summaryrefslogtreecommitdiff
path: root/runtimes/pure_arm_compute/src/internal/layers/SimpleNeg.cc
blob: d3943ad40c43c993c25e1f9f6a003550c5d1412e (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
/*
 * Copyright (c) 2018 Samsung Electronics Co., Ltd. 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 "internal/layers/SimpleNeg.h"

#include <arm_compute/runtime/CL/CLScheduler.h>

void SimpleNeg::configure(::arm_compute::ITensor *input, ::arm_compute::ITensor *output)
{
  _input = input;
  _output = output;
}

void SimpleNeg::run()
{
  auto &queue = ::arm_compute::CLScheduler::get().queue();
  if (::internal::arm_compute::isGpuMode())
  {
    CAST_CL(_input)->map(queue);
    CAST_CL(_output)->map(queue);
  }

  arm_compute::Window window;
  window.use_tensor_dimensions(_output->info()->tensor_shape());

  execute_window_loop(window, [this](const arm_compute::Coordinates &id) {
    // NOTE Must be two input tensors of identical type
    //      Must be output tensor of the same type as input0.
    assert(_input->info()->data_type() == _output->info()->data_type());

    switch (_input->info()->data_type())
    {
      case ::arm_compute::DataType::F32:
      {
        const auto input_value = *reinterpret_cast<float *>(_input->ptr_to_element(id));
        *reinterpret_cast<float *>(_output->ptr_to_element(id)) = -input_value;
        break;
      }
      case ::arm_compute::DataType::S32:
      {
        const auto input_value = *reinterpret_cast<int32_t *>(_input->ptr_to_element(id));
        *reinterpret_cast<int32_t *>(_output->ptr_to_element(id)) = -input_value;
        break;
      }
      case ::arm_compute::DataType::U32:
      {
        const auto input_value = *reinterpret_cast<uint32_t *>(_input->ptr_to_element(id));
        *reinterpret_cast<uint32_t *>(_output->ptr_to_element(id)) = -input_value;
        break;
      }
      default:
        throw std::runtime_error("Not supported, yet");
        break;
    }
  });

  if (::internal::arm_compute::isGpuMode())
  {
    CAST_CL(_input)->unmap(queue);
    CAST_CL(_output)->unmap(queue);
  }
}