Blame view

ffmpeg-4.2.2/libavcodec/mips/blockdsp_msa.c 2.45 KB
aac5773f   hucm   功能基本完成,接口待打磨
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
  /*
   * Copyright (c) 2015 Parag Salasakar (parag.salasakar@imgtec.com)
   *
   * This file is part of FFmpeg.
   *
   * FFmpeg is free software; you can redistribute it and/or
   * modify it under the terms of the GNU Lesser General Public
   * License as published by the Free Software Foundation; either
   * version 2.1 of the License, or (at your option) any later version.
   *
   * FFmpeg is distributed in the hope that it will be useful,
   * but WITHOUT ANY WARRANTY; without even the implied warranty of
   * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   * Lesser General Public License for more details.
   *
   * You should have received a copy of the GNU Lesser General Public
   * License along with FFmpeg; if not, write to the Free Software
   * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
   */
  
  #include "libavutil/mips/generic_macros_msa.h"
  #include "blockdsp_mips.h"
  
  static void copy_8bit_value_width8_msa(uint8_t *src, uint8_t val,
                                         int32_t src_stride, int32_t height)
  {
      int32_t cnt;
      uint64_t dst0;
      v16u8 val0;
  
      val0 = (v16u8) __msa_fill_b(val);
      dst0 = __msa_copy_u_d((v2i64) val0, 0);
  
      for (cnt = (height >> 2); cnt--;) {
          SD4(dst0, dst0, dst0, dst0, src, src_stride);
          src += (4 * src_stride);
      }
  }
  
  static void copy_8bit_value_width16_msa(uint8_t *src, uint8_t val,
                                          int32_t src_stride, int32_t height)
  {
      int32_t cnt;
      v16u8 val0;
  
      val0 = (v16u8) __msa_fill_b(val);
  
      for (cnt = (height >> 3); cnt--;) {
          ST_UB8(val0, val0, val0, val0, val0, val0, val0, val0, src, src_stride);
          src += (8 * src_stride);
      }
  }
  
  static void memset_zero_16width_msa(uint8_t *src, int32_t stride,
                                      int32_t height)
  {
      int8_t cnt;
      v16u8 zero = { 0 };
  
      for (cnt = (height / 2); cnt--;) {
          ST_UB(zero, src);
          src += stride;
          ST_UB(zero, src);
          src += stride;
      }
  }
  
  void ff_fill_block16_msa(uint8_t *src, uint8_t val, ptrdiff_t stride, int height)
  {
      copy_8bit_value_width16_msa(src, val, stride, height);
  }
  
  void ff_fill_block8_msa(uint8_t *src, uint8_t val, ptrdiff_t stride, int height)
  {
      copy_8bit_value_width8_msa(src, val, stride, height);
  }
  
  void ff_clear_block_msa(int16_t *block)
  {
      memset_zero_16width_msa((uint8_t *) block, 16, 8);
  }
  
  void ff_clear_blocks_msa(int16_t *block)
  {
      memset_zero_16width_msa((uint8_t *) block, 16, 8 * 6);
  }