summaryrefslogtreecommitdiff
path: root/runtimes/libs/ARMComputeEx/arm_compute/runtime/CL/functions/CLReduceOperation.h
blob: e1a6f6ab42076a4a3b67e69d7e2aee635c220d9f (plain)
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
/*
 * Copyright (c) 2018 Samsung Electronics Co., Ltd. All Rights Reserved
 * Copyright (c) 2016-2018 ARM Limited.
 *
 * 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.
 */

/**
 * @file CLReduceOperation.h
 * @ingroup COM_AI_RUNTIME
 * @brief This file contains arm_compute::CLReduceOperation class
 */

#ifndef __ARM_COMPUTE_CLREDUCEOPERATION_H__
#define __ARM_COMPUTE_CLREDUCEOPERATION_H__

#include "arm_compute/core/CL/kernels/CLReduceOperationKernel.h"
#include "arm_compute/core/TypesEx.h"
#include "arm_compute/runtime/CL/CLTensor.h"
#include "arm_compute/runtime/IFunction.h"

namespace arm_compute
{
class ICLTensor;

/**
 * @brief Class to perform ReduceOperation
 */
class CLReduceOperation : public IFunction
{
public:
  /**
   * @brief Construct a new ReduceOperation object
   */
  CLReduceOperation();

  /**
   * @brief Set the input and output tensors.
   * @param[in]  input    Source tensor. Data types supported: U8/S32/F32
   * @param[out] output   Destination tensor. Data types and data layouts supported: Same as @p
   *                      input.
   * @param[in]  axis     Axis along which to reduce. It must be sorted and no duplicates.
   * @param[in]  op       Reduce operation to perform.
   * @return N/A
   */
  void configure(ICLTensor *input, ICLTensor *output, const std::set<uint32_t> &axis,
                 ReduceOperation op);

  /**
   * @brief Static function to check if given info will lead to a valid configuration of @ref
   *        CLReduceOperation.
   * @param[in] input   Source tensor info. Data types supported: U8/S32/F32
   * @param[in] output  Destination tensor info. Data types and data layouts supported: Same as @p
   *                    input.
   * @param[in] axis    Axis along which to reduce. It must be sorted and no duplicates.
   * @param[in] op      Reduce operation to perform.
   * @return a status
   */
  static Status validate(const ITensorInfo *input, const ITensorInfo *output,
                         const std::set<uint32_t> &axis, const ReduceOperation &op);

  /**
   * @brief Run the OpenCL kernel for this operation
   * @return N/A
   */
  void run() override;

private:
  ICLTensor *_input;
  ICLTensor *_output;
  std::set<uint32_t> _axis;

  std::unique_ptr<CLTensor[]> _interm_tensors{nullptr};
  std::unique_ptr<CLReduceOperationKernel[]> _reduce_kernels{nullptr};
};
}
#endif /*__ARM_COMPUTE_CLREDUCEOPERATION_H__ */