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
|
/* 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:
* 2021 Evan Nemerson <evan@nemerson.com>
*/
#if !defined(SIMDE_ARM_NEON_SUBHN_H)
#define SIMDE_ARM_NEON_SUBHN_H
#include "sub.h"
#include "shr_n.h"
#include "movn.h"
#include "reinterpret.h"
HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_
SIMDE_FUNCTION_ATTRIBUTES
simde_int8x8_t
simde_vsubhn_s16(simde_int16x8_t a, simde_int16x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vsubhn_s16(a, b);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && HEDLEY_HAS_BUILTIN(__builtin_shufflevector)
simde_int8x8_private r_;
simde_int8x16_private tmp_ =
simde_int8x16_to_private(
simde_vreinterpretq_s8_s16(
simde_vsubq_s16(a, b)
)
);
#if SIMDE_ENDIAN_ORDER == SIMDE_ENDIAN_LITTLE
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 1, 3, 5, 7, 9, 11, 13, 15);
#else
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 0, 2, 4, 6, 8, 10, 12, 14);
#endif
return simde_int8x8_from_private(r_);
#else
return simde_vmovn_s16(simde_vshrq_n_s16(simde_vsubq_s16(a, b), 8));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vsubhn_s16
#define vsubhn_s16(a, b) simde_vsubhn_s16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int16x4_t
simde_vsubhn_s32(simde_int32x4_t a, simde_int32x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vsubhn_s32(a, b);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && HEDLEY_HAS_BUILTIN(__builtin_shufflevector)
simde_int16x4_private r_;
simde_int16x8_private tmp_ =
simde_int16x8_to_private(
simde_vreinterpretq_s16_s32(
simde_vsubq_s32(a, b)
)
);
#if SIMDE_ENDIAN_ORDER == SIMDE_ENDIAN_LITTLE
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 1, 3, 5, 7);
#else
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 0, 2, 4, 6);
#endif
return simde_int16x4_from_private(r_);
#else
return simde_vmovn_s32(simde_vshrq_n_s32(simde_vsubq_s32(a, b), 16));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vsubhn_s32
#define vsubhn_s32(a, b) simde_vsubhn_s32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int32x2_t
simde_vsubhn_s64(simde_int64x2_t a, simde_int64x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vsubhn_s64(a, b);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && HEDLEY_HAS_BUILTIN(__builtin_shufflevector)
simde_int32x2_private r_;
simde_int32x4_private tmp_ =
simde_int32x4_to_private(
simde_vreinterpretq_s32_s64(
simde_vsubq_s64(a, b)
)
);
#if SIMDE_ENDIAN_ORDER == SIMDE_ENDIAN_LITTLE
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 1, 3);
#else
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 0, 2);
#endif
return simde_int32x2_from_private(r_);
#else
return simde_vmovn_s64(simde_vshrq_n_s64(simde_vsubq_s64(a, b), 32));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vsubhn_s64
#define vsubhn_s64(a, b) simde_vsubhn_s64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x8_t
simde_vsubhn_u16(simde_uint16x8_t a, simde_uint16x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vsubhn_u16(a, b);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && HEDLEY_HAS_BUILTIN(__builtin_shufflevector)
simde_uint8x8_private r_;
simde_uint8x16_private tmp_ =
simde_uint8x16_to_private(
simde_vreinterpretq_u8_u16(
simde_vsubq_u16(a, b)
)
);
#if SIMDE_ENDIAN_ORDER == SIMDE_ENDIAN_LITTLE
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 1, 3, 5, 7, 9, 11, 13, 15);
#else
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 0, 2, 4, 6, 8, 10, 12, 14);
#endif
return simde_uint8x8_from_private(r_);
#else
return simde_vmovn_u16(simde_vshrq_n_u16(simde_vsubq_u16(a, b), 8));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vsubhn_u16
#define vsubhn_u16(a, b) simde_vsubhn_u16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x4_t
simde_vsubhn_u32(simde_uint32x4_t a, simde_uint32x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vsubhn_u32(a, b);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && HEDLEY_HAS_BUILTIN(__builtin_shufflevector)
simde_uint16x4_private r_;
simde_uint16x8_private tmp_ =
simde_uint16x8_to_private(
simde_vreinterpretq_u16_u32(
simde_vsubq_u32(a, b)
)
);
#if SIMDE_ENDIAN_ORDER == SIMDE_ENDIAN_LITTLE
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 1, 3, 5, 7);
#else
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 0, 2, 4, 6);
#endif
return simde_uint16x4_from_private(r_);
#else
return simde_vmovn_u32(simde_vshrq_n_u32(simde_vsubq_u32(a, b), 16));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vsubhn_u32
#define vsubhn_u32(a, b) simde_vsubhn_u32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x2_t
simde_vsubhn_u64(simde_uint64x2_t a, simde_uint64x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vsubhn_u64(a, b);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && HEDLEY_HAS_BUILTIN(__builtin_shufflevector)
simde_uint32x2_private r_;
simde_uint32x4_private tmp_ =
simde_uint32x4_to_private(
simde_vreinterpretq_u32_u64(
simde_vsubq_u64(a, b)
)
);
#if SIMDE_ENDIAN_ORDER == SIMDE_ENDIAN_LITTLE
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 1, 3);
#else
r_.values = __builtin_shufflevector(tmp_.values, tmp_.values, 0, 2);
#endif
return simde_uint32x2_from_private(r_);
#else
return simde_vmovn_u64(simde_vshrq_n_u64(simde_vsubq_u64(a, b), 32));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vsubhn_u64
#define vsubhn_u64(a, b) simde_vsubhn_u64((a), (b))
#endif
SIMDE_END_DECLS_
HEDLEY_DIAGNOSTIC_POP
#endif /* !defined(SIMDE_ARM_NEON_SUBHN_H) */
|
