ArmNN
 24.02
NeonSoftmaxWorkload Class Reference

#include <NeonSoftmaxWorkload.hpp>

Inheritance diagram for NeonSoftmaxWorkload:
[legend]
Collaboration diagram for NeonSoftmaxWorkload:
[legend]

Public Member Functions

 NeonSoftmaxWorkload (const SoftmaxQueueDescriptor &descriptor, const WorkloadInfo &info, std::shared_ptr< arm_compute::MemoryManagerOnDemand > &memoryManager)
 
virtual void Execute () const override
 
- Public Member Functions inherited from NeonBaseWorkload< SoftmaxQueueDescriptor >
 NeonBaseWorkload (const SoftmaxQueueDescriptor &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< SoftmaxQueueDescriptor >
 BaseWorkload (const SoftmaxQueueDescriptor &descriptor, const WorkloadInfo &info)
 
virtual const std::string & GetName () const override
 
void ExecuteAsync (ExecutionData &executionData) override
 
void PostAllocationConfigure () override
 
const SoftmaxQueueDescriptorGetData () const
 
arm::pipe::ProfilingGuid GetGuid () const final
 
virtual bool SupportsTensorHandleReplacement () const override
 
- Public Member Functions inherited from IWorkload
virtual ~IWorkload ()
 
virtual arm::pipe::ProfilingGuid GetGuid () const =0
 
virtual bool SupportsTensorHandleReplacement () const =0
 
virtual const std::string & GetName () const =0
 
virtual void RegisterDebugCallback (const DebugCallbackFunction &)
 
virtual armnn::Optional< armnn::MemoryRequirementsGetMemoryRequirements ()
 

Additional Inherited Members

- Protected Member Functions inherited from NeonBaseWorkload< SoftmaxQueueDescriptor >
virtual void Reconfigure ()
 
- Protected Attributes inherited from BaseWorkload< SoftmaxQueueDescriptor >
SoftmaxQueueDescriptor m_Data
 
const arm::pipe::ProfilingGuid m_Guid
 
const std::string m_Name
 

Detailed Description

Definition at line 24 of file NeonSoftmaxWorkload.hpp.

Constructor & Destructor Documentation

◆ NeonSoftmaxWorkload()

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

Definition at line 33 of file NeonSoftmaxWorkload.cpp.

35  : NeonBaseWorkload<SoftmaxQueueDescriptor>(descriptor, info)
36 {
37  // Report Profiling Details
38  ARMNN_REPORT_PROFILING_WORKLOAD_DESC("NeonSoftmaxWorkload_Construct",
39  descriptor.m_Parameters,
40  info,
41  this->GetGuid());
42 
43  m_Data.ValidateInputsOutputs("NeonSoftmaxWorkload", 1, 1);
44 
45  // The ArmCompute softmax layer uses 2D input/output tensors, so flatten the first three dimensions.
46  arm_compute::ITensor& input = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
47  arm_compute::ITensor& output = PolymorphicDowncast<IAclTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
48 
49  auto layer = std::make_unique<arm_compute::NESoftmaxLayer>(memoryManager);
50  int aclAxis = ComputeAclAxis(m_Data.m_Parameters.m_Axis, info.m_InputTensorInfos[0]);
51  layer->configure(&input, &output, m_Data.m_Parameters.m_Beta, aclAxis);
52  m_SoftmaxLayer.reset(layer.release());
53 }

References ARMNN_REPORT_PROFILING_WORKLOAD_DESC, armnn::ComputeAclAxis(), armnn::info, SoftmaxDescriptor::m_Axis, SoftmaxDescriptor::m_Beta, BaseWorkload< SoftmaxQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, QueueDescriptorWithParameters< LayerDescriptor >::m_Parameters, and QueueDescriptor::ValidateInputsOutputs().

Member Function Documentation

◆ Execute()

void Execute ( ) const
overridevirtual

Implements IWorkload.

Definition at line 55 of file NeonSoftmaxWorkload.cpp.

56 {
57  ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID("NeonSoftmaxWorkload_Execute");
58  m_SoftmaxLayer->run();
59 }

References ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID.


The documentation for this class was generated from the following files:
armnn::QueueDescriptor::ValidateInputsOutputs
void ValidateInputsOutputs(const std::string &descName, unsigned int numExpectedIn, unsigned int numExpectedOut) const
Definition: WorkloadData.cpp:446
armnn::SoftmaxDescriptor::m_Beta
float m_Beta
Exponentiation value.
Definition: Descriptors.hpp:190
armnn::QueueDescriptorWithParameters::m_Parameters
LayerDescriptor m_Parameters
Definition: WorkloadData.hpp:66
armnn::BoostLogSeverityMapping::info
@ info
armnn::QueueDescriptor::m_Outputs
std::vector< ITensorHandle * > m_Outputs
Definition: WorkloadData.hpp:27
ARMNN_REPORT_PROFILING_WORKLOAD_DESC
#define ARMNN_REPORT_PROFILING_WORKLOAD_DESC(name, desc, infos, guid)
Definition: Profiling.hpp:227
armnn::BaseWorkload< SoftmaxQueueDescriptor >::m_Data
SoftmaxQueueDescriptor m_Data
Definition: Workload.hpp:89
armnn::SoftmaxDescriptor::m_Axis
int m_Axis
Scalar, defaulted to the last index (-1), specifying the dimension the activation will be performed o...
Definition: Descriptors.hpp:192
ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID
#define ARMNN_SCOPED_PROFILING_EVENT_NEON_NAME_GUID(label)
Creates a profiling event that uses GetGuid() and GetName() from the calling class.
Definition: NeonWorkloadUtils.hpp:32
armnn::ComputeAclAxis
int ComputeAclAxis(const int &armnnAxis, const armnn::TensorInfo &tensor)
Function to convert ArmNN axis (left to right) to ACL axis (right to left) ranging from [-rank,...
Definition: ArmComputeUtils.hpp:273
armnn::QueueDescriptor::m_Inputs
std::vector< ITensorHandle * > m_Inputs
Definition: WorkloadData.hpp:26