summaryrefslogtreecommitdiffstats
path: root/apps/plugins/mpegplayer/libmpeg2/idct_arm.S
blob: 8ff7c9062973465df69d583b6270a879902a63ab (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
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
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
/***************************************************************************
 *             __________               __   ___.
 *   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
 *   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
 *   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
 *   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
 *                     \/            \/     \/    \/            \/
 * $Id$
 *
 * Copyright (C) 2007 by Michael Sevakis
 *
 * 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 software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 ****************************************************************************/

#include "config.h"

    .syntax     unified

    .global     mpeg2_idct_copy
    .type       mpeg2_idct_copy, %function
    .global     mpeg2_idct_add
    .type       mpeg2_idct_add, %function


/* Custom calling convention:
 * r0 contains block pointer and is non-volatile
 * all non-volatile c context saved and restored on its behalf
 */
.idct:
    add    r12, r0, #128
1:
    ldrsh  r1, [r0, #0]           /* d0 */
    ldrsh  r2, [r0, #2]           /* d1 */
    ldrsh  r3, [r0, #4]           /* d2 */
    ldrsh  r4, [r0, #6]           /* d3 */
    ldrsh  r5, [r0, #8]           /* d0 */
    ldrsh  r6, [r0, #10]          /* d1 */
    ldrsh  r7, [r0, #12]          /* d2 */
    ldrsh  r8, [r0, #14]          /* d3 */
    orrs   r9, r2, r3
    orrseq r9, r4, r5
    orrseq r9, r6, r7
    cmpeq  r8, #0
    bne    2f
    mov    r1, r1, asl #15
    bic    r1, r1, #0x8000
    orr    r1, r1, r1, lsr #16
    str    r1, [r0], #4
    str    r1, [r0], #4
    str    r1, [r0], #4
    str    r1, [r0], #4
    cmp    r0, r12
    blo    1b
    b      3f
2:
    mov    r1, r1, asl #11        /* r1 = d0 = (block[0] << 11) + 2048 */
    add    r1, r1, #2048
    add    r1, r1, r3, asl #11    /* r1 = t0 = d0 + (block[2] << 11) */
    sub    r3, r1, r3, asl #12    /* r3 = t1 = d0 - (block[2] << 11) */

    add    r9, r2, r4             /* r9 = tmp = (d1+d3)*(1108/4) */
    add    r10, r9, r9, asl #2
    add    r10, r10, r9, asl #4
    add    r9, r10, r9, asl #8

    add    r10, r2, r2, asl #4    /* r2 = t2 = tmp + (d1*(1568/32)*8) */
    add    r2, r10, r2, asl #5
    add    r2, r9, r2, asl #3

    add    r10, r4, r4, asl #2    /* r4 = t3 = tmp - (d3*(3784/8)*2) */
    rsb    r10, r10, r4, asl #6
    add    r4, r4, r10, asl #3
    sub    r4, r9, r4, asl #1
    /* t2 & t3 are 1/4 final value here */
    add    r1, r1, r2, asl #2     /* r1 = a0 = t0 + t2 */
    sub    r2, r1, r2, asl #3     /* r2 = a3 = t0 - t2 */
    add    r3, r3, r4, asl #2     /* r3 = a1 = t1 + t3 */
    sub    r4, r3, r4, asl #3     /* r4 = a2 = t1 - t3 */

    add    r9, r8, r5             /* r9 = tmp = 565*(d3 + d0) */
    add    r10, r9, r9, asl #4
    add    r10, r10, r10, asl #5
    add    r9, r10, r9, asl #2

    add    r10, r5, r5, asl #4    /* r5 = t0 = tmp + (((2276/4)*d0)*4) */
    add    r10, r10, r10, asl #5
    add    r5, r10, r5, asl #3
    add    r5, r9, r5, asl #2

    add    r10, r8, r8, asl #2    /* r8 = t1 = tmp - (((3406/2)*d3)*2) */
    add    r10, r10, r10, asl #4
    add    r10, r10, r8, asl #7
    rsb    r8, r8, r10, asl #3
    sub    r8, r9, r8, asl #1

    add    r9, r6, r7             /* r9 = tmp = (2408/8)*(d1 + d2) */
    add    r10, r9, r9, asl #3
    add    r10, r10, r10, asl #5
    add    r9, r10, r9, asl #2

    add    r10, r7, r7, asl #3    /* r7 = t2 = (tmp*8) - 799*d2 */
    add    r10, r10, r7, asl #4
    rsb    r7, r7, r10, asl #5
    rsb    r7, r7, r9, asl #3

    sub    r10, r6, r6, asl #4    /* r6 = t3 = (tmp*8) - 4017*d1 */
    sub    r10, r10, r6, asl #6
    add    r10, r10, r6, asl #12
    add    r6, r10, r6
    rsb    r6, r6, r9, asl #3
    /* t0 = r5, t1 = r8, t2 = r7, t3 = r6*/
    add    r9, r5, r7             /* r9 = b0 = t0 + t2 */
    add    r10, r8, r6            /* r10 = b3 = t1 + t3 */
    sub    r5, r5, r7             /* t0 -= t2 */
    sub    r8, r8, r6             /* t1 -= t3 */
    add    r6, r5, r8             /* r6 = t0 + t1 */
    sub    r7, r5, r8             /* r7 = t0 - t1 */

    add    r11, r6, r6, asr #2    /* r6 = b1 = r6*(181/128) */
    add    r11, r11, r11, asr #5
    add    r6, r11, r6, asr #3
    add    r11, r7, r7, asr #2    /* r7 = b2 = r7*(181/128) */
    add    r11, r11, r11, asr #5
    add    r7, r11, r7, asr #3
    /* r1 = a0, r3 = a1,   r4 = a2,   r2 = a3 */
    /* r9 = b0, r6 = b1*2, r7 = b2*2, r10 = b3 */
    add    r5, r1, r9             /* block[0] = (a0 + b0) >> 12 */
    mov    r5, r5, asr #12
    strh   r5, [r0], #2
    add    r8, r3, r6, asr #1     /* block[1] = (a1 + b1) >> 12 */
    mov    r8, r8, asr #12
    strh   r8, [r0], #2
    add    r5, r4, r7, asr #1     /* block[2] = (a2 + b2) >> 12 */
    mov    r5, r5, asr #12
    strh   r5, [r0], #2
    add    r8, r2, r10            /* block[3] = (a3 + b3) >> 12 */
    mov    r8, r8, asr #12
    strh   r8, [r0], #2
    sub    r5, r2, r10            /* block[4] = (a3 - b3) >> 12 */
    mov    r5, r5, asr #12
    strh   r5, [r0], #2
    sub    r8, r4, r7, asr #1     /* block[5] = (a2 - b2) >> 12 */
    mov    r8, r8, asr #12
    strh   r8, [r0], #2
    sub    r5, r3, r6, asr #1     /* block[6] = (a1 - b1) >> 12 */
    mov    r5, r5, asr #12
    strh   r5, [r0], #2
    sub    r8, r1, r9             /* block[7] = (a0 - b0) >> 12 */
    mov    r8, r8, asr #12
    strh   r8, [r0], #2
    cmp    r0, r12
    blo    1b
3:
    sub    r0, r0, #128
    add    r12, r0, #16
4:
    ldrsh  r1, [r0, #0*8]         /* d0 */
    ldrsh  r2, [r0, #2*8]         /* d1 */
    ldrsh  r3, [r0, #4*8]         /* d2 */
    ldrsh  r4, [r0, #6*8]         /* d3 */
    ldrsh  r5, [r0, #8*8]         /* d0 */
    ldrsh  r6, [r0, #10*8]        /* d1 */
    ldrsh  r7, [r0, #12*8]        /* d2 */
    ldrsh  r8, [r0, #14*8]        /* d3 */

    mov    r1, r1, asl #11        /* r1 = d0 = (block[0] << 11) + 2048 */
    add    r1, r1, #65536
    add    r1, r1, r3, asl #11    /* r1 = t0 = d0 + d2:(block[2] << 11) */
    sub    r3, r1, r3, asl #12    /* r3 = t1 = d0 - d2:(block[2] << 11) */

    add    r9, r2, r4             /* r9 = tmp = (d1+d3)*(1108/4) */
    add    r10, r9, r9, asl #2
    add    r10, r10, r9, asl #4
    add    r9, r10, r9, asl #8

    add    r11, r2, r2, asl #4    /* r2 = t2 = tmp + (d1*(1568/32)*8) */
    add    r2, r11, r2, asl #5
    add    r2, r9, r2, asl #3

    add    r10, r4, r4, asl #2    /* r4 = t3 = tmp - (d3*(3784/8)*2) */
    rsb    r10, r10, r4, asl #6
    add    r4, r4, r10, asl #3
    sub    r4, r9, r4, asl #1
    /* t2 & t3 are 1/4 final value here */
    add    r1, r1, r2, asl #2     /* r1 = a0 = t0 + t2 */
    sub    r2, r1, r2, asl #3     /* r2 = a3 = t0 - t2 */
    add    r3, r3, r4, asl #2     /* r3 = a1 = t1 + t3 */
    sub    r4, r3, r4, asl #3     /* r4 = a2 = t1 - t3 */

    add    r9, r8, r5             /* r9 = tmp = 565*(d3 + d0) */
    add    r10, r9, r9, asl #4
    add    r10, r10, r10, asl #5
    add    r9, r10, r9, asl #2

    add    r10, r5, r5, asl #4    /* r5 = t0 = tmp + (((2276/4)*d0)*4) */
    add    r10, r10, r10, asl #5
    add    r5, r10, r5, asl #3
    add    r5, r9, r5, asl #2

    add    r10, r8, r8, asl #2    /* r8 = t1 = tmp - (((3406/2)*d3)*2) */
    add    r10, r10, r10, asl #4
    add    r10, r10, r8, asl #7
    rsb    r8, r8, r10, asl #3
    sub    r8, r9, r8, asl #1

    add    r9, r6, r7             /* r9 = tmp = (2408/8)*(d1 + d2) */
    add    r10, r9, r9, asl #3
    add    r10, r10, r10, asl #5
    add    r9, r10, r9, asl #2

    add    r10, r7, r7, asl #3    /* r7 = t2 = (tmp*8) - 799*d2 */
    add    r10, r10, r7, asl #4
    rsb    r7, r7, r10, asl #5
    rsb    r7, r7, r9, asl #3

    sub    r10, r6, r6, asl #4    /* r6 = t3 = (tmp*8) - 4017*d1 */
    sub    r10, r10, r6, asl #6
    add    r10, r10, r6, asl #12
    add    r6, r10, r6
    rsb    r6, r6, r9, asl #3
                                    /* t0=r5, t1=r8, t2=r7, t3=r6*/
    add    r9, r5, r7             /* r9 = b0 = t0 + t2 */
    add    r10, r8, r6            /* r10 = b3 = t1 + t3 */
    sub    r5, r5, r7             /* t0 -= t2 */
    sub    r8, r8, r6             /* t1 -= t3 */
    add    r6, r5, r8             /* r6 = t0 + t1 */
    sub    r7, r5, r8             /* r7 = t0 - t1 */

    add    r11, r6, r6, asr #2    /* r6 = b1 = r5*(181/128) */
    add    r11, r11, r11, asr #5
    add    r6, r11, r6, asr #3
    add    r11, r7, r7, asr #2    /* r7 = b2 = r6*(181/128) */
    add    r11, r11, r11, asr #5
    add    r7, r11, r7, asr #3
    /* r1 = a0, r3 = a1,   r4 = a2,    r2 = a3 */
    /* r9 = b0, r6 = b1*2, r7 = b2*2, r10 = b3 */
    add    r5, r1, r9             /* block[0] = (a0 + b0) >> 17 */
    mov    r5, r5, asr #17
    strh   r5, [r0, #0*8]
    add    r8, r3, r6, asr #1     /* block[1] = (a1 + b1) >> 17 */
    mov    r8, r8, asr #17
    strh   r8, [r0, #2*8]
    add    r5, r4, r7, asr #1     /* block[2] = (a2 + b2) >> 17 */
    mov    r5, r5, asr #17
    strh   r5, [r0, #4*8]
    add    r8, r2, r10            /* block[3] = (a3 + b3) >> 17 */
    mov    r8, r8, asr #17
    strh   r8, [r0, #6*8]
    sub    r5, r2, r10            /* block[4] = (a3 - b3) >> 17 */
    mov    r5, r5, asr #17
    strh   r5, [r0, #8*8]
    sub    r8, r4, r7, asr #1     /* block[5] = (a2 - b2) >> 17 */
    mov    r8, r8, asr #17
    strh   r8, [r0, #10*8]
    sub    r5, r3, r6, asr #1     /* block[6] = (a1 - b1) >> 17 */
    mov    r5, r5, asr #17
    strh   r5, [r0, #12*8]
    sub    r8, r1, r9             /* block[7] = (a0 - b0) >> 17 */
    mov    r8, r8, asr #17
    strh   r8, [r0, #14*8]
    add    r0, r0, #2
    cmp    r0, r12
    blo    4b
    sub    r0, r0, #16
    bx     lr

mpeg2_idct_copy:
    stmfd  sp!, { r1-r2, r4-r11, lr }
    bl     .idct
    ldmfd  sp!, { r1-r2 }
    mov    r11, #0
    add    r12, r0, #128
1:
    ldrsh  r3, [r0, #0]
    ldrsh  r4, [r0, #2]
    ldrsh  r5, [r0, #4]
    ldrsh  r6, [r0, #6]
    ldrsh  r7, [r0, #8]
    ldrsh  r8, [r0, #10]
    ldrsh  r9, [r0, #12]
    ldrsh  r10, [r0, #14]
    cmp    r3, #255
    mvnhi  r3, r3, asr #31
    strb   r3, [r1, #0]
    str    r11, [r0], #4
    cmp    r4, #255
    mvnhi  r4, r4, asr #31
    strb   r4, [r1, #1]
    cmp    r5, #255
    mvnhi  r5, r5, asr #31
    strb   r5, [r1, #2]
    str    r11, [r0], #4
    cmp    r6, #255
    mvnhi  r6, r6, asr #31
    strb   r6, [r1, #3]
    cmp    r7, #255
    mvnhi  r7, r7, asr #31
    strb   r7, [r1, #4]
    str    r11, [r0], #4
    cmp    r8, #255
    mvnhi  r8, r8, asr #31
    strb   r8, [r1, #5]
    cmp    r9, #255
    mvnhi  r9, r9, asr #31
    strb   r9, [r1, #6]
    str    r11, [r0], #4
    cmp    r10, #255
    mvnhi  r10, r10, asr #31
    strb   r10, [r1, #7]
    add    r1, r1, r2
    cmp    r0, r12
    blo    1b
    ldmpc  regs=r4-r11

mpeg2_idct_add:
    cmp    r0, #129
    mov    r0, r1
    ldrsheq r1, [r0, #0]
    bne    1f
    and    r1, r1, #0x70
    cmp    r1, #0x40
    bne    3f
1:
    stmfd  sp!, { r2-r11, lr }
    bl     .idct
    ldmfd  sp!, { r1-r2 }
    mov    r11, #0
    add    r12, r0, #128
2:
    ldrb   r3, [r1, #0]
    ldrb   r4, [r1, #1]
    ldrb   r5, [r1, #2]
    ldrb   r6, [r1, #3]
    ldrsh  r7, [r0, #0]
    ldrsh  r8, [r0, #2]
    ldrsh  r9, [r0, #4]
    ldrsh  r10, [r0, #6]
    add    r7, r7, r3
    ldrb   r3, [r1, #4]
    cmp    r7, #255
    mvnhi  r7, r7, asr #31
    strb   r7, [r1, #0]
    ldrsh  r7, [r0, #8]
    add    r8, r8, r4
    ldrb   r4, [r1, #5]
    cmp    r8, #255
    mvnhi  r8, r8, asr #31
    strb   r8, [r1, #1]
    ldrsh  r8, [r0, #10]
    add    r9, r9, r5
    ldrb   r5, [r1, #6]
    cmp    r9, #255
    mvnhi  r9, r9, asr #31
    strb   r9, [r1, #2]
    ldrsh  r9, [r0, #12]
    add    r10, r10, r6
    ldrb   r6, [r1, #7]
    cmp    r10, #255
    mvnhi  r10, r10, asr #31
    strb   r10, [r1, #3]
    ldrsh  r10, [r0, #14]
    str    r11, [r0], #4
    add    r7, r7, r3
    cmp    r7, #255
    mvnhi  r7, r7, asr #31
    strb   r7, [r1, #4]
    str    r11, [r0], #4
    add    r8, r8, r4
    cmp    r8, #255
    mvnhi  r8, r8, asr #31
    strb   r8, [r1, #5]
    str    r11, [r0], #4
    add    r9, r9, r5
    cmp    r9, #255
    mvnhi  r9, r9, asr #31
    strb   r9, [r1, #6]
    add    r10, r10, r6
    cmp    r10, #255
    mvnhi  r10, r10, asr #31
    strb   r10, [r1, #7]
    str    r11, [r0], #4
    add    r1, r1, r2
    cmp    r0, r12
    blo    2b
    ldmpc  regs=r4-r11
3:
    stmfd  sp!, { r4-r5, lr }
    ldrsh  r1, [r0, #0]           /* r1 = block[0] */
    mov    r4, #0
    strh   r4, [r0, #0]           /* block[0] = 0 */
    strh   r4, [r0, #126]         /* block[63] = 0 */
    add    r1, r1, #64            /* r1 = DC << 7 */
    add    r0, r2, r3, asl #3
4:
    ldrb   r4, [r2, #0]
    ldrb   r5, [r2, #1]
    ldrb   r12, [r2, #2]
    ldrb   lr, [r2, #3]
    add    r4, r4, r1, asr #7
    cmp    r4, #255
    mvnhi  r4, r4, asr #31
    strb   r4, [r2, #0]
    add    r5, r5, r1, asr #7
    cmp    r5, #255
    mvnhi  r5, r5, asr #31
    strb   r5, [r2, #1]
    add    r12, r12, r1, asr #7
    cmp    r12, #255
    mvnhi  r12, r12, asr #31
    strb   r12, [r2, #2]
    add    lr, lr, r1, asr #7
    cmp    lr, #255
    mvnhi  lr, lr, asr #31
    strb   lr, [r2, #3]
    ldrb   r4, [r2, #4]
    ldrb   r5, [r2, #5]
    ldrb   r12, [r2, #6]
    ldrb   lr, [r2, #7]
    add    r4, r4, r1, asr #7
    cmp    r4, #255
    mvnhi  r4, r4, asr #31
    strb   r4, [r2, #4]
    add    r5, r5, r1, asr #7
    cmp    r5, #255
    mvnhi  r5, r5, asr #31
    strb   r5, [r2, #5]
    add    r12, r12, r1, asr #7
    cmp    r12, #255
    mvnhi  r12, r12, asr #31
    strb   r12, [r2, #6]
    add    lr, lr, r1, asr #7
    cmp    lr, #255
    mvnhi  lr, lr, asr #31
    strb   lr, [r2, #7]
    add    r2, r2, r3
    cmp    r2, r0
    blo    4b
    ldmpc  regs=r4-r5