pixel.h 7.54 KB
Newer Older
1
/*****************************************************************************
2
 * pixel.c: pixel metrics
3
 *****************************************************************************
Henrik Gramner's avatar
Henrik Gramner committed
4
 * Copyright (C) 2004-2019 x264 project
5 6 7
 *
 * Authors: Loren Merritt <lorenm@u.washington.edu>
 *          Fiona Glaser <fiona@x264.com>
Henrik Gramner's avatar
Henrik Gramner committed
8
            Henrik Gramner <henrik@gramner.com>
9 10 11 12 13 14 15 16 17 18 19 20 21
 *
 * 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
22
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
23 24 25
 *
 * This program is also available under a commercial proprietary license.
 * For more information, contact us at licensing@x264.com.
26 27
 *****************************************************************************/

28 29
#ifndef X264_PIXEL_H
#define X264_PIXEL_H
30

Loren Merritt's avatar
Loren Merritt committed
31 32
// SSD assumes all args aligned
// other cmp functions assume first arg aligned
Anton Mitrofanov's avatar
Anton Mitrofanov committed
33 34 35
typedef int  (*x264_pixel_cmp_t)( pixel *, intptr_t, pixel *, intptr_t );
typedef void (*x264_pixel_cmp_x3_t)( pixel *, pixel *, pixel *, pixel *, intptr_t, int[3] );
typedef void (*x264_pixel_cmp_x4_t)( pixel *, pixel *, pixel *, pixel *, pixel *, intptr_t, int[4] );
36 37 38 39 40 41 42 43 44 45

enum
{
    PIXEL_16x16 = 0,
    PIXEL_16x8  = 1,
    PIXEL_8x16  = 2,
    PIXEL_8x8   = 3,
    PIXEL_8x4   = 4,
    PIXEL_4x8   = 5,
    PIXEL_4x4   = 6,
Henrik Gramner's avatar
Henrik Gramner committed
46 47 48 49 50 51 52

    /* Subsampled chroma only */
    PIXEL_4x16  = 7,  /* 4:2:2 */
    PIXEL_4x2   = 8,
    PIXEL_2x8   = 9,  /* 4:2:2 */
    PIXEL_2x4   = 10,
    PIXEL_2x2   = 11,
53 54
};

Henrik Gramner's avatar
Henrik Gramner committed
55
static const struct { uint8_t w, h; } x264_pixel_size[12] =
56
{
Henrik Gramner's avatar
Henrik Gramner committed
57 58
    { 16, 16 }, { 16, 8 }, { 8, 16 }, { 8, 8 }, { 8, 4 }, { 4, 8 }, { 4, 4 },
    {  4, 16 }, {  4, 2 }, { 2,  8 }, { 2, 4 }, { 2, 2 },
59 60
};

61 62
static const uint8_t x264_size2pixel[5][5] =
{
63 64 65 66 67 68 69
    { 0, },
    { 0, PIXEL_4x4, PIXEL_8x4, 0, 0 },
    { 0, PIXEL_4x8, PIXEL_8x8, 0, PIXEL_16x8 },
    { 0, },
    { 0, 0,        PIXEL_8x16, 0, PIXEL_16x16 }
};

Henrik Gramner's avatar
Henrik Gramner committed
70 71 72 73 74 75 76 77
static const uint8_t x264_luma2chroma_pixel[4][7] =
{
    { 0 },
    { PIXEL_8x8,   PIXEL_8x4,  PIXEL_4x8,  PIXEL_4x4, PIXEL_4x2, PIXEL_2x4, PIXEL_2x2 }, /* 4:2:0 */
    { PIXEL_8x16,  PIXEL_8x8,  PIXEL_4x16, PIXEL_4x8, PIXEL_4x4, PIXEL_2x8, PIXEL_2x4 }, /* 4:2:2 */
    { PIXEL_16x16, PIXEL_16x8, PIXEL_8x16, PIXEL_8x8, PIXEL_8x4, PIXEL_4x8, PIXEL_4x4 }, /* 4:4:4 */
};

78 79
typedef struct
{
Henrik Gramner's avatar
Henrik Gramner committed
80 81 82
    x264_pixel_cmp_t  sad[8];
    x264_pixel_cmp_t  ssd[8];
    x264_pixel_cmp_t satd[8];
83
    x264_pixel_cmp_t ssim[7];
84
    x264_pixel_cmp_t sa8d[4];
Henrik Gramner's avatar
Henrik Gramner committed
85 86 87
    x264_pixel_cmp_t mbcmp[8]; /* either satd or sad for subpel refine and mode decision */
    x264_pixel_cmp_t mbcmp_unaligned[8]; /* unaligned mbcmp for subpel */
    x264_pixel_cmp_t fpelcmp[8]; /* either satd or sad for fullpel motion search */
88 89
    x264_pixel_cmp_x3_t fpelcmp_x3[7];
    x264_pixel_cmp_x4_t fpelcmp_x4[7];
Henrik Gramner's avatar
Henrik Gramner committed
90
    x264_pixel_cmp_t sad_aligned[8]; /* Aligned SAD for mbcmp */
91
    int (*vsad)( pixel *, intptr_t, int );
92
    int (*asd8)( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2, int height );
93
    uint64_t (*sa8d_satd[1])( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 );
94

95
    uint64_t (*var[4])( pixel *pix, intptr_t stride );
Henrik Gramner's avatar
Henrik Gramner committed
96
    int (*var2[4])( pixel *fenc, pixel *fdec, int ssd[2] );
97
    uint64_t (*hadamard_ac[4])( pixel *pix, intptr_t stride );
Loren Merritt's avatar
Loren Merritt committed
98

99 100
    void (*ssd_nv12_core)( pixel *pixuv1, intptr_t stride1,
                           pixel *pixuv2, intptr_t stride2, int width, int height,
101
                           uint64_t *ssd_u, uint64_t *ssd_v );
102 103
    void (*ssim_4x4x2_core)( const pixel *pix1, intptr_t stride1,
                             const pixel *pix2, intptr_t stride2, int sums[2][4] );
104
    float (*ssim_end4)( int sum0[5][4], int sum1[5][4], int width );
105

106
    /* multiple parallel calls to cmp. */
107 108
    x264_pixel_cmp_x3_t sad_x3[7];
    x264_pixel_cmp_x4_t sad_x4[7];
109 110
    x264_pixel_cmp_x3_t satd_x3[7];
    x264_pixel_cmp_x4_t satd_x4[7];
111

Loren Merritt's avatar
Loren Merritt committed
112
    /* abs-diff-sum for successive elimination.
113 114 115
     * may round width up to a multiple of 16. */
    int (*ads[7])( int enc_dc[4], uint16_t *sums, int delta,
                   uint16_t *cost_mvx, int16_t *mvs, int width, int thresh );
Loren Merritt's avatar
Loren Merritt committed
116

117 118 119 120 121 122 123
    /* calculate satd or sad of V, H, and DC modes. */
    void (*intra_mbcmp_x3_16x16)( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_satd_x3_16x16) ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_sad_x3_16x16)  ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_mbcmp_x3_4x4)  ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_satd_x3_4x4)   ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_sad_x3_4x4)    ( pixel *fenc, pixel *fdec, int res[3] );
Henrik Gramner's avatar
Henrik Gramner committed
124 125 126 127 128 129 130 131 132
    void (*intra_mbcmp_x3_chroma)( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_satd_x3_chroma) ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_sad_x3_chroma)  ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_mbcmp_x3_8x16c) ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_satd_x3_8x16c)  ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_sad_x3_8x16c)   ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_mbcmp_x3_8x8c)  ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_satd_x3_8x8c)   ( pixel *fenc, pixel *fdec, int res[3] );
    void (*intra_sad_x3_8x8c)    ( pixel *fenc, pixel *fdec, int res[3] );
133 134 135
    void (*intra_mbcmp_x3_8x8)  ( pixel *fenc, pixel edge[36], int res[3] );
    void (*intra_sa8d_x3_8x8)   ( pixel *fenc, pixel edge[36], int res[3] );
    void (*intra_sad_x3_8x8)    ( pixel *fenc, pixel edge[36], int res[3] );
136
    /* find minimum satd or sad of all modes, and set fdec.
137 138 139 140
     * may be NULL, in which case just use pred+satd instead. */
    int (*intra_mbcmp_x9_4x4)( pixel *fenc, pixel *fdec, uint16_t *bitcosts );
    int (*intra_satd_x9_4x4) ( pixel *fenc, pixel *fdec, uint16_t *bitcosts );
    int (*intra_sad_x9_4x4)  ( pixel *fenc, pixel *fdec, uint16_t *bitcosts );
141 142 143
    int (*intra_mbcmp_x9_8x8)( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds );
    int (*intra_sa8d_x9_8x8) ( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds );
    int (*intra_sad_x9_8x8)  ( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds );
144 145
} x264_pixel_function_t;

146
#define x264_pixel_init x264_template(pixel_init)
147
void x264_pixel_init( int cpu, x264_pixel_function_t *pixf );
148
#define x264_pixel_ssd_nv12 x264_template(pixel_ssd_nv12)
149 150
void x264_pixel_ssd_nv12   ( x264_pixel_function_t *pf, pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2,
                             int i_width, int i_height, uint64_t *ssd_u, uint64_t *ssd_v );
151
#define x264_pixel_ssd_wxh x264_template(pixel_ssd_wxh)
152 153
uint64_t x264_pixel_ssd_wxh( x264_pixel_function_t *pf, pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2,
                             int i_width, int i_height );
154
#define x264_pixel_ssim_wxh x264_template(pixel_ssim_wxh)
155 156
float x264_pixel_ssim_wxh  ( x264_pixel_function_t *pf, pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2,
                             int i_width, int i_height, void *buf, int *cnt );
157
#define x264_field_vsad x264_template(field_vsad)
158
int x264_field_vsad( x264_t *h, int mb_x, int mb_y );
159 160

#endif