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
|
//===----------------------------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
// UNSUPPORTED: c++98, c++03, c++11, c++14
// <experimental/simd>
//
// loads [simd.load]
// template <class U, class Flags> void copy_from(const U* mem, Flags f);
#include <experimental/simd>
#include <cstdint>
#include "test_macros.h"
namespace ex = std::experimental::parallelism_v2;
template <class T, class... Args>
auto not_supported_load(Args&&... args) -> decltype(
std::declval<ex::native_simd<T>>().copy_from(std::forward<Args>(args)...),
void()) = delete;
template <class T>
void not_supported_load(...) {}
template <class T, class... Args>
auto supported_load(Args&&... args) -> decltype(
std::declval<ex::native_simd<T>>().copy_from(std::forward<Args>(args)...),
void()) {}
template <class T>
void supported_load(...) = delete;
void compile_load() {
supported_load<int>((int*)nullptr, ex::element_aligned_tag());
supported_load<uint32_t>((int*)nullptr, ex::element_aligned_tag());
supported_load<double>((float*)nullptr, ex::element_aligned_tag());
supported_load<uint16_t>((unsigned int*)nullptr, ex::element_aligned_tag());
supported_load<uint32_t>((float*)nullptr, ex::element_aligned_tag());
not_supported_load<int>((int*)nullptr, int());
}
template <typename SimdType>
void test_load() {
alignas(32) int32_t buffer[] = {4, 3, 2, 1};
{
SimdType a;
a.copy_from(buffer, ex::element_aligned_tag());
assert(a[0] == 4);
assert(a[1] == 3);
assert(a[2] == 2);
assert(a[3] == 1);
}
{
SimdType a;
a.copy_from(buffer, ex::vector_aligned_tag());
assert(a[0] == 4);
assert(a[1] == 3);
assert(a[2] == 2);
assert(a[3] == 1);
}
{
SimdType a;
a.copy_from(buffer, ex::overaligned_tag<32>());
assert(a[0] == 4);
assert(a[1] == 3);
assert(a[2] == 2);
assert(a[3] == 1);
}
{
SimdType a;
a.copy_from(buffer, ex::element_aligned);
assert(a[0] == 4);
assert(a[1] == 3);
assert(a[2] == 2);
assert(a[3] == 1);
}
{
SimdType a;
a.copy_from(buffer, ex::vector_aligned);
assert(a[0] == 4);
assert(a[1] == 3);
assert(a[2] == 2);
assert(a[3] == 1);
}
{
SimdType a;
a.copy_from(buffer, ex::overaligned<32>);
assert(a[0] == 4);
assert(a[1] == 3);
assert(a[2] == 2);
assert(a[3] == 1);
}
}
template <typename SimdType>
void test_converting_load() {
float buffer[] = {1., 2., 4., 8.};
SimdType a;
a.copy_from(buffer, ex::element_aligned_tag());
assert(a[0] == 1);
assert(a[1] == 2);
assert(a[2] == 4);
assert(a[3] == 8);
}
int main() {
// TODO: adjust the tests when this assertion fails.
assert(ex::native_simd<int32_t>::size() >= 4);
test_load<ex::native_simd<int32_t>>();
test_load<ex::fixed_size_simd<int32_t, 4>>();
test_converting_load<ex::native_simd<int32_t>>();
test_converting_load<ex::fixed_size_simd<int32_t, 4>>();
}
|
