-#undef MOVNTQ
-#undef PAVGB
-
-//#undef HAVE_MMX2
-//#define HAVE_AMD3DNOW
-//#undef HAVE_MMX
-//#undef ARCH_X86
-#define DITHER1XBPP
-
-#define isPacked(x) ( \
- (x)==PIX_FMT_PAL8 \
- || (x)==PIX_FMT_YUYV422 \
- || (x)==PIX_FMT_UYVY422 \
- || (x)==PIX_FMT_Y400A \
- || isAnyRGB(x) \
- )
-
-#define RGB2YUV_SHIFT 15
-#define BY ( (int)(0.114*219/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define BV (-(int)(0.081*224/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define BU ( (int)(0.500*224/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define GY ( (int)(0.587*219/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define GV (-(int)(0.419*224/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define GU (-(int)(0.331*224/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define RY ( (int)(0.299*219/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define RV ( (int)(0.500*224/255*(1<<RGB2YUV_SHIFT)+0.5))
-#define RU (-(int)(0.169*224/255*(1<<RGB2YUV_SHIFT)+0.5))
-
-static const double rgb2yuv_table[8][9]={
- {0.7152, 0.0722, 0.2126, -0.386, 0.5, -0.115, -0.454, -0.046, 0.5}, //ITU709
- {0.7152, 0.0722, 0.2126, -0.386, 0.5, -0.115, -0.454, -0.046, 0.5}, //ITU709
- {0.587 , 0.114 , 0.299 , -0.331, 0.5, -0.169, -0.419, -0.081, 0.5}, //DEFAULT / ITU601 / ITU624 / SMPTE 170M
- {0.587 , 0.114 , 0.299 , -0.331, 0.5, -0.169, -0.419, -0.081, 0.5}, //DEFAULT / ITU601 / ITU624 / SMPTE 170M
- {0.59 , 0.11 , 0.30 , -0.331, 0.5, -0.169, -0.421, -0.079, 0.5}, //FCC
- {0.587 , 0.114 , 0.299 , -0.331, 0.5, -0.169, -0.419, -0.081, 0.5}, //DEFAULT / ITU601 / ITU624 / SMPTE 170M
- {0.587 , 0.114 , 0.299 , -0.331, 0.5, -0.169, -0.419, -0.081, 0.5}, //DEFAULT / ITU601 / ITU624 / SMPTE 170M
- {0.701 , 0.087 , 0.212 , -0.384, 0.5, -0.116, -0.445, -0.055, 0.5}, //SMPTE 240M
-};
-
-/*
-NOTES
-Special versions: fast Y 1:1 scaling (no interpolation in y direction)
-
-TODO
-more intelligent misalignment avoidance for the horizontal scaler
-write special vertical cubic upscale version
-optimize C code (YV12 / minmax)
-add support for packed pixel YUV input & output
-add support for Y8 output
-optimize BGR24 & BGR32
-add BGR4 output support
-write special BGR->BGR scaler
-*/
-
-DECLARE_ALIGNED(8, static const uint8_t, dither_2x2_4)[2][8]={
-{ 1, 3, 1, 3, 1, 3, 1, 3, },
-{ 2, 0, 2, 0, 2, 0, 2, 0, },
-};
-
-DECLARE_ALIGNED(8, static const uint8_t, dither_2x2_8)[2][8]={
-{ 6, 2, 6, 2, 6, 2, 6, 2, },
-{ 0, 4, 0, 4, 0, 4, 0, 4, },
-};
-
-DECLARE_ALIGNED(8, const uint8_t, dither_4x4_16)[4][8]={
-{ 8, 4, 11, 7, 8, 4, 11, 7, },
-{ 2, 14, 1, 13, 2, 14, 1, 13, },
-{ 10, 6, 9, 5, 10, 6, 9, 5, },
-{ 0, 12, 3, 15, 0, 12, 3, 15, },
-};
-
-DECLARE_ALIGNED(8, const uint8_t, dither_8x8_32)[8][8]={
-{ 17, 9, 23, 15, 16, 8, 22, 14, },
-{ 5, 29, 3, 27, 4, 28, 2, 26, },
-{ 21, 13, 19, 11, 20, 12, 18, 10, },
-{ 0, 24, 6, 30, 1, 25, 7, 31, },
-{ 16, 8, 22, 14, 17, 9, 23, 15, },
-{ 4, 28, 2, 26, 5, 29, 3, 27, },
-{ 20, 12, 18, 10, 21, 13, 19, 11, },
-{ 1, 25, 7, 31, 0, 24, 6, 30, },
-};
-
-DECLARE_ALIGNED(8, const uint8_t, dither_8x8_73)[8][8]={
-{ 0, 55, 14, 68, 3, 58, 17, 72, },
-{ 37, 18, 50, 32, 40, 22, 54, 35, },
-{ 9, 64, 5, 59, 13, 67, 8, 63, },
-{ 46, 27, 41, 23, 49, 31, 44, 26, },
-{ 2, 57, 16, 71, 1, 56, 15, 70, },
-{ 39, 21, 52, 34, 38, 19, 51, 33, },
-{ 11, 66, 7, 62, 10, 65, 6, 60, },
-{ 48, 30, 43, 25, 47, 29, 42, 24, },
+DECLARE_ALIGNED(8, const uint8_t, dither_8x8_128)[8][8] = {
+ { 36, 68, 60, 92, 34, 66, 58, 90, },
+ { 100, 4, 124, 28, 98, 2, 122, 26, },
+ { 52, 84, 44, 76, 50, 82, 42, 74, },
+ { 116, 20, 108, 12, 114, 18, 106, 10, },
+ { 32, 64, 56, 88, 38, 70, 62, 94, },
+ { 96, 0, 120, 24, 102, 6, 126, 30, },
+ { 48, 80, 40, 72, 54, 86, 46, 78, },
+ { 112, 16, 104, 8, 118, 22, 110, 14, },