ArmNN
 21.08
NeonLogSoftmaxWorkload Class Reference

#include <NeonLogSoftmaxWorkload.hpp>

Inheritance diagram for NeonLogSoftmaxWorkload:
BaseWorkload< LogSoftmaxQueueDescriptor > IWorkload

Public Member Functions

 NeonLogSoftmaxWorkload (const LogSoftmaxQueueDescriptor &descriptor, const WorkloadInfo &info, std::shared_ptr< arm_compute::MemoryManagerOnDemand > &memoryManager)
 
virtual void Execute () const override
 
- Public Member Functions inherited from BaseWorkload< LogSoftmaxQueueDescriptor >
 BaseWorkload (const LogSoftmaxQueueDescriptor &descriptor, const WorkloadInfo &info)
 
void ExecuteAsync (WorkingMemDescriptor &workingMemDescriptor) override
 
void PostAllocationConfigure () override
 
const LogSoftmaxQueueDescriptorGetData () 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< LogSoftmaxQueueDescriptor >
LogSoftmaxQueueDescriptor m_Data
 
const profiling::ProfilingGuid m_Guid
 

Detailed Description

Definition at line 24 of file NeonLogSoftmaxWorkload.hpp.

Constructor & Destructor Documentation

◆ NeonLogSoftmaxWorkload()

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

Definition at line 33 of file NeonLogSoftmaxWorkload.cpp.

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

36  : BaseWorkload<LogSoftmaxQueueDescriptor>(descriptor, info)
37 {
38  // Report Profiling Details
39  ARMNN_REPORT_PROFILING_WORKLOAD_DESC("NeonLogSoftmaxWorkload_Construct",
40  descriptor.m_Parameters,
41  info,
42  this->GetGuid());
43 
44  m_Data.ValidateInputsOutputs("NeonLogSoftmaxWorkload", 1, 1);
45 
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::NELogSoftmaxLayer>(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_LogSoftmaxLayer.reset(layer.release());
53 }
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...
int m_Axis
Scalar, defaulted to the last index (-1), specifying the dimension the activation will be performed o...
float m_Beta
Exponentiation value.
void ValidateInputsOutputs(const std::string &descName, unsigned int numExpectedIn, unsigned int numExpectedOut) const
std::vector< ITensorHandle * > m_Outputs
#define ARMNN_REPORT_PROFILING_WORKLOAD_DESC(name, desc, infos, guid)
Definition: Profiling.hpp:226
std::vector< ITensorHandle * > m_Inputs

Member Function Documentation

◆ Execute()

void Execute ( ) const
overridevirtual

Implements IWorkload.

Definition at line 55 of file NeonLogSoftmaxWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT_NEON_GUID, and BaseWorkload< LogSoftmaxQueueDescriptor >::GetGuid().

56 {
57  ARMNN_SCOPED_PROFILING_EVENT_NEON_GUID("NeonLogSoftmaxWorkload_Execute", this->GetGuid());
58  m_LogSoftmaxLayer->run();
59 }
profiling::ProfilingGuid GetGuid() const final
Definition: Workload.hpp:55
#define ARMNN_SCOPED_PROFILING_EVENT_NEON_GUID(name, guid)

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