Blame view

3rdparty/ffmpeg-4.4.4/libswscale/aarch64/rgb2rgb_neon.S 2.5 KB
09c2d08c   Hu Chunming   arm交付版
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
  /*
   * Copyright (c) 2020 Martin Storsjo
   *
   * 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/aarch64/asm.S"
  
  // void ff_interleave_bytes_neon(const uint8_t *src1, const uint8_t *src2,
  //                               uint8_t *dest, int width, int height,
  //                               int src1Stride, int src2Stride, int dstStride);
  function ff_interleave_bytes_neon, export=1
          sub             w5,  w5,  w3
          sub             w6,  w6,  w3
          sub             w7,  w7,  w3, lsl #1
  1:
          ands            w8,  w3,  #0xfffffff0 // & ~15
          b.eq            3f
  2:
          ld1             {v0.16b}, [x0], #16
          ld1             {v1.16b}, [x1], #16
          subs            w8,  w8,  #16
          st2             {v0.16b, v1.16b}, [x2], #32
          b.gt            2b
  
          tst             w3,  #15
          b.eq            9f
  
  3:
          tst             w3,  #8
          b.eq            4f
          ld1             {v0.8b}, [x0], #8
          ld1             {v1.8b}, [x1], #8
          st2             {v0.8b, v1.8b}, [x2], #16
  4:
          tst             w3,  #4
          b.eq            5f
  
          ld1             {v0.s}[0], [x0], #4
          ld1             {v1.s}[0], [x1], #4
          zip1            v0.8b,   v0.8b,   v1.8b
          st1             {v0.8b}, [x2], #8
  
  5:
          ands            w8,  w3,  #3
          b.eq            9f
  6:
          ldrb            w9,  [x0], #1
          ldrb            w10, [x1], #1
          subs            w8,  w8,  #1
          bfi             w9,  w10, #8,  #8
          strh            w9,  [x2], #2
          b.gt            6b
  
  9:
          subs            w4,  w4,  #1
          b.eq            0f
          add             x0,  x0,  w5, sxtw
          add             x1,  x1,  w6, sxtw
          add             x2,  x2,  w7, sxtw
          b               1b
  
  0:
          ret
  endfunc