RefConvertFp32ToFp16Workload Class Reference

#include <RefConvertFp32ToFp16Workload.hpp>

Inheritance diagram for RefConvertFp32ToFp16Workload:

Public Member Functions
virtual void	Execute () const override
Public Member Functions inherited from MultiTypedWorkload< QueueDescriptor, InputDataType, OutputDataType >
	MultiTypedWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info)
Public Member Functions inherited from BaseWorkload< QueueDescriptor >
	BaseWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info)
void	PostAllocationConfigure () override
const QueueDescriptor &	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< QueueDescriptor >
const QueueDescriptor	m_Data
const profiling::ProfilingGuid	m_Guid

Detailed Description

Definition at line 14 of file RefConvertFp32ToFp16Workload.hpp.

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 17 of file RefConvertFp32ToFp16Workload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT, FloatingPointConverter::ConvertFloat32To16(), armnn::CpuRef, armnn::GetInputTensorDataFloat(), TensorInfo::GetNumElements(), armnn::GetOutputTensorDataHalf(), armnn::GetTensorInfo(), BaseWorkload< QueueDescriptor >::m_Data, and QueueDescriptor::m_Inputs.

{
    ARMNN_SCOPED_PROFILING_EVENT(Compute::CpuRef, "RefConvertFp32ToFp16Workload_Execute");

    const float* const input = GetInputTensorDataFloat(0, m_Data);
    Half*  const output = GetOutputTensorDataHalf(0, m_Data);

    // convert Fp32 input to Fp16 output
    unsigned int numElements = GetTensorInfo(m_Data.m_Inputs[0]).GetNumElements();
    armnnUtils::FloatingPointConverter::ConvertFloat32To16(input, numElements, output);
}

---

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

• src/backends/reference/workloads/RefConvertFp32ToFp16Workload.hpp
• src/backends/reference/workloads/RefConvertFp32ToFp16Workload.cpp