TensorRT  8.0.2
nvinfer1::IPluginV2Ext Class Referenceabstract

Plugin class for user-implemented layers. More...

#include <NvInferRuntimeCommon.h>

Inheritance diagram for nvinfer1::IPluginV2Ext:
nvinfer1::IPluginV2 nvinfer1::IPluginV2DynamicExt nvinfer1::IPluginV2IOExt

Public Member Functions

virtual nvinfer1::DataType getOutputDataType (int32_t index, nvinfer1::DataType const *inputTypes, int32_t nbInputs) const noexcept=0
 Return the DataType of the plugin output at the requested index. The default behavior should be to return the type of the first input, or DataType::kFLOAT if the layer has no inputs. The returned data type must have a format that is supported by the plugin. More...
 
virtual bool isOutputBroadcastAcrossBatch (int32_t outputIndex, bool const *inputIsBroadcasted, int32_t nbInputs) const noexcept=0
 Return true if output tensor is broadcast across a batch. More...
 
virtual bool canBroadcastInputAcrossBatch (int32_t inputIndex) const noexcept=0
 Return true if plugin can use input that is broadcast across batch without replication. More...
 
virtual void configurePlugin (Dims const *inputDims, int32_t nbInputs, Dims const *outputDims, int32_t nbOutputs, DataType const *inputTypes, DataType const *outputTypes, bool const *inputIsBroadcast, bool const *outputIsBroadcast, PluginFormat floatFormat, int32_t maxBatchSize) noexcept=0
 Configure the layer with input and output data types. More...
 
virtual void attachToContext (cudnnContext *, cublasContext *, IGpuAllocator *) noexcept
 Attach the plugin object to an execution context and grant the plugin the access to some context resource. More...
 
virtual void detachFromContext () noexcept
 Detach the plugin object from its execution context. More...
 
IPluginV2Extclone () const noexcept override=0
 Clone the plugin object. This copies over internal plugin parameters as well and returns a new plugin object with these parameters. If the source plugin is pre-configured with configurePlugin(), the returned object should also be pre-configured. The returned object should allow attachToContext() with a new execution context. Cloned plugin objects can share the same per-engine immutable resource (e.g. weights) with the source object (e.g. via ref-counting) to avoid duplication.
 
- Public Member Functions inherited from nvinfer1::IPluginV2
virtual AsciiChar const * getPluginType () const noexcept=0
 Return the plugin type. Should match the plugin name returned by the corresponding plugin creator. More...
 
virtual AsciiChar const * getPluginVersion () const noexcept=0
 Return the plugin version. Should match the plugin version returned by the corresponding plugin creator. More...
 
virtual int32_t getNbOutputs () const noexcept=0
 Get the number of outputs from the layer. More...
 
virtual Dims getOutputDimensions (int32_t index, Dims const *inputs, int32_t nbInputDims) noexcept=0
 Get the dimension of an output tensor. More...
 
virtual bool supportsFormat (DataType type, PluginFormat format) const noexcept=0
 Check format support. More...
 
virtual int32_t initialize () noexcept=0
 Initialize the layer for execution. This is called when the engine is created. More...
 
virtual void terminate () noexcept=0
 Release resources acquired during plugin layer initialization. This is called when the engine is destroyed. More...
 
virtual size_t getWorkspaceSize (int32_t maxBatchSize) const noexcept=0
 Find the workspace size required by the layer. More...
 
virtual int32_t enqueue (int32_t batchSize, void const *const *inputs, void *const *outputs, void *workspace, cudaStream_t stream) noexcept=0
 Execute the layer. More...
 
virtual size_t getSerializationSize () const noexcept=0
 Find the size of the serialization buffer required. More...
 
virtual void serialize (void *buffer) const noexcept=0
 Serialize the layer. More...
 
virtual void destroy () noexcept=0
 Destroy the plugin object. This will be called when the network, builder or engine is destroyed.
 
virtual void setPluginNamespace (AsciiChar const *pluginNamespace) noexcept=0
 Set the namespace that this plugin object belongs to. Ideally, all plugin objects from the same plugin library should have the same namespace.
 
virtual AsciiChar const * getPluginNamespace () const noexcept=0
 Return the namespace of the plugin object.
 

Protected Member Functions

 IPluginV2Ext (IPluginV2Ext const &)=default
 
 IPluginV2Ext (IPluginV2Ext &&)=default
 
IPluginV2Extoperator= (IPluginV2Ext const &) &=default
 
IPluginV2Extoperator= (IPluginV2Ext &&) &=default
 
int32_t getTensorRTVersion () const noexcept override
 Return the API version with which this plugin was built. The upper byte reserved by TensorRT and is used to differentiate this from IPluginV2. More...
 
void configureWithFormat (Dims const *, int32_t, Dims const *, int32_t, DataType, PluginFormat, int32_t) noexcept override
 Derived classes should not implement this. In a C++11 API it would be override final.
 
- Protected Member Functions inherited from nvinfer1::IPluginV2
 IPluginV2 (IPluginV2 const &)=default
 
 IPluginV2 (IPluginV2 &&)=default
 
IPluginV2operator= (IPluginV2 const &) &=default
 
IPluginV2operator= (IPluginV2 &&) &=default
 

Detailed Description

Plugin class for user-implemented layers.

Plugins are a mechanism for applications to implement custom layers. This interface provides additional capabilities to the IPluginV2 interface by supporting different output data types and broadcast across batch.

See also
IPluginV2

Member Function Documentation

◆ attachToContext()

virtual void nvinfer1::IPluginV2Ext::attachToContext ( cudnnContext *  ,
cublasContext *  ,
IGpuAllocator  
)
inlinevirtualnoexcept

Attach the plugin object to an execution context and grant the plugin the access to some context resource.

Parameters
cudnnThe CUDNN context handle of the execution context
cublasThe cublas context handle of the execution context
allocatorThe allocator used by the execution context

This function is called automatically for each plugin when a new execution context is created. If the context was created without resources, this method is not called until the resources are assigned. It is also called if new resources are assigned to the context.

If the plugin needs per-context resource, it can be allocated here. The plugin can also get context-owned CUDNN and CUBLAS context here.

Note
In the automotive safety context, the CUDNN and CUBLAS parameters will be nullptr because CUDNN and CUBLAS is not used by the safe runtime.

◆ canBroadcastInputAcrossBatch()

virtual bool nvinfer1::IPluginV2Ext::canBroadcastInputAcrossBatch ( int32_t  inputIndex) const
pure virtualnoexcept

Return true if plugin can use input that is broadcast across batch without replication.

Parameters
inputIndexIndex of input that could be broadcast.

For each input whose tensor is semantically broadcast across a batch, TensorRT calls this method before calling configurePlugin. If canBroadcastInputAcrossBatch returns true, TensorRT will not replicate the input tensor; i.e., there will be a single copy that the plugin should share across the batch. If it returns false, TensorRT will replicate the input tensor so that it appears like a non-broadcasted tensor.

This method is called only for inputs that can be broadcast.

◆ configurePlugin()

virtual void nvinfer1::IPluginV2Ext::configurePlugin ( Dims const *  inputDims,
int32_t  nbInputs,
Dims const *  outputDims,
int32_t  nbOutputs,
DataType const *  inputTypes,
DataType const *  outputTypes,
bool const *  inputIsBroadcast,
bool const *  outputIsBroadcast,
PluginFormat  floatFormat,
int32_t  maxBatchSize 
)
pure virtualnoexcept

Configure the layer with input and output data types.

This function is called by the builder prior to initialize(). It provides an opportunity for the layer to make algorithm choices on the basis of its weights, dimensions, data types and maximum batch size.

Parameters
inputDimsThe input tensor dimensions.
nbInputsThe number of inputs.
outputDimsThe output tensor dimensions.
nbOutputsThe number of outputs.
inputTypesThe data types selected for the plugin inputs.
outputTypesThe data types selected for the plugin outputs.
inputIsBroadcastTrue for each input that the plugin must broadcast across the batch.
outputIsBroadcastTrue for each output that TensorRT will broadcast across the batch.
floatFormatThe format selected for the engine for the floating point inputs/outputs.
maxBatchSizeThe maximum batch size.

The dimensions passed here do not include the outermost batch size (i.e. for 2-D image networks, they will be 3-dimensional CHW dimensions). When inputIsBroadcast or outputIsBroadcast is true, the outermost batch size for that input or output should be treated as if it is one. inputIsBroadcast[i] is true only if the input is semantically broadcast across the batch and canBroadcastInputAcrossBatch(i) returned true. outputIsBroadcast[i] is true only if isOutputBroadcastAcrossBatch(i) returns true.

Warning
for the floatFormat field, the values PluginFormat::kCHW4, PluginFormat::kCHW16, and PluginFormat::kCHW32 will not be passed in, this is to keep backward compatibility with TensorRT 5.x series. Use PluginV2IOExt or PluginV2DynamicExt for other PluginFormats.

◆ detachFromContext()

virtual void nvinfer1::IPluginV2Ext::detachFromContext ( )
inlinevirtualnoexcept

Detach the plugin object from its execution context.

This function is called automatically for each plugin when a execution context is destroyed or the context resources are unassigned from the context.

If the plugin owns per-context resource, it can be released here.

◆ getOutputDataType()

virtual nvinfer1::DataType nvinfer1::IPluginV2Ext::getOutputDataType ( int32_t  index,
nvinfer1::DataType const *  inputTypes,
int32_t  nbInputs 
) const
pure virtualnoexcept

Return the DataType of the plugin output at the requested index. The default behavior should be to return the type of the first input, or DataType::kFLOAT if the layer has no inputs. The returned data type must have a format that is supported by the plugin.

See also
supportsFormat()
Warning
DataType:kBOOL not supported.

◆ getTensorRTVersion()

int32_t nvinfer1::IPluginV2Ext::getTensorRTVersion ( ) const
inlineoverrideprotectedvirtualnoexcept

Return the API version with which this plugin was built. The upper byte reserved by TensorRT and is used to differentiate this from IPluginV2.

Do not override this method as it is used by the TensorRT library to maintain backwards-compatibility with plugins.

Reimplemented from nvinfer1::IPluginV2.

Reimplemented in nvinfer1::IPluginV2IOExt.

◆ isOutputBroadcastAcrossBatch()

virtual bool nvinfer1::IPluginV2Ext::isOutputBroadcastAcrossBatch ( int32_t  outputIndex,
bool const *  inputIsBroadcasted,
int32_t  nbInputs 
) const
pure virtualnoexcept

Return true if output tensor is broadcast across a batch.

Parameters
outputIndexThe index of the output
inputIsBroadcastedThe ith element is true if the tensor for the ith input is broadcast across a batch.
nbInputsThe number of inputs

The values in inputIsBroadcasted refer to broadcasting at the semantic level, i.e. are unaffected by whether method canBroadcastInputAcrossBatch requests physical replication of the values.


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