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
|
/***************************************************************************
* __________ __ ___.
* Open \______ \ ____ ____ | | _\_ |__ _______ ___
* Source | _// _ \_/ ___\| |/ /| __ \ / _ \ \/ /
* Jukebox | | ( <_> ) \___| < | \_\ ( <_> > < <
* Firmware |____|_ /\____/ \___ >__|_ \|___ /\____/__/\_ \
* \/ \/ \/ \/ \/
* $Id$
*
* Code for the scaling algorithm:
* Imlib2 is (C) Carsten Haitzler and various contributors. The MMX code
* is by Willem Monsuwe <willem@stack.nl>. Additional modifications are by
* (C) Daniel M. Duley.
*
* Port to Rockbox
* Copyright (C) 2007 Jonas Hurrelmann (j@outpo.st)
*
* 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.
*
****************************************************************************/
/*
* Copyright (C) 2004, 2005 Daniel M. Duley
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
*/
/* OTHER CREDITS:
*
* This is the normal smoothscale method, based on Imlib2's smoothscale.
*
* Originally I took the algorithm used in NetPBM and Qt and added MMX/3dnow
* optimizations. It ran in about 1/2 the time as Qt. Then I ported Imlib's
* C algorithm and it ran at about the same speed as my MMX optimized one...
* Finally I ported Imlib's MMX version and it ran in less than half the
* time as my MMX algorithm, (taking only a quarter of the time Qt does).
* After further optimization it seems to run at around 1/6th.
*
* Changes include formatting, namespaces and other C++'ings, removal of old
* #ifdef'ed code, and removal of unneeded border calculation code.
*
* Imlib2 is (C) Carsten Haitzler and various contributors. The MMX code
* is by Willem Monsuwe <willem@stack.nl>. All other modifications are
* (C) Daniel M. Duley.
*/
#include "pluginlib_bmp.h"
#include "lcd.h"
void smooth_resize_bitmap(struct bitmap *src_bmp, struct bitmap *dest_bmp)
{
fb_data *sptr, *dptr;
int x, y, end;
int val_y = 0, val_x;
const int sw = src_bmp->width;
const int sh = src_bmp->height;
const int dw = dest_bmp->width;
const int dh = dest_bmp->height;
const int inc_x = (sw << 16) / dw;
const int inc_y = (sh << 16) / dh;
const int Cp_x = ((dw << 14) / sw) + 1;
const int Cp_y = ((dh << 14) / sh) + 1;
const int xup_yup = (dw >= sw) + ((dh >= sh) << 1);
const int dow = dw;
const int sow = sw;
fb_data *src = (fb_data*)src_bmp->data;
fb_data *dest = (fb_data*)dest_bmp->data;
int XAP, YAP, INV_YAP, INV_XAP;
int xpoint;
fb_data *ypoint;
end = dw;
/* scaling up both ways */
if (xup_yup == 3) {
/* go through every scanline in the output buffer */
for (y = 0; y < dh; y++) {
/* calculate the source line we'll scan from */
ypoint = src + ((val_y >> 16) * sw);
YAP = ((val_y >> 16) >= (sh - 1)) ? 0 : (val_y >> 8) - ((val_y >> 8) & 0xffffff00);
INV_YAP = 256 - YAP;
val_y += inc_y;
val_x = 0;
dptr = dest + (y * dow);
sptr = ypoint;
if (YAP > 0) {
for (x = 0; x < end; x++) {
int r = 0, g = 0, b = 0;
int rr = 0, gg = 0, bb = 0;
fb_data *pix;
xpoint = (val_x >> 16);
XAP = ((val_x >> 16) >= (sw - 1)) ? 0 : (val_x >> 8) - ((val_x >> 8) & 0xffffff00);
INV_XAP = 256 - XAP;
val_x += inc_x;
if (XAP > 0) {
pix = ypoint + xpoint;
r = RGB_UNPACK_RED(*pix) * INV_XAP;
g = RGB_UNPACK_GREEN(*pix) * INV_XAP;
b = RGB_UNPACK_BLUE(*pix) * INV_XAP;
pix++;
r += RGB_UNPACK_RED(*pix) * XAP;
g += RGB_UNPACK_GREEN(*pix) * XAP;
b += RGB_UNPACK_BLUE(*pix) * XAP;
pix += sow;
rr = RGB_UNPACK_RED(*pix) * XAP;
gg = RGB_UNPACK_GREEN(*pix) * XAP;
bb = RGB_UNPACK_BLUE(*pix) * XAP;
pix--;
rr += RGB_UNPACK_RED(*pix) * INV_XAP;
gg += RGB_UNPACK_GREEN(*pix) * INV_XAP;
bb += RGB_UNPACK_BLUE(*pix) * INV_XAP;
r = ((rr * YAP) + (r * INV_YAP)) >> 16;
g = ((gg * YAP) + (g * INV_YAP)) >> 16;
b = ((bb * YAP) + (b * INV_YAP)) >> 16;
*dptr++ = LCD_RGBPACK(r, g, b);
} else {
pix = ypoint + xpoint;
r = RGB_UNPACK_RED(*pix) * INV_YAP;
g = RGB_UNPACK_GREEN(*pix) * INV_YAP;
b = RGB_UNPACK_BLUE(*pix) * INV_YAP;
pix += sow;
r += RGB_UNPACK_RED(*pix) * YAP;
g += RGB_UNPACK_GREEN(*pix) * YAP;
b += RGB_UNPACK_BLUE(*pix) * YAP;
r >>= 8;
g >>= 8;
b >>= 8;
*dptr++ = LCD_RGBPACK(r, g, b);
}
}
} else {
for (x = 0; x < end; x++) {
int r = 0, g = 0, b = 0;
fb_data *pix;
xpoint = (val_x >> 16);
XAP = ((val_x >> 16) >= (sw - 1)) ? 0 : (val_x >> 8) - ((val_x >> 8) & 0xffffff00);
INV_XAP = 256 - XAP;
val_x += inc_x;
if (XAP > 0) {
pix = ypoint + xpoint;
r = RGB_UNPACK_RED(*pix) * INV_XAP;
g = RGB_UNPACK_GREEN(*pix) * INV_XAP;
b = RGB_UNPACK_BLUE(*pix) * INV_XAP;
pix++;
r += RGB_UNPACK_RED(*pix) * XAP;
g += RGB_UNPACK_GREEN(*pix) * XAP;
b += RGB_UNPACK_BLUE(*pix) * XAP;
r >>= 8;
g >>= 8;
b >>= 8;
*dptr++ = LCD_RGBPACK(r, g, b);
} else
*dptr++ = sptr[xpoint];
}
}
}
}
/* if we're scaling down vertically */
else if (xup_yup == 1) {
/*\ 'Correct' version, with math units prepared for MMXification \ */
int Cy, j;
fb_data *pix;
int r, g, b, rr, gg, bb;
int yap;
/* go through every scanline in the output buffer */
for (y = 0; y < dh; y++) {
ypoint = src + ((val_y >> 16) * sw);
YAP = (((0x100 - ((val_y >> 8) & 0xff)) * Cp_y) >> 8) | (Cp_y << 16);
INV_YAP = 256 - YAP;
val_y += inc_y;
val_x = 0;
Cy = YAP >> 16;
yap = YAP & 0xffff;
dptr = dest + (y * dow);
for (x = 0; x < end; x++) {
xpoint = (val_x >> 16);
XAP = ((val_x >> 16) >= (sw - 1)) ? 0 : (val_x >> 8) - ((val_x >> 8) & 0xffffff00);
INV_XAP = 256 - XAP;
val_x += inc_x;
pix = ypoint + xpoint;
r = (RGB_UNPACK_RED(*pix) * yap) >> 10;
g = (RGB_UNPACK_GREEN(*pix) * yap) >> 10;
b = (RGB_UNPACK_BLUE(*pix) * yap) >> 10;
pix += sow;
for (j = (1 << 14) - yap; j > Cy; j -= Cy) {
r += (RGB_UNPACK_RED(*pix) * Cy) >> 10;
g += (RGB_UNPACK_GREEN(*pix) * Cy) >> 10;
b += (RGB_UNPACK_BLUE(*pix) * Cy) >> 10;
pix += sow;
}
if (j > 0) {
r += (RGB_UNPACK_RED(*pix) * j) >> 10;
g += (RGB_UNPACK_GREEN(*pix) * j) >> 10;
b += (RGB_UNPACK_BLUE(*pix) * j) >> 10;
}
if (XAP > 0) {
pix = ypoint + xpoint + 1;
rr = (RGB_UNPACK_RED(*pix) * yap) >> 10;
gg = (RGB_UNPACK_GREEN(*pix) * yap) >> 10;
bb = (RGB_UNPACK_BLUE(*pix) * yap) >> 10;
pix += sow;
for (j = (1 << 14) - yap; j > Cy; j -= Cy) {
rr += (RGB_UNPACK_RED(*pix) * Cy) >> 10;
gg += (RGB_UNPACK_GREEN(*pix) * Cy) >> 10;
bb += (RGB_UNPACK_BLUE(*pix) * Cy) >> 10;
pix += sow;
}
if (j > 0) {
rr += (RGB_UNPACK_RED(*pix) * j) >> 10;
gg += (RGB_UNPACK_GREEN(*pix) * j) >> 10;
bb += (RGB_UNPACK_BLUE(*pix) * j) >> 10;
}
r = r * INV_XAP;
g = g * INV_XAP;
b = b * INV_XAP;
r = (r + ((rr * XAP))) >> 12;
g = (g + ((gg * XAP))) >> 12;
b = (b + ((bb * XAP))) >> 12;
} else {
r >>= 4;
g >>= 4;
b >>= 4;
}
*dptr = LCD_RGBPACK(r, g, b);
dptr++;
}
}
}
/* if we're scaling down horizontally */
else if (xup_yup == 2) {
/*\ 'Correct' version, with math units prepared for MMXification \ */
int Cx, j;
fb_data *pix;
int r, g, b, rr, gg, bb;
int xap;
/* go through every scanline in the output buffer */
for (y = 0; y < dh; y++) {
ypoint = src + ((val_y >> 16) * sw);
YAP = ((val_y >> 16) >= (sh - 1)) ? 0 : (val_y >> 8) - ((val_y >> 8) & 0xffffff00);
INV_YAP = 256 - YAP;
val_y += inc_y;
val_x = 0;
dptr = dest + (y * dow);
for (x = 0; x < end; x++) {
xpoint = (val_x >> 16);
XAP = (((0x100 - ((val_x >> 8) & 0xff)) * Cp_x) >> 8) | (Cp_x << 16);
INV_XAP = 256 - XAP;
val_x += inc_x;
Cx = XAP >> 16;
xap = XAP & 0xffff;
pix = ypoint + xpoint;
r = (RGB_UNPACK_RED(*pix) * xap) >> 10;
g = (RGB_UNPACK_GREEN(*pix) * xap) >> 10;
b = (RGB_UNPACK_BLUE(*pix) * xap) >> 10;
pix++;
for (j = (1 << 14) - xap; j > Cx; j -= Cx) {
r += (RGB_UNPACK_RED(*pix) * Cx) >> 10;
g += (RGB_UNPACK_GREEN(*pix) * Cx) >> 10;
b += (RGB_UNPACK_BLUE(*pix) * Cx) >> 10;
pix++;
}
if (j > 0) {
r += (RGB_UNPACK_RED(*pix) * j) >> 10;
g += (RGB_UNPACK_GREEN(*pix) * j) >> 10;
b += (RGB_UNPACK_BLUE(*pix) * j) >> 10;
}
if (YAP > 0) {
pix = ypoint + xpoint + sow;
rr = (RGB_UNPACK_RED(*pix) * xap) >> 10;
gg = (RGB_UNPACK_GREEN(*pix) * xap) >> 10;
bb = (RGB_UNPACK_BLUE(*pix) * xap) >> 10;
pix++;
for (j = (1 << 14) - xap; j > Cx; j -= Cx) {
rr += (RGB_UNPACK_RED(*pix) * Cx) >> 10;
gg += (RGB_UNPACK_GREEN(*pix) * Cx) >> 10;
bb += (RGB_UNPACK_BLUE(*pix) * Cx) >> 10;
pix++;
}
if (j > 0) {
rr += (RGB_UNPACK_RED(*pix) * j) >> 10;
gg += (RGB_UNPACK_GREEN(*pix) * j) >> 10;
bb += (RGB_UNPACK_BLUE(*pix) * j) >> 10;
}
r = r * INV_YAP;
g = g * INV_YAP;
b = b * INV_YAP;
r = (r + ((rr * YAP))) >> 12;
g = (g + ((gg * YAP))) >> 12;
b = (b + ((bb * YAP))) >> 12;
} else {
r >>= 4;
g >>= 4;
b >>= 4;
}
*dptr = LCD_RGBPACK(r, g, b);
dptr++;
}
}
}
/* fully optimized (i think) - only change of algorithm can help */
/* if we're scaling down horizontally & vertically */
else {
/*\ 'Correct' version, with math units prepared for MMXification \ */
int Cx, Cy, i, j;
fb_data *pix;
int r, g, b, rx, gx, bx;
int xap, yap;
for (y = 0; y < dh; y++) {
ypoint = src + ((val_y >> 16) * sw);
YAP = (((0x100 - ((val_y >> 8) & 0xff)) * Cp_y) >> 8) | (Cp_y << 16);
INV_YAP = 256 - YAP;
val_y += inc_y;
val_x = 0;
Cy = YAP >> 16;
yap = YAP & 0xffff;
dptr = dest + (y * dow);
for (x = 0; x < end; x++) {
xpoint = (val_x >> 16);
XAP = (((0x100 - ((val_x >> 8) & 0xff)) * Cp_x) >> 8) | (Cp_x << 16);
INV_XAP = 256 - XAP;
val_x += inc_x;
Cx = XAP >> 16;
xap = XAP & 0xffff;
sptr = ypoint + xpoint;
pix = sptr;
sptr += sow;
rx = (RGB_UNPACK_RED(*pix) * xap) >> 9;
gx = (RGB_UNPACK_GREEN(*pix) * xap) >> 9;
bx = (RGB_UNPACK_BLUE(*pix) * xap) >> 9;
pix++;
for (i = (1 << 14) - xap; i > Cx; i -= Cx) {
rx += (RGB_UNPACK_RED(*pix) * Cx) >> 9;
gx += (RGB_UNPACK_GREEN(*pix) * Cx) >> 9;
bx += (RGB_UNPACK_BLUE(*pix) * Cx) >> 9;
pix++;
}
if (i > 0) {
rx += (RGB_UNPACK_RED(*pix) * i) >> 9;
gx += (RGB_UNPACK_GREEN(*pix) * i) >> 9;
bx += (RGB_UNPACK_BLUE(*pix) * i) >> 9;
}
r = (rx * yap) >> 14;
g = (gx * yap) >> 14;
b = (bx * yap) >> 14;
for (j = (1 << 14) - yap; j > Cy; j -= Cy) {
pix = sptr;
sptr += sow;
rx = (RGB_UNPACK_RED(*pix) * xap) >> 9;
gx = (RGB_UNPACK_GREEN(*pix) * xap) >> 9;
bx = (RGB_UNPACK_BLUE(*pix) * xap) >> 9;
pix++;
for (i = (1 << 14) - xap; i > Cx; i -= Cx) {
rx += (RGB_UNPACK_RED(*pix) * Cx) >> 9;
gx += (RGB_UNPACK_GREEN(*pix) * Cx) >> 9;
bx += (RGB_UNPACK_BLUE(*pix) * Cx) >> 9;
pix++;
}
if (i > 0) {
rx += (RGB_UNPACK_RED(*pix) * i) >> 9;
gx += (RGB_UNPACK_GREEN(*pix) * i) >> 9;
bx += (RGB_UNPACK_BLUE(*pix) * i) >> 9;
}
r += (rx * Cy) >> 14;
g += (gx * Cy) >> 14;
b += (bx * Cy) >> 14;
}
if (j > 0) {
pix = sptr;
sptr += sow;
rx = (RGB_UNPACK_RED(*pix) * xap) >> 9;
gx = (RGB_UNPACK_GREEN(*pix) * xap) >> 9;
bx = (RGB_UNPACK_BLUE(*pix) * xap) >> 9;
pix++;
for (i = (1 << 14) - xap; i > Cx; i -= Cx) {
rx += (RGB_UNPACK_RED(*pix) * Cx) >> 9;
gx += (RGB_UNPACK_GREEN(*pix) * Cx) >> 9;
bx += (RGB_UNPACK_BLUE(*pix) * Cx) >> 9;
pix++;
}
if (i > 0) {
rx += (RGB_UNPACK_RED(*pix) * i) >> 9;
gx += (RGB_UNPACK_GREEN(*pix) * i) >> 9;
bx += (RGB_UNPACK_BLUE(*pix) * i) >> 9;
}
r += (rx * j) >> 14;
g += (gx * j) >> 14;
b += (bx * j) >> 14;
}
*dptr = LCD_RGBPACK(r >> 5, g >> 5, b >> 5);
dptr++;
}
}
}
}
|
