ClMultiplicationWorkload Class Reference

#include <ClMultiplicationWorkload.hpp>

Inheritance diagram for ClMultiplicationWorkload:

Public Member Functions
	ClMultiplicationWorkload (const MultiplicationQueueDescriptor &descriptor, const WorkloadInfo &info, const arm_compute::CLCompileContext &clCompileContext)
void	Execute () const override
Public Member Functions inherited from BaseWorkload< MultiplicationQueueDescriptor >
	BaseWorkload (const MultiplicationQueueDescriptor &descriptor, const WorkloadInfo &info)
void	PostAllocationConfigure () override
const MultiplicationQueueDescriptor &	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< MultiplicationQueueDescriptor >
const MultiplicationQueueDescriptor	m_Data
const profiling::ProfilingGuid	m_Guid

Detailed Description

Definition at line 20 of file ClMultiplicationWorkload.hpp.

Constructor & Destructor Documentation

ClMultiplicationWorkload()

ClMultiplicationWorkload	(	const MultiplicationQueueDescriptor &	descriptor,
		const WorkloadInfo &	info,
		const arm_compute::CLCompileContext &	clCompileContext
	)

Definition at line 47 of file ClMultiplicationWorkload.cpp.

References armnn::ConvertAdditionalInfoToAclActivationLayerInfo(), armnn::IsQuantizedType(), BaseWorkload< MultiplicationQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, WorkloadInfo::m_InputTensorInfos, QueueDescriptor::m_Outputs, and QueueDescriptor::ValidateInputsOutputs().

    : BaseWorkload<MultiplicationQueueDescriptor>(descriptor, info)
{
    m_Data.ValidateInputsOutputs("ClMultiplicationWorkload", 2, 1);

    arm_compute::ICLTensor& input0 = static_cast<IClTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
    arm_compute::ICLTensor& input1 = static_cast<IClTensorHandle*>(m_Data.m_Inputs[1])->GetTensor();
    arm_compute::ICLTensor& output = static_cast<IClTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();

    auto convertPolicy = (IsQuantizedType(info.m_InputTensorInfos[0].GetDataType()) ||
                          IsQuantizedType(info.m_InputTensorInfos[1].GetDataType())) ?
                          arm_compute::ConvertPolicy::SATURATE :
                          arm_compute::ConvertPolicy::WRAP;

    const arm_compute::ActivationLayerInfo activationInfo = ConvertAdditionalInfoToAclActivationLayerInfo(descriptor);

    // Construct
    m_PixelWiseMultiplication.configure(clCompileContext,
                                        &input0,
                                        &input1,
                                        &output,
                                        1.0f,
                                        convertPolicy,
                                        arm_compute::RoundingPolicy::TO_NEAREST_EVEN,
                                        activationInfo);
}

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 76 of file ClMultiplicationWorkload.cpp.

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

{
    ARMNN_SCOPED_PROFILING_EVENT_CL("ClMultiplicationWorkload_Execute");
    RunClFunction(m_PixelWiseMultiplication, CHECK_LOCATION());
}

---

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

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