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
|
/*
* Copyright 2008-2013 NVIDIA Corporation
* Modifications Copyright© 2019 Advanced Micro Devices, Inc. All rights reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include <thrust/sort.h>
#include <thrust/transform.h>
#include <thrust/tuple.h>
#include "test_header.hpp"
TESTS_DEFINE(TupleReduceTests, IntegerTestsParams);
struct SumTupleFunctor
{
template <typename Tuple>
__host__ __device__ Tuple operator()(const Tuple& lhs, const Tuple& rhs)
{
using thrust::get;
return thrust::make_tuple(get<0>(lhs) + get<0>(rhs), get<1>(lhs) + get<1>(rhs));
}
};
struct MakeTupleFunctor
{
template <typename T1, typename T2>
__host__ __device__ thrust::tuple<T1, T2> operator()(T1& lhs, T2& rhs)
{
return thrust::make_tuple(lhs, rhs);
}
};
TYPED_TEST(TupleReduceTests, TestTupleReduce)
{
using T = typename TestFixture::input_type;
SCOPED_TRACE(testing::Message() << "with device_id= " << test::set_device_from_ctest());
for(auto size : get_sizes())
{
SCOPED_TRACE(testing::Message() << "with size= " << size);
for(auto seed : get_seeds())
{
SCOPED_TRACE(testing::Message() << "with seed= " << seed);
thrust::host_vector<T> h_t1 = get_random_data<T>(
size, std::numeric_limits<T>::min(), std::numeric_limits<T>::max(), seed);
thrust::host_vector<T> h_t2 = get_random_data<T>(
size,
std::numeric_limits<T>::min(),
std::numeric_limits<T>::max(),
seed + seed_value_addition
);
// zip up the data
thrust::host_vector<thrust::tuple<T, T>> h_tuples(size);
thrust::transform(
h_t1.begin(), h_t1.end(), h_t2.begin(), h_tuples.begin(), MakeTupleFunctor());
// copy to device
thrust::device_vector<thrust::tuple<T, T>> d_tuples = h_tuples;
thrust::tuple<T, T> zero(0, 0);
// sum on host
thrust::tuple<T, T> h_result
= thrust::reduce(h_tuples.begin(), h_tuples.end(), zero, SumTupleFunctor());
// sum on device
thrust::tuple<T, T> d_result
= thrust::reduce(d_tuples.begin(), d_tuples.end(), zero, SumTupleFunctor());
ASSERT_EQ_QUIET(h_result, d_result);
}
}
}
|
