summaryrefslogblamecommitdiffstats
path: root/external/include/glm/gtx/simd_vec4.hpp
blob: cde540bb840e7dd3588ded85ba1c146845cd040c (plain) (tree)
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

































































































































































































































































































































































































































































































































































                                                                                                                                                                   
/// @ref gtx_simd_vec4
/// @file glm/gtx/simd_vec4.hpp
///
/// @see core (dependence)
///
/// @defgroup gtx_simd_vec4 GLM_GTX_simd_vec4
/// @ingroup gtx
///
/// @brief SIMD implementation of vec4 type.
///
/// <glm/gtx/simd_vec4.hpp> need to be included to use these functionalities.

#pragma once

// Dependency:
#include "../glm.hpp"

#if(GLM_ARCH != GLM_ARCH_PURE)

#if(GLM_ARCH & GLM_ARCH_SSE2_BIT)
#	include "../detail/intrinsic_common.hpp"
#	include "../detail/intrinsic_geometric.hpp"
#	include "../detail/intrinsic_integer.hpp"
#else
#	error "GLM: GLM_GTX_simd_vec4 requires compiler support of SSE2 through intrinsics"
#endif

#if GLM_MESSAGES == GLM_MESSAGES_ENABLED && !defined(GLM_EXT_INCLUDED)
#	pragma message("GLM: GLM_GTX_simd_vec4 extension included")
#	pragma message("GLM: GLM_GTX_simd_vec4 extension is deprecated and will be removed in GLM 0.9.9. Use *vec4 types instead and use compiler SIMD arguments.")
#endif


// Warning silencer for nameless struct/union.
#if (GLM_COMPILER & GLM_COMPILER_VC)
#	pragma warning(push)
#	pragma warning(disable:4201)   // warning C4201: nonstandard extension used : nameless struct/union
#endif

namespace glm
{
	enum comp
	{
		X = 0,
		R = 0,
		S = 0,
		Y = 1,
		G = 1,
		T = 1,
		Z = 2,
		B = 2,
		P = 2,
		W = 3,
		A = 3,
		Q = 3
	};

}//namespace glm

namespace glm{
namespace detail
{
	/// 4-dimensional vector implemented using SIMD SEE intrinsics.
	/// \ingroup gtx_simd_vec4
	GLM_ALIGNED_STRUCT(16) fvec4SIMD
	{
		typedef float value_type;
		typedef std::size_t size_type;

		typedef fvec4SIMD type;
		typedef tvec4<float, defaultp> pure_type;
		typedef tvec4<bool, highp> bool_type;

#ifdef GLM_SIMD_ENABLE_XYZW_UNION
		union
		{
			__m128 Data;
			struct {float x, y, z, w;};
		};
#else
		__m128 Data;
#endif

		//////////////////////////////////////
		// Implicit basic constructors

		fvec4SIMD() GLM_DEFAULT_CTOR;
		fvec4SIMD(fvec4SIMD const & v) GLM_DEFAULT;
		fvec4SIMD(__m128 const & Data);

		//////////////////////////////////////
		// Explicit basic constructors

		explicit fvec4SIMD(
			ctor);
		explicit fvec4SIMD(
			float const & s);
		explicit fvec4SIMD(
			float const & x,
			float const & y,
			float const & z,
			float const & w);
		explicit fvec4SIMD(
			vec4 const & v);

		////////////////////////////////////////
		//// Conversion vector constructors

		fvec4SIMD(vec2 const & v, float const & s1, float const & s2);
		fvec4SIMD(float const & s1, vec2 const & v, float const & s2);
		fvec4SIMD(float const & s1, float const & s2, vec2 const & v);
		fvec4SIMD(vec3 const & v, float const & s);
		fvec4SIMD(float const & s, vec3 const & v);
		fvec4SIMD(vec2 const & v1, vec2 const & v2);
		//fvec4SIMD(ivec4SIMD const & v);

		//////////////////////////////////////
		// Unary arithmetic operators

		fvec4SIMD& operator= (fvec4SIMD const & v) GLM_DEFAULT;
		fvec4SIMD& operator+=(fvec4SIMD const & v);
		fvec4SIMD& operator-=(fvec4SIMD const & v);
		fvec4SIMD& operator*=(fvec4SIMD const & v);
		fvec4SIMD& operator/=(fvec4SIMD const & v);

		fvec4SIMD& operator+=(float const & s);
		fvec4SIMD& operator-=(float const & s);
		fvec4SIMD& operator*=(float const & s);
		fvec4SIMD& operator/=(float const & s);

		fvec4SIMD& operator++();
		fvec4SIMD& operator--();

		//////////////////////////////////////
		// Swizzle operators

		template <comp X_, comp Y_, comp Z_, comp W_>
		fvec4SIMD& swizzle();
		template <comp X_, comp Y_, comp Z_, comp W_>
		fvec4SIMD swizzle() const;
		template <comp X_, comp Y_, comp Z_>
		fvec4SIMD swizzle() const;
		template <comp X_, comp Y_>
		fvec4SIMD swizzle() const;
		template <comp X_>
		fvec4SIMD swizzle() const;
	};
}//namespace detail

	typedef glm::detail::fvec4SIMD simdVec4;

	/// @addtogroup gtx_simd_vec4
	/// @{

	//! Convert a simdVec4 to a vec4.
	/// @see gtx_simd_vec4
	vec4 vec4_cast(
		detail::fvec4SIMD const & x);

	//! Returns x if x >= 0; otherwise, it returns -x.
	/// @see gtx_simd_vec4
	detail::fvec4SIMD abs(detail::fvec4SIMD const & x);

	//! Returns 1.0 if x > 0, 0.0 if x = 0, or -1.0 if x < 0.
	/// @see gtx_simd_vec4
	detail::fvec4SIMD sign(detail::fvec4SIMD const & x);

	//! Returns a value equal to the nearest integer that is less then or equal to x.
	/// @see gtx_simd_vec4
	detail::fvec4SIMD floor(detail::fvec4SIMD const & x);

	//! Returns a value equal to the nearest integer to x
	//! whose absolute value is not larger than the absolute value of x.
	/// @see gtx_simd_vec4
	detail::fvec4SIMD trunc(detail::fvec4SIMD const & x);

	//! Returns a value equal to the nearest integer to x.
	//! The fraction 0.5 will round in a direction chosen by the
	//! implementation, presumably the direction that is fastest.
	//! This includes the possibility that round(x) returns the
	//! same value as roundEven(x) for all values of x.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD round(detail::fvec4SIMD const & x);

	//! Returns a value equal to the nearest integer to x.
	//! A fractional part of 0.5 will round toward the nearest even
	//! integer. (Both 3.5 and 4.5 for x will return 4.0.)
	///
	/// @see gtx_simd_vec4
	//detail::fvec4SIMD roundEven(detail::fvec4SIMD const & x);

	//! Returns a value equal to the nearest integer
	//! that is greater than or equal to x.
	/// @see gtx_simd_vec4
	detail::fvec4SIMD ceil(detail::fvec4SIMD const & x);

	//! Return x - floor(x).
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD fract(detail::fvec4SIMD const & x);

	//! Modulus. Returns x - y * floor(x / y)
	//! for each component in x using the floating point value y.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD mod(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y);

	//! Modulus. Returns x - y * floor(x / y)
	//! for each component in x using the floating point value y.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD mod(
		detail::fvec4SIMD const & x,
		float const & y);

	//! Returns the fractional part of x and sets i to the integer
	//! part (as a whole number floating point value). Both the
	//! return value and the output parameter will have the same
	//! sign as x.
	//! (From GLM_GTX_simd_vec4 extension, common function)
	//detail::fvec4SIMD modf(
	//	detail::fvec4SIMD const & x,
	//	detail::fvec4SIMD & i);

	//! Returns y if y < x; otherwise, it returns x.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD min(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y);

	detail::fvec4SIMD min(
		detail::fvec4SIMD const & x,
		float const & y);

	//! Returns y if x < y; otherwise, it returns x.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD max(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y);

	detail::fvec4SIMD max(
		detail::fvec4SIMD const & x,
		float const & y);

	//! Returns min(max(x, minVal), maxVal) for each component in x
	//! using the floating-point values minVal and maxVal.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD clamp(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & minVal,
		detail::fvec4SIMD const & maxVal);

	detail::fvec4SIMD clamp(
		detail::fvec4SIMD const & x,
		float const & minVal,
		float const & maxVal);

	//! \return If genTypeU is a floating scalar or vector:
	//! Returns x * (1.0 - a) + y * a, i.e., the linear blend of
	//! x and y using the floating-point value a.
	//! The value for a is not restricted to the range [0, 1].
	//!
	//! \return If genTypeU is a boolean scalar or vector:
	//! Selects which vector each returned component comes
	//! from. For a component of a that is false, the
	//! corresponding component of x is returned. For a
	//! component of a that is true, the corresponding
	//! component of y is returned. Components of x and y that
	//! are not selected are allowed to be invalid floating point
	//! values and will have no effect on the results. Thus, this
	//! provides different functionality than
	//! genType mix(genType x, genType y, genType(a))
	//! where a is a Boolean vector.
	//!
	//! From GLSL 1.30.08 specification, section 8.3
	//!
	//! \param[in]  x Floating point scalar or vector.
	//! \param[in]  y Floating point scalar or vector.
	//! \param[in]  a Floating point or boolean scalar or vector.
	//!
	/// \todo Test when 'a' is a boolean.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD mix(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y,
		detail::fvec4SIMD const & a);

	//! Returns 0.0 if x < edge, otherwise it returns 1.0.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD step(
		detail::fvec4SIMD const & edge,
		detail::fvec4SIMD const & x);

	detail::fvec4SIMD step(
		float const & edge,
		detail::fvec4SIMD const & x);

	//! Returns 0.0 if x <= edge0 and 1.0 if x >= edge1 and
	//! performs smooth Hermite interpolation between 0 and 1
	//! when edge0 < x < edge1. This is useful in cases where
	//! you would want a threshold function with a smooth
	//! transition. This is equivalent to:
	//! genType t;
	//! t = clamp ((x - edge0) / (edge1 - edge0), 0, 1);
	//! return t * t * (3 - 2 * t);
	//! Results are undefined if edge0 >= edge1.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD smoothstep(
		detail::fvec4SIMD const & edge0,
		detail::fvec4SIMD const & edge1,
		detail::fvec4SIMD const & x);

	detail::fvec4SIMD smoothstep(
		float const & edge0,
		float const & edge1,
		detail::fvec4SIMD const & x);

	//! Returns true if x holds a NaN (not a number)
	//! representation in the underlying implementation's set of
	//! floating point representations. Returns false otherwise,
	//! including for implementations with no NaN
	//! representations.
	///
	/// @see gtx_simd_vec4
	//bvec4 isnan(detail::fvec4SIMD const & x);

	//! Returns true if x holds a positive infinity or negative
	//! infinity representation in the underlying implementation's
	//! set of floating point representations. Returns false
	//! otherwise, including for implementations with no infinity
	//! representations.
	///
	/// @see gtx_simd_vec4
	//bvec4 isinf(detail::fvec4SIMD const & x);

	//! Returns a signed or unsigned integer value representing
	//! the encoding of a floating-point value. The floatingpoint
	//! value's bit-level representation is preserved.
	///
	/// @see gtx_simd_vec4
	//detail::ivec4SIMD floatBitsToInt(detail::fvec4SIMD const & value);

	//! Returns a floating-point value corresponding to a signed
	//! or unsigned integer encoding of a floating-point value.
	//! If an inf or NaN is passed in, it will not signal, and the
	//! resulting floating point value is unspecified. Otherwise,
	//! the bit-level representation is preserved.
	///
	/// @see gtx_simd_vec4
	//detail::fvec4SIMD intBitsToFloat(detail::ivec4SIMD const & value);

	//! Computes and returns a * b + c.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD fma(
		detail::fvec4SIMD const & a,
		detail::fvec4SIMD const & b,
		detail::fvec4SIMD const & c);

	//! Splits x into a floating-point significand in the range
	//! [0.5, 1.0) and an integral exponent of two, such that:
	//! x = significand * exp(2, exponent)
	//! The significand is returned by the function and the
	//! exponent is returned in the parameter exp. For a
	//! floating-point value of zero, the significant and exponent
	//! are both zero. For a floating-point value that is an
	//! infinity or is not a number, the results are undefined.
	///
	/// @see gtx_simd_vec4
	//detail::fvec4SIMD frexp(detail::fvec4SIMD const & x, detail::ivec4SIMD & exp);

	//! Builds a floating-point number from x and the
	//! corresponding integral exponent of two in exp, returning:
	//! significand * exp(2, exponent)
	//! If this product is too large to be represented in the
	//! floating-point type, the result is undefined.
	///
	/// @see gtx_simd_vec4
	//detail::fvec4SIMD ldexp(detail::fvec4SIMD const & x, detail::ivec4SIMD const & exp);

	//! Returns the length of x, i.e., sqrt(x * x).
	///
	/// @see gtx_simd_vec4
	float length(
		detail::fvec4SIMD const & x);

	//! Returns the length of x, i.e., sqrt(x * x).
	//! Less accurate but much faster than simdLength.
	///
	/// @see gtx_simd_vec4
	float fastLength(
		detail::fvec4SIMD const & x);

	//! Returns the length of x, i.e., sqrt(x * x).
	//! Slightly more accurate but much slower than simdLength.
	///
	/// @see gtx_simd_vec4
	float niceLength(
		detail::fvec4SIMD const & x);

	//! Returns the length of x, i.e., sqrt(x * x).
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD length4(
		detail::fvec4SIMD const & x);

	//! Returns the length of x, i.e., sqrt(x * x).
	//! Less accurate but much faster than simdLength4.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD fastLength4(
		detail::fvec4SIMD const & x);

	//! Returns the length of x, i.e., sqrt(x * x).
	//! Slightly more accurate but much slower than simdLength4.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD niceLength4(
		detail::fvec4SIMD const & x);

	//! Returns the distance betwwen p0 and p1, i.e., length(p0 - p1).
	///
	/// @see gtx_simd_vec4
	float distance(
		detail::fvec4SIMD const & p0,
		detail::fvec4SIMD const & p1);

	//! Returns the distance betwwen p0 and p1, i.e., length(p0 - p1).
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD distance4(
		detail::fvec4SIMD const & p0,
		detail::fvec4SIMD const & p1);

	//! Returns the dot product of x and y, i.e., result = x * y.
	///
	/// @see gtx_simd_vec4
	float simdDot(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y);

	//! Returns the dot product of x and y, i.e., result = x * y.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD dot4(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y);

	//! Returns the cross product of x and y.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD cross(
		detail::fvec4SIMD const & x,
		detail::fvec4SIMD const & y);

	//! Returns a vector in the same direction as x but with length of 1.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD normalize(
		detail::fvec4SIMD const & x);

	//! Returns a vector in the same direction as x but with length of 1.
	//! Less accurate but much faster than simdNormalize.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD fastNormalize(
		detail::fvec4SIMD const & x);

	//! If dot(Nref, I) < 0.0, return N, otherwise, return -N.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD simdFaceforward(
		detail::fvec4SIMD const & N,
		detail::fvec4SIMD const & I,
		detail::fvec4SIMD const & Nref);

	//! For the incident vector I and surface orientation N,
	//! returns the reflection direction : result = I - 2.0 * dot(N, I) * N.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD reflect(
		detail::fvec4SIMD const & I,
		detail::fvec4SIMD const & N);

	//! For the incident vector I and surface normal N,
	//! and the ratio of indices of refraction eta,
	//! return the refraction vector.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD refract(
		detail::fvec4SIMD const & I,
		detail::fvec4SIMD const & N,
		float const & eta);

	//! Returns the positive square root of x.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD sqrt(
		detail::fvec4SIMD const & x);

	//! Returns the positive square root of x with the nicest quality but very slow.
	//! Slightly more accurate but much slower than simdSqrt.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD niceSqrt(
		detail::fvec4SIMD const & x);

	//! Returns the positive square root of x
	//! Less accurate but much faster than sqrt.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD fastSqrt(
		detail::fvec4SIMD const & x);

	//! Returns the reciprocal of the positive square root of x.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD inversesqrt(
		detail::fvec4SIMD const & x);

	//! Returns the reciprocal of the positive square root of x.
	//! Faster than inversesqrt but less accurate.
	///
	/// @see gtx_simd_vec4
	detail::fvec4SIMD fastInversesqrt(
		detail::fvec4SIMD const & x);

	/// @}
}//namespace glm

#include "simd_vec4.inl"

#if (GLM_COMPILER & GLM_COMPILER_VC)
#	pragma warning(pop)
#endif

#endif//(GLM_ARCH != GLM_ARCH_PURE)