forked from aosp-mirror/platform_system_core
-
Notifications
You must be signed in to change notification settings - Fork 0
/
scanline.cpp
2347 lines (2127 loc) · 75.7 KB
/
scanline.cpp
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
/* libs/pixelflinger/scanline.cpp
**
** Copyright 2006-2011, The Android Open Source Project
**
** Licensed under the Apache License, Version 2.0 (the "License");
** you may not use this file except in compliance with the License.
** You may obtain a copy of the License at
**
** http://www.apache.org/licenses/LICENSE-2.0
**
** Unless required by applicable law or agreed to in writing, software
** distributed under the License is distributed on an "AS IS" BASIS,
** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
** See the License for the specific language governing permissions and
** limitations under the License.
*/
#define LOG_TAG "pixelflinger"
#include <assert.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <cutils/memory.h>
#include <cutils/log.h>
#include "buffer.h"
#include "scanline.h"
#include "codeflinger/CodeCache.h"
#include "codeflinger/GGLAssembler.h"
#include "codeflinger/ARMAssembler.h"
#if defined(__mips__)
#include "codeflinger/MIPSAssembler.h"
#endif
//#include "codeflinger/ARMAssemblerOptimizer.h"
// ----------------------------------------------------------------------------
#define ANDROID_CODEGEN_GENERIC 0 // force generic pixel pipeline
#define ANDROID_CODEGEN_C 1 // hand-written C, fallback generic
#define ANDROID_CODEGEN_ASM 2 // hand-written asm, fallback generic
#define ANDROID_CODEGEN_GENERATED 3 // hand-written asm, fallback codegen
#ifdef NDEBUG
# define ANDROID_RELEASE
# define ANDROID_CODEGEN ANDROID_CODEGEN_GENERATED
#else
# define ANDROID_DEBUG
# define ANDROID_CODEGEN ANDROID_CODEGEN_GENERATED
#endif
#if defined(__arm__) || defined(__mips__)
# define ANDROID_ARM_CODEGEN 1
#else
# define ANDROID_ARM_CODEGEN 0
#endif
#define DEBUG__CODEGEN_ONLY 0
/* Set to 1 to dump to the log the states that need a new
* code-generated scanline callback, i.e. those that don't
* have a corresponding shortcut function.
*/
#define DEBUG_NEEDS 0
#ifdef __mips__
#define ASSEMBLY_SCRATCH_SIZE 4096
#else
#define ASSEMBLY_SCRATCH_SIZE 2048
#endif
// ----------------------------------------------------------------------------
namespace android {
// ----------------------------------------------------------------------------
static void init_y(context_t*, int32_t);
static void init_y_noop(context_t*, int32_t);
static void init_y_packed(context_t*, int32_t);
static void init_y_error(context_t*, int32_t);
static void step_y__generic(context_t* c);
static void step_y__nop(context_t*);
static void step_y__smooth(context_t* c);
static void step_y__tmu(context_t* c);
static void step_y__w(context_t* c);
static void scanline(context_t* c);
static void scanline_perspective(context_t* c);
static void scanline_perspective_single(context_t* c);
static void scanline_t32cb16blend(context_t* c);
static void scanline_t32cb16blend_dither(context_t* c);
static void scanline_t32cb16blend_srca(context_t* c);
static void scanline_t32cb16blend_clamp(context_t* c);
static void scanline_t32cb16blend_clamp_dither(context_t* c);
static void scanline_t32cb16blend_clamp_mod(context_t* c);
static void scanline_x32cb16blend_clamp_mod(context_t* c);
static void scanline_t32cb16blend_clamp_mod_dither(context_t* c);
static void scanline_x32cb16blend_clamp_mod_dither(context_t* c);
static void scanline_t32cb16(context_t* c);
static void scanline_t32cb16_dither(context_t* c);
static void scanline_t32cb16_clamp(context_t* c);
static void scanline_t32cb16_clamp_dither(context_t* c);
static void scanline_col32cb16blend(context_t* c);
static void scanline_t16cb16_clamp(context_t* c);
static void scanline_t16cb16blend_clamp_mod(context_t* c);
static void scanline_memcpy(context_t* c);
static void scanline_memset8(context_t* c);
static void scanline_memset16(context_t* c);
static void scanline_memset32(context_t* c);
static void scanline_noop(context_t* c);
static void scanline_set(context_t* c);
static void scanline_clear(context_t* c);
static void rect_generic(context_t* c, size_t yc);
static void rect_memcpy(context_t* c, size_t yc);
#if defined( __arm__)
extern "C" void scanline_t32cb16blend_arm(uint16_t*, uint32_t*, size_t);
extern "C" void scanline_t32cb16_arm(uint16_t *dst, uint32_t *src, size_t ct);
extern "C" void scanline_col32cb16blend_neon(uint16_t *dst, uint32_t *col, size_t ct);
extern "C" void scanline_col32cb16blend_arm(uint16_t *dst, uint32_t col, size_t ct);
#elif defined(__mips__)
extern "C" void scanline_t32cb16blend_mips(uint16_t*, uint32_t*, size_t);
#endif
// ----------------------------------------------------------------------------
static inline uint16_t convertAbgr8888ToRgb565(uint32_t pix)
{
return uint16_t( ((pix << 8) & 0xf800) |
((pix >> 5) & 0x07e0) |
((pix >> 19) & 0x001f) );
}
struct shortcut_t {
needs_filter_t filter;
const char* desc;
void (*scanline)(context_t*);
void (*init_y)(context_t*, int32_t);
};
// Keep in sync with needs
/* To understand the values here, have a look at:
* system/core/include/private/pixelflinger/ggl_context.h
*
* Especially the lines defining and using GGL_RESERVE_NEEDS
*
* Quick reminders:
* - the last nibble of the first value is the destination buffer format.
* - the last nibble of the third value is the source texture format
* - formats: 4=rgb565 1=abgr8888 2=xbgr8888
*
* In the descriptions below:
*
* SRC means we copy the source pixels to the destination
*
* SRC_OVER means we blend the source pixels to the destination
* with dstFactor = 1-srcA, srcFactor=1 (premultiplied source).
* This mode is otherwise called 'blend'.
*
* SRCA_OVER means we blend the source pixels to the destination
* with dstFactor=srcA*(1-srcA) srcFactor=srcA (non-premul source).
* This mode is otherwise called 'blend_srca'
*
* clamp means we fetch source pixels from a texture with u/v clamping
*
* mod means the source pixels are modulated (multiplied) by the
* a/r/g/b of the current context's color. Typically used for
* fade-in / fade-out.
*
* dither means we dither 32 bit values to 16 bits
*/
static shortcut_t shortcuts[] = {
{ { { 0x03515104, 0x00000077, { 0x00000A01, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, blend SRC_OVER", scanline_t32cb16blend, init_y_noop },
{ { { 0x03010104, 0x00000077, { 0x00000A01, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC", scanline_t32cb16, init_y_noop },
/* same as first entry, but with dithering */
{ { { 0x03515104, 0x00000177, { 0x00000A01, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, blend SRC_OVER dither", scanline_t32cb16blend_dither, init_y_noop },
/* same as second entry, but with dithering */
{ { { 0x03010104, 0x00000177, { 0x00000A01, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC dither", scanline_t32cb16_dither, init_y_noop },
/* this is used during the boot animation - CHEAT: ignore dithering */
{ { { 0x03545404, 0x00000077, { 0x00000A01, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFEFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, blend dst:ONE_MINUS_SRCA src:SRCA", scanline_t32cb16blend_srca, init_y_noop },
/* special case for arbitrary texture coordinates (think scaling) */
{ { { 0x03515104, 0x00000077, { 0x00000001, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC_OVER clamp", scanline_t32cb16blend_clamp, init_y },
{ { { 0x03515104, 0x00000177, { 0x00000001, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC_OVER clamp dither", scanline_t32cb16blend_clamp_dither, init_y },
/* another case used during emulation */
{ { { 0x03515104, 0x00000077, { 0x00001001, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC_OVER clamp modulate", scanline_t32cb16blend_clamp_mod, init_y },
/* and this */
{ { { 0x03515104, 0x00000077, { 0x00001002, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, x888 tx, SRC_OVER clamp modulate", scanline_x32cb16blend_clamp_mod, init_y },
{ { { 0x03515104, 0x00000177, { 0x00001001, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC_OVER clamp modulate dither", scanline_t32cb16blend_clamp_mod_dither, init_y },
{ { { 0x03515104, 0x00000177, { 0x00001002, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, x888 tx, SRC_OVER clamp modulate dither", scanline_x32cb16blend_clamp_mod_dither, init_y },
{ { { 0x03010104, 0x00000077, { 0x00000001, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC clamp", scanline_t32cb16_clamp, init_y },
{ { { 0x03010104, 0x00000077, { 0x00000002, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, x888 tx, SRC clamp", scanline_t32cb16_clamp, init_y },
{ { { 0x03010104, 0x00000177, { 0x00000001, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 8888 tx, SRC clamp dither", scanline_t32cb16_clamp_dither, init_y },
{ { { 0x03010104, 0x00000177, { 0x00000002, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, x888 tx, SRC clamp dither", scanline_t32cb16_clamp_dither, init_y },
{ { { 0x03010104, 0x00000077, { 0x00000004, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 565 tx, SRC clamp", scanline_t16cb16_clamp, init_y },
{ { { 0x03515104, 0x00000077, { 0x00001004, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0x0000003F } } },
"565 fb, 565 tx, SRC_OVER clamp", scanline_t16cb16blend_clamp_mod, init_y },
{ { { 0x03515104, 0x00000077, { 0x00000000, 0x00000000 } },
{ 0xFFFFFFFF, 0xFFFFFFFF, { 0xFFFFFFFF, 0xFFFFFFFF } } },
"565 fb, 8888 fixed color", scanline_col32cb16blend, init_y_packed },
{ { { 0x00000000, 0x00000000, { 0x00000000, 0x00000000 } },
{ 0x00000000, 0x00000007, { 0x00000000, 0x00000000 } } },
"(nop) alpha test", scanline_noop, init_y_noop },
{ { { 0x00000000, 0x00000000, { 0x00000000, 0x00000000 } },
{ 0x00000000, 0x00000070, { 0x00000000, 0x00000000 } } },
"(nop) depth test", scanline_noop, init_y_noop },
{ { { 0x05000000, 0x00000000, { 0x00000000, 0x00000000 } },
{ 0x0F000000, 0x00000080, { 0x00000000, 0x00000000 } } },
"(nop) logic_op", scanline_noop, init_y_noop },
{ { { 0xF0000000, 0x00000000, { 0x00000000, 0x00000000 } },
{ 0xF0000000, 0x00000080, { 0x00000000, 0x00000000 } } },
"(nop) color mask", scanline_noop, init_y_noop },
{ { { 0x0F000000, 0x00000077, { 0x00000000, 0x00000000 } },
{ 0xFF000000, 0x000000F7, { 0x00000000, 0x00000000 } } },
"(set) logic_op", scanline_set, init_y_noop },
{ { { 0x00000000, 0x00000077, { 0x00000000, 0x00000000 } },
{ 0xFF000000, 0x000000F7, { 0x00000000, 0x00000000 } } },
"(clear) logic_op", scanline_clear, init_y_noop },
{ { { 0x03000000, 0x00000077, { 0x00000000, 0x00000000 } },
{ 0xFFFFFF00, 0x000000F7, { 0x00000000, 0x00000000 } } },
"(clear) blending 0/0", scanline_clear, init_y_noop },
{ { { 0x00000000, 0x00000000, { 0x00000000, 0x00000000 } },
{ 0x0000003F, 0x00000000, { 0x00000000, 0x00000000 } } },
"(error) invalid color-buffer format", scanline_noop, init_y_error },
};
static const needs_filter_t noblend1to1 = {
// (disregard dithering, see below)
{ 0x03010100, 0x00000077, { 0x00000A00, 0x00000000 } },
{ 0xFFFFFFC0, 0xFFFFFEFF, { 0xFFFFFFC0, 0x0000003F } }
};
static const needs_filter_t fill16noblend = {
{ 0x03010100, 0x00000077, { 0x00000000, 0x00000000 } },
{ 0xFFFFFFC0, 0xFFFFFFFF, { 0x0000003F, 0x0000003F } }
};
// ----------------------------------------------------------------------------
#if ANDROID_ARM_CODEGEN
#if defined(__mips__)
static CodeCache gCodeCache(32 * 1024);
#else
static CodeCache gCodeCache(12 * 1024);
#endif
class ScanlineAssembly : public Assembly {
AssemblyKey<needs_t> mKey;
public:
ScanlineAssembly(needs_t needs, size_t size)
: Assembly(size), mKey(needs) { }
const AssemblyKey<needs_t>& key() const { return mKey; }
};
#endif
// ----------------------------------------------------------------------------
void ggl_init_scanline(context_t* c)
{
c->init_y = init_y;
c->step_y = step_y__generic;
c->scanline = scanline;
}
void ggl_uninit_scanline(context_t* c)
{
if (c->state.buffers.coverage)
free(c->state.buffers.coverage);
#if ANDROID_ARM_CODEGEN
if (c->scanline_as)
c->scanline_as->decStrong(c);
#endif
}
// ----------------------------------------------------------------------------
static void pick_scanline(context_t* c)
{
#if (!defined(DEBUG__CODEGEN_ONLY) || (DEBUG__CODEGEN_ONLY == 0))
#if ANDROID_CODEGEN == ANDROID_CODEGEN_GENERIC
c->init_y = init_y;
c->step_y = step_y__generic;
c->scanline = scanline;
return;
#endif
//printf("*** needs [%08lx:%08lx:%08lx:%08lx]\n",
// c->state.needs.n, c->state.needs.p,
// c->state.needs.t[0], c->state.needs.t[1]);
// first handle the special case that we cannot test with a filter
const uint32_t cb_format = GGL_READ_NEEDS(CB_FORMAT, c->state.needs.n);
if (GGL_READ_NEEDS(T_FORMAT, c->state.needs.t[0]) == cb_format) {
if (c->state.needs.match(noblend1to1)) {
// this will match regardless of dithering state, since both
// src and dest have the same format anyway, there is no dithering
// to be done.
const GGLFormat* f =
&(c->formats[GGL_READ_NEEDS(T_FORMAT, c->state.needs.t[0])]);
if ((f->components == GGL_RGB) ||
(f->components == GGL_RGBA) ||
(f->components == GGL_LUMINANCE) ||
(f->components == GGL_LUMINANCE_ALPHA))
{
// format must have all of RGB components
// (so the current color doesn't show through)
c->scanline = scanline_memcpy;
c->init_y = init_y_noop;
return;
}
}
}
if (c->state.needs.match(fill16noblend)) {
c->init_y = init_y_packed;
switch (c->formats[cb_format].size) {
case 1: c->scanline = scanline_memset8; return;
case 2: c->scanline = scanline_memset16; return;
case 4: c->scanline = scanline_memset32; return;
}
}
const int numFilters = sizeof(shortcuts)/sizeof(shortcut_t);
for (int i=0 ; i<numFilters ; i++) {
if (c->state.needs.match(shortcuts[i].filter)) {
c->scanline = shortcuts[i].scanline;
c->init_y = shortcuts[i].init_y;
return;
}
}
#if DEBUG_NEEDS
ALOGI("Needs: n=0x%08x p=0x%08x t0=0x%08x t1=0x%08x",
c->state.needs.n, c->state.needs.p,
c->state.needs.t[0], c->state.needs.t[1]);
#endif
#endif // DEBUG__CODEGEN_ONLY
c->init_y = init_y;
c->step_y = step_y__generic;
#if ANDROID_ARM_CODEGEN
// we're going to have to generate some code...
// here, generate code for our pixel pipeline
const AssemblyKey<needs_t> key(c->state.needs);
sp<Assembly> assembly = gCodeCache.lookup(key);
if (assembly == 0) {
// create a new assembly region
sp<ScanlineAssembly> a = new ScanlineAssembly(c->state.needs,
ASSEMBLY_SCRATCH_SIZE);
// initialize our assembler
#if defined(__arm__)
GGLAssembler assembler( new ARMAssembler(a) );
//GGLAssembler assembler(
// new ARMAssemblerOptimizer(new ARMAssembler(a)) );
#endif
#if defined(__mips__)
GGLAssembler assembler( new ArmToMipsAssembler(a) );
#endif
// generate the scanline code for the given needs
int err = assembler.scanline(c->state.needs, c);
if (ggl_likely(!err)) {
// finally, cache this assembly
err = gCodeCache.cache(a->key(), a);
}
if (ggl_unlikely(err)) {
ALOGE("error generating or caching assembly. Reverting to NOP.");
c->scanline = scanline_noop;
c->init_y = init_y_noop;
c->step_y = step_y__nop;
return;
}
assembly = a;
}
// release the previous assembly
if (c->scanline_as) {
c->scanline_as->decStrong(c);
}
//ALOGI("using generated pixel-pipeline");
c->scanline_as = assembly.get();
c->scanline_as->incStrong(c); // hold on to assembly
c->scanline = (void(*)(context_t* c))assembly->base();
#else
// ALOGW("using generic (slow) pixel-pipeline");
c->scanline = scanline;
#endif
}
void ggl_pick_scanline(context_t* c)
{
pick_scanline(c);
if ((c->state.enables & GGL_ENABLE_W) &&
(c->state.enables & GGL_ENABLE_TMUS))
{
c->span = c->scanline;
c->scanline = scanline_perspective;
if (!(c->state.enabled_tmu & (c->state.enabled_tmu - 1))) {
// only one TMU enabled
c->scanline = scanline_perspective_single;
}
}
}
// ----------------------------------------------------------------------------
static void blending(context_t* c, pixel_t* fragment, pixel_t* fb);
static void blend_factor(context_t* c, pixel_t* r, uint32_t factor,
const pixel_t* src, const pixel_t* dst);
static void rescale(uint32_t& u, uint8_t& su, uint32_t& v, uint8_t& sv);
#if ANDROID_ARM_CODEGEN && (ANDROID_CODEGEN == ANDROID_CODEGEN_GENERATED)
// no need to compile the generic-pipeline, it can't be reached
void scanline(context_t*)
{
}
#else
void rescale(uint32_t& u, uint8_t& su, uint32_t& v, uint8_t& sv)
{
if (su && sv) {
if (su > sv) {
v = ggl_expand(v, sv, su);
sv = su;
} else if (su < sv) {
u = ggl_expand(u, su, sv);
su = sv;
}
}
}
void blending(context_t* c, pixel_t* fragment, pixel_t* fb)
{
rescale(fragment->c[0], fragment->s[0], fb->c[0], fb->s[0]);
rescale(fragment->c[1], fragment->s[1], fb->c[1], fb->s[1]);
rescale(fragment->c[2], fragment->s[2], fb->c[2], fb->s[2]);
rescale(fragment->c[3], fragment->s[3], fb->c[3], fb->s[3]);
pixel_t sf, df;
blend_factor(c, &sf, c->state.blend.src, fragment, fb);
blend_factor(c, &df, c->state.blend.dst, fragment, fb);
fragment->c[1] =
gglMulAddx(fragment->c[1], sf.c[1], gglMulx(fb->c[1], df.c[1]));
fragment->c[2] =
gglMulAddx(fragment->c[2], sf.c[2], gglMulx(fb->c[2], df.c[2]));
fragment->c[3] =
gglMulAddx(fragment->c[3], sf.c[3], gglMulx(fb->c[3], df.c[3]));
if (c->state.blend.alpha_separate) {
blend_factor(c, &sf, c->state.blend.src_alpha, fragment, fb);
blend_factor(c, &df, c->state.blend.dst_alpha, fragment, fb);
}
fragment->c[0] =
gglMulAddx(fragment->c[0], sf.c[0], gglMulx(fb->c[0], df.c[0]));
// clamp to 1.0
if (fragment->c[0] >= (1LU<<fragment->s[0]))
fragment->c[0] = (1<<fragment->s[0])-1;
if (fragment->c[1] >= (1LU<<fragment->s[1]))
fragment->c[1] = (1<<fragment->s[1])-1;
if (fragment->c[2] >= (1LU<<fragment->s[2]))
fragment->c[2] = (1<<fragment->s[2])-1;
if (fragment->c[3] >= (1LU<<fragment->s[3]))
fragment->c[3] = (1<<fragment->s[3])-1;
}
static inline int blendfactor(uint32_t x, uint32_t size, uint32_t def = 0)
{
if (!size)
return def;
// scale to 16 bits
if (size > 16) {
x >>= (size - 16);
} else if (size < 16) {
x = ggl_expand(x, size, 16);
}
x += x >> 15;
return x;
}
void blend_factor(context_t* c, pixel_t* r,
uint32_t factor, const pixel_t* src, const pixel_t* dst)
{
switch (factor) {
case GGL_ZERO:
r->c[1] =
r->c[2] =
r->c[3] =
r->c[0] = 0;
break;
case GGL_ONE:
r->c[1] =
r->c[2] =
r->c[3] =
r->c[0] = FIXED_ONE;
break;
case GGL_DST_COLOR:
r->c[1] = blendfactor(dst->c[1], dst->s[1]);
r->c[2] = blendfactor(dst->c[2], dst->s[2]);
r->c[3] = blendfactor(dst->c[3], dst->s[3]);
r->c[0] = blendfactor(dst->c[0], dst->s[0]);
break;
case GGL_SRC_COLOR:
r->c[1] = blendfactor(src->c[1], src->s[1]);
r->c[2] = blendfactor(src->c[2], src->s[2]);
r->c[3] = blendfactor(src->c[3], src->s[3]);
r->c[0] = blendfactor(src->c[0], src->s[0]);
break;
case GGL_ONE_MINUS_DST_COLOR:
r->c[1] = FIXED_ONE - blendfactor(dst->c[1], dst->s[1]);
r->c[2] = FIXED_ONE - blendfactor(dst->c[2], dst->s[2]);
r->c[3] = FIXED_ONE - blendfactor(dst->c[3], dst->s[3]);
r->c[0] = FIXED_ONE - blendfactor(dst->c[0], dst->s[0]);
break;
case GGL_ONE_MINUS_SRC_COLOR:
r->c[1] = FIXED_ONE - blendfactor(src->c[1], src->s[1]);
r->c[2] = FIXED_ONE - blendfactor(src->c[2], src->s[2]);
r->c[3] = FIXED_ONE - blendfactor(src->c[3], src->s[3]);
r->c[0] = FIXED_ONE - blendfactor(src->c[0], src->s[0]);
break;
case GGL_SRC_ALPHA:
r->c[1] =
r->c[2] =
r->c[3] =
r->c[0] = blendfactor(src->c[0], src->s[0], FIXED_ONE);
break;
case GGL_ONE_MINUS_SRC_ALPHA:
r->c[1] =
r->c[2] =
r->c[3] =
r->c[0] = FIXED_ONE - blendfactor(src->c[0], src->s[0], FIXED_ONE);
break;
case GGL_DST_ALPHA:
r->c[1] =
r->c[2] =
r->c[3] =
r->c[0] = blendfactor(dst->c[0], dst->s[0], FIXED_ONE);
break;
case GGL_ONE_MINUS_DST_ALPHA:
r->c[1] =
r->c[2] =
r->c[3] =
r->c[0] = FIXED_ONE - blendfactor(dst->c[0], dst->s[0], FIXED_ONE);
break;
case GGL_SRC_ALPHA_SATURATE:
// XXX: GGL_SRC_ALPHA_SATURATE
break;
}
}
static GGLfixed wrapping(int32_t coord, uint32_t size, int tx_wrap)
{
GGLfixed d;
if (tx_wrap == GGL_REPEAT) {
d = (uint32_t(coord)>>16) * size;
} else if (tx_wrap == GGL_CLAMP) { // CLAMP_TO_EDGE semantics
const GGLfixed clamp_min = FIXED_HALF;
const GGLfixed clamp_max = (size << 16) - FIXED_HALF;
if (coord < clamp_min) coord = clamp_min;
if (coord > clamp_max) coord = clamp_max;
d = coord;
} else { // 1:1
const GGLfixed clamp_min = 0;
const GGLfixed clamp_max = (size << 16);
if (coord < clamp_min) coord = clamp_min;
if (coord > clamp_max) coord = clamp_max;
d = coord;
}
return d;
}
static inline
GGLcolor ADJUST_COLOR_ITERATOR(GGLcolor v, GGLcolor dvdx, int len)
{
const int32_t end = dvdx * (len-1) + v;
if (end < 0)
v -= end;
v &= ~(v>>31);
return v;
}
void scanline(context_t* c)
{
const uint32_t enables = c->state.enables;
const int xs = c->iterators.xl;
const int x1 = c->iterators.xr;
int xc = x1 - xs;
const int16_t* covPtr = c->state.buffers.coverage + xs;
// All iterated values are sampled at the pixel center
// reset iterators for that scanline...
GGLcolor r, g, b, a;
iterators_t& ci = c->iterators;
if (enables & GGL_ENABLE_SMOOTH) {
r = (xs * c->shade.drdx) + ci.ydrdy;
g = (xs * c->shade.dgdx) + ci.ydgdy;
b = (xs * c->shade.dbdx) + ci.ydbdy;
a = (xs * c->shade.dadx) + ci.ydady;
r = ADJUST_COLOR_ITERATOR(r, c->shade.drdx, xc);
g = ADJUST_COLOR_ITERATOR(g, c->shade.dgdx, xc);
b = ADJUST_COLOR_ITERATOR(b, c->shade.dbdx, xc);
a = ADJUST_COLOR_ITERATOR(a, c->shade.dadx, xc);
} else {
r = ci.ydrdy;
g = ci.ydgdy;
b = ci.ydbdy;
a = ci.ydady;
}
// z iterators are 1.31
GGLfixed z = (xs * c->shade.dzdx) + ci.ydzdy;
GGLfixed f = (xs * c->shade.dfdx) + ci.ydfdy;
struct {
GGLfixed s, t;
} tc[GGL_TEXTURE_UNIT_COUNT];
if (enables & GGL_ENABLE_TMUS) {
for (int i=0 ; i<GGL_TEXTURE_UNIT_COUNT ; ++i) {
if (c->state.texture[i].enable) {
texture_iterators_t& ti = c->state.texture[i].iterators;
if (enables & GGL_ENABLE_W) {
tc[i].s = ti.ydsdy;
tc[i].t = ti.ydtdy;
} else {
tc[i].s = (xs * ti.dsdx) + ti.ydsdy;
tc[i].t = (xs * ti.dtdx) + ti.ydtdy;
}
}
}
}
pixel_t fragment;
pixel_t texel;
pixel_t fb;
uint32_t x = xs;
uint32_t y = c->iterators.y;
while (xc--) {
{ // just a scope
// read color (convert to 8 bits by keeping only the integer part)
fragment.s[1] = fragment.s[2] =
fragment.s[3] = fragment.s[0] = 8;
fragment.c[1] = r >> (GGL_COLOR_BITS-8);
fragment.c[2] = g >> (GGL_COLOR_BITS-8);
fragment.c[3] = b >> (GGL_COLOR_BITS-8);
fragment.c[0] = a >> (GGL_COLOR_BITS-8);
// texturing
if (enables & GGL_ENABLE_TMUS) {
for (int i=0 ; i<GGL_TEXTURE_UNIT_COUNT ; ++i) {
texture_t& tx = c->state.texture[i];
if (!tx.enable)
continue;
texture_iterators_t& ti = tx.iterators;
int32_t u, v;
// s-coordinate
if (tx.s_coord != GGL_ONE_TO_ONE) {
const int w = tx.surface.width;
u = wrapping(tc[i].s, w, tx.s_wrap);
tc[i].s += ti.dsdx;
} else {
u = (((tx.shade.is0>>16) + x)<<16) + FIXED_HALF;
}
// t-coordinate
if (tx.t_coord != GGL_ONE_TO_ONE) {
const int h = tx.surface.height;
v = wrapping(tc[i].t, h, tx.t_wrap);
tc[i].t += ti.dtdx;
} else {
v = (((tx.shade.it0>>16) + y)<<16) + FIXED_HALF;
}
// read texture
if (tx.mag_filter == GGL_NEAREST &&
tx.min_filter == GGL_NEAREST)
{
u >>= 16;
v >>= 16;
tx.surface.read(&tx.surface, c, u, v, &texel);
} else {
const int w = tx.surface.width;
const int h = tx.surface.height;
u -= FIXED_HALF;
v -= FIXED_HALF;
int u0 = u >> 16;
int v0 = v >> 16;
int u1 = u0 + 1;
int v1 = v0 + 1;
if (tx.s_wrap == GGL_REPEAT) {
if (u0<0) u0 += w;
if (u1<0) u1 += w;
if (u0>=w) u0 -= w;
if (u1>=w) u1 -= w;
} else {
if (u0<0) u0 = 0;
if (u1<0) u1 = 0;
if (u0>=w) u0 = w-1;
if (u1>=w) u1 = w-1;
}
if (tx.t_wrap == GGL_REPEAT) {
if (v0<0) v0 += h;
if (v1<0) v1 += h;
if (v0>=h) v0 -= h;
if (v1>=h) v1 -= h;
} else {
if (v0<0) v0 = 0;
if (v1<0) v1 = 0;
if (v0>=h) v0 = h-1;
if (v1>=h) v1 = h-1;
}
pixel_t texels[4];
uint32_t mm[4];
tx.surface.read(&tx.surface, c, u0, v0, &texels[0]);
tx.surface.read(&tx.surface, c, u0, v1, &texels[1]);
tx.surface.read(&tx.surface, c, u1, v0, &texels[2]);
tx.surface.read(&tx.surface, c, u1, v1, &texels[3]);
u = (u >> 12) & 0xF;
v = (v >> 12) & 0xF;
u += u>>3;
v += v>>3;
mm[0] = (0x10 - u) * (0x10 - v);
mm[1] = (0x10 - u) * v;
mm[2] = u * (0x10 - v);
mm[3] = 0x100 - (mm[0] + mm[1] + mm[2]);
for (int j=0 ; j<4 ; j++) {
texel.s[j] = texels[0].s[j];
if (!texel.s[j]) continue;
texel.s[j] += 8;
texel.c[j] = texels[0].c[j]*mm[0] +
texels[1].c[j]*mm[1] +
texels[2].c[j]*mm[2] +
texels[3].c[j]*mm[3] ;
}
}
// Texture environnement...
for (int j=0 ; j<4 ; j++) {
uint32_t& Cf = fragment.c[j];
uint32_t& Ct = texel.c[j];
uint8_t& sf = fragment.s[j];
uint8_t& st = texel.s[j];
uint32_t At = texel.c[0];
uint8_t sat = texel.s[0];
switch (tx.env) {
case GGL_REPLACE:
if (st) {
Cf = Ct;
sf = st;
}
break;
case GGL_MODULATE:
if (st) {
uint32_t factor = Ct + (Ct>>(st-1));
Cf = (Cf * factor) >> st;
}
break;
case GGL_DECAL:
if (sat) {
rescale(Cf, sf, Ct, st);
Cf += ((Ct - Cf) * (At + (At>>(sat-1)))) >> sat;
}
break;
case GGL_BLEND:
if (st) {
uint32_t Cc = tx.env_color[i];
if (sf>8) Cc = (Cc * ((1<<sf)-1))>>8;
else if (sf<8) Cc = (Cc - (Cc>>(8-sf)))>>(8-sf);
uint32_t factor = Ct + (Ct>>(st-1));
Cf = ((((1<<st) - factor) * Cf) + Ct*Cc)>>st;
}
break;
case GGL_ADD:
if (st) {
rescale(Cf, sf, Ct, st);
Cf += Ct;
}
break;
}
}
}
}
// coverage application
if (enables & GGL_ENABLE_AA) {
int16_t cf = *covPtr++;
fragment.c[0] = (int64_t(fragment.c[0]) * cf) >> 15;
}
// alpha-test
if (enables & GGL_ENABLE_ALPHA_TEST) {
GGLcolor ref = c->state.alpha_test.ref;
GGLcolor alpha = (uint64_t(fragment.c[0]) *
((1<<GGL_COLOR_BITS)-1)) / ((1<<fragment.s[0])-1);
switch (c->state.alpha_test.func) {
case GGL_NEVER: goto discard;
case GGL_LESS: if (alpha<ref) break; goto discard;
case GGL_EQUAL: if (alpha==ref) break; goto discard;
case GGL_LEQUAL: if (alpha<=ref) break; goto discard;
case GGL_GREATER: if (alpha>ref) break; goto discard;
case GGL_NOTEQUAL: if (alpha!=ref) break; goto discard;
case GGL_GEQUAL: if (alpha>=ref) break; goto discard;
}
}
// depth test
if (c->state.buffers.depth.format) {
if (enables & GGL_ENABLE_DEPTH_TEST) {
surface_t* cb = &(c->state.buffers.depth);
uint16_t* p = (uint16_t*)(cb->data)+(x+(cb->stride*y));
uint16_t zz = uint32_t(z)>>(16);
uint16_t depth = *p;
switch (c->state.depth_test.func) {
case GGL_NEVER: goto discard;
case GGL_LESS: if (zz<depth) break; goto discard;
case GGL_EQUAL: if (zz==depth) break; goto discard;
case GGL_LEQUAL: if (zz<=depth) break; goto discard;
case GGL_GREATER: if (zz>depth) break; goto discard;
case GGL_NOTEQUAL: if (zz!=depth) break; goto discard;
case GGL_GEQUAL: if (zz>=depth) break; goto discard;
}
// depth buffer is not enabled, if depth-test is not enabled
/*
fragment.s[1] = fragment.s[2] =
fragment.s[3] = fragment.s[0] = 8;
fragment.c[1] =
fragment.c[2] =
fragment.c[3] =
fragment.c[0] = 255 - (zz>>8);
*/
if (c->state.mask.depth) {
*p = zz;
}
}
}
// fog
if (enables & GGL_ENABLE_FOG) {
for (int i=1 ; i<=3 ; i++) {
GGLfixed fc = (c->state.fog.color[i] * 0x10000) / 0xFF;
uint32_t& c = fragment.c[i];
uint8_t& s = fragment.s[i];
c = (c * 0x10000) / ((1<<s)-1);
c = gglMulAddx(c, f, gglMulx(fc, 0x10000 - f));
s = 16;
}
}
// blending
if (enables & GGL_ENABLE_BLENDING) {
fb.c[1] = fb.c[2] = fb.c[3] = fb.c[0] = 0; // placate valgrind
fb.s[1] = fb.s[2] = fb.s[3] = fb.s[0] = 0;
c->state.buffers.color.read(
&(c->state.buffers.color), c, x, y, &fb);
blending( c, &fragment, &fb );
}
// write
c->state.buffers.color.write(
&(c->state.buffers.color), c, x, y, &fragment);
}
discard:
// iterate...
x += 1;
if (enables & GGL_ENABLE_SMOOTH) {
r += c->shade.drdx;
g += c->shade.dgdx;
b += c->shade.dbdx;
a += c->shade.dadx;
}
z += c->shade.dzdx;
f += c->shade.dfdx;
}
}
#endif // ANDROID_ARM_CODEGEN && (ANDROID_CODEGEN == ANDROID_CODEGEN_GENERATED)
// ----------------------------------------------------------------------------
#if 0
#pragma mark -
#pragma mark Scanline
#endif
/* Used to parse a 32-bit source texture linearly. Usage is:
*
* horz_iterator32 hi(context);
* while (...) {
* uint32_t src_pixel = hi.get_pixel32();
* ...
* }
*
* Use only for one-to-one texture mapping.
*/
struct horz_iterator32 {
horz_iterator32(context_t* c) {
const int x = c->iterators.xl;
const int y = c->iterators.y;
texture_t& tx = c->state.texture[0];
const int32_t u = (tx.shade.is0>>16) + x;
const int32_t v = (tx.shade.it0>>16) + y;
m_src = reinterpret_cast<uint32_t*>(tx.surface.data)+(u+(tx.surface.stride*v));
}
uint32_t get_pixel32() {
return *m_src++;
}
protected:
uint32_t* m_src;
};
/* A variant for 16-bit source textures. */
struct horz_iterator16 {
horz_iterator16(context_t* c) {
const int x = c->iterators.xl;
const int y = c->iterators.y;
texture_t& tx = c->state.texture[0];
const int32_t u = (tx.shade.is0>>16) + x;
const int32_t v = (tx.shade.it0>>16) + y;
m_src = reinterpret_cast<uint16_t*>(tx.surface.data)+(u+(tx.surface.stride*v));
}
uint16_t get_pixel16() {
return *m_src++;
}
protected:
uint16_t* m_src;
};
/* A clamp iterator is used to iterate inside a texture with GGL_CLAMP.
* After initialization, call get_src16() or get_src32() to get the current
* texture pixel value.
*/
struct clamp_iterator {
clamp_iterator(context_t* c) {
const int xs = c->iterators.xl;
texture_t& tx = c->state.texture[0];
texture_iterators_t& ti = tx.iterators;
m_s = (xs * ti.dsdx) + ti.ydsdy;
m_t = (xs * ti.dtdx) + ti.ydtdy;
m_ds = ti.dsdx;
m_dt = ti.dtdx;
m_width_m1 = tx.surface.width - 1;
m_height_m1 = tx.surface.height - 1;
m_data = tx.surface.data;
m_stride = tx.surface.stride;
}
uint16_t get_pixel16() {
int u, v;
get_uv(u, v);
uint16_t* src = reinterpret_cast<uint16_t*>(m_data) + (u + (m_stride*v));
return src[0];
}