qpel_template.c 14.6 KB
Newer Older
1
/*
2
 * quarterpel DSP function templates
3 4
 * Copyright (c) 2000, 2001 Fabrice Bellard
 * Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
5
 *
6
 * This file is part of FFmpeg.
7
 *
8
 * FFmpeg is free software; you can redistribute it and/or
9 10 11 12
 * 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.
 *
13
 * FFmpeg is distributed in the hope that it will be useful,
14 15 16 17 18
 * 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
19
 * License along with FFmpeg; if not, write to the Free Software
20 21 22 23 24
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

/**
 * @file
25
 * quarterpel DSP function templates
26 27
 */

28
#define PIXOP2(OPNAME, OP)                                              \
29 30 31 32 33 34 35
static inline void OPNAME ## _no_rnd_pixels8_l2_8(uint8_t *dst,         \
                                                  const uint8_t *src1,  \
                                                  const uint8_t *src2,  \
                                                  int dst_stride,       \
                                                  int src_stride1,      \
                                                  int src_stride2,      \
                                                  int h)                \
36 37 38 39
{                                                                       \
    int i;                                                              \
                                                                        \
    for (i = 0; i < h; i++) {                                           \
40 41 42 43 44 45 46 47 48
        uint32_t a, b;                                                  \
        a = AV_RN32(&src1[i * src_stride1]);                            \
        b = AV_RN32(&src2[i * src_stride2]);                            \
        OP(*((uint32_t *) &dst[i * dst_stride]),                        \
           no_rnd_avg32(a, b));                                         \
        a = AV_RN32(&src1[i * src_stride1 + 4]);                        \
        b = AV_RN32(&src2[i * src_stride2 + 4]);                        \
        OP(*((uint32_t *) &dst[i * dst_stride + 4]),                    \
           no_rnd_avg32(a, b));                                         \
49 50 51
    }                                                                   \
}                                                                       \
                                                                        \
52 53 54 55 56 57 58
static inline void OPNAME ## _no_rnd_pixels16_l2_8(uint8_t *dst,        \
                                                   const uint8_t *src1, \
                                                   const uint8_t *src2, \
                                                   int dst_stride,      \
                                                   int src_stride1,     \
                                                   int src_stride2,     \
                                                   int h)               \
59
{                                                                       \
60 61 62 63 64 65 66
    OPNAME ## _no_rnd_pixels8_l2_8(dst, src1, src2, dst_stride,         \
                                   src_stride1, src_stride2, h);        \
    OPNAME ## _no_rnd_pixels8_l2_8(dst  + 8,                            \
                                   src1 + 8,                            \
                                   src2 + 8,                            \
                                   dst_stride, src_stride1,             \
                                   src_stride2, h);                     \
67 68
}                                                                       \
                                                                        \
69 70 71 72 73 74 75 76 77 78 79
static inline void OPNAME ## _pixels8_l4_8(uint8_t *dst,                \
                                           const uint8_t *src1,         \
                                           const uint8_t *src2,         \
                                           const uint8_t *src3,         \
                                           const uint8_t *src4,         \
                                           int dst_stride,              \
                                           int src_stride1,             \
                                           int src_stride2,             \
                                           int src_stride3,             \
                                           int src_stride4,             \
                                           int h)                       \
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
{                                                                       \
    /* FIXME HIGH BIT DEPTH */                                          \
    int i;                                                              \
                                                                        \
    for (i = 0; i < h; i++) {                                           \
        uint32_t a, b, c, d, l0, l1, h0, h1;                            \
        a  = AV_RN32(&src1[i * src_stride1]);                           \
        b  = AV_RN32(&src2[i * src_stride2]);                           \
        c  = AV_RN32(&src3[i * src_stride3]);                           \
        d  = AV_RN32(&src4[i * src_stride4]);                           \
        l0 = (a & 0x03030303UL) +                                       \
             (b & 0x03030303UL) +                                       \
                  0x02020202UL;                                         \
        h0 = ((a & 0xFCFCFCFCUL) >> 2) +                                \
             ((b & 0xFCFCFCFCUL) >> 2);                                 \
        l1 = (c & 0x03030303UL) +                                       \
             (d & 0x03030303UL);                                        \
        h1 = ((c & 0xFCFCFCFCUL) >> 2) +                                \
             ((d & 0xFCFCFCFCUL) >> 2);                                 \
        OP(*((uint32_t *) &dst[i * dst_stride]),                        \
           h0 + h1 + (((l0 + l1) >> 2) & 0x0F0F0F0FUL));                \
        a  = AV_RN32(&src1[i * src_stride1 + 4]);                       \
        b  = AV_RN32(&src2[i * src_stride2 + 4]);                       \
        c  = AV_RN32(&src3[i * src_stride3 + 4]);                       \
        d  = AV_RN32(&src4[i * src_stride4 + 4]);                       \
        l0 = (a & 0x03030303UL) +                                       \
             (b & 0x03030303UL) +                                       \
                  0x02020202UL;                                         \
        h0 = ((a & 0xFCFCFCFCUL) >> 2) +                                \
             ((b & 0xFCFCFCFCUL) >> 2);                                 \
        l1 = (c & 0x03030303UL) +                                       \
             (d & 0x03030303UL);                                        \
        h1 = ((c & 0xFCFCFCFCUL) >> 2) +                                \
             ((d & 0xFCFCFCFCUL) >> 2);                                 \
        OP(*((uint32_t *) &dst[i * dst_stride + 4]),                    \
           h0 + h1 + (((l0 + l1) >> 2) & 0x0F0F0F0FUL));                \
    }                                                                   \
}                                                                       \
                                                                        \
119 120 121 122 123 124 125 126 127 128 129
static inline void OPNAME ## _no_rnd_pixels8_l4_8(uint8_t *dst,         \
                                                  const uint8_t *src1,  \
                                                  const uint8_t *src2,  \
                                                  const uint8_t *src3,  \
                                                  const uint8_t *src4,  \
                                                  int dst_stride,       \
                                                  int src_stride1,      \
                                                  int src_stride2,      \
                                                  int src_stride3,      \
                                                  int src_stride4,      \
                                                  int h)                \
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
{                                                                       \
    /* FIXME HIGH BIT DEPTH */                                          \
    int i;                                                              \
                                                                        \
    for (i = 0; i < h; i++) {                                           \
        uint32_t a, b, c, d, l0, l1, h0, h1;                            \
        a  = AV_RN32(&src1[i * src_stride1]);                           \
        b  = AV_RN32(&src2[i * src_stride2]);                           \
        c  = AV_RN32(&src3[i * src_stride3]);                           \
        d  = AV_RN32(&src4[i * src_stride4]);                           \
        l0 = (a & 0x03030303UL) +                                       \
             (b & 0x03030303UL) +                                       \
                  0x01010101UL;                                         \
        h0 = ((a & 0xFCFCFCFCUL) >> 2) +                                \
             ((b & 0xFCFCFCFCUL) >> 2);                                 \
        l1 = (c & 0x03030303UL) +                                       \
             (d & 0x03030303UL);                                        \
        h1 = ((c & 0xFCFCFCFCUL) >> 2) +                                \
             ((d & 0xFCFCFCFCUL) >> 2);                                 \
        OP(*((uint32_t *) &dst[i * dst_stride]),                        \
           h0 + h1 + (((l0 + l1) >> 2) & 0x0F0F0F0FUL));                \
        a  = AV_RN32(&src1[i * src_stride1 + 4]);                       \
        b  = AV_RN32(&src2[i * src_stride2 + 4]);                       \
        c  = AV_RN32(&src3[i * src_stride3 + 4]);                       \
        d  = AV_RN32(&src4[i * src_stride4 + 4]);                       \
        l0 = (a & 0x03030303UL) +                                       \
             (b & 0x03030303UL) +                                       \
                  0x01010101UL;                                         \
        h0 = ((a & 0xFCFCFCFCUL) >> 2) +                                \
             ((b & 0xFCFCFCFCUL) >> 2);                                 \
        l1 = (c & 0x03030303UL) +                                       \
             (d & 0x03030303UL);                                        \
        h1 = ((c & 0xFCFCFCFCUL) >> 2) +                                \
             ((d & 0xFCFCFCFCUL) >> 2);                                 \
        OP(*((uint32_t *) &dst[i * dst_stride + 4]),                    \
           h0 + h1 + (((l0 + l1) >> 2) & 0x0F0F0F0FUL));                \
    }                                                                   \
}                                                                       \
168 169 170 171 172 173 174 175 176 177 178 179
                                                                        \
static inline void OPNAME ## _pixels16_l4_8(uint8_t *dst,               \
                                            const uint8_t *src1,        \
                                            const uint8_t *src2,        \
                                            const uint8_t *src3,        \
                                            const uint8_t *src4,        \
                                            int dst_stride,             \
                                            int src_stride1,            \
                                            int src_stride2,            \
                                            int src_stride3,            \
                                            int src_stride4,            \
                                            int h)                      \
180
{                                                                       \
181 182 183 184 185 186 187 188
    OPNAME ## _pixels8_l4_8(dst, src1, src2, src3, src4, dst_stride,    \
                            src_stride1, src_stride2, src_stride3,      \
                            src_stride4, h);                            \
    OPNAME ## _pixels8_l4_8(dst  + 8,                                   \
                            src1 + 8, src2 + 8,                         \
                            src3 + 8, src4 + 8,                         \
                            dst_stride, src_stride1, src_stride2,       \
                            src_stride3, src_stride4, h);               \
189
}                                                                       \
190 191 192 193 194 195 196 197 198 199 200 201
                                                                        \
static inline void OPNAME ## _no_rnd_pixels16_l4_8(uint8_t *dst,        \
                                                   const uint8_t *src1, \
                                                   const uint8_t *src2, \
                                                   const uint8_t *src3, \
                                                   const uint8_t *src4, \
                                                   int dst_stride,      \
                                                   int src_stride1,     \
                                                   int src_stride2,     \
                                                   int src_stride3,     \
                                                   int src_stride4,     \
                                                   int h)               \
202
{                                                                       \
203 204 205 206 207 208 209 210 211 212
    OPNAME ## _no_rnd_pixels8_l4_8(dst, src1, src2, src3, src4,         \
                                   dst_stride, src_stride1,             \
                                   src_stride2, src_stride3,            \
                                   src_stride4, h);                     \
    OPNAME ## _no_rnd_pixels8_l4_8(dst  + 8,                            \
                                   src1 + 8, src2 + 8,                  \
                                   src3 + 8, src4 + 8,                  \
                                   dst_stride, src_stride1,             \
                                   src_stride2, src_stride3,            \
                                   src_stride4, h);                     \
213
}                                                                       \
214

215
#define op_avg(a, b) a = rnd_avg32(a, b)
216
#define op_put(a, b) a = b
217
#define put_no_rnd_pixels8_8_c put_pixels8_8_c
218 219 220 221
PIXOP2(avg, op_avg)
PIXOP2(put, op_put)
#undef op_avg
#undef op_put