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
|
/*
* Copyright (c) 2020, 2022 Arm Limited.
*
* 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.
*/
#ifndef ARM_COMPUTE_WRAPPER_CVT_H
#define ARM_COMPUTE_WRAPPER_CVT_H
#include <arm_neon.h>
namespace arm_compute
{
namespace wrapper
{
#define VCVT_TO_F32_IMPL(ptype, vtype, prefix, postfix1, postfix2) \
template <typename T> \
inline typename std::enable_if<std::is_same<T, float>::value, float32x4_t>::type \
vcvt(const vtype &a) \
{ \
return prefix##_##postfix1##_##postfix2(a); \
}
VCVT_TO_F32_IMPL(float32x4_t, uint32x4_t, vcvtq, f32, u32)
VCVT_TO_F32_IMPL(float32x4_t, int32x4_t, vcvtq, f32, s32)
#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
VCVT_TO_F32_IMPL(float32x4_t, float16x4_t, vcvt, f32, f16)
#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
#undef VCVT_TO_F32_IMPL
#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
#define VCVT_TO_F16_IMPL(ptype, vtype, prefix, postfix1, postfix2) \
template <typename T> \
inline typename std::enable_if<std::is_same<T, float16_t>::value, float16x4_t>::type \
vcvt(const vtype &a) \
{ \
return prefix##_##postfix1##_##postfix2(a); \
}
VCVT_TO_F16_IMPL(float16x4_t, float32x4_t, vcvt, f16, f32)
#undef VCVT_TO_F16_IMPL
#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
template <typename T>
inline typename std::enable_if < std::is_same<T, uint8_t>::value || std::is_same<T, uint32_t>::value, uint32x4_t >::type
vcvt(const float32x4_t &a)
{
return vcvtq_u32_f32(a);
}
template <typename T>
inline typename std::enable_if < std::is_same<T, int8_t>::value || std::is_same<T, int32_t>::value, int32x4_t >::type
vcvt(const float32x4_t &a)
{
return vcvtq_s32_f32(a);
}
#ifdef __aarch64__
template <typename T>
inline typename std::enable_if<std::is_same<T, uint32_t>::value, uint32x4_t>::type
vcvta(const float32x4_t &a)
{
return vcvtaq_u32_f32(a);
}
template <typename T>
inline typename std::enable_if<std::is_same<T, int32_t>::value, int32x4_t>::type
vcvta(const float32x4_t &a)
{
return vcvtaq_s32_f32(a);
}
#endif //__aarch64__
} // namespace wrapper
} // namespace arm_compute
#endif /* ARM_COMPUTE_WRAPPER_CVT_H */
|
