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 "libavutil/attributes.h"
24#include "libavutil/cpu.h"
25#include "libavutil/ppc/cpu.h"
26#include "libavutil/ppc/util_altivec.h"
27
28#include "libavcodec/lossless_audiodsp.h"
29
30#if HAVE_BIGENDIAN
31#define GET_T(tt0,tt1,src,a,b){       \
32        a = vec_ld(16, src);          \
33        tt0 = vec_perm(b, a, align);  \
34        b = vec_ld(32, src);          \
35        tt1 = vec_perm(a, b, align);  \
36 }
37#else
38#define GET_T(tt0,tt1,src,a,b){       \
39        tt0 = vec_vsx_ld(0, src);     \
40        tt1 = vec_vsx_ld(16, src);    \
41 }
42#endif
43
44#if HAVE_ALTIVEC
45static int32_t scalarproduct_and_madd_int16_altivec(int16_t *v1,
46                                                    const int16_t *v2,
47                                                    const int16_t *v3,
48                                                    int order, int mul)
49{
50    LOAD_ZERO;
51    vec_s16 *pv1 = (vec_s16 *) v1;
52    register vec_s16 muls = { mul, mul, mul, mul, mul, mul, mul, mul };
53    register vec_s16 t0, t1, i0, i1, i4, i2, i3;
54    register vec_s32 res = zero_s32v;
55#if HAVE_BIGENDIAN
56    register vec_u8 align = vec_lvsl(0, v2);
57    i2 = vec_ld(0, v2);
58    i3 = vec_ld(0, v3);
59#endif
60    int32_t ires;
61
62    order >>= 4;
63    do {
64        GET_T(t0,t1,v2,i1,i2);
65        i0     = pv1[0];
66        i1     = pv1[1];
67        res    = vec_msum(t0, i0, res);
68        res    = vec_msum(t1, i1, res);
69        GET_T(t0,t1,v3,i4,i3);
70        pv1[0] = vec_mladd(t0, muls, i0);
71        pv1[1] = vec_mladd(t1, muls, i1);
72        pv1   += 2;
73        v2    += 16;
74        v3    += 16;
75    } while (--order);
76    res = vec_splat(vec_sums(res, zero_s32v), 3);
77    vec_ste(res, 0, &ires);
78
79    return ires;
80}
81#endif /* HAVE_ALTIVEC */
82
83av_cold void ff_llauddsp_init_ppc(LLAudDSPContext *c)
84{
85#if HAVE_ALTIVEC
86    if (!PPC_ALTIVEC(av_get_cpu_flags()))
87        return;
88
89    c->scalarproduct_and_madd_int16 = scalarproduct_and_madd_int16_altivec;
90#endif /* HAVE_ALTIVEC */
91}
92