1 /*
2 * Copyright (c) 2015 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
23
25 const float *
src0,
const float *
src1,
27 {
30 for (
i = 0;
i <
len - 7;
i += 8) {
31 d0 = vec_vsx_ld( 0,
src0 +
i);
32 d1 = vec_vsx_ld(16,
src0 +
i);
33 d0 = vec_madd(d0, vec_vsx_ld( 0,
src1 +
i),
zero);
34 d1 = vec_madd(d1, vec_vsx_ld(16,
src1 +
i),
zero);
35 vec_vsx_st(d0, 0,
dst +
i);
36 vec_vsx_st(d1, 16,
dst +
i);
37 }
38 }
39
41 const float *
src1,
const float *
win,
43 {
45 const vec_u8 reverse = vcprm(3, 2, 1, 0);
47
51
53
54 for (
i = -
len * 4, j =
len * 4 - 16;
i < 0;
i += 16, j -= 16) {
55 s0 = vec_vsx_ld(
i,
src0);
56 s1 = vec_vsx_ld(j,
src1);
57 wi = vec_vsx_ld(
i,
win);
58 wj = vec_vsx_ld(j,
win);
59
60 s1 = vec_perm(s1, s1, reverse);
61 wj = vec_perm(wj, wj, reverse);
62
63 t0 = vec_madd(s0, wj,
zero);
64 t0 = vec_nmsub(s1, wi, t0);
65 t1 = vec_madd(s0, wi,
zero);
66 t1 = vec_madd(s1, wj, t1);
67 t1 = vec_perm(t1, t1, reverse);
68
69 vec_vsx_st(t0,
i,
dst);
70 vec_vsx_st(t1, j,
dst);
71 }
72 }
73
75 const float *
src1,
const float *
src2,
77 {
80
81 for (
i = 0;
i <
len - 3;
i += 4) {
82 s0 = vec_vsx_ld(0,
src0 +
i);
83 s1 = vec_vsx_ld(0,
src1 +
i);
84 s2 = vec_vsx_ld(0,
src2 +
i);
85 d = vec_madd(s0, s1, s2);
86 vec_vsx_st(d, 0,
dst +
i);
87 }
88 }
89
92 {
94 vec_f d, s0, s1,
h0, l0, s2, s3;
96
98 for (
i = 0;
i <
len - 7;
i += 8) {
99 s1 = vec_vsx_ld(0,
src1 -
i);
// [a,b,c,d]
100 s0 = vec_vsx_ld(0,
src0 +
i);
101 l0 = vec_mergel(s1, s1); // [c,c,d,d]
102 s3 = vec_vsx_ld(-16,
src1 -
i);
103 h0 = vec_mergeh(s1, s1);
// [a,a,b,b]
104 s2 = vec_vsx_ld(16,
src0 +
i);
105 s1 = vec_mergeh(vec_mergel(l0,
h0),
// [d,b,d,b]
106 vec_mergeh(l0,
h0));
// [c,a,c,a]
107 // [d,c,b,a]
108 l0 = vec_mergel(s3, s3);
109 d = vec_madd(s0, s1,
zero);
110 h0 = vec_mergeh(s3, s3);
111 vec_vsx_st(d, 0,
dst +
i);
112 s3 = vec_mergeh(vec_mergel(l0,
h0),
114 d = vec_madd(s2, s3,
zero);
115 vec_vsx_st(d, 16,
dst +
i);
116 }
117 }