blob: adffd8123e8dd188f8f58f2d43796019218be2f8 (
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
|
//
// Copyright © 2017 Arm Ltd and Contributors. All rights reserved.
// SPDX-License-Identifier: MIT
//
#pragma once
#include <armnn/backends/Workload.hpp>
#include <arm_compute/runtime/CL/functions/CLDepthConvertLayer.h>
#include <cl/ICLTensorProxy.hpp>
namespace armnn
{
class ClConvertFp32ToFp16Workload : public Float32ToFloat16Workload<ConvertFp32ToFp16QueueDescriptor>
{
public:
ClConvertFp32ToFp16Workload(const ConvertFp32ToFp16QueueDescriptor& descriptor,
const WorkloadInfo& info,
const arm_compute::CLCompileContext& clCompileContext);
virtual void Execute() const override;
// Replace input tensor handle with the given TensorHandle
void ReplaceInputTensorHandle(ITensorHandle* tensorHandle, unsigned int slot) override;
// Replace output tensor handle with the given TensorHandle
void ReplaceOutputTensorHandle(ITensorHandle* tensorHandle, unsigned int slot) override;
private:
mutable arm_compute::CLDepthConvertLayer m_Layer;
virtual void Reconfigure();
std::unique_ptr<ICLTensorProxy> m_InputProxy;
std::unique_ptr<ICLTensorProxy> m_OutputProxy;
};
arm_compute::Status ClConvertFp32ToFp16WorkloadValidate(const TensorInfo& input, const TensorInfo& output);
} //namespace armnn
|
