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
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
|
/* -*- Mode: c; c-basic-offset: 4; tab-width: 8; indent-tabs-mode: t; -*- */
/*
* Copyright © 2000 SuSE, Inc.
* Copyright © 2007 Red Hat, Inc.
*
* Permission to use, copy, modify, distribute, and sell this software and its
* documentation for any purpose is hereby granted without fee, provided that
* the above copyright notice appear in all copies and that both that
* copyright notice and this permission notice appear in supporting
* documentation, and that the name of SuSE not be used in advertising or
* publicity pertaining to distribution of the software without specific,
* written prior permission. SuSE makes no representations about the
* suitability of this software for any purpose. It is provided "as is"
* without express or implied warranty.
*
* SuSE DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL SuSE
* BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
* OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
* CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*
* Author: Keith Packard, SuSE, Inc.
*/
#ifndef PIXMAN_FAST_PATH_H__
#define PIXMAN_FAST_PATH_H__
#include "pixman-private.h"
#define PIXMAN_REPEAT_COVER -1
static force_inline pixman_bool_t
repeat (pixman_repeat_t repeat, int *c, int size)
{
if (repeat == PIXMAN_REPEAT_NONE)
{
if (*c < 0 || *c >= size)
return FALSE;
}
else if (repeat == PIXMAN_REPEAT_NORMAL)
{
while (*c >= size)
*c -= size;
while (*c < 0)
*c += size;
}
else if (repeat == PIXMAN_REPEAT_PAD)
{
*c = CLIP (*c, 0, size - 1);
}
else /* REFLECT */
{
*c = MOD (*c, size * 2);
if (*c >= size)
*c = size * 2 - *c - 1;
}
return TRUE;
}
/*
* For each scanline fetched from source image with PAD repeat:
* - calculate how many pixels need to be padded on the left side
* - calculate how many pixels need to be padded on the right side
* - update width to only count pixels which are fetched from the image
* All this information is returned via 'width', 'left_pad', 'right_pad'
* arguments. The code is assuming that 'unit_x' is positive.
*
* Note: 64-bit math is used in order to avoid potential overflows, which
* is probably excessive in many cases. This particular function
* may need its own correctness test and performance tuning.
*/
static force_inline void
pad_repeat_get_scanline_bounds (int32_t source_image_width,
pixman_fixed_t vx,
pixman_fixed_t unit_x,
int32_t * width,
int32_t * left_pad,
int32_t * right_pad)
{
int64_t max_vx = (int64_t) source_image_width << 16;
int64_t tmp;
if (vx < 0)
{
tmp = ((int64_t) unit_x - 1 - vx) / unit_x;
if (tmp > *width)
{
*left_pad = *width;
*width = 0;
}
else
{
*left_pad = (int32_t) tmp;
*width -= (int32_t) tmp;
}
}
else
{
*left_pad = 0;
}
tmp = ((int64_t) unit_x - 1 - vx + max_vx) / unit_x - *left_pad;
if (tmp < 0)
{
*right_pad = *width;
*width = 0;
}
else if (tmp >= *width)
{
*right_pad = 0;
}
else
{
*right_pad = *width - (int32_t) tmp;
*width = (int32_t) tmp;
}
}
/* A macroified version of specialized nearest scalers for some
* common 8888 and 565 formats. It supports SRC and OVER ops.
*
* There are two repeat versions, one that handles repeat normal,
* and one without repeat handling that only works if the src region
* used is completely covered by the pre-repeated source samples.
*
* The loops are unrolled to process two pixels per iteration for better
* performance on most CPU architectures (superscalar processors
* can issue several operations simultaneously, other processors can hide
* instructions latencies by pipelining operations). Unrolling more
* does not make much sense because the compiler will start running out
* of spare registers soon.
*/
#define GET_8888_ALPHA(s) ((s) >> 24)
/* This is not actually used since we don't have an OVER with
565 source, but it is needed to build. */
#define GET_0565_ALPHA(s) 0xff
#define FAST_NEAREST_SCANLINE(scanline_func_name, SRC_FORMAT, DST_FORMAT, \
src_type_t, dst_type_t, OP, repeat_mode) \
static force_inline void \
scanline_func_name (dst_type_t *dst, \
const src_type_t *src, \
int32_t w, \
pixman_fixed_t vx, \
pixman_fixed_t unit_x, \
pixman_fixed_t max_vx, \
pixman_bool_t fully_transparent_src) \
{ \
uint32_t d; \
src_type_t s1, s2; \
uint8_t a1, a2; \
int x1, x2; \
\
if (PIXMAN_OP_ ## OP == PIXMAN_OP_OVER && fully_transparent_src) \
return; \
\
if (PIXMAN_OP_ ## OP != PIXMAN_OP_SRC && PIXMAN_OP_ ## OP != PIXMAN_OP_OVER) \
abort(); \
\
while ((w -= 2) >= 0) \
{ \
x1 = vx >> 16; \
vx += unit_x; \
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NORMAL) \
{ \
/* This works because we know that unit_x is positive */ \
while (vx >= max_vx) \
vx -= max_vx; \
} \
s1 = src[x1]; \
\
x2 = vx >> 16; \
vx += unit_x; \
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NORMAL) \
{ \
/* This works because we know that unit_x is positive */ \
while (vx >= max_vx) \
vx -= max_vx; \
} \
s2 = src[x2]; \
\
if (PIXMAN_OP_ ## OP == PIXMAN_OP_OVER) \
{ \
a1 = GET_ ## SRC_FORMAT ## _ALPHA(s1); \
a2 = GET_ ## SRC_FORMAT ## _ALPHA(s2); \
\
if (a1 == 0xff) \
{ \
*dst = CONVERT_ ## SRC_FORMAT ## _TO_ ## DST_FORMAT (s1); \
} \
else if (s1) \
{ \
d = CONVERT_ ## DST_FORMAT ## _TO_8888 (*dst); \
s1 = CONVERT_ ## SRC_FORMAT ## _TO_8888 (s1); \
a1 ^= 0xff; \
UN8x4_MUL_UN8_ADD_UN8x4 (d, a1, s1); \
*dst = CONVERT_8888_TO_ ## DST_FORMAT (d); \
} \
dst++; \
\
if (a2 == 0xff) \
{ \
*dst = CONVERT_ ## SRC_FORMAT ## _TO_ ## DST_FORMAT (s2); \
} \
else if (s2) \
{ \
d = CONVERT_## DST_FORMAT ## _TO_8888 (*dst); \
s2 = CONVERT_## SRC_FORMAT ## _TO_8888 (s2); \
a2 ^= 0xff; \
UN8x4_MUL_UN8_ADD_UN8x4 (d, a2, s2); \
*dst = CONVERT_8888_TO_ ## DST_FORMAT (d); \
} \
dst++; \
} \
else /* PIXMAN_OP_SRC */ \
{ \
*dst++ = CONVERT_ ## SRC_FORMAT ## _TO_ ## DST_FORMAT (s1); \
*dst++ = CONVERT_ ## SRC_FORMAT ## _TO_ ## DST_FORMAT (s2); \
} \
} \
\
if (w & 1) \
{ \
x1 = vx >> 16; \
s1 = src[x1]; \
\
if (PIXMAN_OP_ ## OP == PIXMAN_OP_OVER) \
{ \
a1 = GET_ ## SRC_FORMAT ## _ALPHA(s1); \
\
if (a1 == 0xff) \
{ \
*dst = CONVERT_ ## SRC_FORMAT ## _TO_ ## DST_FORMAT (s1); \
} \
else if (s1) \
{ \
d = CONVERT_## DST_FORMAT ## _TO_8888 (*dst); \
s1 = CONVERT_ ## SRC_FORMAT ## _TO_8888 (s1); \
a1 ^= 0xff; \
UN8x4_MUL_UN8_ADD_UN8x4 (d, a1, s1); \
*dst = CONVERT_8888_TO_ ## DST_FORMAT (d); \
} \
dst++; \
} \
else /* PIXMAN_OP_SRC */ \
{ \
*dst++ = CONVERT_ ## SRC_FORMAT ## _TO_ ## DST_FORMAT (s1); \
} \
} \
}
#define FAST_NEAREST_MAINLOOP_INT(scale_func_name, scanline_func, src_type_t, mask_type_t, \
dst_type_t, repeat_mode, have_mask, mask_is_solid) \
static void \
fast_composite_scaled_nearest ## scale_func_name (pixman_implementation_t *imp, \
pixman_op_t op, \
pixman_image_t * src_image, \
pixman_image_t * mask_image, \
pixman_image_t * dst_image, \
int32_t src_x, \
int32_t src_y, \
int32_t mask_x, \
int32_t mask_y, \
int32_t dst_x, \
int32_t dst_y, \
int32_t width, \
int32_t height) \
{ \
dst_type_t *dst_line; \
mask_type_t *mask_line; \
src_type_t *src_first_line; \
int y; \
pixman_fixed_t max_vx = INT32_MAX; /* suppress uninitialized variable warning */ \
pixman_fixed_t max_vy; \
pixman_vector_t v; \
pixman_fixed_t vx, vy; \
pixman_fixed_t unit_x, unit_y; \
int32_t left_pad, right_pad; \
\
src_type_t *src; \
dst_type_t *dst; \
mask_type_t solid_mask; \
const mask_type_t *mask = &solid_mask; \
int src_stride, mask_stride, dst_stride; \
\
PIXMAN_IMAGE_GET_LINE (dst_image, dst_x, dst_y, dst_type_t, dst_stride, dst_line, 1); \
if (have_mask) \
{ \
if (mask_is_solid) \
solid_mask = _pixman_image_get_solid (imp, mask_image, dst_image->bits.format); \
else \
PIXMAN_IMAGE_GET_LINE (mask_image, mask_x, mask_y, mask_type_t, \
mask_stride, mask_line, 1); \
} \
/* pass in 0 instead of src_x and src_y because src_x and src_y need to be \
* transformed from destination space to source space */ \
PIXMAN_IMAGE_GET_LINE (src_image, 0, 0, src_type_t, src_stride, src_first_line, 1); \
\
/* reference point is the center of the pixel */ \
v.vector[0] = pixman_int_to_fixed (src_x) + pixman_fixed_1 / 2; \
v.vector[1] = pixman_int_to_fixed (src_y) + pixman_fixed_1 / 2; \
v.vector[2] = pixman_fixed_1; \
\
if (!pixman_transform_point_3d (src_image->common.transform, &v)) \
return; \
\
unit_x = src_image->common.transform->matrix[0][0]; \
unit_y = src_image->common.transform->matrix[1][1]; \
\
/* Round down to closest integer, ensuring that 0.5 rounds to 0, not 1 */ \
v.vector[0] -= pixman_fixed_e; \
v.vector[1] -= pixman_fixed_e; \
\
vx = v.vector[0]; \
vy = v.vector[1]; \
\
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NORMAL) \
{ \
/* Clamp repeating positions inside the actual samples */ \
max_vx = src_image->bits.width << 16; \
max_vy = src_image->bits.height << 16; \
\
repeat (PIXMAN_REPEAT_NORMAL, &vx, max_vx); \
repeat (PIXMAN_REPEAT_NORMAL, &vy, max_vy); \
} \
\
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_PAD || \
PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NONE) \
{ \
pad_repeat_get_scanline_bounds (src_image->bits.width, vx, unit_x, \
&width, &left_pad, &right_pad); \
vx += left_pad * unit_x; \
} \
\
while (--height >= 0) \
{ \
dst = dst_line; \
dst_line += dst_stride; \
if (have_mask && !mask_is_solid) \
{ \
mask = mask_line; \
mask_line += mask_stride; \
} \
\
y = vy >> 16; \
vy += unit_y; \
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NORMAL) \
repeat (PIXMAN_REPEAT_NORMAL, &vy, max_vy); \
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_PAD) \
{ \
repeat (PIXMAN_REPEAT_PAD, &y, src_image->bits.height); \
src = src_first_line + src_stride * y; \
if (left_pad > 0) \
{ \
scanline_func (mask, dst, src, left_pad, 0, 0, 0, FALSE); \
} \
if (width > 0) \
{ \
scanline_func (mask + (mask_is_solid ? 0 : left_pad), \
dst + left_pad, src, width, vx, unit_x, 0, FALSE); \
} \
if (right_pad > 0) \
{ \
scanline_func (mask + (mask_is_solid ? 0 : left_pad + width), \
dst + left_pad + width, src + src_image->bits.width - 1, \
right_pad, 0, 0, 0, FALSE); \
} \
} \
else if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NONE) \
{ \
static const src_type_t zero[1] = { 0 }; \
if (y < 0 || y >= src_image->bits.height) \
{ \
scanline_func (mask, dst, zero, left_pad + width + right_pad, 0, 0, 0, TRUE); \
continue; \
} \
src = src_first_line + src_stride * y; \
if (left_pad > 0) \
{ \
scanline_func (mask, dst, zero, left_pad, 0, 0, 0, TRUE); \
} \
if (width > 0) \
{ \
scanline_func (mask + (mask_is_solid ? 0 : left_pad), \
dst + left_pad, src, width, vx, unit_x, 0, FALSE); \
} \
if (right_pad > 0) \
{ \
scanline_func (mask + (mask_is_solid ? 0 : left_pad + width), \
dst + left_pad + width, zero, right_pad, 0, 0, 0, TRUE); \
} \
} \
else \
{ \
src = src_first_line + src_stride * y; \
scanline_func (mask, dst, src, width, vx, unit_x, max_vx, FALSE); \
} \
} \
}
/* A workaround for old sun studio, see: https://bugs.freedesktop.org/show_bug.cgi?id=32764 */
#define FAST_NEAREST_MAINLOOP_COMMON(scale_func_name, scanline_func, src_type_t, mask_type_t, \
dst_type_t, repeat_mode, have_mask, mask_is_solid) \
FAST_NEAREST_MAINLOOP_INT(_ ## scale_func_name, scanline_func, src_type_t, mask_type_t, \
dst_type_t, repeat_mode, have_mask, mask_is_solid)
#define FAST_NEAREST_MAINLOOP_NOMASK(scale_func_name, scanline_func, src_type_t, dst_type_t, \
repeat_mode) \
static force_inline void \
scanline_func##scale_func_name##_wrapper ( \
const uint8_t *mask, \
dst_type_t *dst, \
const src_type_t *src, \
int32_t w, \
pixman_fixed_t vx, \
pixman_fixed_t unit_x, \
pixman_fixed_t max_vx, \
pixman_bool_t fully_transparent_src) \
{ \
scanline_func (dst, src, w, vx, unit_x, max_vx, fully_transparent_src); \
} \
FAST_NEAREST_MAINLOOP_INT (scale_func_name, scanline_func##scale_func_name##_wrapper, \
src_type_t, uint8_t, dst_type_t, repeat_mode, FALSE, FALSE)
#define FAST_NEAREST_MAINLOOP(scale_func_name, scanline_func, src_type_t, dst_type_t, \
repeat_mode) \
FAST_NEAREST_MAINLOOP_NOMASK(_ ## scale_func_name, scanline_func, src_type_t, \
dst_type_t, repeat_mode)
#define FAST_NEAREST(scale_func_name, SRC_FORMAT, DST_FORMAT, \
src_type_t, dst_type_t, OP, repeat_mode) \
FAST_NEAREST_SCANLINE(scaled_nearest_scanline_ ## scale_func_name ## _ ## OP, \
SRC_FORMAT, DST_FORMAT, src_type_t, dst_type_t, \
OP, repeat_mode) \
FAST_NEAREST_MAINLOOP_NOMASK(_ ## scale_func_name ## _ ## OP, \
scaled_nearest_scanline_ ## scale_func_name ## _ ## OP, \
src_type_t, dst_type_t, repeat_mode)
#define SCALED_NEAREST_FLAGS \
(FAST_PATH_SCALE_TRANSFORM | \
FAST_PATH_NO_ALPHA_MAP | \
FAST_PATH_NEAREST_FILTER | \
FAST_PATH_NO_ACCESSORS | \
FAST_PATH_NARROW_FORMAT)
#define SIMPLE_NEAREST_FAST_PATH_NORMAL(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_NORMAL_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _normal ## _ ## op, \
}
#define SIMPLE_NEAREST_FAST_PATH_PAD(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_PAD_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _pad ## _ ## op, \
}
#define SIMPLE_NEAREST_FAST_PATH_NONE(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_NONE_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _none ## _ ## op, \
}
#define SIMPLE_NEAREST_FAST_PATH_COVER(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
SCALED_NEAREST_FLAGS | FAST_PATH_SAMPLES_COVER_CLIP, \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _cover ## _ ## op, \
}
#define SIMPLE_NEAREST_A8_MASK_FAST_PATH_NORMAL(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_NORMAL_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _normal ## _ ## op, \
}
#define SIMPLE_NEAREST_A8_MASK_FAST_PATH_PAD(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_PAD_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _pad ## _ ## op, \
}
#define SIMPLE_NEAREST_A8_MASK_FAST_PATH_NONE(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_NONE_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _none ## _ ## op, \
}
#define SIMPLE_NEAREST_A8_MASK_FAST_PATH_COVER(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
SCALED_NEAREST_FLAGS | FAST_PATH_SAMPLES_COVER_CLIP, \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _cover ## _ ## op, \
}
#define SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_NORMAL(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_NORMAL_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _normal ## _ ## op, \
}
#define SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_PAD(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_PAD_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _pad ## _ ## op, \
}
#define SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_NONE(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_NEAREST_FLAGS | \
FAST_PATH_NONE_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _none ## _ ## op, \
}
#define SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_COVER(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
SCALED_NEAREST_FLAGS | FAST_PATH_SAMPLES_COVER_CLIP, \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_nearest_ ## func ## _cover ## _ ## op, \
}
/* Prefer the use of 'cover' variant, because it is faster */
#define SIMPLE_NEAREST_FAST_PATH(op,s,d,func) \
SIMPLE_NEAREST_FAST_PATH_COVER (op,s,d,func), \
SIMPLE_NEAREST_FAST_PATH_NONE (op,s,d,func), \
SIMPLE_NEAREST_FAST_PATH_PAD (op,s,d,func), \
SIMPLE_NEAREST_FAST_PATH_NORMAL (op,s,d,func)
#define SIMPLE_NEAREST_A8_MASK_FAST_PATH(op,s,d,func) \
SIMPLE_NEAREST_A8_MASK_FAST_PATH_COVER (op,s,d,func), \
SIMPLE_NEAREST_A8_MASK_FAST_PATH_NONE (op,s,d,func), \
SIMPLE_NEAREST_A8_MASK_FAST_PATH_PAD (op,s,d,func)
#define SIMPLE_NEAREST_SOLID_MASK_FAST_PATH(op,s,d,func) \
SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_COVER (op,s,d,func), \
SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_NONE (op,s,d,func), \
SIMPLE_NEAREST_SOLID_MASK_FAST_PATH_PAD (op,s,d,func)
/*****************************************************************************/
/*
* Identify 5 zones in each scanline for bilinear scaling. Depending on
* whether 2 pixels to be interpolated are fetched from the image itself,
* from the padding area around it or from both image and padding area.
*/
static force_inline void
bilinear_pad_repeat_get_scanline_bounds (int32_t source_image_width,
pixman_fixed_t vx,
pixman_fixed_t unit_x,
int32_t * left_pad,
int32_t * left_tz,
int32_t * width,
int32_t * right_tz,
int32_t * right_pad)
{
int width1 = *width, left_pad1, right_pad1;
int width2 = *width, left_pad2, right_pad2;
pad_repeat_get_scanline_bounds (source_image_width, vx, unit_x,
&width1, &left_pad1, &right_pad1);
pad_repeat_get_scanline_bounds (source_image_width, vx + pixman_fixed_1,
unit_x, &width2, &left_pad2, &right_pad2);
*left_pad = left_pad2;
*left_tz = left_pad1 - left_pad2;
*right_tz = right_pad2 - right_pad1;
*right_pad = right_pad1;
*width -= *left_pad + *left_tz + *right_tz + *right_pad;
}
/*
* Main loop template for single pass bilinear scaling. It needs to be
* provided with 'scanline_func' which should do the compositing operation.
* The needed function has the following prototype:
*
* scanline_func (dst_type_t * dst,
* const mask_type_ * mask,
* const src_type_t * src_top,
* const src_type_t * src_bottom,
* int32_t width,
* int weight_top,
* int weight_bottom,
* pixman_fixed_t vx,
* pixman_fixed_t unit_x,
* pixman_fixed_t max_vx,
* pixman_bool_t zero_src)
*
* Where:
* dst - destination scanline buffer for storing results
* mask - mask buffer (or single value for solid mask)
* src_top, src_bottom - two source scanlines
* width - number of pixels to process
* weight_top - weight of the top row for interpolation
* weight_bottom - weight of the bottom row for interpolation
* vx - initial position for fetching the first pair of
* pixels from the source buffer
* unit_x - position increment needed to move to the next pair
* of pixels
* max_vx - image size as a fixed point value, can be used for
* implementing NORMAL repeat (when it is supported)
* zero_src - boolean hint variable, which is set to TRUE when
* all source pixels are fetched from zero padding
* zone for NONE repeat
*
* Note: normally the sum of 'weight_top' and 'weight_bottom' is equal to 256,
* but sometimes it may be less than that for NONE repeat when handling
* fuzzy antialiased top or bottom image edges. Also both top and
* bottom weight variables are guaranteed to have value in 0-255
* range and can fit into unsigned byte or be used with 8-bit SIMD
* multiplication instructions.
*/
#define FAST_BILINEAR_MAINLOOP_INT(scale_func_name, scanline_func, src_type_t, mask_type_t, \
dst_type_t, repeat_mode, have_mask, mask_is_solid) \
static void \
fast_composite_scaled_bilinear ## scale_func_name (pixman_implementation_t *imp, \
pixman_op_t op, \
pixman_image_t * src_image, \
pixman_image_t * mask_image, \
pixman_image_t * dst_image, \
int32_t src_x, \
int32_t src_y, \
int32_t mask_x, \
int32_t mask_y, \
int32_t dst_x, \
int32_t dst_y, \
int32_t width, \
int32_t height) \
{ \
dst_type_t *dst_line; \
mask_type_t *mask_line; \
src_type_t *src_first_line; \
int y1, y2; \
pixman_fixed_t max_vx = INT32_MAX; /* suppress uninitialized variable warning */ \
pixman_vector_t v; \
pixman_fixed_t vx, vy; \
pixman_fixed_t unit_x, unit_y; \
int32_t left_pad, left_tz, right_tz, right_pad; \
\
dst_type_t *dst; \
mask_type_t solid_mask; \
const mask_type_t *mask = &solid_mask; \
int src_stride, mask_stride, dst_stride; \
\
PIXMAN_IMAGE_GET_LINE (dst_image, dst_x, dst_y, dst_type_t, dst_stride, dst_line, 1); \
if (have_mask) \
{ \
if (mask_is_solid) \
{ \
solid_mask = _pixman_image_get_solid (imp, mask_image, dst_image->bits.format); \
mask_stride = 0; \
} \
else \
{ \
PIXMAN_IMAGE_GET_LINE (mask_image, mask_x, mask_y, mask_type_t, \
mask_stride, mask_line, 1); \
} \
} \
/* pass in 0 instead of src_x and src_y because src_x and src_y need to be \
* transformed from destination space to source space */ \
PIXMAN_IMAGE_GET_LINE (src_image, 0, 0, src_type_t, src_stride, src_first_line, 1); \
\
/* reference point is the center of the pixel */ \
v.vector[0] = pixman_int_to_fixed (src_x) + pixman_fixed_1 / 2; \
v.vector[1] = pixman_int_to_fixed (src_y) + pixman_fixed_1 / 2; \
v.vector[2] = pixman_fixed_1; \
\
if (!pixman_transform_point_3d (src_image->common.transform, &v)) \
return; \
\
unit_x = src_image->common.transform->matrix[0][0]; \
unit_y = src_image->common.transform->matrix[1][1]; \
\
v.vector[0] -= pixman_fixed_1 / 2; \
v.vector[1] -= pixman_fixed_1 / 2; \
\
vy = v.vector[1]; \
\
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_PAD || \
PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NONE) \
{ \
bilinear_pad_repeat_get_scanline_bounds (src_image->bits.width, v.vector[0], unit_x, \
&left_pad, &left_tz, &width, &right_tz, &right_pad); \
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_PAD) \
{ \
/* PAD repeat does not need special handling for 'transition zones' and */ \
/* they can be combined with 'padding zones' safely */ \
left_pad += left_tz; \
right_pad += right_tz; \
left_tz = right_tz = 0; \
} \
v.vector[0] += left_pad * unit_x; \
} \
\
while (--height >= 0) \
{ \
int weight1, weight2; \
dst = dst_line; \
dst_line += dst_stride; \
vx = v.vector[0]; \
if (have_mask && !mask_is_solid) \
{ \
mask = mask_line; \
mask_line += mask_stride; \
} \
\
y1 = pixman_fixed_to_int (vy); \
weight2 = (vy >> 8) & 0xff; \
if (weight2) \
{ \
/* normal case, both row weights are in 0-255 range and fit unsigned byte */ \
y2 = y1 + 1; \
weight1 = 256 - weight2; \
} \
else \
{ \
/* set both top and bottom row to the same scanline, and weights to 128+128 */ \
y2 = y1; \
weight1 = weight2 = 128; \
} \
vy += unit_y; \
if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_PAD) \
{ \
src_type_t *src1, *src2; \
src_type_t buf1[2]; \
src_type_t buf2[2]; \
repeat (PIXMAN_REPEAT_PAD, &y1, src_image->bits.height); \
repeat (PIXMAN_REPEAT_PAD, &y2, src_image->bits.height); \
src1 = src_first_line + src_stride * y1; \
src2 = src_first_line + src_stride * y2; \
\
if (left_pad > 0) \
{ \
buf1[0] = buf1[1] = src1[0]; \
buf2[0] = buf2[1] = src2[0]; \
scanline_func (dst, mask, \
buf1, buf2, left_pad, weight1, weight2, 0, 0, 0, FALSE); \
dst += left_pad; \
if (have_mask && !mask_is_solid) \
mask += left_pad; \
} \
if (width > 0) \
{ \
scanline_func (dst, mask, \
src1, src2, width, weight1, weight2, vx, unit_x, 0, FALSE); \
dst += width; \
if (have_mask && !mask_is_solid) \
mask += width; \
} \
if (right_pad > 0) \
{ \
buf1[0] = buf1[1] = src1[src_image->bits.width - 1]; \
buf2[0] = buf2[1] = src2[src_image->bits.width - 1]; \
scanline_func (dst, mask, \
buf1, buf2, right_pad, weight1, weight2, 0, 0, 0, FALSE); \
} \
} \
else if (PIXMAN_REPEAT_ ## repeat_mode == PIXMAN_REPEAT_NONE) \
{ \
src_type_t *src1, *src2; \
src_type_t buf1[2]; \
src_type_t buf2[2]; \
/* handle top/bottom zero padding by just setting weights to 0 if needed */ \
if (y1 < 0) \
{ \
weight1 = 0; \
y1 = 0; \
} \
if (y1 >= src_image->bits.height) \
{ \
weight1 = 0; \
y1 = src_image->bits.height - 1; \
} \
if (y2 < 0) \
{ \
weight2 = 0; \
y2 = 0; \
} \
if (y2 >= src_image->bits.height) \
{ \
weight2 = 0; \
y2 = src_image->bits.height - 1; \
} \
src1 = src_first_line + src_stride * y1; \
src2 = src_first_line + src_stride * y2; \
\
if (left_pad > 0) \
{ \
buf1[0] = buf1[1] = 0; \
buf2[0] = buf2[1] = 0; \
scanline_func (dst, mask, \
buf1, buf2, left_pad, weight1, weight2, 0, 0, 0, TRUE); \
dst += left_pad; \
if (have_mask && !mask_is_solid) \
mask += left_pad; \
} \
if (left_tz > 0) \
{ \
buf1[0] = 0; \
buf1[1] = src1[0]; \
buf2[0] = 0; \
buf2[1] = src2[0]; \
scanline_func (dst, mask, \
buf1, buf2, left_tz, weight1, weight2, \
pixman_fixed_frac (vx), unit_x, 0, FALSE); \
dst += left_tz; \
if (have_mask && !mask_is_solid) \
mask += left_tz; \
vx += left_tz * unit_x; \
} \
if (width > 0) \
{ \
scanline_func (dst, mask, \
src1, src2, width, weight1, weight2, vx, unit_x, 0, FALSE); \
dst += width; \
if (have_mask && !mask_is_solid) \
mask += width; \
vx += width * unit_x; \
} \
if (right_tz > 0) \
{ \
buf1[0] = src1[src_image->bits.width - 1]; \
buf1[1] = 0; \
buf2[0] = src2[src_image->bits.width - 1]; \
buf2[1] = 0; \
scanline_func (dst, mask, \
buf1, buf2, right_tz, weight1, weight2, \
pixman_fixed_frac (vx), unit_x, 0, FALSE); \
dst += right_tz; \
if (have_mask && !mask_is_solid) \
mask += right_tz; \
} \
if (right_pad > 0) \
{ \
buf1[0] = buf1[1] = 0; \
buf2[0] = buf2[1] = 0; \
scanline_func (dst, mask, \
buf1, buf2, right_pad, weight1, weight2, 0, 0, 0, TRUE); \
} \
} \
else \
{ \
scanline_func (dst, mask, src_first_line + src_stride * y1, \
src_first_line + src_stride * y2, width, \
weight1, weight2, vx, unit_x, max_vx, FALSE); \
} \
} \
}
/* A workaround for old sun studio, see: https://bugs.freedesktop.org/show_bug.cgi?id=32764 */
#define FAST_BILINEAR_MAINLOOP_COMMON(scale_func_name, scanline_func, src_type_t, mask_type_t, \
dst_type_t, repeat_mode, have_mask, mask_is_solid) \
FAST_BILINEAR_MAINLOOP_INT(_ ## scale_func_name, scanline_func, src_type_t, mask_type_t,\
dst_type_t, repeat_mode, have_mask, mask_is_solid)
#define SCALED_BILINEAR_FLAGS \
(FAST_PATH_SCALE_TRANSFORM | \
FAST_PATH_NO_ALPHA_MAP | \
FAST_PATH_BILINEAR_FILTER | \
FAST_PATH_NO_ACCESSORS | \
FAST_PATH_NARROW_FORMAT)
#define SIMPLE_BILINEAR_FAST_PATH_PAD(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_BILINEAR_FLAGS | \
FAST_PATH_PAD_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _pad ## _ ## op, \
}
#define SIMPLE_BILINEAR_FAST_PATH_NONE(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_BILINEAR_FLAGS | \
FAST_PATH_NONE_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _none ## _ ## op, \
}
#define SIMPLE_BILINEAR_FAST_PATH_COVER(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
SCALED_BILINEAR_FLAGS | FAST_PATH_SAMPLES_COVER_CLIP, \
PIXMAN_null, 0, \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _cover ## _ ## op, \
}
#define SIMPLE_BILINEAR_A8_MASK_FAST_PATH_PAD(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_BILINEAR_FLAGS | \
FAST_PATH_PAD_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _pad ## _ ## op, \
}
#define SIMPLE_BILINEAR_A8_MASK_FAST_PATH_NONE(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_BILINEAR_FLAGS | \
FAST_PATH_NONE_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _none ## _ ## op, \
}
#define SIMPLE_BILINEAR_A8_MASK_FAST_PATH_COVER(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
SCALED_BILINEAR_FLAGS | FAST_PATH_SAMPLES_COVER_CLIP, \
PIXMAN_a8, MASK_FLAGS (a8, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _cover ## _ ## op, \
}
#define SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH_PAD(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_BILINEAR_FLAGS | \
FAST_PATH_PAD_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _pad ## _ ## op, \
}
#define SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH_NONE(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
(SCALED_BILINEAR_FLAGS | \
FAST_PATH_NONE_REPEAT | \
FAST_PATH_X_UNIT_POSITIVE), \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _none ## _ ## op, \
}
#define SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH_COVER(op,s,d,func) \
{ PIXMAN_OP_ ## op, \
PIXMAN_ ## s, \
SCALED_BILINEAR_FLAGS | FAST_PATH_SAMPLES_COVER_CLIP, \
PIXMAN_solid, MASK_FLAGS (solid, FAST_PATH_UNIFIED_ALPHA), \
PIXMAN_ ## d, FAST_PATH_STD_DEST_FLAGS, \
fast_composite_scaled_bilinear_ ## func ## _cover ## _ ## op, \
}
/* Prefer the use of 'cover' variant, because it is faster */
#define SIMPLE_BILINEAR_FAST_PATH(op,s,d,func) \
SIMPLE_BILINEAR_FAST_PATH_COVER (op,s,d,func), \
SIMPLE_BILINEAR_FAST_PATH_NONE (op,s,d,func), \
SIMPLE_BILINEAR_FAST_PATH_PAD (op,s,d,func)
#define SIMPLE_BILINEAR_A8_MASK_FAST_PATH(op,s,d,func) \
SIMPLE_BILINEAR_A8_MASK_FAST_PATH_COVER (op,s,d,func), \
SIMPLE_BILINEAR_A8_MASK_FAST_PATH_NONE (op,s,d,func), \
SIMPLE_BILINEAR_A8_MASK_FAST_PATH_PAD (op,s,d,func)
#define SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH(op,s,d,func) \
SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH_COVER (op,s,d,func), \
SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH_NONE (op,s,d,func), \
SIMPLE_BILINEAR_SOLID_MASK_FAST_PATH_PAD (op,s,d,func)
#endif
|