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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
|
/*
Companion assembly file for layer3.c
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program 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 General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
RSEG CODE32:CODE:NOROOT(2)
PUBLIC iii_imdct_s_step1
PUBLIC iii_imdct_s_step2
PUBLIC __asm_mad_f_mul
iii_imdct_s_step1:
// imputs:
// r12 = s
// r11 = X
// r10 = yptr
// r9 = i
// tmp0 = r1-r0
// tmp1 = r3-r2
// tmp2 = r5-r4
// tmp3 = r7-r6
// acc = r9-r8
pushm r0-r7, r8-r9, lr
mov lr, r9 // lr = i
ld.d r0, r12++
ld.d r2, r11[0]
ld.d r4, r11[2*4]
ld.d r6, r11[4*4]
mulwh.d r8, r3, r1:t
macwh.d r8, r2, r1:b
ld.w r1, r12++
macwh.d r8, r5, r0:t
macwh.d r8, r4, r0:b
macwh.d r8, r7, r1:t
macwh.d r8, r6, r1:b
ld.d r0, r12++
rol r8
rol r9
st.w r10[lr << 2], r9
neg r9
rsub lr, lr, 5
st.w r10[lr << 2], r9
rsub lr, lr, 5
mulwh.d r8, r3, r1:t
macwh.d r8, r2, r1:b
ld.w r1, r12++
macwh.d r8, r5, r0:t
macwh.d r8, r4, r0:b
macwh.d r8, r7, r1:t
macwh.d r8, r6, r1:b
rol r8
rol r9
sub lr, -6
st.w r10[lr << 2], r9
rsub lr, lr, 17
st.w r10[lr << 2], r9
popm r0-r7, r8-r9, pc
iii_imdct_s_step2:
// imputs:
// r12 = z
// r11 = wptr
// r10 = yptr
// tmp = r1-r0
// w0123 = r3-r2
// w4567 = r5-r4
// w891011 = r7-r6
// tmp2 = r9-r8
pushm r0-r7, r8-r9, lr
mov r1, 0
mov r0, r1
st.d r12[0], r0
st.d r12[2*4], r0
st.d r12[4*4], r0
st.d r12[30*4], r0
st.d r12[32*4], r0
st.d r12[34*4], r0
/////
ld.d r2, r11[0*4]
ld.d r0, r10[0*4]
ld.d r4, r11[2*4]
ld.d r6, r11[4*4]
mulsatrndwh.w r1, r1, r3:t
mulsatrndwh.w r0, r0, r3:b
ld.d r8, r10[2*4]
st.d r12[6*4], r0
mulsatrndwh.w r9, r9, r2:t
mulsatrndwh.w r8, r8, r2:b
ld.d r0, r10[4*4]
st.d r12[8*4], r8
mulsatrndwh.w r1, r1, r5:t
mulsatrndwh.w r0, r0, r5:b
ld.d r8, r10[30*4]
st.d r12[10*4], r0
mulsatrndwh.w r9, r9, r4:t
mulsatrndwh.w r8, r8, r4:b
ld.d r0, r10[32*4]
st.d r12[24*4], r8
mulsatrndwh.w r1, r1, r7:t
mulsatrndwh.w r0, r0, r7:b
ld.d r8, r10[34*4]
st.d r12[26*4], r0
mulsatrndwh.w r9, r9, r6:t
mulsatrndwh.w r8, r8, r6:b
st.d r12[28*4], r8
//
// tmp3 = r11-r10
mov lr, r10 // lr = yptr
ld.d r0, lr[6*4]
ld.d r8, lr[12*4]
mulwh.d r10, r1, r4:t
macwh.d r10, r9, r3:t
mulwh.d r0, r0, r4:b
macwh.d r0, r8, r3:b
lsl r11, 1
lsl r10, r1, 1
st.d r12[12*4], r10
ld.d r0, lr[18*4]
ld.d r8, lr[24*4]
mulwh.d r10, r1, r4:t
macwh.d r10, r9, r3:t
mulwh.d r0, r0, r4:b
macwh.d r0, r8, r3:b
lsl r11, 1
lsl r10, r1, 1
st.d r12[18*4], r10
//
ld.d r0, lr[8*4]
ld.d r8, lr[14*4]
mulwh.d r10, r1, r7:t
macwh.d r10, r9, r2:t
mulwh.d r0, r0, r7:b
macwh.d r0, r8, r2:b
lsl r11, 1
lsl r10, r1, 1
st.d r12[14*4], r10
ld.d r0, lr[20*4]
ld.d r8, lr[26*4]
mulwh.d r10, r1, r7:t
macwh.d r10, r9, r2:t
mulwh.d r0, r0, r7:b
macwh.d r0, r8, r2:b
lsl r11, 1
lsl r10, r1, 1
st.d r12[20*4], r10
//
ld.d r0, lr[10*4]
ld.d r8, lr[16*4]
mulwh.d r10, r1, r6:t
macwh.d r10, r9, r5:t
mulwh.d r0, r0, r6:b
macwh.d r0, r8, r5:b
lsl r11, 1
lsl r10, r1, 1
st.d r12[16*4], r10
ld.d r0, lr[22*4]
ld.d r8, lr[28*4]
mulwh.d r10, r1, r6:t
macwh.d r10, r9, r5:t
mulwh.d r0, r0, r6:b
macwh.d r0, r8, r5:b
lsl r11, 1
lsl r10, r1, 1
st.d r12[22*4], r10
popm r0-r7, r8-r9, pc
__asm_mad_f_mul:
mulsatrndwh.w r12, r12, r11:b
retal r12
END
|
