variance_ssse3.c 4.16 KB
Newer Older
1 2 3 4 5 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
/*
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
 *
 *  Use of this source code is governed by a BSD-style license
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
 *  in the file PATENTS.  All contributing project authors may
 *  be found in the AUTHORS file in the root of the source tree.
 */


#include "vp8/encoder/variance.h"
#include "vp8/common/pragmas.h"
#include "vpx_ports/mem.h"

extern unsigned int vp8_get16x16var_sse2
(
    const unsigned char *src_ptr,
    int source_stride,
    const unsigned char *ref_ptr,
    int recon_stride,
    unsigned int *SSE,
    int *Sum
);
extern void vp8_half_horiz_vert_variance16x_h_sse2
(
    const unsigned char *ref_ptr,
    int ref_pixels_per_line,
    const unsigned char *src_ptr,
    int src_pixels_per_line,
    unsigned int Height,
    int *sum,
    unsigned int *sumsquared
);
extern void vp8_half_horiz_variance16x_h_sse2
(
    const unsigned char *ref_ptr,
    int ref_pixels_per_line,
    const unsigned char *src_ptr,
    int src_pixels_per_line,
    unsigned int Height,
    int *sum,
    unsigned int *sumsquared
);
extern void vp8_half_vert_variance16x_h_sse2
(
    const unsigned char *ref_ptr,
    int ref_pixels_per_line,
    const unsigned char *src_ptr,
    int src_pixels_per_line,
    unsigned int Height,
    int *sum,
    unsigned int *sumsquared
);
extern void vp8_filter_block2d_bil_var_ssse3
(
    const unsigned char *ref_ptr,
    int ref_pixels_per_line,
    const unsigned char *src_ptr,
    int src_pixels_per_line,
    unsigned int Height,
    int  xoffset,
    int  yoffset,
    int *sum,
    unsigned int *sumsquared
);

unsigned int vp8_sub_pixel_variance16x16_ssse3
(
    const unsigned char  *src_ptr,
    int  src_pixels_per_line,
    int  xoffset,
    int  yoffset,
    const unsigned char *dst_ptr,
    int dst_pixels_per_line,
    unsigned int *sse
)
{
79 80
    int xsum0;
    unsigned int xxsum0;
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

    // note we could avoid these if statements if the calling function
    // just called the appropriate functions inside.
    if (xoffset == 4 && yoffset == 0)
    {
        vp8_half_horiz_variance16x_h_sse2(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 16,
            &xsum0, &xxsum0);
    }
    else if (xoffset == 0 && yoffset == 4)
    {
        vp8_half_vert_variance16x_h_sse2(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 16,
            &xsum0, &xxsum0);
    }
    else if (xoffset == 4 && yoffset == 4)
    {
        vp8_half_horiz_vert_variance16x_h_sse2(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 16,
            &xsum0, &xxsum0);
    }
    else
    {
107 108 109 110 111
        vp8_filter_block2d_bil_var_ssse3(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 16,
            xoffset, yoffset,
            &xsum0, &xxsum0);
112 113 114 115 116
    }

    *sse = xxsum0;
    return (xxsum0 - ((xsum0 * xsum0) >> 8));
}
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165

unsigned int vp8_sub_pixel_variance16x8_ssse3
(
    const unsigned char  *src_ptr,
    int  src_pixels_per_line,
    int  xoffset,
    int  yoffset,
    const unsigned char *dst_ptr,
    int dst_pixels_per_line,
    unsigned int *sse

)
{
    int xsum0;
    unsigned int xxsum0;

    if (xoffset == 4 && yoffset == 0)
    {
        vp8_half_horiz_variance16x_h_sse2(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 8,
            &xsum0, &xxsum0);
    }
    else if (xoffset == 0 && yoffset == 4)
    {
        vp8_half_vert_variance16x_h_sse2(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 8,
            &xsum0, &xxsum0);
    }
    else if (xoffset == 4 && yoffset == 4)
    {
        vp8_half_horiz_vert_variance16x_h_sse2(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 8,
            &xsum0, &xxsum0);
    }
    else
    {
        vp8_filter_block2d_bil_var_ssse3(
            src_ptr, src_pixels_per_line,
            dst_ptr, dst_pixels_per_line, 8,
            xoffset, yoffset,
            &xsum0, &xxsum0);
    }

    *sse = xxsum0;
    return (xxsum0 - ((xsum0 * xsum0) >> 7));
}