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
|
/* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy,
* modify, merge, publish, distribute, sublicense, and/or sell copies
* of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
* Copyright:
* 2020 Evan Nemerson <evan@nemerson.com>
* 2020 Sean Maher <seanptmaher@gmail.com> (Copyright owned by Google, LLC)
*/
#if !defined(SIMDE_ARM_NEON_CAGT_H)
#define SIMDE_ARM_NEON_CAGT_H
#include "types.h"
#include "abs.h"
#include "cgt.h"
HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_
SIMDE_FUNCTION_ATTRIBUTES
uint16_t
simde_vcagth_f16(simde_float16_t a, simde_float16_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && defined(SIMDE_ARM_NEON_FP16)
return vcagth_f16(a, b);
#else
simde_float32_t
af = simde_float16_to_float32(a),
bf = simde_float16_to_float32(b);
return (simde_math_fabsf(af) > simde_math_fabsf(bf)) ? UINT16_MAX : UINT16_C(0);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vcagth_f16
#define vcagth_f16(a, b) simde_vcagth_f16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
uint32_t
simde_vcagts_f32(simde_float32_t a, simde_float32_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vcagts_f32(a, b);
#else
return (simde_math_fabsf(a) > simde_math_fabsf(b)) ? ~UINT32_C(0) : UINT32_C(0);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vcagts_f32
#define vcagts_f32(a, b) simde_vcagts_f32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
uint64_t
simde_vcagtd_f64(simde_float64_t a, simde_float64_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vcagtd_f64(a, b);
#else
return (simde_math_fabs(a) > simde_math_fabs(b)) ? ~UINT64_C(0) : UINT64_C(0);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vcagtd_f64
#define vcagtd_f64(a, b) simde_vcagtd_f64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x4_t
simde_vcagt_f16(simde_float16x4_t a, simde_float16x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARM_NEON_FP16)
return vcagt_f16(a, b);
#else
simde_uint16x4_private r_;
simde_float16x4_private
a_ = simde_float16x4_to_private(a),
b_ = simde_float16x4_to_private(b);
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = simde_vcagth_f16(a_.values[i], b_.values[i]);
}
return simde_uint16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#undef vcagt_f16
#define vcagt_f16(a, b) simde_vcagt_f16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x2_t
simde_vcagt_f32(simde_float32x2_t a, simde_float32x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vcagt_f32(a, b);
#else
return simde_vcgt_f32(simde_vabs_f32(a), simde_vabs_f32(b));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vcagt_f32
#define vcagt_f32(a, b) simde_vcagt_f32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint64x1_t
simde_vcagt_f64(simde_float64x1_t a, simde_float64x1_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vcagt_f64(a, b);
#else
return simde_vcgt_f64(simde_vabs_f64(a), simde_vabs_f64(b));
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vcagt_f64
#define vcagt_f64(a, b) simde_vcagt_f64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x8_t
simde_vcagtq_f16(simde_float16x8_t a, simde_float16x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARM_NEON_FP16)
return vcagtq_f16(a, b);
#else
simde_uint16x8_private r_;
simde_float16x8_private
a_ = simde_float16x8_to_private(a),
b_ = simde_float16x8_to_private(b);
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = simde_vcagth_f16(a_.values[i], b_.values[i]);
}
return simde_uint16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#undef vcagtq_f16
#define vcagtq_f16(a, b) simde_vcagtq_f16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x4_t
simde_vcagtq_f32(simde_float32x4_t a, simde_float32x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vcagtq_f32(a, b);
#else
return simde_vcgtq_f32(simde_vabsq_f32(a), simde_vabsq_f32(b));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vcagtq_f32
#define vcagtq_f32(a, b) simde_vcagtq_f32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint64x2_t
simde_vcagtq_f64(simde_float64x2_t a, simde_float64x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vcagtq_f64(a, b);
#else
return simde_vcgtq_f64(simde_vabsq_f64(a), simde_vabsq_f64(b));
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vcagtq_f64
#define vcagtq_f64(a, b) simde_vcagtq_f64((a), (b))
#endif
SIMDE_END_DECLS_
HEDLEY_DIAGNOSTIC_POP
#endif /* !defined(SIMDE_ARM_NEON_CAGT_H) */
|
