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
122
123
124
125
126
127
128
129
|
/* Copyright 2016 The TensorFlow Authors. 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 "tensorflow/core/common_runtime/kernel_benchmark_testlib.h"
#include "tensorflow/core/framework/allocator.h"
#include "tensorflow/core/framework/fake_input.h"
#include "tensorflow/core/framework/node_def_builder.h"
#include "tensorflow/core/framework/op_kernel.h"
#include "tensorflow/core/framework/tensor.h"
#include "tensorflow/core/framework/tensor_testutil.h"
#include "tensorflow/core/framework/types.h"
#include "tensorflow/core/framework/types.pb.h"
#include "tensorflow/core/graph/node_builder.h"
#include "tensorflow/core/kernels/ops_testutil.h"
#include "tensorflow/core/kernels/ops_util.h"
#include "tensorflow/core/lib/core/status_test_util.h"
#include "tensorflow/core/platform/test.h"
#include "tensorflow/core/platform/test_benchmark.h"
namespace tensorflow {
// Test data from the TensorFlow README.md.
const char* lines[] = {
"**TensorFlow** is an open source software library for numerical "
"computation using data flow graphs.",
"The graph nodes represent mathematical operations, while the graph edges "
"represent the multidimensional data arrays (tensors) that flow between "
"them.",
"This flexible architecture enables you to deploy computation to one or "
"more CPUs or GPUs in a desktop, server, or mobile device without "
"rewriting code.",
"TensorFlow also includes "
"[TensorBoard](https://www.tensorflow.org/guide/"
"summaries_and_tensorboard), a data visualization toolkit.",
"TensorFlow was originally developed by researchers and engineers working "
"on the Google Brain team within Google's Machine Intelligence Research "
"organization for the purposes of conducting machine learning and deep "
"neural networks research.",
"The system is general enough to be applicable in a wide variety of other "
"domains, as well.",
"TensorFlow provides stable Python API and C APIs as well as without API "
"backwards compatibility guarantee like C++, Go, Java, JavaScript and "
"Swift."};
Tensor GetTestTensor(int batch) {
const int sz = TF_ARRAYSIZE(lines);
Tensor t(DT_STRING, {batch});
auto s = t.flat<string>();
for (int i = 0; i < batch; ++i) {
s(i) = lines[i % sz];
}
return t;
}
Graph* SetupStringSplitGraph(const Tensor& input) {
Graph* g = new Graph(OpRegistry::Global());
Tensor delim(DT_STRING, TensorShape({}));
delim.flat<string>().setConstant(" ");
TF_CHECK_OK(NodeBuilder("string_split_op", "StringSplit")
.Input(test::graph::Constant(g, input))
.Input(test::graph::Constant(g, delim))
.Finalize(g, nullptr /* node */));
return g;
}
void BM_StringSplit(int iters, int batch_size) {
testing::StopTiming();
testing::ItemsProcessed(static_cast<int64>(iters));
testing::UseRealTime();
Tensor input = GetTestTensor(batch_size);
Graph* g = SetupStringSplitGraph(input);
testing::StartTiming();
test::Benchmark("cpu", g).Run(iters);
}
BENCHMARK(BM_StringSplit)
->Arg(1)
->Arg(8)
->Arg(16)
->Arg(32)
->Arg(64)
->Arg(128)
->Arg(256);
Graph* SetupStringSplitV2Graph(const Tensor& input) {
Graph* g = new Graph(OpRegistry::Global());
Tensor sep(DT_STRING, TensorShape({}));
sep.flat<string>().setConstant(" ");
TF_CHECK_OK(NodeBuilder("string_split_op", "StringSplitV2")
.Input(test::graph::Constant(g, input))
.Input(test::graph::Constant(g, sep))
.Finalize(g, nullptr /* node */));
return g;
}
void BM_StringSplitV2(int iters, int batch_size) {
testing::StopTiming();
testing::ItemsProcessed(static_cast<int64>(iters));
testing::UseRealTime();
Tensor input = GetTestTensor(batch_size);
Graph* g = SetupStringSplitV2Graph(input);
testing::StartTiming();
test::Benchmark("cpu", g).Run(iters);
}
BENCHMARK(BM_StringSplitV2)
->Arg(1)
->Arg(8)
->Arg(16)
->Arg(32)
->Arg(64)
->Arg(128)
->Arg(256);
} // end namespace tensorflow
|
