File: jcdctmgr.c

package info (click to toggle)
libjpeg-mmx 0.1.3-3
  • links: PTS
  • area: main
  • in suites: woody
  • size: 2,700 kB
  • ctags: 2,672
  • sloc: ansic: 24,900; sh: 4,565; makefile: 59
file content (387 lines) | stat: -rw-r--r-- 12,469 bytes parent folder | download | duplicates (152)
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
/*
 * jcdctmgr.c
 *
 * Copyright (C) 1994-1996, Thomas G. Lane.
 * This file is part of the Independent JPEG Group's software.
 * For conditions of distribution and use, see the accompanying README file.
 *
 * This file contains the forward-DCT management logic.
 * This code selects a particular DCT implementation to be used,
 * and it performs related housekeeping chores including coefficient
 * quantization.
 */

#define JPEG_INTERNALS
#include "jinclude.h"
#include "jpeglib.h"
#include "jdct.h"		/* Private declarations for DCT subsystem */


/* Private subobject for this module */

typedef struct {
  struct jpeg_forward_dct pub;	/* public fields */

  /* Pointer to the DCT routine actually in use */
  forward_DCT_method_ptr do_dct;

  /* The actual post-DCT divisors --- not identical to the quant table
   * entries, because of scaling (especially for an unnormalized DCT).
   * Each table is given in normal array order.
   */
  DCTELEM * divisors[NUM_QUANT_TBLS];

#ifdef DCT_FLOAT_SUPPORTED
  /* Same as above for the floating-point case. */
  float_DCT_method_ptr do_float_dct;
  FAST_FLOAT * float_divisors[NUM_QUANT_TBLS];
#endif
} my_fdct_controller;

typedef my_fdct_controller * my_fdct_ptr;


/*
 * Initialize for a processing pass.
 * Verify that all referenced Q-tables are present, and set up
 * the divisor table for each one.
 * In the current implementation, DCT of all components is done during
 * the first pass, even if only some components will be output in the
 * first scan.  Hence all components should be examined here.
 */

METHODDEF(void)
start_pass_fdctmgr (j_compress_ptr cinfo)
{
  my_fdct_ptr fdct = (my_fdct_ptr) cinfo->fdct;
  int ci, qtblno, i;
  jpeg_component_info *compptr;
  JQUANT_TBL * qtbl;
  DCTELEM * dtbl;

  for (ci = 0, compptr = cinfo->comp_info; ci < cinfo->num_components;
       ci++, compptr++) {
    qtblno = compptr->quant_tbl_no;
    /* Make sure specified quantization table is present */
    if (qtblno < 0 || qtblno >= NUM_QUANT_TBLS ||
	cinfo->quant_tbl_ptrs[qtblno] == NULL)
      ERREXIT1(cinfo, JERR_NO_QUANT_TABLE, qtblno);
    qtbl = cinfo->quant_tbl_ptrs[qtblno];
    /* Compute divisors for this quant table */
    /* We may do this more than once for same table, but it's not a big deal */
    switch (cinfo->dct_method) {
#ifdef DCT_ISLOW_SUPPORTED
    case JDCT_ISLOW:
      /* For LL&M IDCT method, divisors are equal to raw quantization
       * coefficients multiplied by 8 (to counteract scaling).
       */
      if (fdct->divisors[qtblno] == NULL) {
	fdct->divisors[qtblno] = (DCTELEM *)
	  (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
				      DCTSIZE2 * SIZEOF(DCTELEM));
      }
      dtbl = fdct->divisors[qtblno];
      for (i = 0; i < DCTSIZE2; i++) {
	dtbl[i] = ((DCTELEM) qtbl->quantval[i]) << 3;
      }
      break;
#endif
#ifdef DCT_IFAST_SUPPORTED
    case JDCT_IFAST:
      {
	/* For AA&N IDCT method, divisors are equal to quantization
	 * coefficients scaled by scalefactor[row]*scalefactor[col], where
	 *   scalefactor[0] = 1
	 *   scalefactor[k] = cos(k*PI/16) * sqrt(2)    for k=1..7
	 * We apply a further scale factor of 8.
	 */
#define CONST_BITS 14
	static const INT16 aanscales[DCTSIZE2] = {
	  /* precomputed values scaled up by 14 bits */
	  16384, 22725, 21407, 19266, 16384, 12873,  8867,  4520,
	  22725, 31521, 29692, 26722, 22725, 17855, 12299,  6270,
	  21407, 29692, 27969, 25172, 21407, 16819, 11585,  5906,
	  19266, 26722, 25172, 22654, 19266, 15137, 10426,  5315,
	  16384, 22725, 21407, 19266, 16384, 12873,  8867,  4520,
	  12873, 17855, 16819, 15137, 12873, 10114,  6967,  3552,
	   8867, 12299, 11585, 10426,  8867,  6967,  4799,  2446,
	   4520,  6270,  5906,  5315,  4520,  3552,  2446,  1247
	};
	SHIFT_TEMPS

	if (fdct->divisors[qtblno] == NULL) {
	  fdct->divisors[qtblno] = (DCTELEM *)
	    (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
					DCTSIZE2 * SIZEOF(DCTELEM));
	}
	dtbl = fdct->divisors[qtblno];
	for (i = 0; i < DCTSIZE2; i++) {
	  dtbl[i] = (DCTELEM)
	    DESCALE(MULTIPLY16V16((INT32) qtbl->quantval[i],
				  (INT32) aanscales[i]),
		    CONST_BITS-3);
	}
      }
      break;
#endif
#ifdef DCT_FLOAT_SUPPORTED
    case JDCT_FLOAT:
      {
	/* For float AA&N IDCT method, divisors are equal to quantization
	 * coefficients scaled by scalefactor[row]*scalefactor[col], where
	 *   scalefactor[0] = 1
	 *   scalefactor[k] = cos(k*PI/16) * sqrt(2)    for k=1..7
	 * We apply a further scale factor of 8.
	 * What's actually stored is 1/divisor so that the inner loop can
	 * use a multiplication rather than a division.
	 */
	FAST_FLOAT * fdtbl;
	int row, col;
	static const double aanscalefactor[DCTSIZE] = {
	  1.0, 1.387039845, 1.306562965, 1.175875602,
	  1.0, 0.785694958, 0.541196100, 0.275899379
	};

	if (fdct->float_divisors[qtblno] == NULL) {
	  fdct->float_divisors[qtblno] = (FAST_FLOAT *)
	    (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
					DCTSIZE2 * SIZEOF(FAST_FLOAT));
	}
	fdtbl = fdct->float_divisors[qtblno];
	i = 0;
	for (row = 0; row < DCTSIZE; row++) {
	  for (col = 0; col < DCTSIZE; col++) {
	    fdtbl[i] = (FAST_FLOAT)
	      (1.0 / (((double) qtbl->quantval[i] *
		       aanscalefactor[row] * aanscalefactor[col] * 8.0)));
	    i++;
	  }
	}
      }
      break;
#endif
    default:
      ERREXIT(cinfo, JERR_NOT_COMPILED);
      break;
    }
  }
}


/*
 * Perform forward DCT on one or more blocks of a component.
 *
 * The input samples are taken from the sample_data[] array starting at
 * position start_row/start_col, and moving to the right for any additional
 * blocks. The quantized coefficients are returned in coef_blocks[].
 */

METHODDEF(void)
forward_DCT (j_compress_ptr cinfo, jpeg_component_info * compptr,
	     JSAMPARRAY sample_data, JBLOCKROW coef_blocks,
	     JDIMENSION start_row, JDIMENSION start_col,
	     JDIMENSION num_blocks)
/* This version is used for integer DCT implementations. */
{
  /* This routine is heavily used, so it's worth coding it tightly. */
  my_fdct_ptr fdct = (my_fdct_ptr) cinfo->fdct;
  forward_DCT_method_ptr do_dct = fdct->do_dct;
  DCTELEM * divisors = fdct->divisors[compptr->quant_tbl_no];
  DCTELEM workspace[DCTSIZE2];	/* work area for FDCT subroutine */
  JDIMENSION bi;

  sample_data += start_row;	/* fold in the vertical offset once */

  for (bi = 0; bi < num_blocks; bi++, start_col += DCTSIZE) {
    /* Load data into workspace, applying unsigned->signed conversion */
    { register DCTELEM *workspaceptr;
      register JSAMPROW elemptr;
      register int elemr;

      workspaceptr = workspace;
      for (elemr = 0; elemr < DCTSIZE; elemr++) {
	elemptr = sample_data[elemr] + start_col;
#if DCTSIZE == 8		/* unroll the inner loop */
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	*workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
#else
	{ register int elemc;
	  for (elemc = DCTSIZE; elemc > 0; elemc--) {
	    *workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;
	  }
	}
#endif
      }
    }

    /* Perform the DCT */
    (*do_dct) (workspace);

    /* Quantize/descale the coefficients, and store into coef_blocks[] */
    { register DCTELEM temp, qval;
      register int i;
      register JCOEFPTR output_ptr = coef_blocks[bi];

      for (i = 0; i < DCTSIZE2; i++) {
	qval = divisors[i];
	temp = workspace[i];
	/* Divide the coefficient value by qval, ensuring proper rounding.
	 * Since C does not specify the direction of rounding for negative
	 * quotients, we have to force the dividend positive for portability.
	 *
	 * In most files, at least half of the output values will be zero
	 * (at default quantization settings, more like three-quarters...)
	 * so we should ensure that this case is fast.  On many machines,
	 * a comparison is enough cheaper than a divide to make a special test
	 * a win.  Since both inputs will be nonnegative, we need only test
	 * for a < b to discover whether a/b is 0.
	 * If your machine's division is fast enough, define FAST_DIVIDE.
	 */
#ifdef FAST_DIVIDE
#define DIVIDE_BY(a,b)	a /= b
#else
#define DIVIDE_BY(a,b)	if (a >= b) a /= b; else a = 0
#endif
	if (temp < 0) {
	  temp = -temp;
	  temp += qval>>1;	/* for rounding */
	  DIVIDE_BY(temp, qval);
	  temp = -temp;
	} else {
	  temp += qval>>1;	/* for rounding */
	  DIVIDE_BY(temp, qval);
	}
	output_ptr[i] = (JCOEF) temp;
      }
    }
  }
}


#ifdef DCT_FLOAT_SUPPORTED

METHODDEF(void)
forward_DCT_float (j_compress_ptr cinfo, jpeg_component_info * compptr,
		   JSAMPARRAY sample_data, JBLOCKROW coef_blocks,
		   JDIMENSION start_row, JDIMENSION start_col,
		   JDIMENSION num_blocks)
/* This version is used for floating-point DCT implementations. */
{
  /* This routine is heavily used, so it's worth coding it tightly. */
  my_fdct_ptr fdct = (my_fdct_ptr) cinfo->fdct;
  float_DCT_method_ptr do_dct = fdct->do_float_dct;
  FAST_FLOAT * divisors = fdct->float_divisors[compptr->quant_tbl_no];
  FAST_FLOAT workspace[DCTSIZE2]; /* work area for FDCT subroutine */
  JDIMENSION bi;

  sample_data += start_row;	/* fold in the vertical offset once */

  for (bi = 0; bi < num_blocks; bi++, start_col += DCTSIZE) {
    /* Load data into workspace, applying unsigned->signed conversion */
    { register FAST_FLOAT *workspaceptr;
      register JSAMPROW elemptr;
      register int elemr;

      workspaceptr = workspace;
      for (elemr = 0; elemr < DCTSIZE; elemr++) {
	elemptr = sample_data[elemr] + start_col;
#if DCTSIZE == 8		/* unroll the inner loop */
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	*workspaceptr++ = (FAST_FLOAT)(GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
#else
	{ register int elemc;
	  for (elemc = DCTSIZE; elemc > 0; elemc--) {
	    *workspaceptr++ = (FAST_FLOAT)
	      (GETJSAMPLE(*elemptr++) - CENTERJSAMPLE);
	  }
	}
#endif
      }
    }

    /* Perform the DCT */
    (*do_dct) (workspace);

    /* Quantize/descale the coefficients, and store into coef_blocks[] */
    { register FAST_FLOAT temp;
      register int i;
      register JCOEFPTR output_ptr = coef_blocks[bi];

      for (i = 0; i < DCTSIZE2; i++) {
	/* Apply the quantization and scaling factor */
	temp = workspace[i] * divisors[i];
	/* Round to nearest integer.
	 * Since C does not specify the direction of rounding for negative
	 * quotients, we have to force the dividend positive for portability.
	 * The maximum coefficient size is +-16K (for 12-bit data), so this
	 * code should work for either 16-bit or 32-bit ints.
	 */
	output_ptr[i] = (JCOEF) ((int) (temp + (FAST_FLOAT) 16384.5) - 16384);
      }
    }
  }
}

#endif /* DCT_FLOAT_SUPPORTED */


/*
 * Initialize FDCT manager.
 */

GLOBAL(void)
jinit_forward_dct (j_compress_ptr cinfo)
{
  my_fdct_ptr fdct;
  int i;

  fdct = (my_fdct_ptr)
    (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
				SIZEOF(my_fdct_controller));
  cinfo->fdct = (struct jpeg_forward_dct *) fdct;
  fdct->pub.start_pass = start_pass_fdctmgr;

  switch (cinfo->dct_method) {
#ifdef DCT_ISLOW_SUPPORTED
  case JDCT_ISLOW:
    fdct->pub.forward_DCT = forward_DCT;
    fdct->do_dct = jpeg_fdct_islow;
    break;
#endif
#ifdef DCT_IFAST_SUPPORTED
  case JDCT_IFAST:
    fdct->pub.forward_DCT = forward_DCT;
    fdct->do_dct = jpeg_fdct_ifast;
    break;
#endif
#ifdef DCT_FLOAT_SUPPORTED
  case JDCT_FLOAT:
    fdct->pub.forward_DCT = forward_DCT_float;
    fdct->do_float_dct = jpeg_fdct_float;
    break;
#endif
  default:
    ERREXIT(cinfo, JERR_NOT_COMPILED);
    break;
  }

  /* Mark divisor tables unallocated */
  for (i = 0; i < NUM_QUANT_TBLS; i++) {
    fdct->divisors[i] = NULL;
#ifdef DCT_FLOAT_SUPPORTED
    fdct->float_divisors[i] = NULL;
#endif
  }
}