ArmNN
 22.11
Public Member Functions | List of all members
RefSoftmaxWorkload Class Reference

#include <RefSoftmaxWorkload.hpp>

Inheritance diagram for RefSoftmaxWorkload:
RefBaseWorkload< SoftmaxQueueDescriptor > BaseWorkload< SoftmaxQueueDescriptor > IWorkload

Public Member Functions

void Execute () const override
 
void ExecuteAsync (ExecutionData &executionData) override
 
- Public Member Functions inherited from RefBaseWorkload< SoftmaxQueueDescriptor >
 RefBaseWorkload (const SoftmaxQueueDescriptor &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< SoftmaxQueueDescriptor >
 BaseWorkload (const SoftmaxQueueDescriptor &descriptor, const WorkloadInfo &info)
 
void ExecuteAsync (ExecutionData &executionData) override
 
void PostAllocationConfigure () override
 
const SoftmaxQueueDescriptor & 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< SoftmaxQueueDescriptor >
SoftmaxQueueDescriptor m_Data
 
const arm::pipe::ProfilingGuid m_Guid
 

Detailed Description

Definition at line 14 of file RefSoftmaxWorkload.hpp.

Member Function Documentation

◆ Execute()

void Execute ( ) const
overridevirtual

Implements IWorkload.

Definition at line 20 of file RefSoftmaxWorkload.cpp.

References BaseWorkload< SoftmaxQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, and QueueDescriptor::m_Outputs.

Referenced by RefSoftmaxWorkload::ExecuteAsync().

21 {
22  Execute(m_Data.m_Inputs, m_Data.m_Outputs);
23 }
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
armnn::RefSoftmaxWorkload::Execute
void Execute() const override
Definition: RefSoftmaxWorkload.cpp:20

◆ ExecuteAsync()

void ExecuteAsync ( ExecutionData &  executionData)
overridevirtual

Implements IWorkload.

Definition at line 25 of file RefSoftmaxWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT, armnn::CpuRef, RefSoftmaxWorkload::Execute(), armnn::GetTensorInfo(), SoftmaxDescriptor::m_Axis, SoftmaxDescriptor::m_Beta, ExecutionData::m_Data, BaseWorkload< SoftmaxQueueDescriptor >::m_Data, WorkingMemDescriptor::m_Inputs, WorkingMemDescriptor::m_Outputs, QueueDescriptorWithParameters< LayerDescriptor >::m_Parameters, and armnn::Softmax.

26 {
27  WorkingMemDescriptor* workingMemDescriptor = static_cast<WorkingMemDescriptor*>(executionData.m_Data);
28  Execute(workingMemDescriptor->m_Inputs, workingMemDescriptor->m_Outputs);
29 }
armnn::RefSoftmaxWorkload::Execute
void Execute() const override
Definition: RefSoftmaxWorkload.cpp:20
The documentation for this class was generated from the following files: