blob: 735b0535c7dcec53be6325a15baa520033313f94 (
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
|
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// SPDX-License-Identifier: MIT
//
#include "ClBaseConstantWorkload.hpp"
#include "backends/ArmComputeTensorUtils.hpp"
#include "backends/ClTensorHandle.hpp"
#include "backends/CpuTensorHandle.hpp"
#include "Half.hpp"
namespace armnn
{
template class ClBaseConstantWorkload<DataType::Float16, DataType::Float32>;
template class ClBaseConstantWorkload<DataType::QuantisedAsymm8>;
template<armnn::DataType... dataTypes>
void ClBaseConstantWorkload<dataTypes...>::Execute() const
{
// 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::CLTensor& output = static_cast<ClTensorHandle*>(data.m_Outputs[0])->GetTensor();
arm_compute::DataType computeDataType = static_cast<ClTensorHandle*>(data.m_Outputs[0])->GetDataType();
switch (computeDataType)
{
case arm_compute::DataType::F16:
{
CopyArmComputeClTensorData(data.m_LayerOutput->GetConstTensor<Half>(), output);
break;
}
case arm_compute::DataType::F32:
{
CopyArmComputeClTensorData(data.m_LayerOutput->GetConstTensor<float>(), output);
break;
}
case arm_compute::DataType::QASYMM8:
{
CopyArmComputeClTensorData(data.m_LayerOutput->GetConstTensor<uint8_t>(), output);
break;
}
default:
{
BOOST_ASSERT_MSG(false, "Unknown data type");
break;
}
}
m_RanOnce = true;
}
}
} //namespace armnn
|