1 ;******************************************************************************
2 ;* Copyright Nick Kurshev
3 ;* Copyright Michael (michaelni@gmx.at)
4 ;* Copyright 2018 Jokyo Images
6 ;* This file is part of FFmpeg.
8 ;* FFmpeg is free software; you can redistribute it and/or
9 ;* modify it under the terms of the GNU Lesser General Public
10 ;* License as published by the Free Software Foundation; either
11 ;* version 2.1 of the License, or (at your option) any later version.
13 ;* FFmpeg is distributed in the hope that it will be useful,
14 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
15 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 ;* Lesser General Public License for more details.
18 ;* You should have received a copy of the GNU Lesser General Public
19 ;* License along with FFmpeg; if not, write to the Free Software
20 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21 ;******************************************************************************
23 %include "libavutil/x86/x86util.asm"
27 pb_shuffle2103: db 2, 1, 0, 3, 6, 5, 4, 7, 10, 9, 8, 11, 14, 13, 12, 15
28 pb_shuffle0321: db 0, 3, 2, 1, 4, 7, 6, 5, 8, 11, 10, 9, 12, 15, 14, 13
29 pb_shuffle1230: db 1, 2, 3, 0, 5, 6, 7, 4, 9, 10, 11, 8, 13, 14, 15, 12
30 pb_shuffle3012: db 3, 0, 1, 2, 7, 4, 5, 6, 11, 8, 9, 10, 15, 12, 13, 14
31 pb_shuffle3210: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
35 ;------------------------------------------------------------------------------
36 ; shuffle_bytes_## (const uint8_t *src, uint8_t *dst, int src_size)
37 ;------------------------------------------------------------------------------
39 %macro SHUFFLE_BYTES 4
40 cglobal shuffle_bytes_%1%2%3%4, 3, 5, 2, src, dst, w, tmp, x
41 VBROADCASTI128 m0, [pb_shuffle%1%2%3%4]
54 mov tmpb, [srcq + wq + %1]
55 mov [dstq+wq + 0], tmpb
56 mov tmpb, [srcq + wq + %2]
57 mov [dstq+wq + 1], tmpb
58 mov tmpb, [srcq + wq + %3]
59 mov [dstq+wq + 2], tmpb
60 mov tmpb, [srcq + wq + %4]
61 mov [dstq+wq + 3], tmpb
66 ;check if src_size < mmsize
82 SHUFFLE_BYTES 2, 1, 0, 3
83 SHUFFLE_BYTES 0, 3, 2, 1
84 SHUFFLE_BYTES 1, 2, 3, 0
85 SHUFFLE_BYTES 3, 0, 1, 2
86 SHUFFLE_BYTES 3, 2, 1, 0