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
|
// ----------------------------------------------------------------------------
// - Open3D: www.open3d.org -
// ----------------------------------------------------------------------------
// The MIT License (MIT)
//
// Copyright (c) 2018-2021 www.open3d.org
//
// 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.
// ----------------------------------------------------------------------------
#include <benchmark/benchmark.h>
#include "open3d/core/CUDAUtils.h"
#include "open3d/core/Tensor.h"
namespace open3d {
namespace core {
void Zeros(benchmark::State& state, const Device& device) {
int64_t large_dim = (1ULL << 27) + 10;
SizeVector shape{2, large_dim};
Tensor warm_up = Tensor::Zeros(shape, core::Float32, device);
(void)warm_up;
for (auto _ : state) {
Tensor dst = Tensor::Zeros(shape, core::Float32, device);
cuda::Synchronize(device);
}
}
BENCHMARK_CAPTURE(Zeros, CPU, Device("CPU:0"))->Unit(benchmark::kMillisecond);
#ifdef BUILD_CUDA_MODULE
BENCHMARK_CAPTURE(Zeros, CUDA, Device("CUDA:0"))->Unit(benchmark::kMillisecond);
#endif
} // namespace core
} // namespace open3d
|
