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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
|
/* ------------------------------------------------------------------
* Copyright (C) 1998-2009 PacketVideo
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
* express or implied.
* See the License for the specific language governing permissions
* and limitations under the License.
* -------------------------------------------------------------------
*/
/* Filename: dct_inline.h */
/* Description: Implementation for in-line functions used in dct.cpp */
/* Modified: */
/*********************************************************************************/
#ifndef _DCT_INLINE_H_
#define _DCT_INLINE_H_
#if !defined(PV_ARM_GCC_V5) && !defined(PV_ARM_GCC_V4)
__inline int32 mla724(int32 op1, int32 op2, int32 op3)
{
int32 out;
OSCL_UNUSED_ARG(op1);
out = op2 * 724 + op3; /* op1 is not used here */
return out;
}
__inline int32 mla392(int32 k0, int32 k14, int32 round)
{
int32 k1;
OSCL_UNUSED_ARG(k14);
k1 = k0 * 392 + round;
return k1;
}
__inline int32 mla554(int32 k4, int32 k12, int32 k1)
{
int32 k0;
OSCL_UNUSED_ARG(k12);
k0 = k4 * 554 + k1;
return k0;
}
__inline int32 mla1338(int32 k6, int32 k14, int32 k1)
{
int32 out;
OSCL_UNUSED_ARG(k14);
out = k6 * 1338 + k1;
return out;
}
__inline int32 mla946(int32 k6, int32 k14, int32 k1)
{
int32 out;
OSCL_UNUSED_ARG(k14);
out = k6 * 946 + k1;
return out;
}
__inline int32 sum_abs(int32 k0, int32 k1, int32 k2, int32 k3,
int32 k4, int32 k5, int32 k6, int32 k7)
{
int32 carry, abs_sum;
carry = k0 >> 31;
abs_sum = (k0 ^ carry);
carry = k1 >> 31;
abs_sum += (k1 ^ carry) - carry;
carry = k2 >> 31;
abs_sum += (k2 ^ carry) - carry;
carry = k3 >> 31;
abs_sum += (k3 ^ carry) - carry;
carry = k4 >> 31;
abs_sum += (k4 ^ carry) - carry;
carry = k5 >> 31;
abs_sum += (k5 ^ carry) - carry;
carry = k6 >> 31;
abs_sum += (k6 ^ carry) - carry;
carry = k7 >> 31;
abs_sum += (k7 ^ carry) - carry;
return abs_sum;
}
#elif defined(__CC_ARM) /* only work with arm v5 */
#if defined(__TARGET_ARCH_5TE)
__inline int32 mla724(int32 op1, int32 op2, int32 op3)
{
int32 out;
__asm
{
smlabb out, op1, op2, op3
}
return out;
}
__inline int32 mla392(int32 k0, int32 k14, int32 round)
{
int32 k1;
__asm
{
smlabt k1, k0, k14, round
}
return k1;
}
__inline int32 mla554(int32 k4, int32 k12, int32 k1)
{
int32 k0;
__asm
{
smlabt k0, k4, k12, k1
}
return k0;
}
__inline int32 mla1338(int32 k6, int32 k14, int32 k1)
{
int32 out;
__asm
{
smlabb out, k6, k14, k1
}
return out;
}
__inline int32 mla946(int32 k6, int32 k14, int32 k1)
{
int32 out;
__asm
{
smlabb out, k6, k14, k1
}
return out;
}
#else // not ARM5TE
__inline int32 mla724(int32 op1, int32 op2, int32 op3)
{
int32 out;
__asm
{
and out, op2, #0xFFFF
mla out, op1, out, op3
}
return out;
}
__inline int32 mla392(int32 k0, int32 k14, int32 round)
{
int32 k1;
__asm
{
mov k1, k14, asr #16
mla k1, k0, k1, round
}
return k1;
}
__inline int32 mla554(int32 k4, int32 k12, int32 k1)
{
int32 k0;
__asm
{
mov k0, k12, asr #16
mla k0, k4, k0, k1
}
return k0;
}
__inline int32 mla1338(int32 k6, int32 k14, int32 k1)
{
int32 out;
__asm
{
and out, k14, 0xFFFF
mla out, k6, out, k1
}
return out;
}
__inline int32 mla946(int32 k6, int32 k14, int32 k1)
{
int32 out;
__asm
{
and out, k14, 0xFFFF
mla out, k6, out, k1
}
return out;
}
#endif
__inline int32 sum_abs(int32 k0, int32 k1, int32 k2, int32 k3,
int32 k4, int32 k5, int32 k6, int32 k7)
{
int32 carry, abs_sum;
__asm
{
eor carry, k0, k0, asr #31 ;
eors abs_sum, k1, k1, asr #31 ;
adc abs_sum, abs_sum, carry ;
eors carry, k2, k2, asr #31 ;
adc abs_sum, abs_sum, carry ;
eors carry, k3, k3, asr #31 ;
adc abs_sum, abs_sum, carry ;
eors carry, k4, k4, asr #31 ;
adc abs_sum, abs_sum, carry ;
eors carry, k5, k5, asr #31 ;
adc abs_sum, abs_sum, carry ;
eors carry, k6, k6, asr #31 ;
adc abs_sum, abs_sum, carry ;
eors carry, k7, k7, asr #31 ;
adc abs_sum, abs_sum, carry ;
}
return abs_sum;
}
#elif ( defined(PV_ARM_GCC_V5) || defined(PV_ARM_GCC_V4) ) /* ARM GNU COMPILER */
__inline int32 mla724(int32 op1, int32 op2, int32 op3)
{
register int32 out;
register int32 aa = (int32)op1;
register int32 bb = (int32)op2;
register int32 cc = (int32)op3;
asm volatile("smlabb %0, %1, %2, %3"
: "=&r"(out)
: "r"(aa),
"r"(bb),
"r"(cc));
return out;
}
__inline int32 mla392(int32 k0, int32 k14, int32 round)
{
register int32 out;
register int32 aa = (int32)k0;
register int32 bb = (int32)k14;
register int32 cc = (int32)round;
asm volatile("smlabt %0, %1, %2, %3"
: "=&r"(out)
: "r"(aa),
"r"(bb),
"r"(cc));
return out;
}
__inline int32 mla554(int32 k4, int32 k12, int32 k1)
{
register int32 out;
register int32 aa = (int32)k4;
register int32 bb = (int32)k12;
register int32 cc = (int32)k1;
asm volatile("smlabt %0, %1, %2, %3"
: "=&r"(out)
: "r"(aa),
"r"(bb),
"r"(cc));
return out;
}
__inline int32 mla1338(int32 k6, int32 k14, int32 k1)
{
register int32 out;
register int32 aa = (int32)k6;
register int32 bb = (int32)k14;
register int32 cc = (int32)k1;
asm volatile("smlabb %0, %1, %2, %3"
: "=&r"(out)
: "r"(aa),
"r"(bb),
"r"(cc));
return out;
}
__inline int32 mla946(int32 k6, int32 k14, int32 k1)
{
register int32 out;
register int32 aa = (int32)k6;
register int32 bb = (int32)k14;
register int32 cc = (int32)k1;
asm volatile("smlabb %0, %1, %2, %3"
: "=&r"(out)
: "r"(aa),
"r"(bb),
"r"(cc));
return out;
}
__inline int32 sum_abs(int32 k0, int32 k1, int32 k2, int32 k3,
int32 k4, int32 k5, int32 k6, int32 k7)
{
register int32 carry;
register int32 abs_sum;
register int32 aa = (int32)k0;
register int32 bb = (int32)k1;
register int32 cc = (int32)k2;
register int32 dd = (int32)k3;
register int32 ee = (int32)k4;
register int32 ff = (int32)k5;
register int32 gg = (int32)k6;
register int32 hh = (int32)k7;
asm volatile("eor %0, %2, %2, asr #31\n\t"
"eors %1, %3, %3, asr #31\n\t"
"adc %1, %1, %0\n\t"
"eors %0, %4, %4, asr #31\n\t"
"adc %1, %1, %0\n\t"
"eors %0, %5, %5, asr #31\n\t"
"adc %1, %1, %0\n\t"
"eors %0, %6, %6, asr #31\n\t"
"adc %1, %1, %0\n\t"
"eors %0, %7, %7, asr #31\n\t"
"adc %1, %1, %0\n\t"
"eors %0, %8, %8, asr #31\n\t"
"adc %1, %1, %0\n\t"
"eors %0, %9, %9, asr #31\n\t"
"adc %1, %1, %0\n\t"
: "=&r"(carry),
"=&r"(abs_sum):
"r"(aa),
"r"(bb),
"r"(cc),
"r"(dd),
"r"(ee),
"r"(ff),
"r"(gg),
"r"(hh));
return abs_sum;
}
#endif // Diff. OS
#endif //_DCT_INLINE_H_
|
