ClPooling2dWorkload Class Reference

#include <ClPooling2dWorkload.hpp>

Inheritance diagram for ClPooling2dWorkload:

Public Member Functions
	ClPooling2dWorkload (const Pooling2dQueueDescriptor &descriptor, const WorkloadInfo &info)
void	Execute () const override
Public Member Functions inherited from BaseWorkload< Pooling2dQueueDescriptor >
	BaseWorkload (const Pooling2dQueueDescriptor &descriptor, const WorkloadInfo &info)
void	PostAllocationConfigure () override
const Pooling2dQueueDescriptor &	GetData () const
profiling::ProfilingGuid	GetGuid () const final
Public Member Functions inherited from IWorkload
virtual	~IWorkload ()
virtual void	RegisterDebugCallback (const DebugCallbackFunction &)

Additional Inherited Members
Protected Attributes inherited from BaseWorkload< Pooling2dQueueDescriptor >
const Pooling2dQueueDescriptor	m_Data
const profiling::ProfilingGuid	m_Guid

Detailed Description

Definition at line 19 of file ClPooling2dWorkload.hpp.

Constructor & Destructor Documentation

ClPooling2dWorkload()

ClPooling2dWorkload	(	const Pooling2dQueueDescriptor &	descriptor,
		const WorkloadInfo &	info
	)

Definition at line 30 of file ClPooling2dWorkload.cpp.

References BaseWorkload< Pooling2dQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, and QueueDescriptor::ValidateInputsOutputs().

    : BaseWorkload<Pooling2dQueueDescriptor>(descriptor, info)
{
    m_Data.ValidateInputsOutputs("ClPooling2dWorkload", 1, 1);

    arm_compute::ICLTensor& input = static_cast<IClTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
    arm_compute::ICLTensor& output = static_cast<IClTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();

    arm_compute::DataLayout aclDataLayout = ConvertDataLayout(m_Data.m_Parameters.m_DataLayout);
    input.info()->set_data_layout(aclDataLayout);
    output.info()->set_data_layout(aclDataLayout);

    // flag to use wider accumulators (32 bit instead of 16 for FP16) to improve accuracy
    // enable fp_mixed_precision for the the FP16 cases that
    // accumulation reaches a limit beyond which there is no more increment of the value
    bool fpMixedPrecision = false;

    arm_compute::PoolingLayerInfo layerInfo = BuildArmComputePoolingLayerInfo(m_Data.m_Parameters, fpMixedPrecision);

    // Run the layer.
    m_PoolingLayer.configure(&input, &output, layerInfo);
}

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 54 of file ClPooling2dWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT_CL, CHECK_LOCATION, and armnn::RunClFunction().

{
    ARMNN_SCOPED_PROFILING_EVENT_CL("ClPooling2dWorkload_Execute");
    RunClFunction(m_PoolingLayer, CHECK_LOCATION());
}

---

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

• src/backends/cl/workloads/ClPooling2dWorkload.hpp
• src/backends/cl/workloads/ClPooling2dWorkload.cpp