1/*
2 * Copyright (c) 2015 Parag Salasakar (parag.salasakar@imgtec.com)
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 "libavutil/mips/generic_macros_msa.h"
22#include "blockdsp_mips.h"
23
24static void copy_8bit_value_width8_msa(uint8_t *src, uint8_t val,
25                                       int32_t src_stride, int32_t height)
26{
27    int32_t cnt;
28    uint64_t dst0;
29    v16u8 val0;
30
31    val0 = (v16u8) __msa_fill_b(val);
32    dst0 = __msa_copy_u_d((v2i64) val0, 0);
33
34    for (cnt = (height >> 2); cnt--;) {
35        SD4(dst0, dst0, dst0, dst0, src, src_stride);
36        src += (4 * src_stride);
37    }
38}
39
40static void copy_8bit_value_width16_msa(uint8_t *src, uint8_t val,
41                                        int32_t src_stride, int32_t height)
42{
43    int32_t cnt;
44    v16u8 val0;
45
46    val0 = (v16u8) __msa_fill_b(val);
47
48    for (cnt = (height >> 3); cnt--;) {
49        ST_UB8(val0, val0, val0, val0, val0, val0, val0, val0, src, src_stride);
50        src += (8 * src_stride);
51    }
52}
53
54static void memset_zero_16width_msa(uint8_t *src, int32_t stride,
55                                    int32_t height)
56{
57    int8_t cnt;
58    v16u8 zero = { 0 };
59
60    for (cnt = (height / 2); cnt--;) {
61        ST_UB(zero, src);
62        src += stride;
63        ST_UB(zero, src);
64        src += stride;
65    }
66}
67
68void ff_fill_block16_msa(uint8_t *src, uint8_t val, ptrdiff_t stride, int height)
69{
70    copy_8bit_value_width16_msa(src, val, stride, height);
71}
72
73void ff_fill_block8_msa(uint8_t *src, uint8_t val, ptrdiff_t stride, int height)
74{
75    copy_8bit_value_width8_msa(src, val, stride, height);
76}
77
78void ff_clear_block_msa(int16_t *block)
79{
80    memset_zero_16width_msa((uint8_t *) block, 16, 8);
81}
82
83void ff_clear_blocks_msa(int16_t *block)
84{
85    memset_zero_16width_msa((uint8_t *) block, 16, 8 * 6);
86}
87