NeonMinimumWorkload Class Reference

#include <NeonMinimumWorkload.hpp>

Inheritance diagram for NeonMinimumWorkload:

Collaboration diagram for NeonMinimumWorkload:

Public Member Functions
	NeonMinimumWorkload (const MinimumQueueDescriptor &descriptor, const WorkloadInfo &info)
	Create a NeonMinimumWorkload. More...
virtual void	Execute () const override
	Execute the Minimum operation. More...
Public Member Functions inherited from NeonBaseWorkload< MinimumQueueDescriptor >
	NeonBaseWorkload (const MinimumQueueDescriptor &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< MinimumQueueDescriptor >
	BaseWorkload (const MinimumQueueDescriptor &descriptor, const WorkloadInfo &info)
virtual const std::string &	GetName () const override
void	ExecuteAsync (ExecutionData &executionData) override
void	PostAllocationConfigure () override
const MinimumQueueDescriptor &	GetData () const
arm::pipe::ProfilingGuid	GetGuid () const final
virtual bool	SupportsTensorHandleReplacement () const override
Public Member Functions inherited from IWorkload
virtual	~IWorkload ()
virtual arm::pipe::ProfilingGuid	GetGuid () const =0
virtual bool	SupportsTensorHandleReplacement () const =0
virtual const std::string &	GetName () const =0
virtual void	RegisterDebugCallback (const DebugCallbackFunction &)
virtual armnn::Optional< armnn::MemoryRequirements >	GetMemoryRequirements ()

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

Detailed Description

Definition at line 25 of file NeonMinimumWorkload.hpp.

Constructor & Destructor Documentation

NeonMinimumWorkload()

NeonMinimumWorkload	(	const MinimumQueueDescriptor &	descriptor,
		const WorkloadInfo &	info
	)

Create a NeonMinimumWorkload.

Parameters

[in]	descriptor	The MinimumQueueDescriptor to configure this operation.
[in]	info	The workload where this operation can be found.

Definition at line 28 of file NeonMinimumWorkload.cpp.

    : NeonBaseWorkload<MinimumQueueDescriptor>(descriptor, info)
{
    m_Data.ValidateInputsOutputs("NeonMinimumWorkload", 2, 1);
 
    arm_compute::ITensor& input0 = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
    arm_compute::ITensor& input1 = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Inputs[1])->GetTensor();
    arm_compute::ITensor& output = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
 
    m_MinLayer.configure(&input0, &input1, &output);
}

References armnn::info, BaseWorkload< MinimumQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, and QueueDescriptor::ValidateInputsOutputs().

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Execute the Minimum operation.

Implements IWorkload.

Definition at line 41 of file NeonMinimumWorkload.cpp.

{
    ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID("NeonMinimumWorkload_Execute");
    m_MinLayer.run();
}

References ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID.

---

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

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