1/*
2 * Copyright (c) 2007 Luca Barbato <lu_zero@gentoo.org>
3 *
4 * This file is part of FFmpeg.
5 *
6 * FFmpeg is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
10 *
11 * FFmpeg is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with FFmpeg; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 */
20
21#include "config.h"
22
23#include <stdint.h>
24
25#include "libavutil/attributes.h"
26#include "libavutil/cpu.h"
27#include "libavutil/ppc/cpu.h"
28#include "libavutil/ppc/util_altivec.h"
29
30#include "libavcodec/svq1enc.h"
31
32#if HAVE_ALTIVEC
33static int ssd_int8_vs_int16_altivec(const int8_t *pix1, const int16_t *pix2,
34                                     intptr_t size)
35{
36    int i, size16 = size >> 4;
37    vector signed char vpix1;
38    vector signed short vpix2, vdiff, vpix1l, vpix1h;
39    union {
40        vector signed int vscore;
41        int32_t score[4];
42    } u = { .vscore = vec_splat_s32(0) };
43
44    while (size16) {
45        // score += (pix1[i] - pix2[i]) * (pix1[i] - pix2[i]);
46        // load pix1 and the first batch of pix2
47
48        vpix1 = vec_unaligned_load(pix1);
49        vpix2 = vec_unaligned_load(pix2);
50        pix2 += 8;
51        // unpack
52        vpix1h = vec_unpackh(vpix1);
53        vdiff  = vec_sub(vpix1h, vpix2);
54        vpix1l = vec_unpackl(vpix1);
55        // load another batch from pix2
56        vpix2    = vec_unaligned_load(pix2);
57        u.vscore = vec_msum(vdiff, vdiff, u.vscore);
58        vdiff    = vec_sub(vpix1l, vpix2);
59        u.vscore = vec_msum(vdiff, vdiff, u.vscore);
60        pix1    += 16;
61        pix2    += 8;
62        size16--;
63    }
64    u.vscore = vec_sums(u.vscore, vec_splat_s32(0));
65
66    size %= 16;
67    for (i = 0; i < size; i++)
68        u.score[3] += (pix1[i] - pix2[i]) * (pix1[i] - pix2[i]);
69
70    return u.score[3];
71}
72#endif /* HAVE_ALTIVEC */
73
74av_cold void ff_svq1enc_init_ppc(SVQ1EncContext *c)
75{
76#if HAVE_ALTIVEC
77    if (!PPC_ALTIVEC(av_get_cpu_flags()))
78        return;
79
80    c->ssd_int8_vs_int16 = ssd_int8_vs_int16_altivec;
81#endif /* HAVE_ALTIVEC */
82}
83