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) 2024, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of the NVIDIA CORPORATION nor the
* names of its contributors may be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
* DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
******************************************************************************/
#include <thrust/copy.h>
#include <thrust/count.h>
#include <thrust/device_vector.h>
#include <thrust/execution_policy.h>
#include <nvbench_helper.cuh>
template <class InT, class OutT>
struct fib_t
{
__device__ OutT operator()(InT n)
{
OutT t1 = 0;
OutT t2 = 1;
if (n < 1)
{
return t1;
}
else if (n == 1)
{
return t1;
}
else if (n == 2)
{
return t2;
}
for (InT i = 3; i <= n; ++i)
{
const auto next = t1 + t2;
t1 = t2;
t2 = next;
}
return t2;
}
};
template <typename T>
static void basic(nvbench::state& state, nvbench::type_list<T>)
{
const auto elements = static_cast<std::size_t>(state.get_int64("Elements"));
thrust::device_vector<T> input = generate(elements, bit_entropy::_1_000, T{0}, T{42});
thrust::device_vector<T> output(elements);
state.add_element_count(elements);
state.add_global_memory_reads<T>(elements);
state.add_global_memory_writes<nvbench::uint32_t>(elements);
caching_allocator_t alloc;
fib_t<T, nvbench::uint32_t> op{};
thrust::transform(policy(alloc), input.cbegin(), input.cend(), output.begin(), op);
state.exec(nvbench::exec_tag::no_batch | nvbench::exec_tag::sync, [&](nvbench::launch& launch) {
thrust::transform(policy(alloc, launch), input.cbegin(), input.cend(), output.begin(), op);
});
}
using types = nvbench::type_list<nvbench::uint32_t, nvbench::uint64_t>;
NVBENCH_BENCH_TYPES(basic, NVBENCH_TYPE_AXES(types))
.set_name("base")
.set_type_axes_names({"T{ct}"})
.add_int64_power_of_two_axis("Elements", nvbench::range(16, 28, 4));
|
