RefBackend Class Reference

#include <RefBackend.hpp>

Inheritance diagram for RefBackend:

Collaboration diagram for RefBackend:

Public Member Functions
	RefBackend ()=default
	~RefBackend ()=default
const BackendId &	GetId () const override
IBackendInternal::IMemoryManagerUniquePtr	CreateMemoryManager () const override
IBackendInternal::IWorkloadFactoryPtr	CreateWorkloadFactory (const IBackendInternal::IMemoryManagerSharedPtr &memoryManager=nullptr) const override
IBackendInternal::IWorkloadFactoryPtr	CreateWorkloadFactory (class TensorHandleFactoryRegistry &tensorHandleFactoryRegistry) const override
IBackendInternal::IBackendContextPtr	CreateBackendContext (const IRuntime::CreationOptions &) const override
	Create the runtime context of the backend. More...
IBackendInternal::IBackendProfilingContextPtr	CreateBackendProfilingContext (const IRuntime::CreationOptions &creationOptions, IBackendProfilingPtr &backendProfiling) override
	Create context specifically used for profiling interaction from backends. More...
IBackendInternal::ILayerSupportSharedPtr	GetLayerSupport () const override
OptimizationViews	OptimizeSubgraphView (const SubgraphView &subgraph, const ModelOptions &modelOptions) const override
std::vector< ITensorHandleFactory::FactoryId >	GetHandleFactoryPreferences () const override
	(Optional) Returns a vector of supported TensorHandleFactory ids in preference order. More...
void	RegisterTensorHandleFactories (class TensorHandleFactoryRegistry &registry) override
	(Optional) Register TensorHandleFactories Either this method or CreateMemoryManager() and IWorkloadFactory::CreateTensor() IWorkloadFactory::CreateSubtensor() methods must be implemented. More...
BackendCapabilities	GetCapabilities () const override
	Returns a BackendCapability if the backend lists the capability The BackendCapability must then be inspected to check whether or not that BackendCapability is supported Otherwise returns an EmptyOptional if the BackendCapability is unlisted. More...
std::unique_ptr< ICustomAllocator >	GetDefaultAllocator () const override
	Returns the default memory allocator for the backend. More...
Public Member Functions inherited from IBackendInternal
	~IBackendInternal () override=default
	Allow backends created by the factory function to be destroyed through IBackendInternal. More...
virtual IWorkloadFactoryPtr	CreateWorkloadFactory (const IMemoryManagerSharedPtr &memoryManager, const ModelOptions &modelOptions) const
virtual IWorkloadFactoryPtr	CreateWorkloadFactory (class TensorHandleFactoryRegistry &tensorHandleFactoryRegistry, const ModelOptions &modelOptions) const
virtual IWorkloadFactoryPtr	CreateWorkloadFactory (class TensorHandleFactoryRegistry &tensorHandleFactoryRegistry, const ModelOptions &modelOptions, MemorySourceFlags inputFlags, MemorySourceFlags outputFlags) const
virtual IBackendSpecificModelContextPtr	CreateBackendSpecificModelContext (const ModelOptions &modelOptions) const
virtual ILayerSupportSharedPtr	GetLayerSupport (const ModelOptions &modelOptions) const
virtual OptimizationViews	OptimizeSubgraphView (const SubgraphView &subgraph) const
bool	SupportsTensorAllocatorAPI () const
ITensorHandleFactory::FactoryId	GetBackwardCompatibleFavoriteHandleFactory ()
virtual void	RegisterTensorHandleFactories (class TensorHandleFactoryRegistry &registry, MemorySourceFlags inputFlags, MemorySourceFlags outputFlags)
	(Optional) Register TensorHandleFactories Either this method or CreateMemoryManager() and IWorkloadFactory::CreateTensor() IWorkloadFactory::CreateSubtensor() methods must be implemented. More...
virtual bool	UseCustomMemoryAllocator (std::shared_ptr< ICustomAllocator > allocator, armnn::Optional< std::string & > errMsg)
	Signals the backend to use a custom memory allocator provided by the user. More...
virtual unsigned int	GetNumberOfCacheFiles () const
	Returns the number of files cached if backend supports caching. More...

Static Public Member Functions
static const BackendId &	GetIdStatic ()
Static Public Member Functions inherited from IBackendInternal
static constexpr BackendVersion	GetApiVersion ()
	Returns the version of the Backend API. More...

Additional Inherited Members
Public Types inherited from IBackendInternal
using	IWorkloadFactoryPtr = std::unique_ptr< IWorkloadFactory >
using	IBackendContextPtr = std::unique_ptr< IBackendContext >
using	IBackendProfilingContextPtr = std::shared_ptr< arm::pipe::IBackendProfilingContext >
	This is the bridge between backend and backend profiling we'll keep it in the backend namespace. More...
using	IBackendProfilingPtr = std::unique_ptr< arm::pipe::IBackendProfiling >
using	ILayerSupportSharedPtr = std::shared_ptr< ILayerSupport >
using	IBackendSpecificModelContextPtr = std::shared_ptr< IBackendModelContext >
using	IMemoryManagerUniquePtr = std::unique_ptr< IMemoryManager >
using	IMemoryManagerSharedPtr = std::shared_ptr< IMemoryManager >
Protected Member Functions inherited from IBackendInternal
	IBackendInternal ()=default
	Creation must be done through a specific backend interface. More...
Protected Member Functions inherited from IBackend
	IBackend ()
virtual	~IBackend ()

Detailed Description

Definition at line 30 of file RefBackend.hpp.

Constructor & Destructor Documentation

RefBackend()

RefBackend ( )

default

~RefBackend()

~RefBackend ( )

default

Member Function Documentation

CreateBackendContext()

IBackendInternal::IBackendContextPtr CreateBackendContext ( const IRuntime::CreationOptions &  ) const

overridevirtual

Create the runtime context of the backend.

Implementations may return a default-constructed IBackendContextPtr if no context is needed at runtime. Implementations must throw BackendUnavailableException if the backend cannot be used (for example, necessary accelerator hardware is not present). The default implementation always returns a default-constructed pointer.

Reimplemented from IBackendInternal.

Definition at line 50 of file RefBackend.cpp.

{
    return IBackendContextPtr{};
}

CreateBackendProfilingContext()

IBackendInternal::IBackendProfilingContextPtr CreateBackendProfilingContext ( const IRuntime::CreationOptions &  creationOptions, IBackendProfilingPtr &  backendProfiling  )

overridevirtual

Create context specifically used for profiling interaction from backends.

Reimplemented from IBackendInternal.

Definition at line 55 of file RefBackend.cpp.

{
    return IBackendProfilingContextPtr{};
}

CreateMemoryManager()

IBackendInternal::IMemoryManagerUniquePtr CreateMemoryManager ( ) const

overridevirtual

Reimplemented from IBackendInternal.

Definition at line 61 of file RefBackend.cpp.

{
    return std::make_unique<RefMemoryManager>();
}

CreateWorkloadFactory() [1/2]

IBackendInternal::IWorkloadFactoryPtr CreateWorkloadFactory ( class TensorHandleFactoryRegistry &  tensorHandleFactoryRegistry ) const

overridevirtual

Reimplemented from IBackendInternal.

Definition at line 34 of file RefBackend.cpp.

{
    auto memoryManager = std::make_shared<RefMemoryManager>();
 
    tensorHandleFactoryRegistry.RegisterMemoryManager(memoryManager);
 
    std::unique_ptr<RefTensorHandleFactory> factory = std::make_unique<RefTensorHandleFactory>(memoryManager);
    // Register copy and import factory pair
    tensorHandleFactoryRegistry.RegisterCopyAndImportFactoryPair(factory->GetId(), factory->GetId());
    // Register the factory
    tensorHandleFactoryRegistry.RegisterFactory(std::move(factory));
 
    return std::make_unique<RefWorkloadFactory>(PolymorphicPointerDowncast<RefMemoryManager>(memoryManager));
}

References TensorHandleFactoryRegistry::RegisterCopyAndImportFactoryPair(), TensorHandleFactoryRegistry::RegisterFactory(), and TensorHandleFactoryRegistry::RegisterMemoryManager().

CreateWorkloadFactory() [2/2]

IBackendInternal::IWorkloadFactoryPtr CreateWorkloadFactory ( const IBackendInternal::IMemoryManagerSharedPtr &  memoryManager = nullptr ) const

overridevirtual

Implements IBackendInternal.

Definition at line 28 of file RefBackend.cpp.

{
    return std::make_unique<RefWorkloadFactory>(PolymorphicPointerDowncast<RefMemoryManager>(memoryManager));
}

GetCapabilities()

BackendCapabilities GetCapabilities ( ) const

inlineoverridevirtual

Returns a BackendCapability if the backend lists the capability The BackendCapability must then be inspected to check whether or not that BackendCapability is supported Otherwise returns an EmptyOptional if the BackendCapability is unlisted.

Reimplemented from IBackendInternal.

Definition at line 61 of file RefBackend.hpp.

    {
        return cpuRefCapabilities;
    };

References armnn::cpuRefCapabilities.

GetDefaultAllocator()

std::unique_ptr< ICustomAllocator > GetDefaultAllocator ( ) const

overridevirtual

Returns the default memory allocator for the backend.

Returns

- Returns unique pointer to the Default Allocator of the Backend

Reimplemented from IBackendInternal.

Definition at line 157 of file RefBackend.cpp.

{
    return std::make_unique<DefaultAllocator>();
}

GetHandleFactoryPreferences()

std::vector< ITensorHandleFactory::FactoryId > GetHandleFactoryPreferences ( ) const

overridevirtual

(Optional) Returns a vector of supported TensorHandleFactory ids in preference order.

Reimplemented from IBackendInternal.

Definition at line 138 of file RefBackend.cpp.

{
    return std::vector<ITensorHandleFactory::FactoryId> { RefTensorHandleFactory::GetIdStatic() };
}

References RefTensorHandleFactory::GetIdStatic().

GetId()

const BackendId& GetId ( ) const

inlineoverridevirtual

Implements IBackend.

Definition at line 37 of file RefBackend.hpp.

{ return GetIdStatic(); }

References RefBackend::GetIdStatic().

GetIdStatic()

const BackendId & GetIdStatic ( )

static

Definition at line 22 of file RefBackend.cpp.

{
    static const BackendId s_Id{RefBackendId()};
    return s_Id;
}

References armnn::RefBackendId().

Referenced by GetBackendId(), and RefBackend::GetId().

GetLayerSupport()

IBackendInternal::ILayerSupportSharedPtr GetLayerSupport ( ) const

overridevirtual

Implements IBackendInternal.

Definition at line 66 of file RefBackend.cpp.

{
    static ILayerSupportSharedPtr layerSupport{new RefLayerSupport};
    return layerSupport;
}

OptimizeSubgraphView()

OptimizationViews OptimizeSubgraphView ( const SubgraphView &  subgraph, const ModelOptions &  modelOptions  ) const

overridevirtual

Reimplemented from IBackendInternal.

Definition at line 72 of file RefBackend.cpp.

{
    OptimizationViews optimizationViews(modelOptions);
 
    auto it = subgraph.end();
    std::map<LayerGuid, Layer*> untouched;
 
    while (it != subgraph.begin())
    {
        --it;
        Layer& base = *(PolymorphicDowncast<Layer*>(*it));
        untouched.insert({base.GetGuid(), &base});
    }
 
    it = subgraph.end();
    while (it != subgraph.begin())
    {
        --it;
        Layer& base = *(PolymorphicDowncast<Layer*>(*it));
 
        // Special case to fuse padding into average pooling 2d for quantized datatype.
        // Required to be done as a backend specific optimization as Neon does not support this special case.
        if (base.GetType() == LayerType::Pooling2d)
        {
            Pooling2dLayer* baseLayer = PolymorphicDowncast<Pooling2dLayer*>(&base);
            Pooling2dDescriptor poolingDescriptor = baseLayer->GetParameters();
 
            if (baseLayer->GetInputSlot(0).GetConnectedOutputSlot()->GetOwningLayer().GetType() == LayerType::Pad)
            {
                PadLayer* padLayer = PolymorphicDowncast<PadLayer*>(
                    &baseLayer->GetInputSlot(0).GetConnectedOutputSlot()->GetOwningLayer());
                if (padLayer->GetOutputSlot(0).GetNumConnections() == 1 &&
                    optimizations::pad_fold::TryFoldPadIntoLayer2d(padLayer->GetParameters(),
                                                                   poolingDescriptor,
                                                                   padLayer->GetOutputSlot().GetTensorInfo(),
                                                                   true))
                {
                    FoldPadIntoAveragePool2d<Pooling2dLayer>(optimizationViews, baseLayer,
                                                             poolingDescriptor, padLayer);
                    untouched.erase(baseLayer->GetGuid());
                    untouched.erase(padLayer->GetGuid());
                }
            }
        }
 
        // Remove Reshape where possible
        if (base.GetType() == LayerType::Reshape)
        {
            ReshapeLayer* baseLayer = PolymorphicDowncast<ReshapeLayer*>(&base);
            RemoveReshapeLayer(baseLayer, untouched, optimizationViews);
        }
    }
 
    if (optimizationViews.GetSubstitutions().empty() && optimizationViews.GetDeletedSubgraphs().empty())
    {
        optimizationViews.AddUntouchedSubgraph(SubgraphView(subgraph));
    }
    else
    {
        ReportUntouchedLayers(optimizationViews, untouched);
    }
 
    return optimizationViews;
}

References OptimizationViews::AddUntouchedSubgraph(), SubgraphView::begin(), SubgraphView::end(), InputSlot::GetConnectedOutputSlot(), OptimizationViews::GetDeletedSubgraphs(), Layer::GetGuid(), Layer::GetInputSlot(), OutputSlot::GetNumConnections(), Layer::GetOutputSlot(), OutputSlot::GetOwningLayer(), LayerWithParameters< Parameters >::GetParameters(), OptimizationViews::GetSubstitutions(), OutputSlot::GetTensorInfo(), Layer::GetType(), armnn::Pad, armnn::Pooling2d, armnn::RemoveReshapeLayer(), armnn::ReportUntouchedLayers(), armnn::Reshape, and armnn::optimizations::pad_fold::TryFoldPadIntoLayer2d().

RegisterTensorHandleFactories()

void RegisterTensorHandleFactories ( class TensorHandleFactoryRegistry &  )

overridevirtual

(Optional) Register TensorHandleFactories Either this method or CreateMemoryManager() and IWorkloadFactory::CreateTensor() IWorkloadFactory::CreateSubtensor() methods must be implemented.

Reimplemented from IBackendInternal.

Definition at line 143 of file RefBackend.cpp.

{
    auto memoryManager = std::make_shared<RefMemoryManager>();
 
    registry.RegisterMemoryManager(memoryManager);
 
    std::unique_ptr<RefTensorHandleFactory> factory = std::make_unique<RefTensorHandleFactory>(memoryManager);
 
    // Register copy and import factory pair
    registry.RegisterCopyAndImportFactoryPair(factory->GetId(), factory->GetId());
    // Register the factory
    registry.RegisterFactory(std::move(factory));
}

References TensorHandleFactoryRegistry::RegisterCopyAndImportFactoryPair(), TensorHandleFactoryRegistry::RegisterFactory(), and TensorHandleFactoryRegistry::RegisterMemoryManager().

---

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

• src/backends/reference/RefBackend.hpp
• src/backends/reference/RefBackend.cpp