float_dsp.c 3.91 KB
Newer Older
1
/*
2 3
 * Copyright 2005 Balatoni Denes
 * Copyright 2006 Loren Merritt
4
 *
5 6 7
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
8 9 10 11
 * 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.
 *
12
 * FFmpeg is distributed in the hope that it will be useful,
13 14 15 16 17
 * 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
18
 * License along with FFmpeg; if not, write to the Free Software
19 20 21 22
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "config.h"
23
#include "attributes.h"
24
#include "float_dsp.h"
25
#include "mem.h"
26 27 28 29 30 31 32 33 34

static void vector_fmul_c(float *dst, const float *src0, const float *src1,
                          int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] = src0[i] * src1[i];
}

35 36 37 38 39 40 41 42
static void vector_fmac_scalar_c(float *dst, const float *src, float mul,
                                 int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] += src[i] * mul;
}

43 44 45 46 47 48 49 50
static void vector_fmul_scalar_c(float *dst, const float *src, float mul,
                                 int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] = src[i] * mul;
}

51 52 53 54 55 56 57 58
static void vector_dmul_scalar_c(double *dst, const double *src, double mul,
                                 int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] = src[i] * mul;
}

59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
static void vector_fmul_window_c(float *dst, const float *src0,
                                 const float *src1, const float *win, int len)
{
    int i, j;

    dst  += len;
    win  += len;
    src0 += len;

    for (i = -len, j = len - 1; i < 0; i++, j--) {
        float s0 = src0[i];
        float s1 = src1[j];
        float wi = win[i];
        float wj = win[j];
        dst[i] = s0 * wj - s1 * wi;
        dst[j] = s0 * wi + s1 * wj;
    }
}

78 79 80 81 82 83 84 85
static void vector_fmul_add_c(float *dst, const float *src0, const float *src1,
                              const float *src2, int len){
    int i;

    for (i = 0; i < len; i++)
        dst[i] = src0[i] * src1[i] + src2[i];
}

86 87 88 89 90 91 92 93 94 95
static void vector_fmul_reverse_c(float *dst, const float *src0,
                                  const float *src1, int len)
{
    int i;

    src1 += len-1;
    for (i = 0; i < len; i++)
        dst[i] = src0[i] * src1[-i];
}

96
static void butterflies_float_c(float *av_restrict v1, float *av_restrict v2,
97 98 99 100 101 102 103 104 105 106 107
                                int len)
{
    int i;

    for (i = 0; i < len; i++) {
        float t = v1[i] - v2[i];
        v1[i] += v2[i];
        v2[i] = t;
    }
}

108 109 110 111 112 113 114 115 116 117 118
float avpriv_scalarproduct_float_c(const float *v1, const float *v2, int len)
{
    float p = 0.0;
    int i;

    for (i = 0; i < len; i++)
        p += v1[i] * v2[i];

    return p;
}

119
av_cold AVFloatDSPContext *avpriv_float_dsp_alloc(int bit_exact)
120
{
121 122 123 124
    AVFloatDSPContext *fdsp = av_mallocz(sizeof(AVFloatDSPContext));
    if (!fdsp)
        return NULL;

125
    fdsp->vector_fmul = vector_fmul_c;
126
    fdsp->vector_fmac_scalar = vector_fmac_scalar_c;
127
    fdsp->vector_fmul_scalar = vector_fmul_scalar_c;
128
    fdsp->vector_dmul_scalar = vector_dmul_scalar_c;
129
    fdsp->vector_fmul_window = vector_fmul_window_c;
130
    fdsp->vector_fmul_add = vector_fmul_add_c;
131
    fdsp->vector_fmul_reverse = vector_fmul_reverse_c;
132
    fdsp->butterflies_float = butterflies_float_c;
133
    fdsp->scalarproduct_float = avpriv_scalarproduct_float_c;
134

135 136 137 138 139 140 141 142
    if (ARCH_AARCH64)
        ff_float_dsp_init_aarch64(fdsp);
    if (ARCH_ARM)
        ff_float_dsp_init_arm(fdsp);
    if (ARCH_PPC)
        ff_float_dsp_init_ppc(fdsp, bit_exact);
    if (ARCH_X86)
        ff_float_dsp_init_x86(fdsp);
143 144
    if (ARCH_MIPS)
        ff_float_dsp_init_mips(fdsp);
145
    return fdsp;
146
}