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
|
/* Copyright 2015 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/kernels/reduction_ops_common.h"
namespace tensorflow {
#define REGISTER_CPU_KERNELS(type) \
REGISTER_KERNEL_BUILDER( \
Name("Sum") \
.Device(DEVICE_CPU) \
.TypeConstraint<type>("T") \
.TypeConstraint<int32>("Tidx"), \
ReductionOp<CPUDevice, type, int32, Eigen::internal::SumReducer<type>>); \
REGISTER_KERNEL_BUILDER( \
Name("Sum") \
.Device(DEVICE_CPU) \
.TypeConstraint<type>("T") \
.TypeConstraint<int64>("Tidx"), \
ReductionOp<CPUDevice, type, int64, Eigen::internal::SumReducer<type>>);
TF_CALL_NUMBER_TYPES(REGISTER_CPU_KERNELS);
#undef REGISTER_CPU_KERNELS
#if GOOGLE_CUDA
#define REGISTER_GPU_KERNELS(type) \
REGISTER_KERNEL_BUILDER( \
Name("Sum") \
.Device(DEVICE_GPU) \
.TypeConstraint<type>("T") \
.TypeConstraint<int32>("Tidx") \
.HostMemory("reduction_indices"), \
ReductionOp<GPUDevice, type, int32, Eigen::internal::SumReducer<type>>); \
REGISTER_KERNEL_BUILDER( \
Name("Sum") \
.Device(DEVICE_GPU) \
.TypeConstraint<type>("T") \
.TypeConstraint<int64>("Tidx") \
.HostMemory("reduction_indices"), \
ReductionOp<GPUDevice, type, int64, Eigen::internal::SumReducer<type>>);
TF_CALL_GPU_NUMBER_TYPES(REGISTER_GPU_KERNELS);
TF_CALL_complex64(REGISTER_GPU_KERNELS);
TF_CALL_complex128(REGISTER_GPU_KERNELS);
#undef REGISTER_GPU_KERNELS
// A special GPU kernel for int32.
// TODO(b/25387198): Also enable int32 in device memory. This kernel
// registration requires all int32 inputs and outputs to be in host memory.
REGISTER_KERNEL_BUILDER(
Name("Sum")
.Device(DEVICE_GPU)
.TypeConstraint<int32>("T")
.TypeConstraint<int32>("Tidx")
.HostMemory("input")
.HostMemory("output")
.HostMemory("reduction_indices"),
ReductionOp<CPUDevice, int32, int32, Eigen::internal::SumReducer<int32>>);
REGISTER_KERNEL_BUILDER(
Name("Sum")
.Device(DEVICE_GPU)
.TypeConstraint<int32>("T")
.TypeConstraint<int64>("Tidx")
.HostMemory("input")
.HostMemory("output")
.HostMemory("reduction_indices"),
ReductionOp<CPUDevice, int32, int64, Eigen::internal::SumReducer<int32>>);
#endif
#ifdef TENSORFLOW_USE_SYCL
#define REGISTER_SYCL_KERNELS(type) \
REGISTER_KERNEL_BUILDER(Name("Sum") \
.Device(DEVICE_SYCL) \
.TypeConstraint<type>("T") \
.TypeConstraint<int32>("Tidx") \
.HostMemory("reduction_indices"), \
ReductionOp<SYCLDevice, type, int32, \
Eigen::internal::SumReducer<type>>); \
REGISTER_KERNEL_BUILDER(Name("Sum") \
.Device(DEVICE_SYCL) \
.TypeConstraint<type>("T") \
.TypeConstraint<int64>("Tidx") \
.HostMemory("reduction_indices"), \
ReductionOp<SYCLDevice, type, int64, \
Eigen::internal::SumReducer<type>>);
REGISTER_SYCL_KERNELS(float);
REGISTER_SYCL_KERNELS(double);
REGISTER_KERNEL_BUILDER(
Name("Sum")
.Device(DEVICE_SYCL)
.TypeConstraint<int32>("T")
.TypeConstraint<int32>("Tidx")
.HostMemory("input")
.HostMemory("output")
.HostMemory("reduction_indices"),
ReductionOp<CPUDevice, int32, int32, Eigen::internal::SumReducer<int32>>);
REGISTER_KERNEL_BUILDER(
Name("Sum")
.Device(DEVICE_SYCL)
.TypeConstraint<int32>("T")
.TypeConstraint<int64>("Tidx")
.HostMemory("input")
.HostMemory("output")
.HostMemory("reduction_indices"),
ReductionOp<CPUDevice, int32, int64, Eigen::internal::SumReducer<int32>>);
#undef REGISTER_SYCL_KERNELS
#endif // TENSORFLOW_USE_SYCL
} // namespace tensorflow
|
