/*
- * Copyright (C) 2001-2003 Michael Niedermayer <michaelni@gmx.at>
+ * Copyright (C) 2001-2012 Michael Niedermayer <michaelni@gmx.at>
*
- * This file is part of Libav.
+ * This file is part of FFmpeg.
*
- * Libav is free software; you can redistribute it and/or
+ * FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
- * Libav is distributed in the hope that it will be useful,
+ * FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with Libav; if not, write to the Free Software
+ * License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <string.h>
#include "libavutil/avutil.h"
+#include "libavutil/avassert.h"
#include "libavutil/bswap.h"
#include "libavutil/cpu.h"
#include "libavutil/intreadwrite.h"
int big_endian, int output_bits)
{
int i;
- int shift = 19 - output_bits;
+ int shift = 3;
+ av_assert0(output_bits == 16);
for (i = 0; i < dstW; i++) {
int val = src[i] + (1 << (shift - 1));
int big_endian, int output_bits)
{
int i;
- int shift = 15 + 16 - output_bits;
+ int shift = 15;
+ av_assert0(output_bits == 16);
for (i = 0; i < dstW; i++) {
- int val = 1 << (30-output_bits);
+ int val = 1 << (shift - 1);
int j;
/* range of val is [0,0x7FFFFFFF], so 31 bits, but with lanczos/spline
int shift = 11 + 16 - output_bits;
for (i = 0; i < dstW; i++) {
- int val = 1 << (26-output_bits);
+ int val = 1 << (shift - 1);
int j;
for (j = 0; j < filterSize; j++)
}
}
+#define accumulate_bit(acc, val) \
+ acc <<= 1; \
+ acc |= (val) >= (128 + 110)
#define output_pixel(pos, acc) \
if (target == PIX_FMT_MONOBLACK) { \
pos = acc; \
int y, enum PixelFormat target)
{
const uint8_t * const d128=dither_8x8_220[y&7];
- uint8_t *g = c->table_gU[128] + c->table_gV[128];
int i;
unsigned acc = 0;
Y1 = av_clip_uint8(Y1);
Y2 = av_clip_uint8(Y2);
}
- acc += acc + g[Y1 + d128[(i + 0) & 7]];
- acc += acc + g[Y2 + d128[(i + 1) & 7]];
+ accumulate_bit(acc, Y1 + d128[(i + 0) & 7]);
+ accumulate_bit(acc, Y2 + d128[(i + 1) & 7]);
if ((i & 7) == 6) {
output_pixel(*dest++, acc);
}
{
const int16_t *buf0 = buf[0], *buf1 = buf[1];
const uint8_t * const d128 = dither_8x8_220[y & 7];
- uint8_t *g = c->table_gU[128] + c->table_gV[128];
int yalpha1 = 4095 - yalpha;
int i;
for (i = 0; i < dstW - 7; i += 8) {
- int acc = g[((buf0[i ] * yalpha1 + buf1[i ] * yalpha) >> 19) + d128[0]];
- acc += acc + g[((buf0[i + 1] * yalpha1 + buf1[i + 1] * yalpha) >> 19) + d128[1]];
- acc += acc + g[((buf0[i + 2] * yalpha1 + buf1[i + 2] * yalpha) >> 19) + d128[2]];
- acc += acc + g[((buf0[i + 3] * yalpha1 + buf1[i + 3] * yalpha) >> 19) + d128[3]];
- acc += acc + g[((buf0[i + 4] * yalpha1 + buf1[i + 4] * yalpha) >> 19) + d128[4]];
- acc += acc + g[((buf0[i + 5] * yalpha1 + buf1[i + 5] * yalpha) >> 19) + d128[5]];
- acc += acc + g[((buf0[i + 6] * yalpha1 + buf1[i + 6] * yalpha) >> 19) + d128[6]];
- acc += acc + g[((buf0[i + 7] * yalpha1 + buf1[i + 7] * yalpha) >> 19) + d128[7]];
+ 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);
}
}
int uvalpha, int y, enum PixelFormat target)
{
const uint8_t * const d128 = dither_8x8_220[y & 7];
- uint8_t *g = c->table_gU[128] + c->table_gV[128];
int i;
for (i = 0; i < dstW - 7; i += 8) {
- int acc = g[(buf0[i ] >> 7) + d128[0]];
- acc += acc + g[(buf0[i + 1] >> 7) + d128[1]];
- acc += acc + g[(buf0[i + 2] >> 7) + d128[2]];
- acc += acc + g[(buf0[i + 3] >> 7) + d128[3]];
- acc += acc + g[(buf0[i + 4] >> 7) + d128[4]];
- acc += acc + g[(buf0[i + 5] >> 7) + d128[5]];
- acc += acc + g[(buf0[i + 6] >> 7) + d128[6]];
- acc += acc + g[(buf0[i + 7] >> 7) + d128[7]];
+ 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);
}
}
#undef output_pixel
+#undef accumulate_bit
#define YUV2PACKEDWRAPPER(name, base, ext, fmt) \
static void name ## ext ## _X_c(SwsContext *c, const int16_t *lumFilter, \
int U = (ubuf0[i] * uvalpha1 + ubuf1[i] * uvalpha) >> 19;
int V = (vbuf0[i] * uvalpha1 + vbuf1[i] * uvalpha) >> 19;
+ if ((Y1 | Y2 | U | V) & 0x100) {
+ Y1 = av_clip_uint8(Y1);
+ Y2 = av_clip_uint8(Y2);
+ U = av_clip_uint8(U);
+ V = av_clip_uint8(V);
+ }
+
output_pixels(i * 4, Y1, U, Y2, V);
}
}
if (uvalpha < 2048) {
for (i = 0; i < (dstW >> 1); i++) {
- int Y1 = buf0[i * 2] >> 7;
- int Y2 = buf0[i * 2 + 1] >> 7;
- int U = ubuf0[i] >> 7;
- int V = vbuf0[i] >> 7;
+ int Y1 = (buf0[i * 2 ]+64) >> 7;
+ int Y2 = (buf0[i * 2 + 1]+64) >> 7;
+ int U = (ubuf0[i] +64) >> 7;
+ int V = (vbuf0[i] +64) >> 7;
+
+ if ((Y1 | Y2 | U | V) & 0x100) {
+ Y1 = av_clip_uint8(Y1);
+ Y2 = av_clip_uint8(Y2);
+ U = av_clip_uint8(U);
+ V = av_clip_uint8(V);
+ }
output_pixels(i * 4, Y1, U, Y2, V);
}
} else {
const int16_t *ubuf1 = ubuf[1], *vbuf1 = vbuf[1];
for (i = 0; i < (dstW >> 1); i++) {
- int Y1 = buf0[i * 2] >> 7;
- int Y2 = buf0[i * 2 + 1] >> 7;
- int U = (ubuf0[i] + ubuf1[i]) >> 8;
- int V = (vbuf0[i] + vbuf1[i]) >> 8;
+ int Y1 = (buf0[i * 2 ] + 64) >> 7;
+ int Y2 = (buf0[i * 2 + 1] + 64) >> 7;
+ int U = (ubuf0[i] + ubuf1[i]+128) >> 8;
+ int V = (vbuf0[i] + vbuf1[i]+128) >> 8;
+
+ if ((Y1 | Y2 | U | V) & 0x100) {
+ Y1 = av_clip_uint8(Y1);
+ Y2 = av_clip_uint8(Y2);
+ U = av_clip_uint8(U);
+ V = av_clip_uint8(V);
+ }
output_pixels(i * 4, Y1, U, Y2, V);
}
* correct RGB values into the destination buffer.
*/
static av_always_inline void
-yuv2rgb_write(uint8_t *_dest, int i, unsigned Y1, unsigned Y2,
+yuv2rgb_write(uint8_t *_dest, int i, int Y1, int Y2,
unsigned A1, unsigned A2,
const void *_r, const void *_g, const void *_b, int y,
enum PixelFormat target, int hasAlpha)
#define r_b ((target == PIX_FMT_RGB24) ? r : b)
#define b_r ((target == PIX_FMT_RGB24) ? b : r)
+
dest[i * 6 + 0] = r_b[Y1];
dest[i * 6 + 1] = g[Y1];
dest[i * 6 + 2] = b_r[Y1];
int i;
for (i = 0; i < (dstW >> 1); i++) {
- int j;
+ int j, A1, A2;
int Y1 = 1 << 18;
int Y2 = 1 << 18;
int U = 1 << 18;
int V = 1 << 18;
- int av_unused A1, A2;
const void *r, *g, *b;
for (j = 0; j < lumFilterSize; j++) {
Y2 >>= 19;
U >>= 19;
V >>= 19;
- if ((Y1 | Y2 | U | V) & 0x100) {
- Y1 = av_clip_uint8(Y1);
- Y2 = av_clip_uint8(Y2);
- U = av_clip_uint8(U);
- V = av_clip_uint8(V);
- }
if (hasAlpha) {
A1 = 1 << 18;
A2 = 1 << 18;
}
}
- /* FIXME fix tables so that clipping is not needed and then use _NOCLIP*/
- r = c->table_rV[V];
- g = (c->table_gU[U] + c->table_gV[V]);
- b = c->table_bU[U];
+ r = c->table_rV[V + YUVRGB_TABLE_HEADROOM];
+ g = (c->table_gU[U + YUVRGB_TABLE_HEADROOM] + c->table_gV[V + YUVRGB_TABLE_HEADROOM]);
+ b = c->table_bU[U + YUVRGB_TABLE_HEADROOM];
yuv2rgb_write(dest, i, Y1, Y2, hasAlpha ? A1 : 0, hasAlpha ? A2 : 0,
r, g, b, y, target, hasAlpha);
int U = (ubuf0[i] * uvalpha1 + ubuf1[i] * uvalpha) >> 19;
int V = (vbuf0[i] * uvalpha1 + vbuf1[i] * uvalpha) >> 19;
int A1, A2;
- const void *r = c->table_rV[V],
- *g = (c->table_gU[U] + c->table_gV[V]),
- *b = c->table_bU[U];
+ const void *r = c->table_rV[V + YUVRGB_TABLE_HEADROOM],
+ *g = (c->table_gU[U + YUVRGB_TABLE_HEADROOM] + c->table_gV[V + YUVRGB_TABLE_HEADROOM]),
+ *b = c->table_bU[U + YUVRGB_TABLE_HEADROOM];
if (hasAlpha) {
A1 = (abuf0[i * 2 ] * yalpha1 + abuf1[i * 2 ] * yalpha) >> 19;
if (uvalpha < 2048) {
for (i = 0; i < (dstW >> 1); i++) {
- int Y1 = buf0[i * 2] >> 7;
- int Y2 = buf0[i * 2 + 1] >> 7;
- int U = ubuf0[i] >> 7;
- int V = vbuf0[i] >> 7;
+ int Y1 = (buf0[i * 2 ] + 64) >> 7;
+ int Y2 = (buf0[i * 2 + 1] + 64) >> 7;
+ int U = (ubuf0[i] + 64) >> 7;
+ int V = (vbuf0[i] + 64) >> 7;
int A1, A2;
- const void *r = c->table_rV[V],
- *g = (c->table_gU[U] + c->table_gV[V]),
- *b = c->table_bU[U];
+ const void *r = c->table_rV[V + YUVRGB_TABLE_HEADROOM],
+ *g = (c->table_gU[U + YUVRGB_TABLE_HEADROOM] + c->table_gV[V + YUVRGB_TABLE_HEADROOM]),
+ *b = c->table_bU[U + YUVRGB_TABLE_HEADROOM];
if (hasAlpha) {
- A1 = abuf0[i * 2 ] >> 7;
- A2 = abuf0[i * 2 + 1] >> 7;
+ A1 = (abuf0[i * 2 ] + 64) >> 7;
+ A2 = (abuf0[i * 2 + 1] + 64) >> 7;
}
yuv2rgb_write(dest, i, Y1, Y2, hasAlpha ? A1 : 0, hasAlpha ? A2 : 0,
} else {
const int16_t *ubuf1 = ubuf[1], *vbuf1 = vbuf[1];
for (i = 0; i < (dstW >> 1); i++) {
- int Y1 = buf0[i * 2] >> 7;
- int Y2 = buf0[i * 2 + 1] >> 7;
- int U = (ubuf0[i] + ubuf1[i]) >> 8;
- int V = (vbuf0[i] + vbuf1[i]) >> 8;
+ int Y1 = (buf0[i * 2 ] + 64) >> 7;
+ int Y2 = (buf0[i * 2 + 1] + 64) >> 7;
+ int U = (ubuf0[i] + ubuf1[i] + 128) >> 8;
+ int V = (vbuf0[i] + vbuf1[i] + 128) >> 8;
int A1, A2;
- const void *r = c->table_rV[V],
- *g = (c->table_gU[U] + c->table_gV[V]),
- *b = c->table_bU[U];
+ const void *r = c->table_rV[V + YUVRGB_TABLE_HEADROOM],
+ *g = (c->table_gU[U + YUVRGB_TABLE_HEADROOM] + c->table_gV[V + YUVRGB_TABLE_HEADROOM]),
+ *b = c->table_bU[U + YUVRGB_TABLE_HEADROOM];
if (hasAlpha) {
- A1 = abuf0[i * 2 ] >> 7;
- A2 = abuf0[i * 2 + 1] >> 7;
+ A1 = (abuf0[i * 2 ] + 64) >> 7;
+ A2 = (abuf0[i * 2 + 1] + 64) >> 7;
}
yuv2rgb_write(dest, i, Y1, Y2, hasAlpha ? A1 : 0, hasAlpha ? A2 : 0,
for (i = 0; i < dstW; i++) {
int j;
- int Y = 0;
- int U = -128 << 19;
- int V = -128 << 19;
- int av_unused A;
- int R, G, B;
+ int Y = 1<<9;
+ int U = (1<<9)-(128 << 19);
+ int V = (1<<9)-(128 << 19);
+ int R, G, B, A;
for (j = 0; j < lumFilterSize; j++) {
Y += lumSrc[j][i] * lumFilter[j];
U >>= 10;
V >>= 10;
if (hasAlpha) {
- A = 1 << 21;
+ A = 1 << 18;
for (j = 0; j < lumFilterSize; j++) {
A += alpSrc[j][i] * lumFilter[j];
}
dest[1] = B >> 22;
dest[2] = G >> 22;
dest[3] = R >> 22;
- dest += 4;
break;
case PIX_FMT_BGR24:
dest[0] = B >> 22;
*yuv2packedX = yuv2bgr24_full_X_c;
break;
}
+ if(!*yuv2packedX)
+ goto YUV_PACKED;
} else {
+ YUV_PACKED:
switch (dstFormat) {
case PIX_FMT_RGB48LE:
*yuv2packed1 = yuv2rgb48le_1_c;