summaryrefslogtreecommitdiffstats
path: root/libavcodec/arm/flacdsp_arm.S
blob: f8861c59675f0961c8fee3ee6ce7fbd6d3d1a555 (plain)
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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
/*
 * Copyright (c) 2012 Mans Rullgard <mans@mansr.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/arm/asm.S"

function flac_lpc_16_1_arm
        ldr             r12, [sp]
        push            {r4, lr}
        ldr             r1,  [r1]
        subs            r12, r12, #2
        ldr             lr,  [r0], #4
        beq             2f
        it              lt
        poplt           {r4, pc}
1:
        mul             r4,  lr,  r1
        ldm             r0,  {r2, lr}
        add_sh          r2,  r2,  r4,  asr r3
        mul             r4,  r2,  r1
        subs            r12, r12, #2
        add_sh          lr,  lr,  r4,  asr r3
        stm             r0!, {r2, lr}
        bgt             1b
        it              lt
        poplt           {r4, pc}
2:
        mul             r4,  lr,  r1
        ldr             r2,  [r0]
        add_sh          r2,  r2,  r4,  asr r3
        str             r2,  [r0]
        pop             {r4, pc}
endfunc

function flac_lpc_16_2_arm
        ldr             r12, [sp]
        subs            r12, r12, r2
        it              le
        bxle            lr

        push            {r4-r9, lr}
        ldm             r0!, {r6, r7}
        ldm             r1,  {r8, r9}
        subs            r12, r12, #1
        beq             2f
1:
        mul             r4,  r6,  r8
        mul             r5,  r7,  r8
        mla             r4,  r7,  r9,  r4
        ldm             r0,  {r6, r7}
        add_sh          r6,  r6,  r4,  asr r3
        mla             r5,  r6,  r9,  r5
        add_sh          r7,  r7,  r5,  asr r3
        stm             r0!, {r6, r7}
        subs            r12, r12, #2
        bgt             1b
        it              lt
        poplt           {r4-r9, pc}
2:
        mul             r4,  r6,  r8
        mla             r4,  r7,  r9,  r4
        ldr             r5,  [r0]
        add_sh          r5,  r5,  r4,  asr r3
        str             r5,  [r0]
        pop             {r4-r9, pc}
endfunc

function ff_flac_lpc_16_arm, export=1
        cmp             r2,  #2
        blt             flac_lpc_16_1_arm
        beq             flac_lpc_16_2_arm

        ldr             r12, [sp]
        subs            r12, r12, r2
        it              le
        bxle            lr

        push            {r4-r9, lr}

        subs            r12, r12, #1
        beq             3f
1:
        sub             lr,  r2,  #2
        mov             r4,  #0
        mov             r5,  #0

        ldr             r7,  [r0], #4
        ldr             r9,  [r1], #4
2:
        mla             r4,  r7,  r9,  r4
        ldm             r0!, {r6, r7}
        mla             r5,  r6,  r9,  r5
        ldm             r1!, {r8, r9}
        mla             r4,  r6,  r8,  r4
        subs            lr,  lr,  #2
        mla             r5,  r7,  r8,  r5
        bgt             2b
        blt             6f

        mla             r4,  r7,  r9,  r4
        ldr             r7,  [r0], #4
        mla             r5,  r7,  r9,  r5
        ldr             r9,  [r1], #4
6:
        mla             r4,  r7,  r9,  r4
        ldm             r0,  {r6, r7}
        add_sh          r6,  r6,  r4,  asr r3
        mla             r5,  r6,  r9,  r5
        add_sh          r7,  r7,  r5,  asr r3
        stm             r0!, {r6, r7}
        sub             r0,  r0,  r2,  lsl #2
        sub             r1,  r1,  r2,  lsl #2

        subs            r12, r12, #2
        bgt             1b
        it              lt
        poplt           {r4-r9, pc}
3:
        mov             r4,  #0
4:
        ldr             r5,  [r1], #4
        ldr             r6,  [r0], #4
        mla             r4,  r5,  r6,  r4
        subs            r2,  r2,  #1
        bgt             4b
        ldr             r5,  [r0]
        add_sh          r5,  r5,  r4,  asr r3
        str             r5,  [r0]
        pop             {r4-r9, pc}
endfunc
OpenPOWER on IntegriCloud