ClSoftmaxUint8Workload Class Reference

#include <ClSoftmaxUint8Workload.hpp>

Inheritance diagram for ClSoftmaxUint8Workload:

Public Member Functions
	ClSoftmaxUint8Workload (const SoftmaxQueueDescriptor &descriptor, const WorkloadInfo &info, std::shared_ptr< arm_compute::MemoryManagerOnDemand > &memoryManager)
void	Execute () const override
Public Member Functions inherited from TypedWorkload< QueueDescriptor, DataTypes >
	TypedWorkload (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 18 of file ClSoftmaxUint8Workload.hpp.

Constructor & Destructor Documentation

ClSoftmaxUint8Workload()

ClSoftmaxUint8Workload	(	const SoftmaxQueueDescriptor &	descriptor,
		const WorkloadInfo &	info,
		std::shared_ptr< arm_compute::MemoryManagerOnDemand > &	memoryManager
	)

Definition at line 16 of file ClSoftmaxUint8Workload.cpp.

References armnn::ComputeSoftmaxAclAxis(), SoftmaxDescriptor::m_Beta, BaseWorkload< QueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, WorkloadInfo::m_InputTensorInfos, QueueDescriptor::m_Outputs, QueueDescriptorWithParameters< LayerDescriptor >::m_Parameters, and QueueDescriptor::ValidateInputsOutputs().

    : Uint8Workload<SoftmaxQueueDescriptor>(descriptor, info)
    , m_SoftmaxLayer(memoryManager)
{
    m_Data.ValidateInputsOutputs("ClSoftmaxUint8Workload", 1, 1);

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

    const auto outputQuantization = output.info()->quantization_info();

    if ((!outputQuantization.scale().empty() && outputQuantization.scale()[0] != (1.0f / 256.0f)) ||
        (!outputQuantization.offset().empty() && outputQuantization.offset()[0] != 0) ||
         outputQuantization.scale().empty() || outputQuantization.offset().empty())
    {
        throw InvalidArgumentException(
            "Invalid quantization for output. Only scale = 1.0f / 256.0f and offset = 0 supported");
    }

    unsigned int aclAxis = ComputeSoftmaxAclAxis(m_Data.m_Parameters, info.m_InputTensorInfos[0]);
    m_SoftmaxLayer.configure(&input, &output, descriptor.m_Parameters.m_Beta, aclAxis);
}

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 40 of file ClSoftmaxUint8Workload.cpp.

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

{
    ARMNN_SCOPED_PROFILING_EVENT_CL("ClSoftmaxUint8Workload_Execute");
    RunClFunction(m_SoftmaxLayer, CHECK_LOCATION());
}

---

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

• src/backends/cl/workloads/ClSoftmaxUint8Workload.hpp
• src/backends/cl/workloads/ClSoftmaxUint8Workload.cpp