static unsigned long long _mask24_2 = 0x0101010202020404LL;
static unsigned long long _mask24_1 = 0x0408080810101020LL;
static unsigned long long _mask24_0 = 0x2020404040808080LL;

static unsigned long long _mask32_3 = 0x0101010102020202LL;
static unsigned long long _mask32_2 = 0x0404040408080808LL;
static unsigned long long _mask32_1 = 0x1010101020202020LL;
static unsigned long long _mask32_0 = 0x4040404080808080LL;

static unsigned long long _mask48_5 = 0x0101010101010202LL;
static unsigned long long _mask48_4 = 0x0202020204040404LL;
static unsigned long long _mask48_3 = 0x0404080808080808LL;
static unsigned long long _mask48_2 = 0x1010101010102020LL;
static unsigned long long _mask48_1 = 0x2020202040404040LL;
static unsigned long long _mask48_0 = 0x4040808080808080LL;

static unsigned long long _const4   = 0x0000000000FFFFFFLL;
//static unsigned long long _const5 = 0x000000FFFFFF0000LL;     // NOT USED
static unsigned long long _const6   = 0x00000000000000FFLL;

// These are used in the row-filter routines and should/would be local
//  variables if not for gcc addressing limitations.
// WARNING: Their presence probably defeats the thread safety of libpng.

#ifdef PNG_THREAD_UNSAFE_OK
static png_uint_32  _FullLength;
static png_uint_32  _MMXLength;
static int          _dif;
static int          _patemp; // temp variables for Paeth routine
static int          _pbtemp;
static int          _pctemp;
#endif

void /* PRIVATE */
png_squelch_warnings(void)
{
#ifdef PNG_THREAD_UNSAFE_OK
   _dif = _dif;
   _patemp = _patemp;
   _pbtemp = _pbtemp;
   _pctemp = _pctemp;
   _MMXLength = _MMXLength;
#endif
   _const4  = _const4;
   _const6  = _const6;
   _mask8_0  = _mask8_0;
   _mask16_1 = _mask16_1;
   _mask16_0 = _mask16_0;
   _mask24_2 = _mask24_2;
   _mask24_1 = _mask24_1;
   _mask24_0 = _mask24_0;
   _mask32_3 = _mask32_3;
   _mask32_2 = _mask32_2;
   _mask32_1 = _mask32_1;
   _mask32_0 = _mask32_0;
   _mask48_5 = _mask48_5;
   _mask48_4 = _mask48_4;
   _mask48_3 = _mask48_3;
   _mask48_2 = _mask48_2;
   _mask48_1 = _mask48_1;
   _mask48_0 = _mask48_0;
}
#endif /* PNG_ASSEMBLER_CODE_SUPPORTED */


static int _mmx_supported = 2;

/*===========================================================================*/
/*                                                                           */
/*                       P N G _ C O M B I N E _ R O W                       */
/*                                                                           */
/*===========================================================================*/

#if defined(PNG_HAVE_ASSEMBLER_COMBINE_ROW)

#define BPP2  2
#define BPP3  3 /* bytes per pixel (a.k.a. pixel_bytes) */
#define BPP4  4
#define BPP6  6 /* (defined only to help avoid cut-and-paste errors) */
#define BPP8  8

/* Combines the row recently read in with the previous row.
   This routine takes care of alpha and transparency if requested.
   This routine also handles the two methods of progressive display
   of interlaced images, depending on the mask value.
   The mask value describes which pixels are to be combined with
   the row.  The pattern always repeats every 8 pixels, so just 8
   bits are needed.  A one indicates the pixel is to be combined; a
   zero indicates the pixel is to be skipped.  This is in addition
   to any alpha or transparency value associated with the pixel.
   If you want all pixels to be combined, pass 0xff (255) in mask. */

/* Use this routine for the x86 platform - it uses a faster MMX routine
   if the machine supports MMX. */

void /* PRIVATE */
png_combine_row(png_structp png_ptr, png_bytep row, int mask)
{
   png_debug(1, "in png_combine_row (pnggccrd.c)\n");

#if defined(PNG_ASSEMBLER_CODE_SUPPORTED)
   if (_mmx_supported == 2) {
#if !defined(PNG_1_0_X)
       /* this should have happened in png_init_mmx_flags() already */
       png_warning(png_ptr, "asm_flags may not have been initialized");
#endif
       png_mmx_support();
   }
#endif

   if (mask == 0xff)
   {
      png_debug(2,"mask == 0xff:  doing single png_memcpy()\n");
      png_memcpy(row, png_ptr->row_buf + 1,
       (png_size_t)PNG_ROWBYTES(png_ptr->row_info.pixel_depth,png_ptr->width));
   }
   else   /* (png_combine_row() is never called with mask == 0) */
   {
      switch (png_ptr->row_info.pixel_depth)
      {
         case 1:        /* png_ptr->row_info.pixel_depth */
         {
            png_bytep sp;
            png_bytep dp;
            int s_inc, s_start, s_end;
            int m;
            int shift;
            png_uint_32 i;

            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 = 7;
                s_inc = 1;
            }
            else
#endif
            {
                s_start = 7;
                s_end = 0;
                s_inc = -1;
            }

            shift = s_start;

            for (i = 0; i < png_ptr->width; i++)
            {
               if (m & mask)
               {
                  int value;

                  value = (*sp >> shift) & 0x1;
                  *dp &= (png_byte)((0x7f7f >> (7 - 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 2:        /* 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 = 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 defined(PNG_ASSEMBLER_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
#if !defined(PNG_1_0_X)
            if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
                /* && _mmx_supported */ )
#else
            if (_mmx_supported)
#endif
            {
               png_uint_32 len;
               int diff;
               int dummy_value_a;   // fix 'forbidden register spilled' error
               int dummy_value_d;
               int dummy_value_c;
               int dummy_value_S;
               int dummy_value_D;
               _unmask = ~mask;            // global variable for -fPIC version
               srcptr = png_ptr->row_buf + 1;
               dstptr = row;
               len  = png_ptr->width &~7;  // reduce to multiple of 8
               diff = (int) (png_ptr->width & 7);  // amount lost

               __asm__ __volatile__ (
                  "movd      _unmask, %%mm7  \n\t" // load bit pattern
                  "psubb     %%mm6, %%mm6    \n\t" // zero mm6
                  "punpcklbw %%mm7, %%mm7    \n\t"