static inline int pixel_sa8d_wxh( uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2,
int i_width, int i_height )
{
int16_t diff[8][8];
int i_satd = 0;
int x, y;
for( y = 0; y < i_height; y += 8 )
{
for( x = 0; x < i_width; x += 8 )
{
int i;
pixel_sub_wxh( (int16_t*)diff, 8, pix1+x, i_pix1, pix2+x, i_pix2 );
#define SRC(x) diff[i][x]
#define DST(x,rhs) diff[i][x] = (rhs)
for( i = 0; i < 8; i++ )
SA8D_1D
#undef SRC
#undef DST
#define SRC(x) diff[x][i]
#define DST(x,rhs) i_satd += abs(rhs)
for( i = 0; i < 8; i++ )
SA8D_1D
#undef SRC
#undef DST
}
pix1 += 8 * i_pix1;
pix2 += 8 * i_pix2;
}
return i_satd;
}
static void sub8x8_dct8( int16_t dct[8][8], uint8_t *pix1, uint8_t *pix2 )
{
int i;
#ifdef HAVE_SSE2
if(1)
{
int16_t tmp[8][8];
xavs_sub8x8_dct8_sse2( (int16_t*) dct[8][8], pix1, pix2 ,tmp);
}
#else
{
pixel_sub_wxh( (int16_t*)dct, 8, pix1, FENC_STRIDE, pix2, FDEC_STRIDE );
#define SRC(x) dct[i][x]
#define DST(x) dct[i][x]
for( i = 0; i < 8; i++ )
DCT8_Horizontal_1D
#undef SRC
#undef DST
#define SRC(x) dct[x][i]
#define DST(x) dct[x][i]
for( i = 0; i < 8; i++ )
DCT8_Vertical_1D
#undef SRC
#undef DST
}
#endif
}
static void
sub8x8_dct8 (int16_t dct[8][8], uint8_t * pix1, uint8_t * pix2)
{
int i;
int16_t tmp[8][8];
#ifdef HAVE_SSE2
xavs_sub8x8_dct8_sse2( dct, pix1, pix2 ,tmp);
#else
pixel_sub_wxh ((int16_t *) tmp, 8, pix1, FENC_STRIDE, pix2, FDEC_STRIDE);
//aloha' i--x
#define SRC(x) tmp[i][x]
#define DST(x) tmp[i][x]
for (i = 0; i < 8; i++)
DCT8_Horizontal_1D
#undef SRC
#undef DST
#define SRC(x) tmp[x][i]
#define DST(x) dct[x][i]
for (i = 0; i < 8; i++)
DCT8_Vertical_1D
#undef SRC
#undef DST
#endif
}
/****************************************************************************
* pixel_satd_WxH: sum of 4x4 Hadamard transformed differences
****************************************************************************/
static int pixel_satd_wxh( uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2, int i_width, int i_height )
{
int16_t tmp[4][4];
int16_t diff[4][4];
int x, y;
int i_satd = 0;
for( y = 0; y < i_height; y += 4 )
{
for( x = 0; x < i_width; x += 4 )
{
int d;
pixel_sub_wxh( (int16_t*)diff, 4, &pix1[x], i_pix1, &pix2[x], i_pix2 );
for( d = 0; d < 4; d++ )
{
int s01, s23;
int d01, d23;
s01 = diff[d][0] + diff[d][1]; s23 = diff[d][2] + diff[d][3];
d01 = diff[d][0] - diff[d][1]; d23 = diff[d][2] - diff[d][3];
tmp[d][0] = s01 + s23;
tmp[d][1] = s01 - s23;
tmp[d][2] = d01 - d23;
tmp[d][3] = d01 + d23;
}
for( d = 0; d < 4; d++ )
{
int s01, s23;
int d01, d23;
s01 = tmp[0][d] + tmp[1][d]; s23 = tmp[2][d] + tmp[3][d];
d01 = tmp[0][d] - tmp[1][d]; d23 = tmp[2][d] - tmp[3][d];
i_satd += abs( s01 + s23 ) + abs( s01 - s23 ) + abs( d01 - d23 ) + abs( d01 + d23 );
}
}
pix1 += 4 * i_pix1;
pix2 += 4 * i_pix2;
}
return i_satd / 2;
}
