d76d34a5b1f8e3c350bb1284ceeccfc94d83fb90
[libav.git] / libavcodec / ppc / int_altivec.c
1 /*
2 * Copyright (c) 2007 Luca Barbato <lu_zero@gentoo.org>
3 *
4 * This file is part of Libav.
5 *
6 * Libav 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 * Libav 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 Libav; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 */
20
21 /**
22 * @file
23 * miscellaneous integer operations
24 */
25
26 #include "config.h"
27 #if HAVE_ALTIVEC_H
28 #include <altivec.h>
29 #endif
30
31 #include "libavutil/attributes.h"
32 #include "libavutil/ppc/types_altivec.h"
33 #include "libavutil/ppc/util_altivec.h"
34 #include "libavcodec/dsputil.h"
35 #include "dsputil_altivec.h"
36
37 static int32_t scalarproduct_int16_altivec(const int16_t *v1, const int16_t *v2,
38 int order)
39 {
40 int i;
41 LOAD_ZERO;
42 register vec_s16 vec1;
43 register vec_s32 res = vec_splat_s32(0), t;
44 int32_t ires;
45
46 for (i = 0; i < order; i += 8) {
47 vec1 = vec_unaligned_load(v1);
48 t = vec_msum(vec1, vec_ld(0, v2), zero_s32v);
49 res = vec_sums(t, res);
50 v1 += 8;
51 v2 += 8;
52 }
53 res = vec_splat(res, 3);
54 vec_ste(res, 0, &ires);
55
56 return ires;
57 }
58
59 av_cold void ff_int_init_altivec(DSPContext *c, AVCodecContext *avctx)
60 {
61 c->scalarproduct_int16 = scalarproduct_int16_altivec;
62 }