Subversion Repository Public Repository

Divide-Dependencies

This repository has no backups
This repository's network speed is throttled to 100KB/sec

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
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
//  * Redistributions of source code must retain the above copyright
//    notice, this list of conditions and the following disclaimer.
//  * Redistributions in binary form must reproduce the above copyright
//    notice, this list of conditions and the following disclaimer in the
//    documentation and/or other materials provided with the distribution.
//  * Neither the name of NVIDIA CORPORATION nor the names of its
//    contributors may be used to endorse or promote products derived
//    from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Copyright (c) 2018 NVIDIA Corporation. All rights reserved.


// Copyright (c) 2004-2008 AGEIA Technologies, Inc. All rights reserved.
// Copyright (c) 2001-2004 NovodeX AG. All rights reserved.

#pragma once

// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
// factory implementation
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

template <>
inline Simd4iFactory<const int&>::operator Simd4i() const
{
	return vdupq_n_s32(v);
}

inline Simd4iFactory<detail::FourTuple>::operator Simd4i() const
{
	return reinterpret_cast<const Simd4i&>(v);
}

template <int i>
inline Simd4iFactory<detail::IntType<i> >::operator Simd4i() const
{
	return vdupq_n_u32(i);
}

template <>
inline Simd4iFactory<const int*>::operator Simd4i() const
{
	return vld1q_s32(v);
}

template <>
inline Simd4iFactory<detail::AlignedPointer<int> >::operator Simd4i() const
{
	return vld1q_s32(v.ptr);
}

template <>
inline Simd4iFactory<detail::OffsetPointer<int> >::operator Simd4i() const
{
	return vld1q_s32(reinterpret_cast<const int*>(reinterpret_cast<const char*>(v.ptr) + v.offset));
}

// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
// expression template
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

template <>
inline ComplementExpr<Simd4i>::operator Simd4i() const
{
	return vbicq_u32(vdupq_n_u32(0xffffffff), v.u4);
}

Simd4i operator&(const ComplementExpr<Simd4i>& complement, const Simd4i& v)
{
	return vbicq_u32(v.u4, complement.v.u4);
}

Simd4i operator&(const Simd4i& v, const ComplementExpr<Simd4i>& complement)
{
	return vbicq_u32(v.u4, complement.v.u4);
}

// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
// operator implementations
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Simd4i simdi::operator==(const Simd4i& v0, const Simd4i& v1)
{
	return vceqq_u32(v0.u4, v1.u4);
}

Simd4i simdi::operator<(const Simd4i& v0, const Simd4i& v1)
{
	return vcltq_s32(v0.i4, v1.i4);
}

Simd4i simdi::operator>(const Simd4i& v0, const Simd4i& v1)
{
	return vcgtq_s32(v0.i4, v1.i4);
}

ComplementExpr<Simd4i> operator~(const Simd4i& v)
{
	return ComplementExpr<Simd4i>(v);
}

Simd4i operator&(const Simd4i& v0, const Simd4i& v1)
{
	return vandq_u32(v0.u4, v1.u4);
}

Simd4i operator|(const Simd4i& v0, const Simd4i& v1)
{
	return vorrq_u32(v0.u4, v1.u4);
}

Simd4i operator^(const Simd4i& v0, const Simd4i& v1)
{
	return veorq_u32(v0.u4, v1.u4);
}

Simd4i operator<<(const Simd4i& v, int shift)
{
	return vshlq_u32(v.u4, vdupq_n_s32(shift));
}

Simd4i operator>>(const Simd4i& v, int shift)
{
	return vshlq_u32(v.u4, vdupq_n_s32(-shift));
}

Simd4i operator<<(const Simd4i& v, const Simd4i& shift)
{
	return vshlq_u32(v.u4, shift.i4);
}

Simd4i operator>>(const Simd4i& v, const Simd4i& shift)
{
	return vshlq_u32(v.u4, vnegq_s32(shift.i4));
}

Simd4i simdi::operator+(const Simd4i& v0, const Simd4i& v1)
{
	return vaddq_u32(v0.u4, v1.u4);
}

Simd4i simdi::operator-(const Simd4i& v)
{
	return vnegq_s32(v.i4);
}

Simd4i simdi::operator-(const Simd4i& v0, const Simd4i& v1)
{
	return vsubq_u32(v0.u4, v1.u4);
}

// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
// function implementations
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Simd4i simd4i(const Simd4f& v)
{
	return v.u4;
}

int (&simdi::array(Simd4i& v))[4]
{
	return (int(&)[4])v;
}

const int (&simdi::array(const Simd4i& v))[4]
{
	return (const int(&)[4])v;
}

void store(int* ptr, const Simd4i& v)
{
	return vst1q_s32(ptr, v.i4);
}

void storeAligned(int* ptr, const Simd4i& v)
{
	vst1q_s32(ptr, v.i4);
}

void storeAligned(int* ptr, unsigned int offset, const Simd4i& v)
{
	return storeAligned(reinterpret_cast<int*>(reinterpret_cast<char*>(ptr) + offset), v);
}

template <size_t i>
Simd4i splat(Simd4i const& v)
{
	return vdupq_n_s32(simdi::array(v)[i]);
}

Simd4i select(Simd4i const& mask, Simd4i const& v0, Simd4i const& v1)
{
	return vbslq_u32(mask.u4, v0.u4, v1.u4);
}

int simdi::allEqual(const Simd4i& v0, const Simd4i& v1)
{
	return allTrue(simdi::operator==(v0, v1));
}

int simdi::allEqual(const Simd4i& v0, const Simd4i& v1, Simd4i& outMask)
{
	return allTrue(outMask = simdi::operator==(v0, v1));
}

int simdi::anyEqual(const Simd4i& v0, const Simd4i& v1)
{
	return anyTrue(simdi::operator==(v0, v1));
}

int simdi::anyEqual(const Simd4i& v0, const Simd4i& v1, Simd4i& outMask)
{
	return anyTrue(outMask = simdi::operator==(v0, v1));
}

int simdi::allGreater(const Simd4i& v0, const Simd4i& v1)
{
	return allTrue(simdi::operator>(v0, v1));
}

int simdi::allGreater(const Simd4i& v0, const Simd4i& v1, Simd4i& outMask)
{
	return allTrue(outMask = simdi::operator>(v0, v1));
}

int simdi::anyGreater(const Simd4i& v0, const Simd4i& v1)
{
	return anyTrue(simdi::operator>(v0, v1));
}

int simdi::anyGreater(const Simd4i& v0, const Simd4i& v1, Simd4i& outMask)
{
	return anyTrue(outMask = simdi::operator>(v0, v1));
}

int allTrue(const Simd4i& v)
{
#if NVMATH_INLINE_ASSEMBLER
	int result;
	asm volatile("vmovq q0, %q1 \n\t"
	             "vand.u32 d0, d0, d1 \n\t"
	             "vpmin.u32 d0, d0, d0 \n\t"
	             "vcmp.f32 s0, #0 \n\t"
	             "fmrx %0, fpscr"
	             : "=r"(result)
	             : "w"(v.u4)
	             : "q0");
	return result >> 28 & 0x1;
#else
	uint16x4_t hi = vget_high_u16(vreinterpretq_u16_u32(v.u4));
	uint16x4_t lo = vmovn_u32(v.u4);
	uint16x8_t combined = vcombine_u16(lo, hi);
	uint32x2_t reduced = vreinterpret_u32_u8(vmovn_u16(combined));
	return vget_lane_u32(reduced, 0) == 0xffffffff;
#endif
}

int anyTrue(const Simd4i& v)
{
#if NVMATH_INLINE_ASSEMBLER
	int result;
	asm volatile("vmovq q0, %q1 \n\t"
	             "vorr.u32 d0, d0, d1 \n\t"
	             "vpmax.u32 d0, d0, d0 \n\t"
	             "vcmp.f32 s0, #0 \n\t"
	             "fmrx %0, fpscr"
	             : "=r"(result)
	             : "w"(v.u4)
	             : "q0");
	return result >> 28 & 0x1;
#else
	uint16x4_t hi = vget_high_u16(vreinterpretq_u16_u32(v.u4));
	uint16x4_t lo = vmovn_u32(v.u4);
	uint16x8_t combined = vcombine_u16(lo, hi);
	uint32x2_t reduced = vreinterpret_u32_u8(vmovn_u16(combined));
	return vget_lane_u32(reduced, 0) != 0x0;
#endif
}

Commits for Divide-Dependencies/physx/APEX_1.4/module/clothing/embedded/LowLevelCloth/src/neon/Simd4i.h

Diff revisions: vs.
Revision Author Commited Message
105 IonutCava picture IonutCava Tue 16 Apr, 2019 19:55:41 +0000

Forgot to actually add physx