summaryrefslogtreecommitdiffstats
path: root/libs/rs/scriptc/rs_core.rsh
blob: 85f3b2529edeb0c24f2cc6bb7b135fa938016871 (plain)
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
#ifndef __RS_CORE_RSH__
#define __RS_CORE_RSH__

static void __attribute__((overloadable)) rsDebug(const char *s, float2 v) {
    rsDebug(s, v.x, v.y);
}
static void __attribute__((overloadable)) rsDebug(const char *s, float3 v) {
    rsDebug(s, v.x, v.y, v.z);
}
static void __attribute__((overloadable)) rsDebug(const char *s, float4 v) {
    rsDebug(s, v.x, v.y, v.z, v.w);
}

static uchar4 __attribute__((overloadable)) rsPackColorTo8888(float r, float g, float b)
{
    uchar4 c;
    c.x = (uchar)(r * 255.f);
    c.y = (uchar)(g * 255.f);
    c.z = (uchar)(b * 255.f);
    c.w = 255;
    return c;
}

static uchar4 __attribute__((overloadable)) rsPackColorTo8888(float r, float g, float b, float a)
{
    uchar4 c;
    c.x = (uchar)(r * 255.f);
    c.y = (uchar)(g * 255.f);
    c.z = (uchar)(b * 255.f);
    c.w = (uchar)(a * 255.f);
    return c;
}

static uchar4 __attribute__((overloadable)) rsPackColorTo8888(float3 color)
{
    color *= 255.f;
    uchar4 c = {color.x, color.y, color.z, 255};
    return c;
}

static uchar4 __attribute__((overloadable)) rsPackColorTo8888(float4 color)
{
    color *= 255.f;
    uchar4 c = {color.x, color.y, color.z, color.w};
    return c;
}

static float4 rsUnpackColor8888(uchar4 c)
{
    float4 ret = (float4)0.0039156862745f;
    ret *= convert_float4(c);
    return ret;
}

//extern uchar4 __attribute__((overloadable)) rsPackColorTo565(float r, float g, float b);
//extern uchar4 __attribute__((overloadable)) rsPackColorTo565(float3);
//extern float4 rsUnpackColor565(uchar4);


/////////////////////////////////////////////////////
// Matrix ops
/////////////////////////////////////////////////////

static void __attribute__((overloadable))
rsMatrixSet(rs_matrix4x4 *m, uint32_t row, uint32_t col, float v) {
    m->m[row * 4 + col] = v;
}

static float __attribute__((overloadable))
rsMatrixGet(const rs_matrix4x4 *m, uint32_t row, uint32_t col) {
    return m->m[row * 4 + col];
}

static void __attribute__((overloadable))
rsMatrixSet(rs_matrix3x3 *m, uint32_t row, uint32_t col, float v) {
    m->m[row * 3 + col] = v;
}

static float __attribute__((overloadable))
rsMatrixGet(const rs_matrix3x3 *m, uint32_t row, uint32_t col) {
    return m->m[row * 3 + col];
}

static void __attribute__((overloadable))
rsMatrixSet(rs_matrix2x2 *m, uint32_t row, uint32_t col, float v) {
    m->m[row * 2 + col] = v;
}

static float __attribute__((overloadable))
rsMatrixGet(const rs_matrix2x2 *m, uint32_t row, uint32_t col) {
    return m->m[row * 2 + col];
}

static void __attribute__((overloadable))
rsMatrixLoadIdentity(rs_matrix4x4 *m) {
    m->m[0] = 1.f;
    m->m[1] = 0.f;
    m->m[2] = 0.f;
    m->m[3] = 0.f;
    m->m[4] = 0.f;
    m->m[5] = 1.f;
    m->m[6] = 0.f;
    m->m[7] = 0.f;
    m->m[8] = 0.f;
    m->m[9] = 0.f;
    m->m[10] = 1.f;
    m->m[11] = 0.f;
    m->m[12] = 0.f;
    m->m[13] = 0.f;
    m->m[14] = 0.f;
    m->m[15] = 1.f;
}

static void __attribute__((overloadable))
rsMatrixLoadIdentity(rs_matrix3x3 *m) {
    m->m[0] = 1.f;
    m->m[1] = 0.f;
    m->m[2] = 0.f;
    m->m[3] = 0.f;
    m->m[4] = 1.f;
    m->m[5] = 0.f;
    m->m[6] = 0.f;
    m->m[7] = 0.f;
    m->m[8] = 1.f;
}

static void __attribute__((overloadable))
rsMatrixLoadIdentity(rs_matrix2x2 *m) {
    m->m[0] = 1.f;
    m->m[1] = 0.f;
    m->m[2] = 0.f;
    m->m[3] = 1.f;
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix4x4 *m, const float *v) {
    m->m[0] = v[0];
    m->m[1] = v[1];
    m->m[2] = v[2];
    m->m[3] = v[3];
    m->m[4] = v[4];
    m->m[5] = v[5];
    m->m[6] = v[6];
    m->m[7] = v[7];
    m->m[8] = v[8];
    m->m[9] = v[9];
    m->m[10] = v[10];
    m->m[11] = v[11];
    m->m[12] = v[12];
    m->m[13] = v[13];
    m->m[14] = v[14];
    m->m[15] = v[15];
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix3x3 *m, const float *v) {
    m->m[0] = v[0];
    m->m[1] = v[1];
    m->m[2] = v[2];
    m->m[3] = v[3];
    m->m[4] = v[4];
    m->m[5] = v[5];
    m->m[6] = v[6];
    m->m[7] = v[7];
    m->m[8] = v[8];
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix2x2 *m, const float *v) {
    m->m[0] = v[0];
    m->m[1] = v[1];
    m->m[2] = v[2];
    m->m[3] = v[3];
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix4x4 *m, const rs_matrix4x4 *v) {
    m->m[0] = v->m[0];
    m->m[1] = v->m[1];
    m->m[2] = v->m[2];
    m->m[3] = v->m[3];
    m->m[4] = v->m[4];
    m->m[5] = v->m[5];
    m->m[6] = v->m[6];
    m->m[7] = v->m[7];
    m->m[8] = v->m[8];
    m->m[9] = v->m[9];
    m->m[10] = v->m[10];
    m->m[11] = v->m[11];
    m->m[12] = v->m[12];
    m->m[13] = v->m[13];
    m->m[14] = v->m[14];
    m->m[15] = v->m[15];
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix4x4 *m, const rs_matrix3x3 *v) {
    m->m[0] = v->m[0];
    m->m[1] = v->m[1];
    m->m[2] = v->m[2];
    m->m[3] = 0.f;
    m->m[4] = v->m[3];
    m->m[5] = v->m[4];
    m->m[6] = v->m[5];
    m->m[7] = 0.f;
    m->m[8] = v->m[6];
    m->m[9] = v->m[7];
    m->m[10] = v->m[8];
    m->m[11] = 0.f;
    m->m[12] = 0.f;
    m->m[13] = 0.f;
    m->m[14] = 0.f;
    m->m[15] = 1.f;
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix4x4 *m, const rs_matrix2x2 *v) {
    m->m[0] = v->m[0];
    m->m[1] = v->m[1];
    m->m[2] = 0.f;
    m->m[3] = 0.f;
    m->m[4] = v->m[3];
    m->m[5] = v->m[4];
    m->m[6] = 0.f;
    m->m[7] = 0.f;
    m->m[8] = v->m[6];
    m->m[9] = v->m[7];
    m->m[10] = 1.f;
    m->m[11] = 0.f;
    m->m[12] = 0.f;
    m->m[13] = 0.f;
    m->m[14] = 0.f;
    m->m[15] = 1.f;
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix3x3 *m, const rs_matrix3x3 *v) {
    m->m[0] = v->m[0];
    m->m[1] = v->m[1];
    m->m[2] = v->m[2];
    m->m[3] = v->m[3];
    m->m[4] = v->m[4];
    m->m[5] = v->m[5];
    m->m[6] = v->m[6];
    m->m[7] = v->m[7];
    m->m[8] = v->m[8];
}

static void __attribute__((overloadable))
rsMatrixLoad(rs_matrix2x2 *m, const rs_matrix2x2 *v) {
    m->m[0] = v->m[0];
    m->m[1] = v->m[1];
    m->m[2] = v->m[2];
    m->m[3] = v->m[3];
}

static void __attribute__((overloadable))
rsMatrixLoadRotate(rs_matrix4x4 *m, float rot, float x, float y, float z) {
    float c, s;
    m->m[3] = 0;
    m->m[7] = 0;
    m->m[11]= 0;
    m->m[12]= 0;
    m->m[13]= 0;
    m->m[14]= 0;
    m->m[15]= 1;
    rot *= (float)(M_PI / 180.0f);
    c = cos(rot);
    s = sin(rot);

    const float len = x*x + y*y + z*z;
    if (len != 1) {
        const float recipLen = 1.f / sqrt(len);
        x *= recipLen;
        y *= recipLen;
        z *= recipLen;
    }
    const float nc = 1.0f - c;
    const float xy = x * y;
    const float yz = y * z;
    const float zx = z * x;
    const float xs = x * s;
    const float ys = y * s;
    const float zs = z * s;
    m->m[ 0] = x*x*nc +  c;
    m->m[ 4] =  xy*nc - zs;
    m->m[ 8] =  zx*nc + ys;
    m->m[ 1] =  xy*nc + zs;
    m->m[ 5] = y*y*nc +  c;
    m->m[ 9] =  yz*nc - xs;
    m->m[ 2] =  zx*nc - ys;
    m->m[ 6] =  yz*nc + xs;
    m->m[10] = z*z*nc +  c;
}

static void __attribute__((overloadable))
rsMatrixLoadScale(rs_matrix4x4 *m, float x, float y, float z) {
    rsMatrixLoadIdentity(m);
    m->m[0] = x;
    m->m[5] = y;
    m->m[10] = z;
}

static void __attribute__((overloadable))
rsMatrixLoadTranslate(rs_matrix4x4 *m, float x, float y, float z) {
    rsMatrixLoadIdentity(m);
    m->m[12] = x;
    m->m[13] = y;
    m->m[14] = z;
}

static void __attribute__((overloadable))
rsMatrixLoadMultiply(rs_matrix4x4 *m, const rs_matrix4x4 *lhs, const rs_matrix4x4 *rhs) {
    for (int i=0 ; i<4 ; i++) {
        float ri0 = 0;
        float ri1 = 0;
        float ri2 = 0;
        float ri3 = 0;
        for (int j=0 ; j<4 ; j++) {
            const float rhs_ij = rsMatrixGet(rhs, i,j);
            ri0 += rsMatrixGet(lhs, j, 0) * rhs_ij;
            ri1 += rsMatrixGet(lhs, j, 1) * rhs_ij;
            ri2 += rsMatrixGet(lhs, j, 2) * rhs_ij;
            ri3 += rsMatrixGet(lhs, j, 3) * rhs_ij;
        }
        rsMatrixSet(m, i, 0, ri0);
        rsMatrixSet(m, i, 1, ri1);
        rsMatrixSet(m, i, 2, ri2);
        rsMatrixSet(m, i, 3, ri3);
    }
}

static void __attribute__((overloadable))
rsMatrixMultiply(rs_matrix4x4 *m, const rs_matrix4x4 *rhs) {
    rs_matrix4x4 mt;
    rsMatrixLoadMultiply(&mt, m, rhs);
    rsMatrixLoad(m, &mt);
}

static void __attribute__((overloadable))
rsMatrixLoadMultiply(rs_matrix3x3 *m, const rs_matrix3x3 *lhs, const rs_matrix3x3 *rhs) {
    for (int i=0 ; i<3 ; i++) {
        float ri0 = 0;
        float ri1 = 0;
        float ri2 = 0;
        for (int j=0 ; j<3 ; j++) {
            const float rhs_ij = rsMatrixGet(rhs, i,j);
            ri0 += rsMatrixGet(lhs, j, 0) * rhs_ij;
            ri1 += rsMatrixGet(lhs, j, 1) * rhs_ij;
            ri2 += rsMatrixGet(lhs, j, 2) * rhs_ij;
        }
        rsMatrixSet(m, i, 0, ri0);
        rsMatrixSet(m, i, 1, ri1);
        rsMatrixSet(m, i, 2, ri2);
    }
}

static void __attribute__((overloadable))
rsMatrixMultiply(rs_matrix3x3 *m, const rs_matrix3x3 *rhs) {
    rs_matrix3x3 mt;
    rsMatrixLoadMultiply(&mt, m, rhs);
    rsMatrixLoad(m, &mt);
}

static void __attribute__((overloadable))
rsMatrixLoadMultiply(rs_matrix2x2 *m, const rs_matrix2x2 *lhs, const rs_matrix2x2 *rhs) {
    for (int i=0 ; i<2 ; i++) {
        float ri0 = 0;
        float ri1 = 0;
        for (int j=0 ; j<2 ; j++) {
            const float rhs_ij = rsMatrixGet(rhs, i,j);
            ri0 += rsMatrixGet(lhs, j, 0) * rhs_ij;
            ri1 += rsMatrixGet(lhs, j, 1) * rhs_ij;
        }
        rsMatrixSet(m, i, 0, ri0);
        rsMatrixSet(m, i, 1, ri1);
    }
}

static void __attribute__((overloadable))
rsMatrixMultiply(rs_matrix2x2 *m, const rs_matrix2x2 *rhs) {
    rs_matrix2x2 mt;
    rsMatrixLoadMultiply(&mt, m, rhs);
    rsMatrixLoad(m, &mt);
}

static void __attribute__((overloadable))
rsMatrixRotate(rs_matrix4x4 *m, float rot, float x, float y, float z) {
    rs_matrix4x4 m1;
    rsMatrixLoadRotate(&m1, rot, x, y, z);
    rsMatrixMultiply(m, &m1);
}

static void __attribute__((overloadable))
rsMatrixScale(rs_matrix4x4 *m, float x, float y, float z) {
    rs_matrix4x4 m1;
    rsMatrixLoadScale(&m1, x, y, z);
    rsMatrixMultiply(m, &m1);
}

static void __attribute__((overloadable))
rsMatrixTranslate(rs_matrix4x4 *m, float x, float y, float z) {
    rs_matrix4x4 m1;
    rsMatrixLoadTranslate(&m1, x, y, z);
    rsMatrixMultiply(m, &m1);
}

static void __attribute__((overloadable))
rsMatrixLoadOrtho(rs_matrix4x4 *m, float left, float right, float bottom, float top, float near, float far) {
    rsMatrixLoadIdentity(m);
    m->m[0] = 2.f / (right - left);
    m->m[5] = 2.f / (top - bottom);
    m->m[10]= -2.f / (far - near);
    m->m[12]= -(right + left) / (right - left);
    m->m[13]= -(top + bottom) / (top - bottom);
    m->m[14]= -(far + near) / (far - near);
}

static void __attribute__((overloadable))
rsMatrixLoadFrustum(rs_matrix4x4 *m, float left, float right, float bottom, float top, float near, float far) {
    rsMatrixLoadIdentity(m);
    m->m[0] = 2.f * near / (right - left);
    m->m[5] = 2.f * near / (top - bottom);
    m->m[8] = (right + left) / (right - left);
    m->m[9] = (top + bottom) / (top - bottom);
    m->m[10]= -(far + near) / (far - near);
    m->m[11]= -1.f;
    m->m[14]= -2.f * far * near / (far - near);
    m->m[15]= 0.f;
}

static float4 __attribute__((overloadable))
rsMatrixMultiply(rs_matrix4x4 *m, float4 in) {
    float4 ret;
    ret.x = (m->m[0] * in.x) + (m->m[4] * in.y) + (m->m[8] * in.z) + (m->m[12] * in.w);
    ret.y = (m->m[1] * in.x) + (m->m[5] * in.y) + (m->m[9] * in.z) + (m->m[13] * in.w);
    ret.z = (m->m[2] * in.x) + (m->m[6] * in.y) + (m->m[10] * in.z) + (m->m[14] * in.w);
    ret.w = (m->m[3] * in.x) + (m->m[7] * in.y) + (m->m[11] * in.z) + (m->m[15] * in.w);
    return ret;
}

static float4 __attribute__((overloadable))
rsMatrixMultiply(rs_matrix4x4 *m, float3 in) {
    float4 ret;
    ret.x = (m->m[0] * in.x) + (m->m[4] * in.y) + (m->m[8] * in.z) + m->m[12];
    ret.y = (m->m[1] * in.x) + (m->m[5] * in.y) + (m->m[9] * in.z) + m->m[13];
    ret.z = (m->m[2] * in.x) + (m->m[6] * in.y) + (m->m[10] * in.z) + m->m[14];
    ret.w = (m->m[3] * in.x) + (m->m[7] * in.y) + (m->m[11] * in.z) + m->m[15];
    return ret;
}

static float4 __attribute__((overloadable))
rsMatrixMultiply(rs_matrix4x4 *m, float2 in) {
    float4 ret;
    ret.x = (m->m[0] * in.x) + (m->m[4] * in.y) + m->m[12];
    ret.y = (m->m[1] * in.x) + (m->m[5] * in.y) + m->m[13];
    ret.z = (m->m[2] * in.x) + (m->m[6] * in.y) + m->m[14];
    ret.w = (m->m[3] * in.x) + (m->m[7] * in.y) + m->m[15];
    return ret;
}

static float3 __attribute__((overloadable))
rsMatrixMultiply(rs_matrix3x3 *m, float3 in) {
    float3 ret;
    ret.x = (m->m[0] * in.x) + (m->m[3] * in.y) + (m->m[6] * in.z);
    ret.y = (m->m[1] * in.x) + (m->m[4] * in.y) + (m->m[7] * in.z);
    ret.z = (m->m[2] * in.x) + (m->m[5] * in.y) + (m->m[8] * in.z);
    return ret;
}

static float3 __attribute__((overloadable))
rsMatrixMultiply(rs_matrix3x3 *m, float2 in) {
    float3 ret;
    ret.x = (m->m[0] * in.x) + (m->m[3] * in.y);
    ret.y = (m->m[1] * in.x) + (m->m[4] * in.y);
    ret.z = (m->m[2] * in.x) + (m->m[5] * in.y);
    return ret;
}

static float2 __attribute__((overloadable))
rsMatrixMultiply(rs_matrix2x2 *m, float2 in) {
    float2 ret;
    ret.x = (m->m[0] * in.x) + (m->m[2] * in.y);
    ret.y = (m->m[1] * in.x) + (m->m[3] * in.y);
    return ret;
}

// Returns true if the matrix was successfully inversed
static bool __attribute__((overloadable))
rsMatrixInverse(rs_matrix4x4 *m) {
    rs_matrix4x4 result;

    int i, j;
    for (i = 0; i < 4; ++i) {
        for (j = 0; j < 4; ++j) {
            // computeCofactor for int i, int j
            int c0 = (i+1) % 4;
            int c1 = (i+2) % 4;
            int c2 = (i+3) % 4;
            int r0 = (j+1) % 4;
            int r1 = (j+2) % 4;
            int r2 = (j+3) % 4;

            float minor = (m->m[c0 + 4*r0] * (m->m[c1 + 4*r1] * m->m[c2 + 4*r2] - m->m[c1 + 4*r2] * m->m[c2 + 4*r1]))
                         - (m->m[c0 + 4*r1] * (m->m[c1 + 4*r0] * m->m[c2 + 4*r2] - m->m[c1 + 4*r2] * m->m[c2 + 4*r0]))
                         + (m->m[c0 + 4*r2] * (m->m[c1 + 4*r0] * m->m[c2 + 4*r1] - m->m[c1 + 4*r1] * m->m[c2 + 4*r0]));

            float cofactor = (i+j) & 1 ? -minor : minor;

            result.m[4*i + j] = cofactor;
        }
    }

    // Dot product of 0th column of source and 0th row of result
    float det = m->m[0]*result.m[0] + m->m[4]*result.m[1] +
                 m->m[8]*result.m[2] + m->m[12]*result.m[3];

    if (fabs(det) < 1e-6) {
        return false;
    }

    det = 1.0f / det;
    for (i = 0; i < 16; ++i) {
        m->m[i] = result.m[i] * det;
    }

    return true;
}

// Returns true if the matrix was successfully inversed
static bool __attribute__((overloadable))
rsMatrixInverseTranspose(rs_matrix4x4 *m) {
    rs_matrix4x4 result;

    int i, j;
    for (i = 0; i < 4; ++i) {
        for (j = 0; j < 4; ++j) {
            // computeCofactor for int i, int j
            int c0 = (i+1) % 4;
            int c1 = (i+2) % 4;
            int c2 = (i+3) % 4;
            int r0 = (j+1) % 4;
            int r1 = (j+2) % 4;
            int r2 = (j+3) % 4;

            float minor = (m->m[c0 + 4*r0] * (m->m[c1 + 4*r1] * m->m[c2 + 4*r2] - m->m[c1 + 4*r2] * m->m[c2 + 4*r1]))
                         - (m->m[c0 + 4*r1] * (m->m[c1 + 4*r0] * m->m[c2 + 4*r2] - m->m[c1 + 4*r2] * m->m[c2 + 4*r0]))
                         + (m->m[c0 + 4*r2] * (m->m[c1 + 4*r0] * m->m[c2 + 4*r1] - m->m[c1 + 4*r1] * m->m[c2 + 4*r0]));

            float cofactor = (i+j) & 1 ? -minor : minor;

            result.m[4*j + i] = cofactor;
        }
    }

    // Dot product of 0th column of source and 0th column of result
    float det = m->m[0]*result.m[0] + m->m[4]*result.m[4] +
                 m->m[8]*result.m[8] + m->m[12]*result.m[12];

    if (fabs(det) < 1e-6) {
        return false;
    }

    det = 1.0f / det;
    for (i = 0; i < 16; ++i) {
        m->m[i] = result.m[i] * det;
    }

    return true;
}

static void __attribute__((overloadable))
rsMatrixTranspose(rs_matrix4x4 *m) {
    int i, j;
    float temp;
    for (i = 0; i < 3; ++i) {
        for (j = i + 1; j < 4; ++j) {
            temp = m->m[i*4 + j];
            m->m[i*4 + j] = m->m[j*4 + i];
            m->m[j*4 + i] = temp;
        }
    }
}

static void __attribute__((overloadable))
rsMatrixTranspose(rs_matrix3x3 *m) {
    int i, j;
    float temp;
    for (i = 0; i < 2; ++i) {
        for (j = i + 1; j < 3; ++j) {
            temp = m->m[i*3 + j];
            m->m[i*3 + j] = m->m[j*4 + i];
            m->m[j*3 + i] = temp;
        }
    }
}

static void __attribute__((overloadable))
rsMatrixTranspose(rs_matrix2x2 *m) {
    float temp = m->m[1];
    m->m[1] = m->m[2];
    m->m[2] = temp;
}


/////////////////////////////////////////////////////
// int ops
/////////////////////////////////////////////////////

__inline__ static uint __attribute__((overloadable, always_inline)) rsClamp(uint amount, uint low, uint high) {
    return amount < low ? low : (amount > high ? high : amount);
}
__inline__ static int __attribute__((overloadable, always_inline)) rsClamp(int amount, int low, int high) {
    return amount < low ? low : (amount > high ? high : amount);
}
__inline__ static ushort __attribute__((overloadable, always_inline)) rsClamp(ushort amount, ushort low, ushort high) {
    return amount < low ? low : (amount > high ? high : amount);
}
__inline__ static short __attribute__((overloadable, always_inline)) rsClamp(short amount, short low, short high) {
    return amount < low ? low : (amount > high ? high : amount);
}
__inline__ static uchar __attribute__((overloadable, always_inline)) rsClamp(uchar amount, uchar low, uchar high) {
    return amount < low ? low : (amount > high ? high : amount);
}
__inline__ static char __attribute__((overloadable, always_inline)) rsClamp(char amount, char low, char high) {
    return amount < low ? low : (amount > high ? high : amount);
}



#endif