RefTileWorkload Class Reference

#include <RefTileWorkload.hpp>

Inheritance diagram for RefTileWorkload:

Collaboration diagram for RefTileWorkload:

Public Member Functions
	RefTileWorkload (const TileQueueDescriptor &descriptor, const WorkloadInfo &info)
void	Execute () const override
Public Member Functions inherited from RefBaseWorkload< TileQueueDescriptor >
	RefBaseWorkload (const TileQueueDescriptor &descriptor, const WorkloadInfo &info)
virtual bool	SupportsTensorHandleReplacement () const override
void	ReplaceInputTensorHandle (ITensorHandle *tensorHandle, unsigned int slot) override
void	ReplaceOutputTensorHandle (ITensorHandle *tensorHandle, unsigned int slot) override
Public Member Functions inherited from BaseWorkload< TileQueueDescriptor >
	BaseWorkload (const TileQueueDescriptor &descriptor, const WorkloadInfo &info)
virtual const std::string &	GetName () const override
void	PostAllocationConfigure () override
const TileQueueDescriptor &	GetData () const
arm::pipe::ProfilingGuid	GetGuid () const final
Public Member Functions inherited from IWorkload
virtual	~IWorkload ()
virtual void	RegisterDebugCallback (const DebugCallbackFunction &)
virtual armnn::Optional< armnn::MemoryRequirements >	GetMemoryRequirements ()

Additional Inherited Members
Protected Attributes inherited from BaseWorkload< TileQueueDescriptor >
TileQueueDescriptor	m_Data
const arm::pipe::ProfilingGuid	m_Guid
const std::string	m_Name

Detailed Description

Definition at line 16 of file RefTileWorkload.hpp.

Constructor & Destructor Documentation

RefTileWorkload()

RefTileWorkload ( const TileQueueDescriptor &  descriptor, const WorkloadInfo &  info  )

explicit

Definition at line 14 of file RefTileWorkload.cpp.

        : RefBaseWorkload(descriptor, info)
    {}

References armnn::info.

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 18 of file RefTileWorkload.cpp.

    {
        auto inputDataType = GetTensorInfo(m_Data.m_Inputs[0]).GetDataType();
        if(inputDataType == DataType::Signed64)
        {
            Execute<double_t>(m_Data.m_Inputs, m_Data.m_Outputs);
        }
        else
        {
            Execute<float>(m_Data.m_Inputs, m_Data.m_Outputs);
        }
    }

References TensorInfo::GetDataType(), armnn::GetTensorInfo(), BaseWorkload< TileQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, and armnn::Signed64.

---

The documentation for this class was generated from the following files:

• src/backends/reference/workloads/RefTileWorkload.hpp
• src/backends/reference/workloads/RefTileWorkload.cpp