Builds an engine from a network definition. More...

#include <NvInfer.h>

Public Member Functions
virtual nvinfer1::INetworkDefinition *	createNetwork ()=0
	Create a network definition object. More...

virtual void	setMaxBatchSize (int batchSize)=0
	Set the maximum batch size. More...

virtual int	getMaxBatchSize () const =0
	Get the maximum batch size. More...

virtual void	setMaxWorkspaceSize (std::size_t workspaceSize)=0
	Set the maximum workspace size. More...

virtual std::size_t	getMaxWorkspaceSize () const =0
	Get the maximum workspace size. More...

virtual void	setHalf2Mode (bool mode)=0
	Set whether half2 mode is used. More...

virtual bool	getHalf2Mode () const =0
	Query whether half2 mode is used. More...

virtual void	setDebugSync (bool sync)=0
	Set whether the builder should use debug synchronization. More...

virtual bool	getDebugSync () const =0
	Query whether the builder will use debug synchronization. More...

virtual void	setMinFindIterations (int minFind)=0
	Set the number of minimization iterations used when timing layers. More...

virtual int	getMinFindIterations () const =0
	Query the number of minimization iterations. More...

virtual void	setAverageFindIterations (int avgFind)=0
	Set the number of averaging iterations used when timing layers. More...

virtual int	getAverageFindIterations () const =0
	Query the number of averaging iterations. More...

virtual nvinfer1::ICudaEngine *	buildCudaEngine (nvinfer1::INetworkDefinition &network)=0
	Build a CUDA engine from a network definition. More...

virtual bool	platformHasFastFp16 () const =0
	Determine whether the platform has fast native fp16.

virtual bool	platformHasFastInt8 () const =0
	Determine whether the platform has fast native int8.

virtual void	destroy ()=0
	Destroy this object.

virtual void	setInt8Mode (bool mode)=0
	Set the maximum value for a region. More...

virtual bool	getInt8Mode () const =0
	Query whether Int8 mode is used. More...

virtual void	setInt8Calibrator (IInt8Calibrator *calibrator)=0
	Set Int8 Calibration interface.

virtual void	setDeviceType (ILayer *layer, DeviceType deviceType)=0
	Set the device that this layer must execute on. More...

virtual DeviceType	getDeviceType (const ILayer *layer) const =0
	Get the device that this layer executes on. More...

virtual bool	isDeviceTypeSet (const ILayer *layer) const =0
	whether the DeviceType has been explicitly set for this layer More...

virtual void	resetDeviceType (ILayer *layer)=0
	reset the DeviceType for this layer More...

virtual bool	canRunOnDLA (const ILayer *layer) const =0
	Checks if a layer can run on DLA. More...

virtual void	setDefaultDeviceType (DeviceType deviceType)=0
	Sets the default DeviceType to be used by the builder. It ensures that all the layers that can run on this device will run on it, unless setDeviceType is used to override the default DeviceType for a layer. More...

virtual DeviceType	getDefaultDeviceType () const =0
	Get the default DeviceType which was set by setDefaultDeviceType.

virtual int	getMaxDLABatchSize () const =0
	Get the maximum batch size DLA can support. For any tensor the total volume of index dimensions combined(dimensions other than CHW) with the requested batch size should not exceed the value returned by this function.

virtual void	allowGPUFallback (bool setFallBackMode)=0
	Sets the builder to use GPU if a layer that was supposed to run on DLA can not run on DLA. More...

virtual int	getNbDLACores () const =0
	Returns number of DLA hardware cores accessible.

virtual void	setDLACore (int dlaCore)=0
	Set the DLA core that the engine must execute on. More...

virtual int	getDLACore () const =0
	Get the DLA core that the engine executes on. More...

virtual void	reset (nvinfer1::INetworkDefinition &network)=0
	Resets the builder state.

virtual void	setGpuAllocator (IGpuAllocator *allocator)=0
	Set the GPU allocator. More...

virtual void	setFp16Mode (bool mode)=0
	Set whether or not 16-bit kernels are permitted. More...

virtual bool	getFp16Mode () const =0
	Query whether 16-bit kernels are permitted. More...

virtual void	setStrictTypeConstraints (bool mode)=0
	Set whether or not type constraints are strict. More...

virtual bool	getStrictTypeConstraints () const =0
	Query whether or not type constraints are strict. More...

virtual void	setRefittable (bool canRefit)=0

virtual bool	getRefittable () const =0
	Query whether or not engines will be refittable. More...

virtual void	setEngineCapability (EngineCapability capability)=0
	Configure the builder to target specified EngineCapability flow.

virtual EngineCapability	getEngineCapability () const =0
	Query EngineCapability flow configured for the builder. More...

Detailed Description

Builds an engine from a network definition.

Warning: Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Member Function Documentation

virtual void nvinfer1::IBuilder::allowGPUFallback ( bool setFallBackMode )

pure virtual

Sets the builder to use GPU if a layer that was supposed to run on DLA can not run on DLA.

Parameters

Allows fallback if setFallBackMode is true else disables fallback option.

Note: GPU fallback may only be specified for non-safety modes.

See Also: EngineCapability Simultaneously enabling GPU fallback and safety-restricted modes is disallowed.

virtual nvinfer1::ICudaEngine* nvinfer1::IBuilder::buildCudaEngine ( nvinfer1::INetworkDefinition & network )

pure virtual

Build a CUDA engine from a network definition.

See Also: INetworkDefinition ICudaEngine

virtual bool nvinfer1::IBuilder::canRunOnDLA ( const ILayer * layer ) const

pure virtual

Checks if a layer can run on DLA.

Returns: status true if the layer can on DLA else returns false.

virtual nvinfer1::INetworkDefinition* nvinfer1::IBuilder::createNetwork ( )

pure virtual

Create a network definition object.

See Also: INetworkDefinition

virtual int nvinfer1::IBuilder::getAverageFindIterations ( ) const

pure virtual

Query the number of averaging iterations.

See Also: setAverageFindIterations()

virtual bool nvinfer1::IBuilder::getDebugSync ( ) const

pure virtual

Query whether the builder will use debug synchronization.

See Also: setDebugSync()

virtual DeviceType nvinfer1::IBuilder::getDeviceType ( const ILayer * layer ) const

pure virtual

Get the device that this layer executes on.

Returns: Returns DeviceType of the layer.

virtual int nvinfer1::IBuilder::getDLACore ( ) const

pure virtual

Get the DLA core that the engine executes on.

Returns: If setDLACore is called, returns DLA core from 0 to N-1, else returns 0.

virtual EngineCapability nvinfer1::IBuilder::getEngineCapability ( ) const

pure virtual

Query EngineCapability flow configured for the builder.

See Also: setEngineCapability()

virtual bool nvinfer1::IBuilder::getFp16Mode ( ) const

pure virtual

Query whether 16-bit kernels are permitted.

See Also: setFp16Mode()

virtual bool nvinfer1::IBuilder::getHalf2Mode ( ) const

pure virtual

Query whether half2 mode is used.

See Also: setHalf2Mode()

Deprecated:: This function is superseded by getFp16Mode.

virtual bool nvinfer1::IBuilder::getInt8Mode ( ) const

pure virtual

Query whether Int8 mode is used.

See Also: setInt8Mode()

virtual int nvinfer1::IBuilder::getMaxBatchSize ( ) const

pure virtual

Get the maximum batch size.

Returns: The maximum batch size.

See Also: setMaxBatchSize(); getMaxDLABatchSize()

virtual std::size_t nvinfer1::IBuilder::getMaxWorkspaceSize ( ) const

pure virtual

Get the maximum workspace size.

Returns: The maximum workspace size.

See Also: setMaxWorkspaceSize()

virtual int nvinfer1::IBuilder::getMinFindIterations ( ) const

pure virtual

Query the number of minimization iterations.

See Also: setMinFindIterations()

virtual bool nvinfer1::IBuilder::getRefittable ( ) const

pure virtual

Query whether or not engines will be refittable.

See Also: getRefittable()

virtual bool nvinfer1::IBuilder::getStrictTypeConstraints ( ) const

pure virtual

Query whether or not type constraints are strict.

See Also: setStrictTypeConstraints()

virtual bool nvinfer1::IBuilder::isDeviceTypeSet ( const ILayer * layer ) const

pure virtual

whether the DeviceType has been explicitly set for this layer

Returns: whether the DeviceType has been explicitly set

See Also: setDeviceType() getDeviceType() resetDeviceType()

virtual void nvinfer1::IBuilder::resetDeviceType ( ILayer * layer )

pure virtual

reset the DeviceType for this layer

See Also: setDeviceType() getDeviceType() isDeviceTypeSet()

virtual void nvinfer1::IBuilder::setAverageFindIterations ( int avgFind )

pure virtual

Set the number of averaging iterations used when timing layers.

When timing layers, the builder minimizes over a set of average times for layer execution. This parameter controls the number of iterations used in averaging.

See Also: getAverageFindIterations()

virtual void nvinfer1::IBuilder::setDebugSync ( bool sync )

pure virtual

Set whether the builder should use debug synchronization.

If this flag is true, the builder will synchronize after timing each layer, and report the layer name. It can be useful when diagnosing issues at build time.

virtual void nvinfer1::IBuilder::setDefaultDeviceType ( DeviceType deviceType )

pure virtual

Sets the default DeviceType to be used by the builder. It ensures that all the layers that can run on this device will run on it, unless setDeviceType is used to override the default DeviceType for a layer.

See Also: getDefaultDeviceType()

virtual void nvinfer1::IBuilder::setDeviceType	(	ILayer *	layer,
		DeviceType	deviceType
	)

pure virtual

Set the device that this layer must execute on.

Parameters

DeviceType that this layer must execute on. If DeviceType is not set or is reset, TensorRT will use the default DeviceType set in the builder.

Note: The device type for a layer must be compatible with the safety flow (if specified). For example a layer cannot be marked for DLA execution while the builder is configured for kSAFE_GPU.

See Also: getDeviceType()

virtual void nvinfer1::IBuilder::setDLACore ( int dlaCore )

pure virtual

Set the DLA core that the engine must execute on.

Parameters

dlaCore The DLA core to execute the engine on (0 to N-1, where N is the maximum number of DLA cores present on the device). Default value is 0. DLA Core is not a property of the engine that is preserved by serialization: when the engine is deserialized it will be associated with the DLA core which is configured for the runtime.

See Also: IRuntime::setDLACore() getDLACore()

virtual void nvinfer1::IBuilder::setFp16Mode ( bool mode )

pure virtual

Set whether or not 16-bit kernels are permitted.

During engine build fp16 kernels will also be tried when this mode is enabled.

Parameters

mode	Whether 16-bit kernels are permitted.

See Also: getFp16Mode()

virtual void nvinfer1::IBuilder::setGpuAllocator ( IGpuAllocator * allocator )

pure virtual

Set the GPU allocator.

Parameters

allocator Set the GPU allocator to be used by the builder. All GPU memory acquired will use this allocator. If NULL is passed, the default allocator will be used.

Default: uses cudaMalloc/cudaFree.

Note: This allocator will be passed to any engines created via the builder; thus the lifetime of the allocator must span the lifetime of those engines as well as that of the builder. If nullptr is passed, the default allocator will be used.

virtual void nvinfer1::IBuilder::setHalf2Mode ( bool mode )

pure virtual

Set whether half2 mode is used.

half2 mode is a paired-image mode that is significantly faster for batch sizes greater than one on platforms with fp16 support.

Parameters

mode	Whether half2 mode is used.

See Also: getHalf2Mode()

Deprecated:: This function is superseded by setFp16Mode.

virtual void nvinfer1::IBuilder::setInt8Mode ( bool mode )

pure virtual

Set the maximum value for a region.

Used for INT8 mode compression.

virtual void nvinfer1::IBuilder::setMaxBatchSize ( int batchSize )

pure virtual

Set the maximum batch size.

Parameters

batchSize The maximum batch size which can be used at execution time, and also the batch size for which the engine will be optimized.

See Also: getMaxBatchSize()

virtual void nvinfer1::IBuilder::setMaxWorkspaceSize ( std::size_t workspaceSize )

pure virtual

Set the maximum workspace size.

Parameters

workspaceSize The maximum GPU temporary memory which the engine can use at execution time.

See Also: getMaxWorkspaceSize()

virtual void nvinfer1::IBuilder::setMinFindIterations ( int minFind )

pure virtual

Set the number of minimization iterations used when timing layers.

When timing layers, the builder minimizes over a set of average times for layer execution. This parameter controls the number of iterations used in minimization.

See Also: getMinFindIterations()

virtual void nvinfer1::IBuilder::setRefittable ( bool canRefit )

pure virtual

Set whether engines will be refittable.

virtual void nvinfer1::IBuilder::setStrictTypeConstraints ( bool mode )

pure virtual

Set whether or not type constraints are strict.

When strict type constraints are in use, TensorRT will always choose a layer implementation that conforms to the type constraints specified, if one exists. If this flag is not set, a higher-precision implementation may be chosen if it results in higher performance.

If no conformant layer exists, TensorRT will choose a non-conformant layer if available regardless of the setting of this flag.

See the developer guide for the definition of strictness.

Parameters

mode	Whether type constraints are strict

See Also: getStrictTypeConstraints()

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

NvInfer.h

Public Member Functions

Detailed Description

Member Function Documentation