#include "libavutil/cpu.h"
#include "libavutil/intreadwrite.h"
#include "libavutil/mathematics.h"
+#include "libavutil/mem_internal.h"
#include "libavutil/pixdesc.h"
#include "config.h"
#include "rgb2rgb.h"
}
}
-static void yuv2p016cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
+static void yuv2p016cX_c(enum AVPixelFormat dstFormat, const uint8_t *chrDither,
+ const int16_t *chrFilter, int chrFilterSize,
const int16_t **chrUSrc, const int16_t **chrVSrc,
uint8_t *dest8, int chrDstW)
{
const int32_t **uSrc = (const int32_t **)chrUSrc;
const int32_t **vSrc = (const int32_t **)chrVSrc;
int shift = 15;
- int big_endian = c->dstFormat == AV_PIX_FMT_P016BE;
+ int big_endian = dstFormat == AV_PIX_FMT_P016BE;
int i, j;
for (i = 0; i < chrDstW; i++) {
}
}
-static void yuv2nv12cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
- const int16_t **chrUSrc, const int16_t **chrVSrc,
- uint8_t *dest, int chrDstW)
+static void yuv2nv12cX_c(enum AVPixelFormat dstFormat, const uint8_t *chrDither,
+ const int16_t *chrFilter, int chrFilterSize,
+ const int16_t **chrUSrc, const int16_t **chrVSrc,
+ uint8_t *dest, int chrDstW)
{
- enum AVPixelFormat dstFormat = c->dstFormat;
- const uint8_t *chrDither = c->chrDither8;
int i;
- if (dstFormat == AV_PIX_FMT_NV12)
+ if (dstFormat == AV_PIX_FMT_NV12 ||
+ dstFormat == AV_PIX_FMT_NV24)
for (i=0; i<chrDstW; i++) {
int u = chrDither[i & 7] << 12;
int v = chrDither[(i + 3) & 7] << 12;
}
}
-static void yuv2p010cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
+static void yuv2p010cX_c(enum AVPixelFormat dstFormat, const uint8_t *chrDither,
+ const int16_t *chrFilter, int chrFilterSize,
const int16_t **chrUSrc, const int16_t **chrVSrc,
uint8_t *dest8, int chrDstW)
{
uint16_t *dest = (uint16_t*)dest8;
int shift = 17;
- int big_endian = c->dstFormat == AV_PIX_FMT_P010BE;
+ int big_endian = dstFormat == AV_PIX_FMT_P010BE;
int i, j;
for (i = 0; i < chrDstW; i++) {
}
c->dither_error[0][i] = err;
} else {
- for (i = 0; i < dstW; i += 8) {
- int Y, acc = 0;
-
- Y = (buf0[i + 0] * yalpha1 + buf1[i + 0] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[0]);
- Y = (buf0[i + 1] * yalpha1 + buf1[i + 1] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[1]);
- Y = (buf0[i + 2] * yalpha1 + buf1[i + 2] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[2]);
- Y = (buf0[i + 3] * yalpha1 + buf1[i + 3] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[3]);
- Y = (buf0[i + 4] * yalpha1 + buf1[i + 4] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[4]);
- Y = (buf0[i + 5] * yalpha1 + buf1[i + 5] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[5]);
- Y = (buf0[i + 6] * yalpha1 + buf1[i + 6] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[6]);
- Y = (buf0[i + 7] * yalpha1 + buf1[i + 7] * yalpha) >> 19;
- accumulate_bit(acc, Y + d128[7]);
-
- output_pixel(*dest++, acc);
- }
+ for (i = 0; i < dstW; i += 8) {
+ int Y, acc = 0;
+
+ Y = (buf0[i + 0] * yalpha1 + buf1[i + 0] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[0]);
+ Y = (buf0[i + 1] * yalpha1 + buf1[i + 1] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[1]);
+ Y = (buf0[i + 2] * yalpha1 + buf1[i + 2] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[2]);
+ Y = (buf0[i + 3] * yalpha1 + buf1[i + 3] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[3]);
+ Y = (buf0[i + 4] * yalpha1 + buf1[i + 4] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[4]);
+ Y = (buf0[i + 5] * yalpha1 + buf1[i + 5] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[5]);
+ Y = (buf0[i + 6] * yalpha1 + buf1[i + 6] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[6]);
+ Y = (buf0[i + 7] * yalpha1 + buf1[i + 7] * yalpha) >> 19;
+ accumulate_bit(acc, Y + d128[7]);
+
+ output_pixel(*dest++, acc);
+ }
}
}
}
c->dither_error[0][i] = err;
} else {
- for (i = 0; i < dstW; i += 8) {
- int acc = 0;
- accumulate_bit(acc, ((buf0[i + 0] + 64) >> 7) + d128[0]);
- accumulate_bit(acc, ((buf0[i + 1] + 64) >> 7) + d128[1]);
- accumulate_bit(acc, ((buf0[i + 2] + 64) >> 7) + d128[2]);
- accumulate_bit(acc, ((buf0[i + 3] + 64) >> 7) + d128[3]);
- accumulate_bit(acc, ((buf0[i + 4] + 64) >> 7) + d128[4]);
- accumulate_bit(acc, ((buf0[i + 5] + 64) >> 7) + d128[5]);
- accumulate_bit(acc, ((buf0[i + 6] + 64) >> 7) + d128[6]);
- accumulate_bit(acc, ((buf0[i + 7] + 64) >> 7) + d128[7]);
-
- output_pixel(*dest++, acc);
- }
+ for (i = 0; i < dstW; i += 8) {
+ int acc = 0;
+ accumulate_bit(acc, ((buf0[i + 0] + 64) >> 7) + d128[0]);
+ accumulate_bit(acc, ((buf0[i + 1] + 64) >> 7) + d128[1]);
+ accumulate_bit(acc, ((buf0[i + 2] + 64) >> 7) + d128[2]);
+ accumulate_bit(acc, ((buf0[i + 3] + 64) >> 7) + d128[3]);
+ accumulate_bit(acc, ((buf0[i + 4] + 64) >> 7) + d128[4]);
+ accumulate_bit(acc, ((buf0[i + 5] + 64) >> 7) + d128[5]);
+ accumulate_bit(acc, ((buf0[i + 6] + 64) >> 7) + d128[6]);
+ accumulate_bit(acc, ((buf0[i + 7] + 64) >> 7) + d128[7]);
+
+ output_pixel(*dest++, acc);
+ }
}
}
for (i = 0; i < dstW; i++) {
int j;
- int Y = 1 << 18;
- int64_t A = 0xffff<<14;
+ int Y = -0x40000000;
+ int A = 0xffff;
for (j = 0; j < lumFilterSize; j++)
Y += lumSrc[j][i] * lumFilter[j];
Y >>= 15;
+ Y += (1<<3) + 0x8000;
Y = av_clip_uint16(Y);
if (hasAlpha) {
+ A = -0x40000000 + (1<<14);
for (j = 0; j < lumFilterSize; j++)
A += alpSrc[j][i] * lumFilter[j];
A >>= 15;
+ A += 0x8000;
A = av_clip_uint16(A);
}
output_pixel(&dest[2 * i ], Y);
- output_pixel(&dest[2 * i + 1], hasAlpha ? A : 65535);
+ output_pixel(&dest[2 * i + 1], A);
}
}
dest[i * 2 + 0] = r[Y1 + dr1] + g[Y1 + dg1] + b[Y1 + db1];
dest[i * 2 + 1] = r[Y2 + dr2] + g[Y2 + dg2] + b[Y2 + db2];
+ } else if (target == AV_PIX_FMT_X2RGB10) {
+ uint32_t *dest = (uint32_t *) _dest;
+ const uint32_t *r = (const uint32_t *) _r;
+ const uint32_t *g = (const uint32_t *) _g;
+ const uint32_t *b = (const uint32_t *) _b;
+ dest[i * 2 + 0] = r[Y1] + g[Y1] + b[Y1];
+ dest[i * 2 + 1] = r[Y2] + g[Y2] + b[Y2];
} else /* 8/4 bits */ {
uint8_t *dest = (uint8_t *) _dest;
const uint8_t *r = (const uint8_t *) _r;
YUV2RGBWRAPPER(yuv2rgb,, 8, AV_PIX_FMT_RGB8, 0)
YUV2RGBWRAPPER(yuv2rgb,, 4, AV_PIX_FMT_RGB4, 0)
YUV2RGBWRAPPER(yuv2rgb,, 4b, AV_PIX_FMT_RGB4_BYTE, 0)
+YUV2RGBWRAPPER(yuv2, rgb, x2rgb10, AV_PIX_FMT_X2RGB10, 0)
static av_always_inline void yuv2rgb_write_full(SwsContext *c,
uint8_t *dest, int i, int Y, int A, int U, int V,
Y -= c->yuv2rgb_y_offset;
Y *= c->yuv2rgb_y_coeff;
Y += 1 << 21;
- R = Y + V*c->yuv2rgb_v2r_coeff;
- G = Y + V*c->yuv2rgb_v2g_coeff + U*c->yuv2rgb_u2g_coeff;
- B = Y + U*c->yuv2rgb_u2b_coeff;
+ R = (unsigned)Y + V*c->yuv2rgb_v2r_coeff;
+ G = (unsigned)Y + V*c->yuv2rgb_v2g_coeff + U*c->yuv2rgb_u2g_coeff;
+ B = (unsigned)Y + U*c->yuv2rgb_u2b_coeff;
if ((R | G | B) & 0xC0000000) {
R = av_clip_uintp2(R, 30);
G = av_clip_uintp2(G, 30);
if (uvalpha < 2048) {
int A = 0; //init to silence warning
for (i = 0; i < dstW; i++) {
- int Y = buf0[i] << 2;
+ int Y = buf0[i] * 4;
int U = (ubuf0[i] - (128<<7)) * 4;
int V = (vbuf0[i] - (128<<7)) * 4;
const int16_t *ubuf1 = ubuf[1], *vbuf1 = vbuf[1];
int A = 0; //init to silence warning
for (i = 0; i < dstW; i++) {
- int Y = buf0[i] << 2;
- int U = (ubuf0[i] + ubuf1[i] - (128<<8)) << 1;
- int V = (vbuf0[i] + vbuf1[i] - (128<<8)) << 1;
+ int Y = buf0[i] * 4;
+ int U = (ubuf0[i] + ubuf1[i] - (128<<8)) * 2;
+ int V = (vbuf0[i] + vbuf1[i] - (128<<8)) * 2;
if (hasAlpha) {
A = (abuf0[i] + 64) >> 7;
A = -0x40000000;
for (j = 0; j < lumFilterSize; j++)
- A += alpSrc[j][i] * lumFilter[j];
+ A += alpSrc[j][i] * (unsigned)lumFilter[j];
A >>= 1;
A += 0x20002000;
}
}
+static void
+yuv2gbrpf32_full_X_c(SwsContext *c, const int16_t *lumFilter,
+ const int16_t **lumSrcx, int lumFilterSize,
+ const int16_t *chrFilter, const int16_t **chrUSrcx,
+ const int16_t **chrVSrcx, int chrFilterSize,
+ const int16_t **alpSrcx, uint8_t **dest,
+ int dstW, int y)
+{
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->dstFormat);
+ int i;
+ int hasAlpha = (desc->flags & AV_PIX_FMT_FLAG_ALPHA) && alpSrcx;
+ uint32_t **dest32 = (uint32_t**)dest;
+ const int32_t **lumSrc = (const int32_t**)lumSrcx;
+ const int32_t **chrUSrc = (const int32_t**)chrUSrcx;
+ const int32_t **chrVSrc = (const int32_t**)chrVSrcx;
+ const int32_t **alpSrc = (const int32_t**)alpSrcx;
+ static const float float_mult = 1.0f / 65535.0f;
+
+ for (i = 0; i < dstW; i++) {
+ int j;
+ int Y = -0x40000000;
+ int U = -(128 << 23);
+ int V = -(128 << 23);
+ int R, G, B, A;
+
+ for (j = 0; j < lumFilterSize; j++)
+ Y += lumSrc[j][i] * (unsigned)lumFilter[j];
+
+ for (j = 0; j < chrFilterSize; j++) {
+ U += chrUSrc[j][i] * (unsigned)chrFilter[j];
+ V += chrVSrc[j][i] * (unsigned)chrFilter[j];
+ }
+
+ Y >>= 14;
+ Y += 0x10000;
+ U >>= 14;
+ V >>= 14;
+
+ if (hasAlpha) {
+ A = -0x40000000;
+
+ for (j = 0; j < lumFilterSize; j++)
+ A += alpSrc[j][i] * (unsigned)lumFilter[j];
+
+ A >>= 1;
+ A += 0x20002000;
+ }
+
+ Y -= c->yuv2rgb_y_offset;
+ Y *= c->yuv2rgb_y_coeff;
+ Y += 1 << 13;
+ R = V * c->yuv2rgb_v2r_coeff;
+ G = V * c->yuv2rgb_v2g_coeff + U * c->yuv2rgb_u2g_coeff;
+ B = U * c->yuv2rgb_u2b_coeff;
+
+ R = av_clip_uintp2(Y + R, 30);
+ G = av_clip_uintp2(Y + G, 30);
+ B = av_clip_uintp2(Y + B, 30);
+
+ dest32[0][i] = av_float2int(float_mult * (float)(G >> 14));
+ dest32[1][i] = av_float2int(float_mult * (float)(B >> 14));
+ dest32[2][i] = av_float2int(float_mult * (float)(R >> 14));
+ if (hasAlpha)
+ dest32[3][i] = av_float2int(float_mult * (float)(av_clip_uintp2(A, 30) >> 14));
+ }
+ if ((!isBE(c->dstFormat)) != (!HAVE_BIGENDIAN)) {
+ for (i = 0; i < dstW; i++) {
+ dest32[0][i] = av_bswap32(dest32[0][i]);
+ dest32[1][i] = av_bswap32(dest32[1][i]);
+ dest32[2][i] = av_bswap32(dest32[2][i]);
+ if (hasAlpha)
+ dest32[3][i] = av_bswap32(dest32[3][i]);
+ }
+ }
+}
+
static void
yuv2ya8_1_c(SwsContext *c, const int16_t *buf0,
const int16_t *ubuf[2], const int16_t *vbuf[2],
} else {
*yuv2plane1 = yuv2plane1_8_c;
*yuv2planeX = yuv2planeX_8_c;
- if (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21)
+ if (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21 ||
+ dstFormat == AV_PIX_FMT_NV24 || dstFormat == AV_PIX_FMT_NV42)
*yuv2nv12cX = yuv2nv12cX_c;
}
case AV_PIX_FMT_GBRAP16LE:
*yuv2anyX = yuv2gbrp16_full_X_c;
break;
+ case AV_PIX_FMT_GBRPF32BE:
+ case AV_PIX_FMT_GBRPF32LE:
+ case AV_PIX_FMT_GBRAPF32BE:
+ case AV_PIX_FMT_GBRAPF32LE:
+ *yuv2anyX = yuv2gbrpf32_full_X_c;
+ break;
}
if (!*yuv2packedX && !*yuv2anyX)
goto YUV_PACKED;
*yuv2packed2 = yuv2rgb4b_2_c;
*yuv2packedX = yuv2rgb4b_X_c;
break;
+ case AV_PIX_FMT_X2RGB10LE:
+ case AV_PIX_FMT_X2RGB10BE:
+ *yuv2packed1 = yuv2x2rgb10_1_c;
+ *yuv2packed2 = yuv2x2rgb10_2_c;
+ *yuv2packedX = yuv2x2rgb10_X_c;
+ break;
}
}
switch (dstFormat) {