ArmNN
 20.02
Public Member Functions | List of all members
NeonQuantizeWorkload Class Reference

#include <NeonQuantizeWorkload.hpp>

Inheritance diagram for NeonQuantizeWorkload:
BaseWorkload< QuantizeQueueDescriptor > IWorkload

Public Member Functions

 NeonQuantizeWorkload (const QuantizeQueueDescriptor &descriptor, const WorkloadInfo &workloadInfo)
 
void Execute () const override
 
- Public Member Functions inherited from BaseWorkload< QuantizeQueueDescriptor >
 BaseWorkload (const QuantizeQueueDescriptor &descriptor, const WorkloadInfo &info)
 
void PostAllocationConfigure () override
 
const QuantizeQueueDescriptor & 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< QuantizeQueueDescriptor >
const QuantizeQueueDescriptor m_Data
 
const profiling::ProfilingGuid m_Guid
 

Detailed Description

Definition at line 16 of file NeonQuantizeWorkload.hpp.

Constructor & Destructor Documentation

◆ NeonQuantizeWorkload()

NeonQuantizeWorkload ( const QuantizeQueueDescriptor &  descriptor,
const WorkloadInfo &  workloadInfo 
)

Definition at line 27 of file NeonQuantizeWorkload.cpp.

References BaseWorkload< QuantizeQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, and QueueDescriptor::ValidateInputsOutputs().

29  : BaseWorkload<QuantizeQueueDescriptor>(descriptor, workloadInfo)
30 {
31  m_Data.ValidateInputsOutputs("NeonQuantizeWorkload", 1, 1);
32 
33  arm_compute::ITensor& input = boost::polymorphic_pointer_downcast<IAclTensorHandle>(
34  m_Data.m_Inputs[0])->GetTensor();
35  arm_compute::ITensor& output = boost::polymorphic_pointer_downcast<IAclTensorHandle>(
36  m_Data.m_Outputs[0])->GetTensor();
37 
38  m_Layer.reset(new arm_compute::NEQuantizationLayer());
39  m_Layer->configure(&input, &output);
40  m_Layer->prepare();
41 }
armnn::BaseWorkload< QuantizeQueueDescriptor >::m_Data
const QuantizeQueueDescriptor m_Data
Definition: Workload.hpp:46
armnn::QueueDescriptor::ValidateInputsOutputs
void ValidateInputsOutputs(const std::string &descName, unsigned int numExpectedIn, unsigned int numExpectedOut) const
Definition: WorkloadData.cpp:461
armnn::QueueDescriptor::m_Outputs
std::vector< ITensorHandle * > m_Outputs
Definition: WorkloadData.hpp:31
armnn::QueueDescriptor::m_Inputs
std::vector< ITensorHandle * > m_Inputs
Definition: WorkloadData.hpp:30

Member Function Documentation

◆ Execute()

void Execute ( ) const
overridevirtual

Implements IWorkload.

Definition at line 43 of file NeonQuantizeWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT_NEON.

44 {
45  if (m_Layer)
46  {
47  ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonQuantizeWorkload_Execute");
48  m_Layer->run();
49  }
50 }
ARMNN_SCOPED_PROFILING_EVENT_NEON
#define ARMNN_SCOPED_PROFILING_EVENT_NEON(name)
Definition: NeonWorkloadUtils.hpp:17
The documentation for this class was generated from the following files: