blob: 828e476d2904e4d3db9e24489d61df01f9694ae9 (
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
|
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// SPDX-License-Identifier: MIT
//
#pragma once
#include <arm_compute/core/Types.h>
#include <armnnUtils/Half.hpp>
#include <backends/aclCommon/ArmComputeTensorUtils.hpp>
#include <backends/neon/NeonTensorHandle.hpp>
#include <backends/neon/workloads/NeonWorkloadUtils.hpp>
#include <backends/CpuTensorHandle.hpp>
#include <backends/Workload.hpp>
#include <boost/cast.hpp>
namespace armnn
{
// Base class template providing an implementation of the Constant layer common to all data types.
template <armnn::DataType... DataFormats>
class NeonBaseConstantWorkload : public TypedWorkload<ConstantQueueDescriptor, DataFormats...>
{
public:
NeonBaseConstantWorkload(const ConstantQueueDescriptor& descriptor, const WorkloadInfo& info)
: TypedWorkload<ConstantQueueDescriptor, DataFormats...>(descriptor, info)
, m_RanOnce(false)
{
}
virtual void Execute() const override
{
using namespace armcomputetensorutils;
// The intermediate tensor held by the corresponding layer output handler can be initialised with the
// given data on the first inference, then reused for subsequent inferences.
// The initialisation cannot happen at workload construction time since the ACL kernel for the next layer
// may not have been configured at the time.
if (!m_RanOnce)
{
const ConstantQueueDescriptor& data = this->m_Data;
BOOST_ASSERT(data.m_LayerOutput != nullptr);
arm_compute::ITensor& output =
boost::polymorphic_downcast<NeonTensorHandle*>(data.m_Outputs[0])->GetTensor();
arm_compute::DataType computeDataType =
boost::polymorphic_downcast<NeonTensorHandle*>(data.m_Outputs[0])->GetDataType();
switch (computeDataType)
{
case arm_compute::DataType::F16:
{
CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor<Half>(), output);
break;
}
case arm_compute::DataType::F32:
{
CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor<float>(), output);
break;
}
case arm_compute::DataType::QASYMM8:
{
CopyArmComputeITensorData(data.m_LayerOutput->GetConstTensor<uint8_t>(), output);
break;
}
default:
{
BOOST_ASSERT_MSG(false, "Unknown data type");
break;
}
}
m_RanOnce = true;
}
}
private:
mutable bool m_RanOnce;
};
} //namespace armnn
|
