{ 112, 16,104, 8,118, 22,110, 14,},
}};
+uint16_t dither_scale[15][16]={
+{ 2, 3, 3, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,},
+{ 2, 3, 7, 7, 13, 13, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25,},
+{ 3, 3, 4, 15, 15, 29, 57, 57, 57, 113, 113, 113, 113, 113, 113, 113,},
+{ 3, 4, 4, 5, 31, 31, 61, 121, 241, 241, 241, 241, 481, 481, 481, 481,},
+{ 3, 4, 5, 5, 6, 63, 63, 125, 249, 497, 993, 993, 993, 993, 993, 1985,},
+{ 3, 5, 6, 6, 6, 7, 127, 127, 253, 505, 1009, 2017, 4033, 4033, 4033, 4033,},
+{ 3, 5, 6, 7, 7, 7, 8, 255, 255, 509, 1017, 2033, 4065, 8129,16257,16257,},
+{ 3, 5, 6, 8, 8, 8, 8, 9, 511, 511, 1021, 2041, 4081, 8161,16321,32641,},
+{ 3, 5, 7, 8, 9, 9, 9, 9, 10, 1023, 1023, 2045, 4089, 8177,16353,32705,},
+{ 3, 5, 7, 8, 10, 10, 10, 10, 10, 11, 2047, 2047, 4093, 8185,16369,32737,},
+{ 3, 5, 7, 8, 10, 11, 11, 11, 11, 11, 12, 4095, 4095, 8189,16377,32753,},
+{ 3, 5, 7, 9, 10, 12, 12, 12, 12, 12, 12, 13, 8191, 8191,16381,32761,},
+{ 3, 5, 7, 9, 10, 12, 13, 13, 13, 13, 13, 13, 14,16383,16383,32765,},
+{ 3, 5, 7, 9, 10, 12, 14, 14, 14, 14, 14, 14, 14, 15,32767,32767,},
+{ 3, 5, 7, 9, 11, 12, 14, 15, 15, 15, 15, 15, 15, 15, 16,65535,},
+};
+
static av_always_inline void yuv2yuvX16inC_template(const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize,
const int16_t *chrFilter, const int16_t **chrSrc, int chrFilterSize,
const int16_t **alpSrc, uint16_t *dest, uint16_t *uDest, uint16_t *vDest, uint16_t *aDest,
- int dstW, int chrDstW, int big_endian)
+ int dstW, int chrDstW, int big_endian, int output_bits)
{
//FIXME Optimize (just quickly written not optimized..)
int i;
-
+ int shift = 11 + 16 - output_bits;
+
+#define output_pixel(pos, val) \
+ if (big_endian) { \
+ if (output_bits == 16) { \
+ AV_WB16(pos, av_clip_uint16(val >> shift)); \
+ } else { \
+ AV_WB16(pos, av_clip_uintp2(val >> shift, output_bits)); \
+ } \
+ } else { \
+ if (output_bits == 16) { \
+ AV_WL16(pos, av_clip_uint16(val >> shift)); \
+ } else { \
+ AV_WL16(pos, av_clip_uintp2(val >> shift, output_bits)); \
+ } \
+ }
for (i = 0; i < dstW; i++) {
int val = 1 << 10;
int j;
for (j = 0; j < lumFilterSize; j++)
val += lumSrc[j][i] * lumFilter[j];
- if (big_endian) {
- AV_WB16(&dest[i], av_clip_uint16(val >> 11));
- } else {
- AV_WL16(&dest[i], av_clip_uint16(val >> 11));
- }
+ output_pixel(&dest[i], val);
}
if (uDest) {
v += chrSrc[j][i + VOFW] * chrFilter[j];
}
- if (big_endian) {
- AV_WB16(&uDest[i], av_clip_uint16(u >> 11));
- AV_WB16(&vDest[i], av_clip_uint16(v >> 11));
- } else {
- AV_WL16(&uDest[i], av_clip_uint16(u >> 11));
- AV_WL16(&vDest[i], av_clip_uint16(v >> 11));
- }
+ output_pixel(&uDest[i], u);
+ output_pixel(&vDest[i], v);
}
}
for (j = 0; j < lumFilterSize; j++)
val += alpSrc[j][i] * lumFilter[j];
- if (big_endian) {
- AV_WB16(&aDest[i], av_clip_uint16(val >> 11));
- } else {
- AV_WL16(&aDest[i], av_clip_uint16(val >> 11));
- }
+ output_pixel(&aDest[i], val);
}
}
}
chrFilter, chrSrc, chrFilterSize,
alpSrc,
dest, uDest, vDest, aDest,
- dstW, chrDstW, 1);
+ dstW, chrDstW, 1, 16);
} else {
yuv2yuvX16inC_template(lumFilter, lumSrc, lumFilterSize,
chrFilter, chrSrc, chrFilterSize,
alpSrc,
dest, uDest, vDest, aDest,
- dstW, chrDstW, 0);
+ dstW, chrDstW, 0, 16);
}
}
}
return srcSliceH;
}
-#define DITHER_COPY(dst, dstStride, src, srcStride, bswap)\
+#define DITHER_COPY(dst, dstStride, src, srcStride, bswap, dbswap)\
+ uint16_t scale= dither_scale[dst_depth-1][src_depth-1];\
+ int shift= src_depth-dst_depth + dither_scale[src_depth-2][dst_depth-1];\
for (i = 0; i < height; i++) {\
- int shift= src_depth-dst_depth;\
uint8_t *dither= dithers[src_depth-9][i&7];\
for (j = 0; j < length-7; j+=8){\
- dst[j+0] = (bswap(src[j+0]) + dither[0])>>shift;\
- dst[j+1] = (bswap(src[j+1]) + dither[1])>>shift;\
- dst[j+2] = (bswap(src[j+2]) + dither[2])>>shift;\
- dst[j+3] = (bswap(src[j+3]) + dither[3])>>shift;\
- dst[j+4] = (bswap(src[j+4]) + dither[4])>>shift;\
- dst[j+5] = (bswap(src[j+5]) + dither[5])>>shift;\
- dst[j+6] = (bswap(src[j+6]) + dither[6])>>shift;\
- dst[j+7] = (bswap(src[j+7]) + dither[7])>>shift;\
+ dst[j+0] = dbswap((bswap(src[j+0]) + dither[0])*scale>>shift);\
+ dst[j+1] = dbswap((bswap(src[j+1]) + dither[1])*scale>>shift);\
+ dst[j+2] = dbswap((bswap(src[j+2]) + dither[2])*scale>>shift);\
+ dst[j+3] = dbswap((bswap(src[j+3]) + dither[3])*scale>>shift);\
+ dst[j+4] = dbswap((bswap(src[j+4]) + dither[4])*scale>>shift);\
+ dst[j+5] = dbswap((bswap(src[j+5]) + dither[5])*scale>>shift);\
+ dst[j+6] = dbswap((bswap(src[j+6]) + dither[6])*scale>>shift);\
+ dst[j+7] = dbswap((bswap(src[j+7]) + dither[7])*scale>>shift);\
}\
for (; j < length; j++)\
- dst[j] = (bswap(src[j]) + dither[j&7])>>shift;\
+ dst[j] = dbswap((bswap(src[j]) + dither[j&7])*scale>>shift);\
dst += dstStride;\
src += srcStride;\
}
length*=2;
fillPlane(dst[plane], dstStride[plane], length, height, y, (plane==3) ? 255 : 128);
} else {
- if(isNBPS(c->srcFormat) || isNBPS(c->dstFormat)) {
+ if(isNBPS(c->srcFormat) || isNBPS(c->dstFormat)
+ || (is16BPS(c->srcFormat) != is16BPS(c->dstFormat))
+ ) {
const int src_depth = av_pix_fmt_descriptors[c->srcFormat].comp[plane].depth_minus1+1;
const int dst_depth = av_pix_fmt_descriptors[c->dstFormat].comp[plane].depth_minus1+1;
- uint16_t *srcPtr2 = (uint16_t*)srcPtr;
+ const uint16_t *srcPtr2 = (const uint16_t*)srcPtr;
uint16_t *dstPtr2 = (uint16_t*)dstPtr;
if (dst_depth == 8) {
- DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, )
+ if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
+ DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, , )
+ } else {
+ DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, av_bswap16, )
+ }
} else if (src_depth == 8) {
for (i = 0; i < height; i++) {
- for (j = 0; j < length; j++)
- dstPtr2[j] = (srcPtr[j]<<(dst_depth-8)) |
- (srcPtr[j]>>(2*8-dst_depth));
+ if(isBE(c->dstFormat)){
+ for (j = 0; j < length; j++)
+ AV_WB16(&dstPtr2[j], (srcPtr[j]<<(dst_depth-8)) |
+ (srcPtr[j]>>(2*8-dst_depth)));
+ } else {
+ for (j = 0; j < length; j++)
+ AV_WL16(&dstPtr2[j], (srcPtr[j]<<(dst_depth-8)) |
+ (srcPtr[j]>>(2*8-dst_depth)));
+ }
dstPtr2 += dstStride[plane]/2;
srcPtr += srcStride[plane];
}
- } else if (src_depth < dst_depth) {
+ } else if (src_depth <= dst_depth) {
for (i = 0; i < height; i++) {
- if(isBE(c->dstFormat)){
- for (j = 0; j < length; j++)
- AV_WB16(&dstPtr2[j], (srcPtr2[j]<<(dst_depth-src_depth)) |
- (srcPtr2[j]>>(2*src_depth-dst_depth)));
- }else{
- for (j = 0; j < length; j++)
- AV_WL16(&dstPtr2[j], (srcPtr2[j]<<(dst_depth-src_depth)) |
- (srcPtr2[j]>>(2*src_depth-dst_depth)));
+#define COPY_UP(r,w) \
+ for (j = 0; j < length; j++){ \
+ unsigned int v= r(&srcPtr2[j]);\
+ w(&dstPtr2[j], (v<<(dst_depth-src_depth)) | \
+ (v>>(2*src_depth-dst_depth)));\
+ }
+ if(isBE(c->srcFormat)){
+ if(isBE(c->dstFormat)){
+ COPY_UP(AV_RB16, AV_WB16)
+ } else {
+ COPY_UP(AV_RB16, AV_WL16)
+ }
+ } else {
+ if(isBE(c->dstFormat)){
+ COPY_UP(AV_RL16, AV_WB16)
+ } else {
+ COPY_UP(AV_RL16, AV_WL16)
+ }
}
dstPtr2 += dstStride[plane]/2;
srcPtr2 += srcStride[plane]/2;
}
} else {
if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
- DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, )
+ if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , )
+ } else {
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , av_bswap16)
+ }
}else{
- DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16)
- }
- }
- } else if(is16BPS(c->srcFormat) && !is16BPS(c->dstFormat)) {
- //FIXME add dither
- if (!isBE(c->srcFormat)) srcPtr++;
- for (i=0; i<height; i++) {
- for (j=0; j<length; j++) dstPtr[j] = srcPtr[j<<1];
- srcPtr+= srcStride[plane];
- dstPtr+= dstStride[plane];
- }
- } else if(!is16BPS(c->srcFormat) && is16BPS(c->dstFormat)) {
- for (i=0; i<height; i++) {
- for (j=0; j<length; j++) {
- dstPtr[ j<<1 ] = srcPtr[j];
- dstPtr[(j<<1)+1] = srcPtr[j];
+ if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, )
+ } else {
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, av_bswap16)
+ }
}
- srcPtr+= srcStride[plane];
- dstPtr+= dstStride[plane];
}
} else if(is16BPS(c->srcFormat) && is16BPS(c->dstFormat)
&& isBE(c->srcFormat) != isBE(c->dstFormat)) {
projects / ffmpeg / blobdiff