]> git.sesse.net Git - ffmpeg/blob - libavcodec/arm/dcadsp_neon.S
Merge commit 'a9099e04026f300924ac363fa6f8aef912677d90'
[ffmpeg] / libavcodec / arm / dcadsp_neon.S
1 /*
2  * Copyright (c) 2010 Mans Rullgard <mans@mansr.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/arm/asm.S"
22
23 function ff_dca_lfe_fir0_neon, export=1
24         push            {r4-r6,lr}
25 NOVFP   vmov            s0,  r3                 @ scale
26         mov             r3,  #32                @ decifactor
27         mov             r6,  #256/32
28         b               dca_lfe_fir
29 endfunc
30
31 function ff_dca_lfe_fir1_neon, export=1
32         push            {r4-r6,lr}
33 NOVFP   vmov            s0,  r3                 @ scale
34         mov             r3,  #64                @ decifactor
35         mov             r6,  #256/64
36 dca_lfe_fir:
37         add             r4,  r0,  r3,  lsl #2   @ out2
38         add             r5,  r2,  #256*4-16     @ cf1
39         sub             r1,  r1,  #12
40         mov             lr,  #-16
41 1:
42         vmov.f32        q2,  #0.0               @ v0
43         vmov.f32        q3,  #0.0               @ v1
44         mov             r12, r6
45 2:
46         vld1.32         {q8},     [r2,:128]!    @ cf0
47         vld1.32         {q9},     [r5,:128], lr @ cf1
48         vld1.32         {q1},     [r1], lr      @ in
49         subs            r12, r12, #4
50         vrev64.32       q10, q8
51         vmla.f32        q3,  q1,  q9
52         vmla.f32        d4,  d2,  d21
53         vmla.f32        d5,  d3,  d20
54         bne             2b
55
56         add             r1,  r1,  r6,  lsl #2
57         subs            r3,  r3,  #1
58         vadd.f32        d4,  d4,  d5
59         vadd.f32        d6,  d6,  d7
60         vpadd.f32       d4,  d4,  d6
61         vmul.f32        d5,  d4,  d0[0]
62         vst1.32         {d5[0]},  [r0,:32]!
63         vst1.32         {d5[1]},  [r4,:32]!
64         bne             1b
65
66         pop             {r4-r6,pc}
67 endfunc