NeonStridedSliceWorkload Class Reference

#include <NeonStridedSliceWorkload.hpp>

Inheritance diagram for NeonStridedSliceWorkload:

Collaboration diagram for NeonStridedSliceWorkload:

Public Member Functions
	NeonStridedSliceWorkload (const StridedSliceQueueDescriptor &descriptor, const WorkloadInfo &info)
virtual void	Execute () const override
Public Member Functions inherited from NeonBaseWorkload< StridedSliceQueueDescriptor >
	NeonBaseWorkload (const StridedSliceQueueDescriptor &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< QueueDescriptor >
	BaseWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info)
virtual const std::string &	GetName () const override
void	PostAllocationConfigure () override
const QueueDescriptor &	GetData () const
arm::pipe::ProfilingGuid	GetGuid () const final
virtual bool	SupportsTensorHandleReplacement () const override
Public Member Functions inherited from IWorkload
virtual	~IWorkload ()
virtual void	RegisterDebugCallback (const DebugCallbackFunction &)
virtual armnn::Optional< armnn::MemoryRequirements >	GetMemoryRequirements ()

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

Detailed Description

Definition at line 24 of file NeonStridedSliceWorkload.hpp.

Constructor & Destructor Documentation

NeonStridedSliceWorkload()

NeonStridedSliceWorkload	(	const StridedSliceQueueDescriptor &	descriptor,
		const WorkloadInfo &	info )

Definition at line 51 of file NeonStridedSliceWorkload.cpp.

        : NeonBaseWorkload<StridedSliceQueueDescriptor>(descriptor, info)
{
    // Report Profiling Details
    ARMNN_REPORT_PROFILING_WORKLOAD_DESC("NeonStridedSliceWorkload_Construct",
                                         descriptor.m_Parameters,
                                         info,
                                         this->GetGuid());
 
    m_Data.ValidateInputsOutputs("NeonStridedSliceWorkload", 1, 1);
 
    arm_compute::ITensor& input = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
    arm_compute::ITensor& output = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
 
    arm_compute::Coordinates starts;
    arm_compute::Coordinates ends;
    arm_compute::Coordinates strides;
 
    std::tie(starts, ends, strides) = SetNeonStridedSliceData(m_Data.m_Parameters.m_Begin,
                                                              m_Data.m_Parameters.m_End,
                                                              m_Data.m_Parameters.m_Stride);
 
    auto numDimensions       = armnn::numeric_cast<int>(info.m_InputTensorInfos[0].GetNumDimensions());
    int32_t begin_mask       = ConvertMaskToACLFormat(m_Data.m_Parameters.m_BeginMask, numDimensions);
    int32_t end_mask         = ConvertMaskToACLFormat(m_Data.m_Parameters.m_EndMask, numDimensions);
    int32_t shrink_axis_mask = ConvertMaskToACLFormat(m_Data.m_Parameters.m_ShrinkAxisMask, numDimensions);
 
    arm_compute::DataLayout aclDataLayout = ConvertDataLayout(m_Data.m_Parameters.m_DataLayout);
    input.info()->set_data_layout(aclDataLayout);
    output.info()->set_data_layout(aclDataLayout);
 
    auto layer = std::make_unique<arm_compute::NEStridedSlice>();
 
    layer->configure(&input,
                     &output,
                     starts,
                     ends,
                     strides,
                     begin_mask,
                     end_mask,
                     shrink_axis_mask);
    m_Layer.reset(layer.release());
}

References ARMNN_REPORT_PROFILING_WORKLOAD_DESC, armnn::ConvertMaskToACLFormat(), armnn::info, BaseWorkload< QueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, QueueDescriptorWithParameters< LayerDescriptor >::m_Parameters, armnn::SetNeonStridedSliceData(), and QueueDescriptor::ValidateInputsOutputs().

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 96 of file NeonStridedSliceWorkload.cpp.

{
    ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID("NeonStridedSliceWorkload_Execute");
    m_Layer->run();
}

References ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID.

---

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

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