ArmNN
 22.08
Public Member Functions | List of all members
RefConvertFp32ToBf16Workload Class Reference

#include <RefConvertFp32ToBf16Workload.hpp>

Inheritance diagram for RefConvertFp32ToBf16Workload:
MultiTypedWorkload< QueueDescriptor, InputDataType, OutputDataType > BaseWorkload< QueueDescriptor > IWorkload

Public Member Functions

void Execute () const override
 
void ExecuteAsync (ExecutionData &executionData) override
 
- Public Member Functions inherited from MultiTypedWorkload< QueueDescriptor, InputDataType, OutputDataType >
 MultiTypedWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info)
 
- Public Member Functions inherited from BaseWorkload< QueueDescriptor >
 BaseWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info)
 
void PostAllocationConfigure () override
 
const QueueDescriptor & GetData () const
 
arm::pipe::ProfilingGuid GetGuid () const final
 
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 IWorkload
virtual ~IWorkload ()
 
virtual void RegisterDebugCallback (const DebugCallbackFunction &)
 
virtual armnn::Optional< armnn::MemoryRequirements > GetMemoryRequirements ()
 

Additional Inherited Members

- Protected Attributes inherited from BaseWorkload< QueueDescriptor >
QueueDescriptor m_Data
 
const arm::pipe::ProfilingGuid m_Guid
 

Detailed Description

Definition at line 14 of file RefConvertFp32ToBf16Workload.hpp.

Member Function Documentation

◆ Execute()

void Execute ( ) const
overridevirtual

Implements IWorkload.

Definition at line 16 of file RefConvertFp32ToBf16Workload.cpp.

References RefConvertFp32ToBf16Workload::Execute(), BaseWorkload< QueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, and QueueDescriptor::m_Outputs.

Referenced by RefConvertFp32ToBf16Workload::Execute(), and RefConvertFp32ToBf16Workload::ExecuteAsync().

17 {
18  Execute(m_Data.m_Inputs, m_Data.m_Outputs);
19 }
armnn::BaseWorkload::m_Data
QueueDescriptor m_Data
Definition: Workload.hpp:83
armnn::QueueDescriptor::m_Outputs
std::vector< ITensorHandle * > m_Outputs
Definition: WorkloadData.hpp:27
armnn::QueueDescriptor::m_Inputs
std::vector< ITensorHandle * > m_Inputs
Definition: WorkloadData.hpp:26

◆ ExecuteAsync()

void ExecuteAsync ( ExecutionData &  executionData)
overridevirtual

Reimplemented from BaseWorkload< QueueDescriptor >.

Definition at line 21 of file RefConvertFp32ToBf16Workload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT, FloatingPointConverter::ConvertFloat32ToBFloat16(), armnn::CpuRef, RefConvertFp32ToBf16Workload::Execute(), TensorInfo::GetNumElements(), armnn::GetTensorInfo(), ExecutionData::m_Data, WorkingMemDescriptor::m_Inputs, and WorkingMemDescriptor::m_Outputs.

22 {
23  WorkingMemDescriptor* workingMemDescriptor = static_cast<WorkingMemDescriptor*>(executionData.m_Data);
24  Execute(workingMemDescriptor->m_Inputs, workingMemDescriptor->m_Outputs);
25 }
The documentation for this class was generated from the following files: