i420_yuy2.h 8.87 KB
Newer Older
1 2 3 4
/*****************************************************************************
 * i420_yuy2.h : YUV to YUV conversion module for vlc
 *****************************************************************************
 * Copyright (C) 2000, 2001 VideoLAN
5
 * $Id: i420_yuy2.h,v 1.2 2003/08/29 18:58:05 fenrir Exp $
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134
 *
 * Authors: Samuel Hocevar <sam@zoy.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 * 
 * This program 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 General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111, USA.
 *****************************************************************************/

#ifdef MODULE_NAME_IS_i420_yuy2_mmx

#define MMX_CALL(MMX_INSTRUCTIONS)                                          \
    do {                                                                    \
    __asm__ __volatile__(                                                   \
        ".align 8 \n\t"                                                     \
        MMX_INSTRUCTIONS                                                    \
        :                                                                   \
        : "r" (p_line1),  "r" (p_line2),  "r" (p_y1),  "r" (p_y2),          \
          "r" (p_u), "r" (p_v) );                                           \
    p_line1 += 16; p_line2 += 16; p_y1 += 8; p_y2 += 8; p_u += 4; p_v += 4; \
    } while(0);                                                             \

#define MMX_YUV420_YUYV "                                                 \n\
movq       (%2), %%mm0  # Load 8 Y            y7 y6 y5 y4 y3 y2 y1 y0     \n\
movd       (%4), %%mm1  # Load 4 Cb           00 00 00 00 u3 u2 u1 u0     \n\
movd       (%5), %%mm2  # Load 4 Cr           00 00 00 00 v3 v2 v1 v0     \n\
punpcklbw %%mm2, %%mm1  #                     v3 u3 v2 u2 v1 u1 v0 u0     \n\
movq      %%mm0, %%mm2  #                     y7 y6 y5 y4 y3 y2 y1 y0     \n\
punpcklbw %%mm1, %%mm2  #                     v1 y3 u1 y2 v0 y1 u0 y0     \n\
movq      %%mm2, (%0)   # Store low YUYV                                  \n\
punpckhbw %%mm1, %%mm0  #                     v3 y7 u3 y6 v2 y5 u2 y4     \n\
movq      %%mm0, 8(%0)  # Store high YUYV                                 \n\
movq       (%3), %%mm0  # Load 8 Y            Y7 Y6 Y5 Y4 Y3 Y2 Y1 Y0     \n\
movq      %%mm0, %%mm2  #                     Y7 Y6 Y5 Y4 Y3 Y2 Y1 Y0     \n\
punpcklbw %%mm1, %%mm2  #                     v1 Y3 u1 Y2 v0 Y1 u0 Y0     \n\
movq      %%mm2, (%1)   # Store low YUYV                                  \n\
punpckhbw %%mm1, %%mm0  #                     v3 Y7 u3 Y6 v2 Y5 u2 Y4     \n\
movq      %%mm0, 8(%1)  # Store high YUYV                                 \n\
"

#define MMX_YUV420_YVYU "                                                 \n\
movq       (%2), %%mm0  # Load 8 Y            y7 y6 y5 y4 y3 y2 y1 y0     \n\
movd       (%4), %%mm2  # Load 4 Cb           00 00 00 00 u3 u2 u1 u0     \n\
movd       (%5), %%mm1  # Load 4 Cr           00 00 00 00 v3 v2 v1 v0     \n\
punpcklbw %%mm2, %%mm1  #                     u3 v3 u2 v2 u1 v1 u0 v0     \n\
movq      %%mm0, %%mm2  #                     y7 y6 y5 y4 y3 y2 y1 y0     \n\
punpcklbw %%mm1, %%mm2  #                     u1 y3 v1 y2 u0 y1 v0 y0     \n\
movq      %%mm2, (%0)   # Store low YUYV                                  \n\
punpckhbw %%mm1, %%mm0  #                     u3 y7 v3 y6 u2 y5 v2 y4     \n\
movq      %%mm0, 8(%0)  # Store high YUYV                                 \n\
movq       (%3), %%mm0  # Load 8 Y            Y7 Y6 Y5 Y4 Y3 Y2 Y1 Y0     \n\
movq      %%mm0, %%mm2  #                     Y7 Y6 Y5 Y4 Y3 Y2 Y1 Y0     \n\
punpcklbw %%mm1, %%mm2  #                     u1 Y3 v1 Y2 u0 Y1 v0 Y0     \n\
movq      %%mm2, (%1)   # Store low YUYV                                  \n\
punpckhbw %%mm1, %%mm0  #                     u3 Y7 v3 Y6 u2 Y5 v2 Y4     \n\
movq      %%mm0, 8(%1)  # Store high YUYV                                 \n\
"

#define MMX_YUV420_UYVY "                                                 \n\
movq       (%2), %%mm0  # Load 8 Y            y7 y6 y5 y4 y3 y2 y1 y0     \n\
movq       (%3), %%mm3  # Load 8 Y            Y7 Y6 Y5 Y4 Y3 Y2 Y1 Y0     \n\
movd       (%4), %%mm2  # Load 4 Cb           00 00 00 00 u3 u2 u1 u0     \n\
movd       (%5), %%mm1  # Load 4 Cr           00 00 00 00 v3 v2 v1 v0     \n\
punpcklbw %%mm2, %%mm1  #                     u3 v3 u2 v2 u1 v1 u0 v0     \n\
movq      %%mm1, %%mm2  #                     u3 v3 u2 v2 u1 v1 u0 v0     \n\
punpcklbw %%mm0, %%mm2  #                     y3 v1 y2 u1 y1 v0 y0 u0     \n\
movq      %%mm2, (%0)   # Store low UYVY                                  \n\
movq      %%mm1, %%mm2  #                     u3 v3 u2 v2 u1 v1 u0 v0     \n\
punpckhbw %%mm0, %%mm2  #                     y3 v1 y2 u1 y1 v0 y0 u0     \n\
movq      %%mm2, 8(%0)  # Store high UYVY                                 \n\
movq      %%mm1, %%mm2  #                     u3 v3 u2 v2 u1 v1 u0 v0     \n\
punpcklbw %%mm3, %%mm2  #                     Y3 v1 Y2 u1 Y1 v0 Y0 u0     \n\
movq      %%mm2, (%1)   # Store low UYVY                                  \n\
punpckhbw %%mm3, %%mm1  #                     Y7 v3 Y6 u3 Y5 v2 Y4 u2     \n\
movq      %%mm1, 8(%1)  # Store high UYVY                                 \n\
"

/* FIXME: this code does not work ! Chroma seems to be wrong. */
#define MMX_YUV420_Y211 "                                                 \n\
movq       (%2), %%mm0  # Load 8 Y            y7 y6 y5 y4 y3 y2 y1 y0     \n\
movq       (%3), %%mm1  # Load 8 Y            Y7 Y6 Y5 Y4 Y3 Y2 Y1 Y0     \n\
movd       (%4), %%mm2  # Load 4 Cb           00 00 00 00 u3 u2 u1 u0     \n\
movd       (%5), %%mm3  # Load 4 Cr           00 00 00 00 v3 v2 v1 v0     \n\
pand    i_00ffw, %%mm0  # get Y even          00 Y6 00 Y4 00 Y2 00 Y0     \n\
packuswb  %%mm0, %%mm0  # pack Y              y6 y4 y2 y0 y6 y4 y2 y0     \n\
pand    i_00ffw, %%mm2  # get U even          00 u6 00 u4 00 u2 00 u0     \n\
packuswb  %%mm2, %%mm2  # pack U              00 00 u2 u0 00 00 u2 u0     \n\
pand    i_00ffw, %%mm3  # get V even          00 v6 00 v4 00 v2 00 v0     \n\
packuswb  %%mm3, %%mm3  # pack V              00 00 v2 v0 00 00 v2 v0     \n\
punpcklbw %%mm3, %%mm2  #                     00 00 00 00 v2 u2 v0 u0     \n\
psubsw    i_80w, %%mm2  # U,V -= 128                                      \n\
punpcklbw %%mm2, %%mm0  #                     v2 y6 u2 y4 v0 y2 u0 y0     \n\
movq      %%mm0, (%0)   # Store YUYV                                      \n\
pand    i_00ffw, %%mm1  # get Y even          00 Y6 00 Y4 00 Y2 00 Y0     \n\
packuswb  %%mm1, %%mm1  # pack Y              Y6 Y4 Y2 Y0 Y6 Y4 Y2 Y0     \n\
punpcklbw %%mm2, %%mm1  #                     v2 Y6 u2 Y4 v0 Y2 u0 Y0     \n\
movq      %%mm1, (%1)   # Store YUYV                                      \n\
"

#else

#define C_YUV420_YUYV( )                                                    \
    *(p_line1)++ = *(p_y1)++; *(p_line2)++ = *(p_y2)++;                     \
    *(p_line1)++ =            *(p_line2)++ = *(p_u)++;                      \
    *(p_line1)++ = *(p_y1)++; *(p_line2)++ = *(p_y2)++;                     \
    *(p_line1)++ =            *(p_line2)++ = *(p_v)++;                      \

#define C_YUV420_YVYU( )                                                    \
    *(p_line1)++ = *(p_y1)++; *(p_line2)++ = *(p_y2)++;                     \
    *(p_line1)++ =            *(p_line2)++ = *(p_v)++;                      \
    *(p_line1)++ = *(p_y1)++; *(p_line2)++ = *(p_y2)++;                     \
    *(p_line1)++ =            *(p_line2)++ = *(p_u)++;                      \

#define C_YUV420_UYVY( )                                                    \
    *(p_line1)++ =            *(p_line2)++ = *(p_u)++;                      \
    *(p_line1)++ = *(p_y1)++; *(p_line2)++ = *(p_y2)++;                     \
    *(p_line1)++ =            *(p_line2)++ = *(p_v)++;                      \
    *(p_line1)++ = *(p_y1)++; *(p_line2)++ = *(p_y2)++;                     \

#define C_YUV420_Y211( )                                                    \
135 136 137 138 139 140
    *(p_line1)++ = *(p_y1); ((uint16_t*)p_y1)++;                            \
    *(p_line2)++ = *(p_y2); ((uint16_t*)p_y2)++;                            \
    *(p_line1)++ = *(p_line2)++ = *(p_u) - 0x80; ((uint16_t*)p_u)++;        \
    *(p_line1)++ = *(p_y1); ((uint16_t*)p_y1)++;                            \
    *(p_line2)++ = *(p_y2); ((uint16_t*)p_y2)++;                            \
    *(p_line1)++ = *(p_line2)++ = *(p_v) - 0x80; ((uint16_t*)p_v)++;        \
141 142 143

#endif