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

#include <NeonMinimumWorkload.hpp>

Inheritance diagram for NeonMinimumWorkload:
BaseWorkload< MinimumQueueDescriptor > IWorkload

Public Member Functions

 NeonMinimumWorkload (const MinimumQueueDescriptor &descriptor, const WorkloadInfo &info)
 Create a NeonMinimumWorkload. More...
 
virtual void Execute () const override
 Execute the Minimum operation. More...
 
- Public Member Functions inherited from BaseWorkload< MinimumQueueDescriptor >
 BaseWorkload (const MinimumQueueDescriptor &descriptor, const WorkloadInfo &info)
 
void PostAllocationConfigure () override
 
const MinimumQueueDescriptor & 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< MinimumQueueDescriptor >
const MinimumQueueDescriptor m_Data
 
const profiling::ProfilingGuid m_Guid
 

Detailed Description

Definition at line 23 of file NeonMinimumWorkload.hpp.

Constructor & Destructor Documentation

◆ NeonMinimumWorkload()

NeonMinimumWorkload ( const MinimumQueueDescriptor &  descriptor,
const WorkloadInfo &  info 
)

Create a NeonMinimumWorkload.

Parameters
[in]descriptorThe MinimumQueueDescriptor to configure this operation.
[in]infoThe workload where this operation can be found.

Definition at line 26 of file NeonMinimumWorkload.cpp.

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

28  : BaseWorkload<MinimumQueueDescriptor>(descriptor, info)
29 {
30  m_Data.ValidateInputsOutputs("NeonMinimumWorkload", 2, 1);
31 
32  arm_compute::ITensor& input0 = boost::polymorphic_downcast<IAclTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
33  arm_compute::ITensor& input1 = boost::polymorphic_downcast<IAclTensorHandle*>(m_Data.m_Inputs[1])->GetTensor();
34  arm_compute::ITensor& output = boost::polymorphic_downcast<IAclTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
35 
36  m_MinLayer.configure(&input0, &input1, &output);
37 }
armnn::BaseWorkload< MinimumQueueDescriptor >::m_Data
const MinimumQueueDescriptor 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

Execute the Minimum operation.

Implements IWorkload.

Definition at line 39 of file NeonMinimumWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT_NEON.

40 {
41  ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonMinimumWorkload_Execute");
42  m_MinLayer.run();
43 }
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: