*6;
                     for (i = width; i; i--)
                     {
                        png_byte v[8];
                        int j;

                        png_memcpy(v, sptr, 3);
                        for (j = 0; j < png_pass_inc[pass]; j++)
                        {
                           png_memcpy(dp, v, 3);
                           dp -= 3;
                        }
                        sptr -= 3;
                     }
                  }
               } /* end of pixel_bytes == 3 */

               //--------------------------------------------------------------
               else if (pixel_bytes == 1)
               {
                  if (((pass == 0) || (pass == 1)) && width)
                  {
                     int width_mmx = ((width >> 2) << 2);
                     width -= width_mmx;        // 0-3 pixels => 0-3 bytes
                     if (width_mmx)
                     {
                        __asm__ (
                           "subl $3, %%esi          \n\t"
                           "subl $31, %%edi         \n\t"

                        ".loop1_pass0:              \n\t"
                           "movd (%%esi), %%mm0     \n\t" // x x x x 3 2 1 0
                           "movq %%mm0, %%mm1       \n\t" // x x x x 3 2 1 0
                           "punpcklbw %%mm0, %%mm0  \n\t" // 3 3 2 2 1 1 0 0
                           "movq %%mm0, %%mm2       \n\t" // 3 3 2 2 1 1 0 0
                           "punpcklwd %%mm0, %%mm0  \n\t" // 1 1 1 1 0 0 0 0
                           "movq %%mm0, %%mm3       \n\t" // 1 1 1 1 0 0 0 0
                           "punpckldq %%mm0, %%mm0  \n\t" // 0 0 0 0 0 0 0 0
                           "punpckhdq %%mm3, %%mm3  \n\t" // 1 1 1 1 1 1 1 1
                           "movq %%mm0, (%%edi)     \n\t"
                           "punpckhwd %%mm2, %%mm2  \n\t" // 3 3 3 3 2 2 2 2
                           "movq %%mm3, 8(%%edi)    \n\t"
                           "movq %%mm2, %%mm4       \n\t" // 3 3 3 3 2 2 2 2
                           "punpckldq %%mm2, %%mm2  \n\t" // 2 2 2 2 2 2 2 2
                           "punpckhdq %%mm4, %%mm4  \n\t" // 3 3 3 3 3 3 3 3
                           "movq %%mm2, 16(%%edi)   \n\t"
                           "subl $4, %%esi          \n\t"
                           "movq %%mm4, 24(%%edi)   \n\t"
                           "subl $32, %%edi         \n\t"
                           "subl $4, %%ecx          \n\t"
                           "jnz .loop1_pass0        \n\t"
                           "EMMS                    \n\t" // DONE

                           :                              // output regs (none)

                           : "S" (sptr),      // esi      // input regs
                             "D" (dp),        // edi
                             "c"