-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdecode_idct.cl
515 lines (474 loc) · 19.2 KB
/
decode_idct.cl
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
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
#define MAX_COMPONENT_INFO_COUNT 5
#define DCTSIZE2 64
#define DCTSIZE 8
#define MAXJSAMPLE 255
#define CENTERJSAMPLE 128
typedef short JCOEF;
typedef JCOEF JBLOCK[DCTSIZE2]; /* one block of coefficients */
typedef unsigned char JSAMPLE;
typedef unsigned int JDIMENSION;
typedef int INT32;
typedef short INT16;
typedef float FAST_FLOAT;
typedef FAST_FLOAT FLOAT_MULT_TYPE; /* preferred floating type */
#define MULTIPLIER int /* type for fastest integer multiply */
// typedef MULTIPLIER ISLOW_MULT_TYPE; /* short or int, whichever is faster */
struct ComponentInfo
{
unsigned int MCU_width;
unsigned int MCU_height;
unsigned int last_col_width;
unsigned int MCU_sample_width;
unsigned int DCT_scaled_size;
unsigned int row_buffer_size;
unsigned int previous_image_size;
unsigned int previous_decoded_mcu_size;
FLOAT_MULT_TYPE dct_table[DCTSIZE2];
};
struct DecodeInfo
{
unsigned int componets_mcu_width;
JSAMPLE sample_range_limit[(5 * (MAXJSAMPLE+1) + CENTERJSAMPLE)];
struct ComponentInfo component_infos[MAX_COMPONENT_INFO_COUNT];
};
#define IDCT_range_limit(cinfo) ((cinfo)->sample_range_limit + CENTERJSAMPLE + (MAXJSAMPLE+1))
#define DEQUANTIZE(coef,quantval) (((FAST_FLOAT) (coef)) * (quantval))
#define CONST_BITS 13
#define PASS1_BITS 2
#define FIX_0_298631336 ((INT32) 2446) /* FIX(0.298631336) */
#define FIX_0_390180644 ((INT32) 3196) /* FIX(0.390180644) */
#define FIX_0_541196100 ((INT32) 4433) /* FIX(0.541196100) */
#define FIX_0_765366865 ((INT32) 6270) /* FIX(0.765366865) */
#define FIX_0_899976223 ((INT32) 7373) /* FIX(0.899976223) */
#define FIX_1_175875602 ((INT32) 9633) /* FIX(1.175875602) */
#define FIX_1_501321110 ((INT32) 12299) /* FIX(1.501321110) */
#define FIX_1_847759065 ((INT32) 15137) /* FIX(1.847759065) */
#define FIX_1_961570560 ((INT32) 16069) /* FIX(1.961570560) */
#define FIX_2_053119869 ((INT32) 16819) /* FIX(2.053119869) */
#define FIX_2_562915447 ((INT32) 20995) /* FIX(2.562915447) */
#define FIX_3_072711026 ((INT32) 25172) /* FIX(3.072711026) */
#define MULTIPLY16C16(var,const) (((INT16) (var)) * ((INT16) (const)))
#define MULTIPLY(var,const) MULTIPLY16C16(var,const)
#define DESCALE(x,n) RIGHT_SHIFT((x) + (ONE << ((n)-1)), n)
#define ONE ((INT32) 1)
#define RIGHT_SHIFT(x,shft) ((x) >> (shft))
#define RANGE_MASK (MAXJSAMPLE * 4 + 3) /* 2 bits wider than legal samples */
// void inverse_DCT(__global struct DecodeInfo * cinfo,
// __global struct ComponentInfo * compptr,
// __global JCOEF * coef_block,
// __global JSAMPLE * output_buf,
// JDIMENSION output_col)
// {
// INT32 tmp0, tmp1, tmp2, tmp3;
// INT32 tmp10, tmp11, tmp12, tmp13;
// INT32 z1, z2, z3, z4, z5;
// __global JCOEF * inptr;
// __global ISLOW_MULT_TYPE * quantptr;
// int * wsptr;
// __global JSAMPLE * outptr;
// __global JSAMPLE *range_limit = IDCT_range_limit(cinfo);
// int ctr;
// int workspace[DCTSIZE2]; /* buffers data between passes */
//
// /* Pass 1: process columns from input, store into work array. */
// /* Note results are scaled up by sqrt(8) compared to a true IDCT; */
// /* furthermore, we scale the results by 2**PASS1_BITS. */
//
// inptr = coef_block;
// quantptr = (__global ISLOW_MULT_TYPE *) compptr->dct_table;
// wsptr = workspace;
// for (ctr = DCTSIZE; ctr > 0; ctr--) {
// /* Due to quantization, we will usually find that many of the input
// * coefficients are zero, especially the AC terms. We can exploit this
// * by short-circuiting the IDCT calculation for any column in which all
// * the AC terms are zero. In that case each output is equal to the
// * DC coefficient (with scale factor as needed).
// * With typical images and quantization tables, half or more of the
// * column DCT calculations can be simplified this way.
// */
//
// if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 &&
// inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 &&
// inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
// inptr[DCTSIZE*7] == 0) {
// /* AC terms all zero */
// int dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]) << PASS1_BITS;
//
// wsptr[DCTSIZE*0] = dcval;
// wsptr[DCTSIZE*1] = dcval;
// wsptr[DCTSIZE*2] = dcval;
// wsptr[DCTSIZE*3] = dcval;
// wsptr[DCTSIZE*4] = dcval;
// wsptr[DCTSIZE*5] = dcval;
// wsptr[DCTSIZE*6] = dcval;
// wsptr[DCTSIZE*7] = dcval;
//
// inptr++; /* advance pointers to next column */
// quantptr++;
// wsptr++;
// continue;
// }
// /* Even part: reverse the even part of the forward DCT. */
// /* The rotator is sqrt(2)*c(-6). */
//
// z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
// z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);
//
// z1 = MULTIPLY(z2 + z3, FIX_0_541196100);
// tmp2 = z1 + MULTIPLY(z3, - FIX_1_847759065);
// tmp3 = z1 + MULTIPLY(z2, FIX_0_765366865);
//
// z2 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
// z3 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
//
// tmp0 = (z2 + z3) << CONST_BITS;
// tmp1 = (z2 - z3) << CONST_BITS;
//
// tmp10 = tmp0 + tmp3;
// tmp13 = tmp0 - tmp3;
// tmp11 = tmp1 + tmp2;
// tmp12 = tmp1 - tmp2;
//
// /* Odd part per figure 8; the matrix is unitary and hence its
// * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively.
// */
//
// tmp0 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);
// tmp1 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);
// tmp2 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);
// tmp3 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);
//
// z1 = tmp0 + tmp3;
// z2 = tmp1 + tmp2;
// z3 = tmp0 + tmp2;
// z4 = tmp1 + tmp3;
// z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
//
// tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
// tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
// tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
// tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
// z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
// z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
// z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
// z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
//
// z3 += z5;
// z4 += z5;
//
// tmp0 += z1 + z3;
// tmp1 += z2 + z4;
// tmp2 += z2 + z3;
// tmp3 += z1 + z4;
//
// /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
//
// wsptr[DCTSIZE*0] = (int) DESCALE(tmp10 + tmp3, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*7] = (int) DESCALE(tmp10 - tmp3, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*1] = (int) DESCALE(tmp11 + tmp2, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*6] = (int) DESCALE(tmp11 - tmp2, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*2] = (int) DESCALE(tmp12 + tmp1, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*5] = (int) DESCALE(tmp12 - tmp1, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*3] = (int) DESCALE(tmp13 + tmp0, CONST_BITS-PASS1_BITS);
// wsptr[DCTSIZE*4] = (int) DESCALE(tmp13 - tmp0, CONST_BITS-PASS1_BITS);
//
// inptr++; /* advance pointers to next column */
// quantptr++;
// wsptr++;
// }
//
// /* Pass 2: process rows from work array, store into output array. */
// /* Note that we must descale the results by a factor of 8 == 2**3, */
// /* and also undo the PASS1_BITS scaling. */
//
// wsptr = workspace;
// for (ctr = 0; ctr < DCTSIZE; ctr++) {
// outptr = output_buf + ctr * compptr->row_buffer_size + output_col;
// /* Rows of zeroes can be exploited in the same way as we did with columns.
// * However, the column calculation has created many nonzero AC terms, so
// * the simplification applies less often (typically 5% to 10% of the time).
// * On machines with very fast multiplication, it's possible that the
// * test takes more time than it's worth. In that case this section
// * may be commented out.
// */
//
// #ifndef NO_ZERO_ROW_TEST
// if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[4] == 0 &&
// wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) {
// /* AC terms all zero */
// JSAMPLE dcval = range_limit[(int) DESCALE((INT32) wsptr[0], PASS1_BITS+3)
// & RANGE_MASK];
//
// outptr[0] = dcval;
// outptr[1] = dcval;
// outptr[2] = dcval;
// outptr[3] = dcval;
// outptr[4] = dcval;
// outptr[5] = dcval;
// outptr[6] = dcval;
// outptr[7] = dcval;
//
// wsptr += DCTSIZE; /* advance pointer to next row */
// continue;
// }
// #endif
//
// /* Even part: reverse the even part of the forward DCT. */
// /* The rotator is sqrt(2)*c(-6). */
//
// z2 = (INT32) wsptr[2];
// z3 = (INT32) wsptr[6];
//
// z1 = MULTIPLY(z2 + z3, FIX_0_541196100);
// tmp2 = z1 + MULTIPLY(z3, - FIX_1_847759065);
// tmp3 = z1 + MULTIPLY(z2, FIX_0_765366865);
//
// tmp0 = ((INT32) wsptr[0] + (INT32) wsptr[4]) << CONST_BITS;
// tmp1 = ((INT32) wsptr[0] - (INT32) wsptr[4]) << CONST_BITS;
//
// tmp10 = tmp0 + tmp3;
// tmp13 = tmp0 - tmp3;
// tmp11 = tmp1 + tmp2;
// tmp12 = tmp1 - tmp2;
//
// /* Odd part per figure 8; the matrix is unitary and hence its
// * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively.
// */
//
// tmp0 = (INT32) wsptr[7];
// tmp1 = (INT32) wsptr[5];
// tmp2 = (INT32) wsptr[3];
// tmp3 = (INT32) wsptr[1];
//
// z1 = tmp0 + tmp3;
// z2 = tmp1 + tmp2;
// z3 = tmp0 + tmp2;
// z4 = tmp1 + tmp3;
// z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
//
// tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
// tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
// tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
// tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
// z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
// z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
// z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
// z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
//
// z3 += z5;
// z4 += z5;
//
// tmp0 += z1 + z3;
// tmp1 += z2 + z4;
// tmp2 += z2 + z3;
// tmp3 += z1 + z4;
//
// /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
//
// outptr[0] = range_limit[(int) DESCALE(tmp10 + tmp3,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[7] = range_limit[(int) DESCALE(tmp10 - tmp3,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[1] = range_limit[(int) DESCALE(tmp11 + tmp2,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[6] = range_limit[(int) DESCALE(tmp11 - tmp2,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[2] = range_limit[(int) DESCALE(tmp12 + tmp1,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[5] = range_limit[(int) DESCALE(tmp12 - tmp1,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[3] = range_limit[(int) DESCALE(tmp13 + tmp0,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
// outptr[4] = range_limit[(int) DESCALE(tmp13 - tmp0,
// CONST_BITS+PASS1_BITS+3)
// & RANGE_MASK];
//
// wsptr += DCTSIZE; /* advance pointer to next row */
// }
// }
void inverse_DCT(__global struct DecodeInfo * cinfo,
__global struct ComponentInfo * compptr,
__global JCOEF * coef_block,
__global JSAMPLE * output_buf,
JDIMENSION output_col)
{
FAST_FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FAST_FLOAT tmp10, tmp11, tmp12, tmp13;
FAST_FLOAT z5, z10, z11, z12, z13;
__global JCOEF * inptr;
__global FLOAT_MULT_TYPE * quantptr;
__local FAST_FLOAT * wsptr;
__global JSAMPLE * outptr;
__global JSAMPLE *range_limit = IDCT_range_limit(cinfo);
int ctr;
__local FAST_FLOAT workspace[DCTSIZE2]; /* buffers data between passes */
/* Pass 1: process columns from input, store into work array. */
inptr = coef_block;
quantptr = (__global FLOAT_MULT_TYPE *) compptr->dct_table;
wsptr = workspace;
ctr = get_local_id(2);
inptr += ctr;
quantptr += ctr;
wsptr += ctr;
/* Due to quantization, we will usually find that many of the input
* coefficients are zero, especially the AC terms. We can exploit this
* by short-circuiting the IDCT calculation for any column in which all
* the AC terms are zero. In that case each output is equal to the
* DC coefficient (with scale factor as needed).
* With typical images and quantization tables, half or more of the
* column DCT calculations can be simplified this way.
*/
if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 &&
inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 &&
inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
inptr[DCTSIZE*7] == 0) {
/* AC terms all zero */
FAST_FLOAT dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
wsptr[DCTSIZE*0] = dcval;
wsptr[DCTSIZE*1] = dcval;
wsptr[DCTSIZE*2] = dcval;
wsptr[DCTSIZE*3] = dcval;
wsptr[DCTSIZE*4] = dcval;
wsptr[DCTSIZE*5] = dcval;
wsptr[DCTSIZE*6] = dcval;
wsptr[DCTSIZE*7] = dcval;
}
else
{
/* Even part */
tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);
tmp10 = tmp0 + tmp2; /* phase 3 */
tmp11 = tmp0 - tmp2;
tmp13 = tmp1 + tmp3; /* phases 5-3 */
tmp12 = (tmp1 - tmp3) * ((FAST_FLOAT) 1.414213562) - tmp13; /* 2*c4 */
tmp0 = tmp10 + tmp13; /* phase 2 */
tmp3 = tmp10 - tmp13;
tmp1 = tmp11 + tmp12;
tmp2 = tmp11 - tmp12;
/* Odd part */
tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);
tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);
tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);
tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);
z13 = tmp6 + tmp5; /* phase 6 */
z10 = tmp6 - tmp5;
z11 = tmp4 + tmp7;
z12 = tmp4 - tmp7;
tmp7 = z11 + z13; /* phase 5 */
tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562); /* 2*c4 */
z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */
tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */
tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */
tmp6 = tmp12 - tmp7; /* phase 2 */
tmp5 = tmp11 - tmp6;
tmp4 = tmp10 + tmp5;
wsptr[DCTSIZE*0] = tmp0 + tmp7;
wsptr[DCTSIZE*7] = tmp0 - tmp7;
wsptr[DCTSIZE*1] = tmp1 + tmp6;
wsptr[DCTSIZE*6] = tmp1 - tmp6;
wsptr[DCTSIZE*2] = tmp2 + tmp5;
wsptr[DCTSIZE*5] = tmp2 - tmp5;
wsptr[DCTSIZE*4] = tmp3 + tmp4;
wsptr[DCTSIZE*3] = tmp3 - tmp4;
}
barrier(CLK_LOCAL_MEM_FENCE);
/* Pass 2: process rows from work array, store into output array. */
/* Note that we must descale the results by a factor of 8 == 2**3. */
wsptr = workspace;
wsptr += DCTSIZE * ctr;
{
outptr = output_buf + ctr * compptr->row_buffer_size + output_col;
/* Rows of zeroes can be exploited in the same way as we did with columns.
* However, the column calculation has created many nonzero AC terms, so
* the simplification applies less often (typically 5% to 10% of the time).
* And testing floats for zero is relatively expensive, so we don't bother.
*/
/* Even part */
tmp10 = wsptr[0] + wsptr[4];
tmp11 = wsptr[0] - wsptr[4];
tmp13 = wsptr[2] + wsptr[6];
tmp12 = (wsptr[2] - wsptr[6]) * ((FAST_FLOAT) 1.414213562) - tmp13;
tmp0 = tmp10 + tmp13;
tmp3 = tmp10 - tmp13;
tmp1 = tmp11 + tmp12;
tmp2 = tmp11 - tmp12;
/* Odd part */
z13 = wsptr[5] + wsptr[3];
z10 = wsptr[5] - wsptr[3];
z11 = wsptr[1] + wsptr[7];
z12 = wsptr[1] - wsptr[7];
tmp7 = z11 + z13;
tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562);
z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */
tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */
tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */
tmp6 = tmp12 - tmp7;
tmp5 = tmp11 - tmp6;
tmp4 = tmp10 + tmp5;
/* Final output stage: scale down by a factor of 8 and range-limit */
outptr[0] = range_limit[(int) DESCALE((INT32) (tmp0 + tmp7), 3)
& RANGE_MASK];
outptr[7] = range_limit[(int) DESCALE((INT32) (tmp0 - tmp7), 3)
& RANGE_MASK];
outptr[1] = range_limit[(int) DESCALE((INT32) (tmp1 + tmp6), 3)
& RANGE_MASK];
outptr[6] = range_limit[(int) DESCALE((INT32) (tmp1 - tmp6), 3)
& RANGE_MASK];
outptr[2] = range_limit[(int) DESCALE((INT32) (tmp2 + tmp5), 3)
& RANGE_MASK];
outptr[5] = range_limit[(int) DESCALE((INT32) (tmp2 - tmp5), 3)
& RANGE_MASK];
outptr[4] = range_limit[(int) DESCALE((INT32) (tmp3 + tmp4), 3)
& RANGE_MASK];
outptr[3] = range_limit[(int) DESCALE((INT32) (tmp3 - tmp4), 3)
& RANGE_MASK];
}
}
__kernel void idct(__global struct DecodeInfo * cinfo,
__global JBLOCK * decoded_mcu_base,
__global JSAMPLE * output)
{
__global struct ComponentInfo * compptr;
JDIMENSION MCU_col_num; /* index of current MCU within row */
int ci, xindex, yindex, yoffset,yheightoffset, useful_width;
int last_MCU_col;
JDIMENSION start_col, output_col;
__global JSAMPLE *cur_row;
__global JBLOCK * sCurrentBlock;
int MCUs_per_row;
yheightoffset = get_global_id(0);
MCU_col_num = get_global_id(1);
ci = get_group_id(2);
MCUs_per_row = get_global_size(1);
last_MCU_col = MCUs_per_row - 1;
cur_row = output;
compptr = &cinfo->component_infos[ci];
cur_row += compptr->previous_image_size;
cur_row += yheightoffset * compptr->DCT_scaled_size * compptr->row_buffer_size * compptr->MCU_height ;
start_col = MCU_col_num * compptr->MCU_sample_width;
useful_width = (MCU_col_num < last_MCU_col) ? compptr->MCU_width
: compptr->last_col_width;
sCurrentBlock = decoded_mcu_base + (( yheightoffset * MCUs_per_row + MCU_col_num) * cinfo->componets_mcu_width) ;
sCurrentBlock += compptr->previous_decoded_mcu_size;
for (yindex = 0; yindex < compptr->MCU_height; yindex++) {
output_col = start_col;
for (xindex = 0; xindex < useful_width; xindex++) {
inverse_DCT (cinfo, compptr,
(__global JCOEF * ) (sCurrentBlock + xindex),
cur_row, output_col);
output_col += compptr->DCT_scaled_size;
}
sCurrentBlock += compptr->MCU_width;
cur_row += compptr->DCT_scaled_size * compptr->row_buffer_size ;
}
}