NeonStackWorkload Class Reference

#include <NeonStackWorkload.hpp>

Inheritance diagram for NeonStackWorkload:

Public Member Functions
	NeonStackWorkload (const StackQueueDescriptor &descriptor, const WorkloadInfo &info)
void	Execute () const override
Public Member Functions inherited from NeonBaseWorkload< StackQueueDescriptor >
	NeonBaseWorkload (const StackQueueDescriptor &descriptor, const WorkloadInfo &info)
void	ReplaceInputTensorHandle (ITensorHandle *tensorHandle, unsigned int slot) override
void	ReplaceOutputTensorHandle (ITensorHandle *tensorHandle, unsigned int slot) override
Public Member Functions inherited from BaseWorkload< StackQueueDescriptor >
	BaseWorkload (const StackQueueDescriptor &descriptor, const WorkloadInfo &info)
void	ExecuteAsync (ExecutionData &executionData) override
void	PostAllocationConfigure () override
const StackQueueDescriptor &	GetData () const
arm::pipe::ProfilingGuid	GetGuid () const final
virtual bool	SupportsTensorHandleReplacement () const override
Public Member Functions inherited from IWorkload
virtual	~IWorkload ()
virtual void	RegisterDebugCallback (const DebugCallbackFunction &)
virtual armnn::Optional< armnn::MemoryRequirements >	GetMemoryRequirements ()

Additional Inherited Members
Protected Member Functions inherited from NeonBaseWorkload< StackQueueDescriptor >
virtual void	Reconfigure ()
Protected Attributes inherited from BaseWorkload< StackQueueDescriptor >
StackQueueDescriptor	m_Data
const arm::pipe::ProfilingGuid	m_Guid

Detailed Description

Definition at line 18 of file NeonStackWorkload.hpp.

Constructor & Destructor Documentation

NeonStackWorkload()

NeonStackWorkload	(	const StackQueueDescriptor &	descriptor,
		const WorkloadInfo &	info
	)

Definition at line 49 of file NeonStackWorkload.cpp.

References ARMNN_REPORT_PROFILING_WORKLOAD_DESC, TensorShape::GetNumDimensions(), StackDescriptor::m_Axis, BaseWorkload< StackQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, StackDescriptor::m_InputShape, QueueDescriptor::m_Outputs, and QueueDescriptorWithParameters< LayerDescriptor >::m_Parameters.

: NeonBaseWorkload<StackQueueDescriptor>(descriptor, info)
{
    // Report Profiling Details
    ARMNN_REPORT_PROFILING_WORKLOAD_DESC("NeonStackWorkload_Construct",
                                         descriptor.m_Parameters,
                                         info,
                                         this->GetGuid());

    std::vector<arm_compute::ITensor*> aclInputs;
    for (auto input : m_Data.m_Inputs)
    {
        arm_compute::ITensor& aclInput = PolymorphicPointerDowncast<IAclTensorHandle>(input)->GetTensor();
        aclInputs.emplace_back(&aclInput);
    }
    arm_compute::ITensor& output = PolymorphicPointerDowncast<IAclTensorHandle>(
        m_Data.m_Outputs[0])->GetTensor();

    m_Layer.reset(new arm_compute::NEStackLayer());
    int aclAxis = CalcAxis(descriptor.m_Parameters.m_Axis, descriptor.m_Parameters.m_InputShape.GetNumDimensions());
    m_Layer->configure(aclInputs, aclAxis, &output);
}

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 72 of file NeonStackWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT_NEON_GUID, and BaseWorkload< StackQueueDescriptor >::GetGuid().

{
    if (m_Layer)
    {
        ARMNN_SCOPED_PROFILING_EVENT_NEON_GUID("NeonStackWorkload_Execute", this->GetGuid());
        m_Layer->run();
    }
}

---

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

• src/backends/neon/workloads/NeonStackWorkload.hpp
• src/backends/neon/workloads/NeonStackWorkload.cpp