forked from sm64-port/sm64-port
-
Notifications
You must be signed in to change notification settings - Fork 34
/
gfx_pc.c
1670 lines (1481 loc) · 56.7 KB
/
gfx_pc.c
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
#include <math.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
#include <stdbool.h>
#include <assert.h>
#ifndef _LANGUAGE_C
#define _LANGUAGE_C
#endif
#include <PR/gbi.h>
#include "gfx_pc.h"
#include "gfx_cc.h"
#include "gfx_window_manager_api.h"
#include "gfx_rendering_api.h"
#include "gfx_screen_config.h"
#define SUPPORT_CHECK(x) assert(x)
// SCALE_M_N: upscale/downscale M-bit integer to N-bit
#define SCALE_5_8(VAL_) (((VAL_) * 0xFF) / 0x1F)
#define SCALE_8_5(VAL_) ((((VAL_) + 4) * 0x1F) / 0xFF)
#define SCALE_4_8(VAL_) ((VAL_) * 0x11)
#define SCALE_8_4(VAL_) ((VAL_) / 0x11)
#define SCALE_3_8(VAL_) ((VAL_) * 0x24)
#define SCALE_8_3(VAL_) ((VAL_) / 0x24)
#define SCREEN_WIDTH 320
#define SCREEN_HEIGHT 240
#define HALF_SCREEN_WIDTH (SCREEN_WIDTH / 2)
#define HALF_SCREEN_HEIGHT (SCREEN_HEIGHT / 2)
#define RATIO_X (gfx_current_dimensions.width / (2.0f * HALF_SCREEN_WIDTH))
#define RATIO_Y (gfx_current_dimensions.height / (2.0f * HALF_SCREEN_HEIGHT))
#define MAX_BUFFERED 256
#define MAX_LIGHTS 2
#define MAX_VERTICES 64
struct RGBA {
uint8_t r, g, b, a;
};
struct XYWidthHeight {
uint16_t x, y, width, height;
};
struct LoadedVertex {
float x, y, z, w;
float u, v;
struct RGBA color;
uint8_t clip_rej;
};
struct TextureHashmapNode {
struct TextureHashmapNode *next;
const uint8_t *texture_addr;
uint8_t fmt, siz;
uint32_t texture_id;
uint8_t cms, cmt;
bool linear_filter;
};
static struct {
struct TextureHashmapNode *hashmap[1024];
struct TextureHashmapNode pool[512];
uint32_t pool_pos;
} gfx_texture_cache;
struct ColorCombiner {
uint32_t cc_id;
struct ShaderProgram *prg;
uint8_t shader_input_mapping[2][4];
};
static struct ColorCombiner color_combiner_pool[64];
static uint8_t color_combiner_pool_size;
static struct RSP {
float modelview_matrix_stack[11][4][4];
uint8_t modelview_matrix_stack_size;
float MP_matrix[4][4];
float P_matrix[4][4];
Light_t current_lights[MAX_LIGHTS + 1];
float current_lights_coeffs[MAX_LIGHTS][3];
float current_lookat_coeffs[2][3]; // lookat_x, lookat_y
uint8_t current_num_lights; // includes ambient light
bool lights_changed;
uint32_t geometry_mode;
int16_t fog_mul, fog_offset;
struct {
// U0.16
uint16_t s, t;
} texture_scaling_factor;
struct LoadedVertex loaded_vertices[MAX_VERTICES + 4];
} rsp;
static struct RDP {
const uint8_t *palette;
struct {
const uint8_t *addr;
uint8_t siz;
uint8_t tile_number;
} texture_to_load;
struct {
const uint8_t *addr;
uint32_t size_bytes;
} loaded_texture[2];
struct {
uint8_t fmt;
uint8_t siz;
uint8_t cms, cmt;
uint16_t uls, ult, lrs, lrt; // U10.2
uint32_t line_size_bytes;
} texture_tile;
bool textures_changed[2];
uint32_t other_mode_l, other_mode_h;
uint32_t combine_mode;
struct RGBA env_color, prim_color, fog_color, fill_color;
struct XYWidthHeight viewport, scissor;
bool viewport_or_scissor_changed;
void *z_buf_address;
void *color_image_address;
} rdp;
static struct RenderingState {
bool depth_test;
bool depth_mask;
bool decal_mode;
bool alpha_blend;
struct XYWidthHeight viewport, scissor;
struct ShaderProgram *shader_program;
struct TextureHashmapNode *textures[2];
} rendering_state;
struct GfxDimensions gfx_current_dimensions;
static bool dropped_frame;
static float buf_vbo[MAX_BUFFERED * (26 * 3)]; // 3 vertices in a triangle and 26 floats per vtx
static size_t buf_vbo_len;
static size_t buf_vbo_num_tris;
static struct GfxWindowManagerAPI *gfx_wapi;
static struct GfxRenderingAPI *gfx_rapi;
#ifdef ENABLE_N3DS_3D_MODE
static void gfx_set_is_2d(bool is_2d)
{
gfx_rapi->set_is_2d(is_2d);
}
#endif
static void gfx_flush(void) {
if (buf_vbo_len > 0) {
gfx_rapi->draw_triangles(buf_vbo, buf_vbo_len, buf_vbo_num_tris);
buf_vbo_len = 0;
buf_vbo_num_tris = 0;
}
}
static struct ShaderProgram *gfx_lookup_or_create_shader_program(uint32_t shader_id) {
struct ShaderProgram *prg = gfx_rapi->lookup_shader(shader_id);
if (prg == NULL) {
gfx_rapi->unload_shader(rendering_state.shader_program);
prg = gfx_rapi->create_and_load_new_shader(shader_id);
rendering_state.shader_program = prg;
}
return prg;
}
static void gfx_generate_cc(struct ColorCombiner *comb, uint32_t cc_id) {
uint8_t c[2][4];
uint32_t shader_id = (cc_id >> 24) << 24;
uint8_t shader_input_mapping[2][4] = {{0}};
for (int i = 0; i < 4; i++) {
c[0][i] = (cc_id >> (i * 3)) & 7;
c[1][i] = (cc_id >> (12 + i * 3)) & 7;
}
for (int i = 0; i < 2; i++) {
if (c[i][0] == c[i][1] || c[i][2] == CC_0) {
c[i][0] = c[i][1] = c[i][2] = 0;
}
uint8_t input_number[8] = {0};
int next_input_number = SHADER_INPUT_1;
for (int j = 0; j < 4; j++) {
int val = 0;
switch (c[i][j]) {
case CC_0:
break;
case CC_TEXEL0:
val = SHADER_TEXEL0;
break;
case CC_TEXEL1:
val = SHADER_TEXEL1;
break;
case CC_TEXEL0A:
val = SHADER_TEXEL0A;
break;
case CC_PRIM:
case CC_SHADE:
case CC_ENV:
case CC_LOD:
if (input_number[c[i][j]] == 0) {
shader_input_mapping[i][next_input_number - 1] = c[i][j];
input_number[c[i][j]] = next_input_number++;
}
val = input_number[c[i][j]];
break;
}
shader_id |= val << (i * 12 + j * 3);
}
}
comb->cc_id = cc_id;
comb->prg = gfx_lookup_or_create_shader_program(shader_id);
memcpy(comb->shader_input_mapping, shader_input_mapping, sizeof(shader_input_mapping));
}
static struct ColorCombiner *gfx_lookup_or_create_color_combiner(uint32_t cc_id) {
static struct ColorCombiner *prev_combiner;
if (prev_combiner != NULL && prev_combiner->cc_id == cc_id) {
return prev_combiner;
}
for (size_t i = 0; i < color_combiner_pool_size; i++) {
if (color_combiner_pool[i].cc_id == cc_id) {
return prev_combiner = &color_combiner_pool[i];
}
}
gfx_flush();
struct ColorCombiner *comb = &color_combiner_pool[color_combiner_pool_size++];
gfx_generate_cc(comb, cc_id);
return prev_combiner = comb;
}
static bool gfx_texture_cache_lookup(int tile, struct TextureHashmapNode **n, const uint8_t *orig_addr, uint32_t fmt, uint32_t siz) {
size_t hash = (uintptr_t)orig_addr;
hash = (hash >> 5) & 0x3ff;
struct TextureHashmapNode **node = &gfx_texture_cache.hashmap[hash];
while (*node != NULL && *node - gfx_texture_cache.pool < (int)gfx_texture_cache.pool_pos) {
if ((*node)->texture_addr == orig_addr && (*node)->fmt == fmt && (*node)->siz == siz) {
gfx_rapi->select_texture(tile, (*node)->texture_id);
*n = *node;
return true;
}
node = &(*node)->next;
}
if (gfx_texture_cache.pool_pos == sizeof(gfx_texture_cache.pool) / sizeof(struct TextureHashmapNode)) {
// Pool is full. We just invalidate everything and start over.
gfx_texture_cache.pool_pos = 0;
node = &gfx_texture_cache.hashmap[hash];
//puts("Clearing texture cache");
}
*node = &gfx_texture_cache.pool[gfx_texture_cache.pool_pos++];
if ((*node)->texture_addr == NULL) {
(*node)->texture_id = gfx_rapi->new_texture();
}
gfx_rapi->select_texture(tile, (*node)->texture_id);
gfx_rapi->set_sampler_parameters(tile, false, 0, 0);
(*node)->cms = 0;
(*node)->cmt = 0;
(*node)->linear_filter = false;
(*node)->next = NULL;
(*node)->texture_addr = orig_addr;
(*node)->fmt = fmt;
(*node)->siz = siz;
*n = *node;
return false;
}
static uint8_t rgba32_buf[32768] __attribute__((aligned(32)));
static void import_texture_rgba16(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes / 2; i++) {
uint16_t col16 = (rdp.loaded_texture[tile].addr[2 * i] << 8) | rdp.loaded_texture[tile].addr[2 * i + 1];
uint8_t a = col16 & 1;
uint8_t r = col16 >> 11;
uint8_t g = (col16 >> 6) & 0x1f;
uint8_t b = (col16 >> 1) & 0x1f;
rgba32_buf[4*i + 0] = SCALE_5_8(r);
rgba32_buf[4*i + 1] = SCALE_5_8(g);
rgba32_buf[4*i + 2] = SCALE_5_8(b);
rgba32_buf[4*i + 3] = a ? 255 : 0;
}
uint32_t width = rdp.texture_tile.line_size_bytes / 2;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_rgba32(int tile) {
uint32_t width = rdp.texture_tile.line_size_bytes / 2;
uint32_t height = (rdp.loaded_texture[tile].size_bytes / 2) / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rdp.loaded_texture[tile].addr, width, height);
}
static void import_texture_ia4(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes * 2; i++) {
uint8_t byte = rdp.loaded_texture[tile].addr[i / 2];
uint8_t part = (byte >> (4 - (i % 2) * 4)) & 0xf;
uint8_t intensity = part >> 1;
uint8_t alpha = part & 1;
uint8_t r = intensity;
uint8_t g = intensity;
uint8_t b = intensity;
rgba32_buf[4*i + 0] = SCALE_3_8(r);
rgba32_buf[4*i + 1] = SCALE_3_8(g);
rgba32_buf[4*i + 2] = SCALE_3_8(b);
rgba32_buf[4*i + 3] = alpha ? 255 : 0;
}
uint32_t width = rdp.texture_tile.line_size_bytes * 2;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_ia8(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes; i++) {
uint8_t intensity = rdp.loaded_texture[tile].addr[i] >> 4;
uint8_t alpha = rdp.loaded_texture[tile].addr[i] & 0xf;
uint8_t r = intensity;
uint8_t g = intensity;
uint8_t b = intensity;
rgba32_buf[4*i + 0] = SCALE_4_8(r);
rgba32_buf[4*i + 1] = SCALE_4_8(g);
rgba32_buf[4*i + 2] = SCALE_4_8(b);
rgba32_buf[4*i + 3] = SCALE_4_8(alpha);
}
uint32_t width = rdp.texture_tile.line_size_bytes;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_ia16(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes / 2; i++) {
uint8_t intensity = rdp.loaded_texture[tile].addr[2 * i];
uint8_t alpha = rdp.loaded_texture[tile].addr[2 * i + 1];
uint8_t r = intensity;
uint8_t g = intensity;
uint8_t b = intensity;
rgba32_buf[4*i + 0] = r;
rgba32_buf[4*i + 1] = g;
rgba32_buf[4*i + 2] = b;
rgba32_buf[4*i + 3] = alpha;
}
uint32_t width = rdp.texture_tile.line_size_bytes / 2;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_i4(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes * 2; i++) {
uint8_t byte = rdp.loaded_texture[tile].addr[i / 2];
uint8_t part = (byte >> (4 - (i % 2) * 4)) & 0xf;
uint8_t intensity = part;
uint8_t r = intensity;
uint8_t g = intensity;
uint8_t b = intensity;
rgba32_buf[4*i + 0] = SCALE_4_8(r);
rgba32_buf[4*i + 1] = SCALE_4_8(g);
rgba32_buf[4*i + 2] = SCALE_4_8(b);
rgba32_buf[4*i + 3] = 255;
}
uint32_t width = rdp.texture_tile.line_size_bytes * 2;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_i8(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes; i++) {
uint8_t intensity = rdp.loaded_texture[tile].addr[i];
uint8_t r = intensity;
uint8_t g = intensity;
uint8_t b = intensity;
rgba32_buf[4*i + 0] = r;
rgba32_buf[4*i + 1] = g;
rgba32_buf[4*i + 2] = b;
rgba32_buf[4*i + 3] = 255;
}
uint32_t width = rdp.texture_tile.line_size_bytes;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_ci4(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes * 2; i++) {
uint8_t byte = rdp.loaded_texture[tile].addr[i / 2];
uint8_t idx = (byte >> (4 - (i % 2) * 4)) & 0xf;
uint16_t col16 = (rdp.palette[idx * 2] << 8) | rdp.palette[idx * 2 + 1]; // Big endian load
uint8_t a = col16 & 1;
uint8_t r = col16 >> 11;
uint8_t g = (col16 >> 6) & 0x1f;
uint8_t b = (col16 >> 1) & 0x1f;
rgba32_buf[4*i + 0] = SCALE_5_8(r);
rgba32_buf[4*i + 1] = SCALE_5_8(g);
rgba32_buf[4*i + 2] = SCALE_5_8(b);
rgba32_buf[4*i + 3] = a ? 255 : 0;
}
uint32_t width = rdp.texture_tile.line_size_bytes * 2;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture_ci8(int tile) {
for (uint32_t i = 0; i < rdp.loaded_texture[tile].size_bytes; i++) {
uint8_t idx = rdp.loaded_texture[tile].addr[i];
uint16_t col16 = (rdp.palette[idx * 2] << 8) | rdp.palette[idx * 2 + 1]; // Big endian load
uint8_t a = col16 & 1;
uint8_t r = col16 >> 11;
uint8_t g = (col16 >> 6) & 0x1f;
uint8_t b = (col16 >> 1) & 0x1f;
rgba32_buf[4*i + 0] = SCALE_5_8(r);
rgba32_buf[4*i + 1] = SCALE_5_8(g);
rgba32_buf[4*i + 2] = SCALE_5_8(b);
rgba32_buf[4*i + 3] = a ? 255 : 0;
}
uint32_t width = rdp.texture_tile.line_size_bytes;
uint32_t height = rdp.loaded_texture[tile].size_bytes / rdp.texture_tile.line_size_bytes;
gfx_rapi->upload_texture(rgba32_buf, width, height);
}
static void import_texture(int tile) {
uint8_t fmt = rdp.texture_tile.fmt;
uint8_t siz = rdp.texture_tile.siz;
if (gfx_texture_cache_lookup(tile, &rendering_state.textures[tile], rdp.loaded_texture[tile].addr, fmt, siz)) {
return;
}
if (fmt == G_IM_FMT_RGBA) {
if (siz == G_IM_SIZ_16b) {
import_texture_rgba16(tile);
} else if (siz == G_IM_SIZ_32b) {
import_texture_rgba32(tile);
} else {
abort();
}
} else if (fmt == G_IM_FMT_IA) {
if (siz == G_IM_SIZ_4b) {
import_texture_ia4(tile);
} else if (siz == G_IM_SIZ_8b) {
import_texture_ia8(tile);
} else if (siz == G_IM_SIZ_16b) {
import_texture_ia16(tile);
} else {
abort();
}
} else if (fmt == G_IM_FMT_CI) {
if (siz == G_IM_SIZ_4b) {
import_texture_ci4(tile);
} else if (siz == G_IM_SIZ_8b) {
import_texture_ci8(tile);
} else {
abort();
}
} else if (fmt == G_IM_FMT_I) {
if (siz == G_IM_SIZ_4b) {
import_texture_i4(tile);
} else if (siz == G_IM_SIZ_8b) {
import_texture_i8(tile);
} else {
abort();
}
} else {
abort();
}
}
static void gfx_normalize_vector(float v[3]) {
float s = sqrtf(v[0] * v[0] + v[1] * v[1] + v[2] * v[2]);
v[0] /= s;
v[1] /= s;
v[2] /= s;
}
static void gfx_transposed_matrix_mul(float res[3], const float a[3], const float b[4][4]) {
res[0] = a[0] * b[0][0] + a[1] * b[0][1] + a[2] * b[0][2];
res[1] = a[0] * b[1][0] + a[1] * b[1][1] + a[2] * b[1][2];
res[2] = a[0] * b[2][0] + a[1] * b[2][1] + a[2] * b[2][2];
}
static void calculate_normal_dir(const Light_t *light, float coeffs[3]) {
float light_dir[3] = {
light->dir[0] / 127.0f,
light->dir[1] / 127.0f,
light->dir[2] / 127.0f
};
gfx_transposed_matrix_mul(coeffs, light_dir, rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1]);
gfx_normalize_vector(coeffs);
}
#ifdef TARGET_N3DS
void multMatrix44FPU(const float a[4][4], const float b[4][4], float res[4][4]);
#define gfx_matrix_mul(res, a, b) multMatrix44FPU( (const float (*)[4])(a), (const float (*)[4])(b), (float (*)[4])(res) )
#else
static void gfx_matrix_mul(float res[4][4], const float a[4][4], const float b[4][4]) {
float tmp[4][4];
for (int i = 0; i < 4; i++) {
for (int j = 0; j < 4; j++) {
tmp[i][j] = a[i][0] * b[0][j] +
a[i][1] * b[1][j] +
a[i][2] * b[2][j] +
a[i][3] * b[3][j];
}
}
memcpy(res, tmp, sizeof(tmp));
}
#endif
static void gfx_sp_matrix(uint8_t parameters, const int32_t *addr) {
float matrix[4][4];
#ifndef GBI_FLOATS
// Original GBI where fixed point matrices are used
for (int i = 0; i < 4; i++) {
for (int j = 0; j < 4; j += 2) {
int32_t int_part = addr[i * 2 + j / 2];
uint32_t frac_part = addr[8 + i * 2 + j / 2];
matrix[i][j] = (int32_t)((int_part & 0xffff0000) | (frac_part >> 16)) / 65536.0f;
matrix[i][j + 1] = (int32_t)((int_part << 16) | (frac_part & 0xffff)) / 65536.0f;
}
}
#else
// For a modified GBI where fixed point values are replaced with floats
memcpy(matrix, addr, sizeof(matrix));
#endif
if (parameters & G_MTX_PROJECTION) {
if (parameters & G_MTX_LOAD) {
memcpy(rsp.P_matrix, matrix, sizeof(matrix));
} else {
gfx_matrix_mul(rsp.P_matrix, matrix, rsp.P_matrix);
}
} else { // G_MTX_MODELVIEW
if ((parameters & G_MTX_PUSH) && rsp.modelview_matrix_stack_size < 11) {
++rsp.modelview_matrix_stack_size;
memcpy(rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1], rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 2], sizeof(matrix));
}
if (parameters & G_MTX_LOAD) {
memcpy(rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1], matrix, sizeof(matrix));
} else {
gfx_matrix_mul(rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1], matrix, rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1]);
}
rsp.lights_changed = 1;
}
gfx_matrix_mul(rsp.MP_matrix, rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1], rsp.P_matrix);
}
static void gfx_sp_pop_matrix(uint32_t count) {
while (count--) {
if (rsp.modelview_matrix_stack_size > 0) {
--rsp.modelview_matrix_stack_size;
if (rsp.modelview_matrix_stack_size > 0) {
gfx_matrix_mul(rsp.MP_matrix, rsp.modelview_matrix_stack[rsp.modelview_matrix_stack_size - 1], rsp.P_matrix);
}
}
}
}
static float gfx_adjust_x_for_aspect_ratio(float x) {
return x * (4.0f / 3.0f) / ((float)gfx_current_dimensions.width / (float)gfx_current_dimensions.height);
}
#ifdef TARGET_N3DS
void transfByMatrix44FPU(const float m[3][4], const float *, float res[4]);
#endif
static void gfx_sp_vertex(size_t n_vertices, size_t dest_index, const Vtx *vertices) {
for (size_t i = 0; i < n_vertices; i++, dest_index++) {
const Vtx_t *v = &vertices[i].v;
const Vtx_tn *vn = &vertices[i].n;
struct LoadedVertex *d = &rsp.loaded_vertices[dest_index];
#ifdef TARGET_N3DS
float vec[4];
transfByMatrix44FPU(rsp.MP_matrix, v->ob, vec);
float x = vec[0];
float y = vec[1];
float z = vec[2];
float w = vec[3];
#else
float x = v->ob[0] * rsp.MP_matrix[0][0] + v->ob[1] * rsp.MP_matrix[1][0] + v->ob[2] * rsp.MP_matrix[2][0] + rsp.MP_matrix[3][0];
float y = v->ob[0] * rsp.MP_matrix[0][1] + v->ob[1] * rsp.MP_matrix[1][1] + v->ob[2] * rsp.MP_matrix[2][1] + rsp.MP_matrix[3][1];
float z = v->ob[0] * rsp.MP_matrix[0][2] + v->ob[1] * rsp.MP_matrix[1][2] + v->ob[2] * rsp.MP_matrix[2][2] + rsp.MP_matrix[3][2];
float w = v->ob[0] * rsp.MP_matrix[0][3] + v->ob[1] * rsp.MP_matrix[1][3] + v->ob[2] * rsp.MP_matrix[2][3] + rsp.MP_matrix[3][3];
#endif
x = gfx_adjust_x_for_aspect_ratio(x);
short U = v->tc[0] * rsp.texture_scaling_factor.s >> 16;
short V = v->tc[1] * rsp.texture_scaling_factor.t >> 16;
if (rsp.geometry_mode & G_LIGHTING) {
if (rsp.lights_changed) {
for (int i = 0; i < rsp.current_num_lights - 1; i++) {
calculate_normal_dir(&rsp.current_lights[i], rsp.current_lights_coeffs[i]);
}
static const Light_t lookat_x = {{0, 0, 0}, 0, {0, 0, 0}, 0, {127, 0, 0}, 0};
static const Light_t lookat_y = {{0, 0, 0}, 0, {0, 0, 0}, 0, {0, 127, 0}, 0};
calculate_normal_dir(&lookat_x, rsp.current_lookat_coeffs[0]);
calculate_normal_dir(&lookat_y, rsp.current_lookat_coeffs[1]);
rsp.lights_changed = false;
}
int r = rsp.current_lights[rsp.current_num_lights - 1].col[0];
int g = rsp.current_lights[rsp.current_num_lights - 1].col[1];
int b = rsp.current_lights[rsp.current_num_lights - 1].col[2];
for (int i = 0; i < rsp.current_num_lights - 1; i++) {
float intensity = 0;
intensity += vn->n[0] * rsp.current_lights_coeffs[i][0];
intensity += vn->n[1] * rsp.current_lights_coeffs[i][1];
intensity += vn->n[2] * rsp.current_lights_coeffs[i][2];
intensity /= 127.0f;
if (intensity > 0.0f) {
r += intensity * rsp.current_lights[i].col[0];
g += intensity * rsp.current_lights[i].col[1];
b += intensity * rsp.current_lights[i].col[2];
}
}
d->color.r = r > 255 ? 255 : r;
d->color.g = g > 255 ? 255 : g;
d->color.b = b > 255 ? 255 : b;
if (rsp.geometry_mode & G_TEXTURE_GEN) {
float dotx = 0, doty = 0;
dotx += vn->n[0] * rsp.current_lookat_coeffs[0][0];
dotx += vn->n[1] * rsp.current_lookat_coeffs[0][1];
dotx += vn->n[2] * rsp.current_lookat_coeffs[0][2];
doty += vn->n[0] * rsp.current_lookat_coeffs[1][0];
doty += vn->n[1] * rsp.current_lookat_coeffs[1][1];
doty += vn->n[2] * rsp.current_lookat_coeffs[1][2];
U = (int32_t)((dotx / 127.0f + 1.0f) / 4.0f * rsp.texture_scaling_factor.s);
V = (int32_t)((doty / 127.0f + 1.0f) / 4.0f * rsp.texture_scaling_factor.t);
}
} else {
d->color.r = v->cn[0];
d->color.g = v->cn[1];
d->color.b = v->cn[2];
}
d->u = U;
d->v = V;
// trivial clip rejection
d->clip_rej = 0;
if (x < -w) d->clip_rej |= 1;
if (x > w) d->clip_rej |= 2;
if (y < -w) d->clip_rej |= 4;
if (y > w) d->clip_rej |= 8;
if (z < -w) d->clip_rej |= 16;
if (z > w) d->clip_rej |= 32;
d->x = x;
d->y = y;
d->z = z;
d->w = w;
if (rsp.geometry_mode & G_FOG) {
if (fabsf(w) < 0.001f) {
// To avoid division by zero
w = 0.001f;
}
float winv = 1.0f / w;
if (winv < 0.0f) {
winv = 32767.0f;
}
float fog_z = z * winv * rsp.fog_mul + rsp.fog_offset;
if (fog_z < 0) fog_z = 0;
if (fog_z > 255) fog_z = 255;
d->color.a = fog_z; // Use alpha variable to store fog factor
} else {
d->color.a = v->cn[3];
}
}
}
static void gfx_sp_tri1(uint8_t vtx1_idx, uint8_t vtx2_idx, uint8_t vtx3_idx) {
struct LoadedVertex *v1 = &rsp.loaded_vertices[vtx1_idx];
struct LoadedVertex *v2 = &rsp.loaded_vertices[vtx2_idx];
struct LoadedVertex *v3 = &rsp.loaded_vertices[vtx3_idx];
struct LoadedVertex *v_arr[3] = {v1, v2, v3};
//if (rand()%2) return;
if (v1->clip_rej & v2->clip_rej & v3->clip_rej) {
// The whole triangle lies outside the visible area
return;
}
if ((rsp.geometry_mode & G_CULL_BOTH) != 0) {
float dx1 = v1->x / (v1->w) - v2->x / (v2->w);
float dy1 = v1->y / (v1->w) - v2->y / (v2->w);
float dx2 = v3->x / (v3->w) - v2->x / (v2->w);
float dy2 = v3->y / (v3->w) - v2->y / (v2->w);
float cross = dx1 * dy2 - dy1 * dx2;
if ((v1->w < 0) ^ (v2->w < 0) ^ (v3->w < 0)) {
// If one vertex lies behind the eye, negating cross will give the correct result.
// If all vertices lie behind the eye, the triangle will be rejected anyway.
cross = -cross;
}
switch (rsp.geometry_mode & G_CULL_BOTH) {
case G_CULL_FRONT:
if (cross <= 0) return;
break;
case G_CULL_BACK:
if (cross >= 0) return;
break;
case G_CULL_BOTH:
// Why is this even an option?
return;
}
}
bool depth_test = (rsp.geometry_mode & G_ZBUFFER) == G_ZBUFFER;
if (depth_test != rendering_state.depth_test) {
gfx_flush();
gfx_rapi->set_depth_test(depth_test);
rendering_state.depth_test = depth_test;
}
bool z_upd = (rdp.other_mode_l & Z_UPD) == Z_UPD;
if (z_upd != rendering_state.depth_mask) {
gfx_flush();
gfx_rapi->set_depth_mask(z_upd);
rendering_state.depth_mask = z_upd;
}
bool zmode_decal = (rdp.other_mode_l & ZMODE_DEC) == ZMODE_DEC;
if (zmode_decal != rendering_state.decal_mode) {
gfx_flush();
gfx_rapi->set_zmode_decal(zmode_decal);
rendering_state.decal_mode = zmode_decal;
}
if (rdp.viewport_or_scissor_changed) {
if (memcmp(&rdp.viewport, &rendering_state.viewport, sizeof(rdp.viewport)) != 0) {
gfx_flush();
gfx_rapi->set_viewport(rdp.viewport.x, rdp.viewport.y, rdp.viewport.width, rdp.viewport.height);
rendering_state.viewport = rdp.viewport;
}
if (memcmp(&rdp.scissor, &rendering_state.scissor, sizeof(rdp.scissor)) != 0) {
gfx_flush();
gfx_rapi->set_scissor(rdp.scissor.x, rdp.scissor.y, rdp.scissor.width, rdp.scissor.height);
rendering_state.scissor = rdp.scissor;
}
rdp.viewport_or_scissor_changed = false;
}
uint32_t cc_id = rdp.combine_mode;
bool use_alpha = (rdp.other_mode_l & (G_BL_A_MEM << 18)) == 0;
bool use_fog = (rdp.other_mode_l >> 30) == G_BL_CLR_FOG;
bool texture_edge = (rdp.other_mode_l & CVG_X_ALPHA) == CVG_X_ALPHA;
bool use_noise = (rdp.other_mode_l & G_AC_DITHER) == G_AC_DITHER;
if (texture_edge) {
use_alpha = true;
}
if (use_alpha) cc_id |= SHADER_OPT_ALPHA;
if (use_fog) cc_id |= SHADER_OPT_FOG;
if (texture_edge) cc_id |= SHADER_OPT_TEXTURE_EDGE;
if (use_noise) cc_id |= SHADER_OPT_NOISE;
if (!use_alpha) {
cc_id &= ~0xfff000;
}
struct ColorCombiner *comb = gfx_lookup_or_create_color_combiner(cc_id);
struct ShaderProgram *prg = comb->prg;
if (prg != rendering_state.shader_program) {
gfx_flush();
gfx_rapi->unload_shader(rendering_state.shader_program);
gfx_rapi->load_shader(prg);
rendering_state.shader_program = prg;
}
if (use_alpha != rendering_state.alpha_blend) {
gfx_flush();
gfx_rapi->set_use_alpha(use_alpha);
rendering_state.alpha_blend = use_alpha;
}
uint8_t num_inputs;
bool used_textures[2];
gfx_rapi->shader_get_info(prg, &num_inputs, used_textures);
for (int i = 0; i < 2; i++) {
if (used_textures[i]) {
if (rdp.textures_changed[i]) {
gfx_flush();
import_texture(i);
rdp.textures_changed[i] = false;
}
bool linear_filter = (rdp.other_mode_h & (3U << G_MDSFT_TEXTFILT)) != G_TF_POINT;
if (linear_filter != rendering_state.textures[i]->linear_filter || rdp.texture_tile.cms != rendering_state.textures[i]->cms || rdp.texture_tile.cmt != rendering_state.textures[i]->cmt) {
gfx_flush();
gfx_rapi->set_sampler_parameters(i, linear_filter, rdp.texture_tile.cms, rdp.texture_tile.cmt);
rendering_state.textures[i]->linear_filter = linear_filter;
rendering_state.textures[i]->cms = rdp.texture_tile.cms;
rendering_state.textures[i]->cmt = rdp.texture_tile.cmt;
}
}
}
bool use_texture = used_textures[0] || used_textures[1];
uint32_t tex_width = (rdp.texture_tile.lrs - rdp.texture_tile.uls + 4) / 4;
uint32_t tex_height = (rdp.texture_tile.lrt - rdp.texture_tile.ult + 4) / 4;
bool z_is_from_0_to_1 = gfx_rapi->z_is_from_0_to_1();
for (int i = 0; i < 3; i++) {
float z = v_arr[i]->z, w = v_arr[i]->w;
if (z_is_from_0_to_1) {
z = (z + w) / 2.0f;
}
#ifdef TARGET_N3DS
buf_vbo[buf_vbo_len++] = v_arr[i]->y;
buf_vbo[buf_vbo_len++] = -v_arr[i]->x;
buf_vbo[buf_vbo_len++] = -z;
#else
buf_vbo[buf_vbo_len++] = v_arr[i]->x;
buf_vbo[buf_vbo_len++] = v_arr[i]->y;
buf_vbo[buf_vbo_len++] = z;
#endif
buf_vbo[buf_vbo_len++] = w;
if (use_texture) {
float u = (v_arr[i]->u - rdp.texture_tile.uls * 8) / 32.0f;
float v = (v_arr[i]->v - rdp.texture_tile.ult * 8) / 32.0f;
if ((rdp.other_mode_h & (3U << G_MDSFT_TEXTFILT)) != G_TF_POINT) {
// Linear filter adds 0.5f to the coordinates
u += 0.5f;
v += 0.5f;
}
buf_vbo[buf_vbo_len++] = u / tex_width;
buf_vbo[buf_vbo_len++] = v / tex_height;
}
if (use_fog) {
buf_vbo[buf_vbo_len++] = rdp.fog_color.r / 255.0f;
buf_vbo[buf_vbo_len++] = rdp.fog_color.g / 255.0f;
buf_vbo[buf_vbo_len++] = rdp.fog_color.b / 255.0f;
buf_vbo[buf_vbo_len++] = v_arr[i]->color.a / 255.0f; // fog factor (not alpha)
}
for (int j = 0; j < num_inputs; j++) {
struct RGBA *color;
struct RGBA tmp;
for (int k = 0; k < 1 + (use_alpha ? 1 : 0); k++) {
switch (comb->shader_input_mapping[k][j]) {
case CC_PRIM:
color = &rdp.prim_color;
break;
case CC_SHADE:
color = &v_arr[i]->color;
break;
case CC_ENV:
color = &rdp.env_color;
break;
case CC_LOD:
{
float distance_frac = (v1->w - 3000.0f) / 3000.0f;
if (distance_frac < 0.0f) distance_frac = 0.0f;
if (distance_frac > 1.0f) distance_frac = 1.0f;
tmp.r = tmp.g = tmp.b = tmp.a = distance_frac * 255.0f;
color = &tmp;
break;
}
default:
memset(&tmp, 0, sizeof(tmp));
color = &tmp;
break;
}
if (k == 0) {
buf_vbo[buf_vbo_len++] = color->r / 255.0f;
buf_vbo[buf_vbo_len++] = color->g / 255.0f;
buf_vbo[buf_vbo_len++] = color->b / 255.0f;
} else {
if (use_fog && color == &v_arr[i]->color) {
// Shade alpha is 100% for fog
buf_vbo[buf_vbo_len++] = 1.0f;
} else {
buf_vbo[buf_vbo_len++] = color->a / 255.0f;
}
}
}
}
/*struct RGBA *color = &v_arr[i]->color;
buf_vbo[buf_vbo_len++] = color->r / 255.0f;
buf_vbo[buf_vbo_len++] = color->g / 255.0f;
buf_vbo[buf_vbo_len++] = color->b / 255.0f;
buf_vbo[buf_vbo_len++] = color->a / 255.0f;*/
}
if (++buf_vbo_num_tris == MAX_BUFFERED) {
gfx_flush();
}
}
static void gfx_sp_geometry_mode(uint32_t clear, uint32_t set) {
rsp.geometry_mode &= ~clear;
rsp.geometry_mode |= set;
}
static void gfx_calc_and_set_viewport(const Vp_t *viewport) {
// 2 bits fraction
float width = 2.0f * viewport->vscale[0] / 4.0f;
float height = 2.0f * viewport->vscale[1] / 4.0f;
float x = (viewport->vtrans[0] / 4.0f) - width / 2.0f;
float y = SCREEN_HEIGHT - ((viewport->vtrans[1] / 4.0f) + height / 2.0f);
width *= RATIO_X;
height *= RATIO_Y;
x *= RATIO_X;
y *= RATIO_Y;
rdp.viewport.x = x;
rdp.viewport.y = y;
rdp.viewport.width = width;
rdp.viewport.height = height;
rdp.viewport_or_scissor_changed = true;
}
static void gfx_sp_movemem(uint8_t index, uint8_t offset, const void* data) {
switch (index) {
case G_MV_VIEWPORT:
gfx_calc_and_set_viewport((const Vp_t *) data);
break;
#if 0
case G_MV_LOOKATY:
case G_MV_LOOKATX:
memcpy(rsp.current_lookat + (index - G_MV_LOOKATY) / 2, data, sizeof(Light_t));
//rsp.lights_changed = 1;
break;
#endif
#ifdef F3DEX_GBI_2
case G_MV_LIGHT: {
int lightidx = offset / 24 - 2;
if (lightidx >= 0 && lightidx <= MAX_LIGHTS) { // skip lookat
// NOTE: reads out of bounds if it is an ambient light
memcpy(rsp.current_lights + lightidx, data, sizeof(Light_t));
}
break;
}
#else
case G_MV_L0:
case G_MV_L1:
case G_MV_L2:
// NOTE: reads out of bounds if it is an ambient light
memcpy(rsp.current_lights + (index - G_MV_L0) / 2, data, sizeof(Light_t));
break;
#endif
}
}
static void gfx_sp_moveword(uint8_t index, uint16_t offset, uint32_t data) {
switch (index) {
case G_MW_NUMLIGHT:
#ifdef F3DEX_GBI_2
rsp.current_num_lights = data / 24 + 1; // add ambient light
#else
// Ambient light is included
// The 31th bit is a flag that lights should be recalculated
rsp.current_num_lights = (data - 0x80000000U) / 32;
#endif
rsp.lights_changed = 1;
break;
case G_MW_FOG:
rsp.fog_mul = (int16_t)(data >> 16);
rsp.fog_offset = (int16_t)data;
break;