aboutsummaryrefslogtreecommitdiff
path: root/src/backends/neon/NeonTensorHandle.hpp
blob: 7206b6fc5a2f1e7e654cf01fd1928ce4fd0a93d6 (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
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// SPDX-License-Identifier: MIT
//
#pragma once

#include <backendsCommon/OutputHandler.hpp>
#include <aclCommon/ArmComputeTensorUtils.hpp>

#include <arm_compute/runtime/MemoryGroup.h>
#include <arm_compute/runtime/IMemoryGroup.h>
#include <arm_compute/runtime/Tensor.h>
#include <arm_compute/runtime/SubTensor.h>
#include <arm_compute/core/TensorShape.h>
#include <arm_compute/core/Coordinates.h>

#include <boost/polymorphic_pointer_cast.hpp>

namespace armnn
{

class INeonTensorHandle : public ITensorHandle
{
public:
    virtual arm_compute::ITensor& GetTensor() = 0;
    virtual arm_compute::ITensor const& GetTensor() const = 0;
    virtual arm_compute::DataType GetDataType() const = 0;
    virtual void SetMemoryGroup(const std::shared_ptr<arm_compute::IMemoryGroup>& memoryGroup) = 0;
};

class NeonTensorHandle : public INeonTensorHandle
{
public:
    NeonTensorHandle(const TensorInfo& tensorInfo)
    {
        armnn::armcomputetensorutils::BuildArmComputeTensor(m_Tensor, tensorInfo);
    }

    NeonTensorHandle(const TensorInfo& tensorInfo, DataLayout dataLayout)
    {
        armnn::armcomputetensorutils::BuildArmComputeTensor(m_Tensor, tensorInfo, dataLayout);
    }

    arm_compute::ITensor& GetTensor() override { return m_Tensor; }
    arm_compute::ITensor const& GetTensor() const override { return m_Tensor; }

    virtual void Allocate() override
    {
        armnn::armcomputetensorutils::InitialiseArmComputeTensorEmpty(m_Tensor);
    };

    virtual void Manage() override
    {
        BOOST_ASSERT(m_MemoryGroup != nullptr);
        m_MemoryGroup->manage(&m_Tensor);
    }

    virtual ITensorHandle* GetParent() const override { return nullptr; }

    virtual arm_compute::DataType GetDataType() const override
    {
        return m_Tensor.info()->data_type();
    }

    virtual void SetMemoryGroup(const std::shared_ptr<arm_compute::IMemoryGroup>& memoryGroup) override
    {
        m_MemoryGroup = boost::polymorphic_pointer_downcast<arm_compute::MemoryGroup>(memoryGroup);
    }

    virtual const void* Map(bool /* blocking = true */) const override
    {
        return static_cast<const void*>(m_Tensor.buffer() + m_Tensor.info()->offset_first_element_in_bytes());
    }
    virtual void Unmap() const override {}


    TensorShape GetStrides() const override
    {
        return armcomputetensorutils::GetStrides(m_Tensor.info()->strides_in_bytes());
    }

    TensorShape GetShape() const override
    {
        return armcomputetensorutils::GetShape(m_Tensor.info()->tensor_shape());
    }

private:
    // Only used for testing
    void CopyOutTo(void* memory) const override
    {
        switch (this->GetDataType())
        {
            case arm_compute::DataType::F32:
                armcomputetensorutils::CopyArmComputeITensorData(this->GetTensor(),
                                                                 static_cast<float*>(memory));
                break;
            case arm_compute::DataType::QASYMM8:
                armcomputetensorutils::CopyArmComputeITensorData(this->GetTensor(),
                                                                 static_cast<uint8_t*>(memory));
                break;
            default:
            {
                throw armnn::UnimplementedException();
            }
        }
    }

    // Only used for testing
    void CopyInFrom(const void* memory) override
    {
        switch (this->GetDataType())
        {
            case arm_compute::DataType::F32:
                armcomputetensorutils::CopyArmComputeITensorData(static_cast<const float*>(memory),
                                                                 this->GetTensor());
                break;
            case arm_compute::DataType::QASYMM8:
                armcomputetensorutils::CopyArmComputeITensorData(static_cast<const uint8_t*>(memory),
                                                                 this->GetTensor());
                break;
            default:
            {
                throw armnn::UnimplementedException();
            }
        }
    }

    arm_compute::Tensor m_Tensor;
    std::shared_ptr<arm_compute::MemoryGroup> m_MemoryGroup;
};

class NeonSubTensorHandle : public INeonTensorHandle
{
public:
    NeonSubTensorHandle(INeonTensorHandle* parent,
                        const arm_compute::TensorShape& shape,
                        const arm_compute::Coordinates& coords)
     : m_Tensor(&parent->GetTensor(), shape, coords)
    {
        parentHandle = parent;
    }

    arm_compute::ITensor& GetTensor() override { return m_Tensor; }
    arm_compute::ITensor const& GetTensor() const override { return m_Tensor; }

    virtual void Allocate() override {}
    virtual void Manage() override {}

    virtual ITensorHandle* GetParent() const override { return parentHandle; }

    virtual arm_compute::DataType GetDataType() const override
    {
        return m_Tensor.info()->data_type();
    }

    virtual void SetMemoryGroup(const std::shared_ptr<arm_compute::IMemoryGroup>&) override {}

    virtual const void* Map(bool /* blocking = true */) const override
    {
        return static_cast<const void*>(m_Tensor.buffer() + m_Tensor.info()->offset_first_element_in_bytes());
    }
    virtual void Unmap() const override {}

    TensorShape GetStrides() const override
    {
        return armcomputetensorutils::GetStrides(m_Tensor.info()->strides_in_bytes());
    }

    TensorShape GetShape() const override
    {
        return armcomputetensorutils::GetShape(m_Tensor.info()->tensor_shape());
    }

private:
    // Only used for testing
    void CopyOutTo(void* memory) const override
    {
        switch (this->GetDataType())
        {
            case arm_compute::DataType::F32:
                armcomputetensorutils::CopyArmComputeITensorData(this->GetTensor(),
                                                                 static_cast<float*>(memory));
                break;
            case arm_compute::DataType::QASYMM8:
                armcomputetensorutils::CopyArmComputeITensorData(this->GetTensor(),
                                                                 static_cast<uint8_t*>(memory));
                break;
            default:
            {
                throw armnn::UnimplementedException();
            }
        }
    }

    // Only used for testing
    void CopyInFrom(const void* memory) override
    {
        switch (this->GetDataType())
        {
            case arm_compute::DataType::F32:
                armcomputetensorutils::CopyArmComputeITensorData(static_cast<const float*>(memory),
                                                                 this->GetTensor());
                break;
            case arm_compute::DataType::QASYMM8:
                armcomputetensorutils::CopyArmComputeITensorData(static_cast<const uint8_t*>(memory),
                                                                 this->GetTensor());
                break;
            default:
            {
                throw armnn::UnimplementedException();
            }
        }
    }

    arm_compute::SubTensor m_Tensor;
    ITensorHandle* parentHandle = nullptr;
};

} // namespace armnn