Similar to IPluginV2Ext, but with support for dynamic shapes. More...

#include <NvInferRuntime.h>

Inheritance diagram for nvinfer1::IPluginV2DynamicExt:

Public Member Functions
IPluginV2DynamicExt *	clone () 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 must also be pre-configured. The returned object must 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. More...

virtual DimsExprs	getOutputDimensions (int32_t outputIndex, DimsExprs const *inputs, int32_t nbInputs, IExprBuilder &exprBuilder) noexcept=0
	Get expressions for computing dimensions of an output tensor from dimensions of the input tensors. More...

virtual bool	supportsFormatCombination (int32_t pos, PluginTensorDesc const *inOut, int32_t nbInputs, int32_t nbOutputs) noexcept=0
	Return true if plugin supports the format and datatype for the input/output indexed by pos. More...

virtual void	configurePlugin (DynamicPluginTensorDesc const in, int32_t nbInputs, DynamicPluginTensorDesc const out, int32_t nbOutputs) noexcept=0
	Configure the plugin. More...

virtual size_t	getWorkspaceSize (PluginTensorDesc const inputs, int32_t nbInputs, PluginTensorDesc const outputs, int32_t nbOutputs) const noexcept=0
	Find the workspace size required by the layer. More...

virtual int32_t	enqueue (PluginTensorDesc const inputDesc, PluginTensorDesc const outputDesc, void const const inputs, void const outputs, void *workspace, cudaStream_t stream) noexcept=0
	Execute the layer. More...

Public Member Functions inherited from nvinfer1::IPluginV2Ext
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. More...

	IPluginV2Ext ()=default

	~IPluginV2Ext () override=default

virtual void	attachToContext (cudnnContext , cublasContext , IGpuAllocator *) noexcept
	Attach the plugin object to an execution context and grant the plugin the access to some context resources. More...

virtual void	detachFromContext () noexcept
	Detach the plugin object from its execution context. More...

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 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	getSerializationSize () const noexcept=0
	Find the size of the serialization buffer required to store the plugin configuration in a binary file. 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. More...

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 must have the same namespace. More...

virtual AsciiChar const *	getPluginNamespace () const noexcept=0
	Return the namespace of the plugin object. More...

Static Public Attributes
static constexpr int32_t	kFORMAT_COMBINATION_LIMIT = 100
	Limit on number of format combinations accepted. More...

Protected Member Functions
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...

virtual	~IPluginV2DynamicExt () noexcept

Protected Member Functions inherited from nvinfer1::IPluginV2Ext
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 must not implement this. In a C++11 API it would be override final. More...

Detailed Description

Similar to IPluginV2Ext, but with support for dynamic shapes.

Clients should override the public methods, including the following inherited methods:

virtual int32_t getNbOutputs() const noexcept = 0;
virtual DataType getOutputDataType(int32_t index, DataType const* inputTypes, int32_t nbInputs) const noexcept = 0;
virtual size_t getSerializationSize() const noexcept = 0;
virtual void serialize(void* buffer) const noexcept = 0;
virtual void destroy() noexcept = 0;
virtual void setPluginNamespace(char const* pluginNamespace) noexcept = 0;
virtual char const* getPluginNamespace() const noexcept = 0;

For weakly typed networks, the inputTypes will always be DataType::kFLOAT or DataType::kINT32, and the returned type is canonicalized to DataType::kFLOAT if it is DataType::kHALF or DataType:kINT8. For strongly typed networks, inputTypes are inferred from previous operations, and getOutputDataType specifies the returned type based on the inputTypes. Details about the floating-point precision are elicited later by method supportsFormatCombination.

Deprecated:: Deprecated in TensorRT 10.0. Please implement IPluginV3 instead.

Constructor & Destructor Documentation

◆ ~IPluginV2DynamicExt()

virtual nvinfer1::IPluginV2DynamicExt::~IPluginV2DynamicExt ( )

inlineprotectedvirtualnoexcept

Member Function Documentation

◆ clone()

IPluginV2DynamicExt * nvinfer1::IPluginV2DynamicExt::clone ( ) const

overridepure virtualnoexcept

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 must also be pre-configured. The returned object must 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.

Returns: A pointer to a cloned plugin object if cloning was successful, otherwise nullptr.

Usage considerations

Allowed context for the API call
- Thread-safe: Yes, this method is required to be thread-safe and may be called from multiple threads when building networks on multiple devices sharing the same plugin.

Implements nvinfer1::IPluginV2Ext.

◆ configurePlugin()

virtual void nvinfer1::IPluginV2DynamicExt::configurePlugin	(	DynamicPluginTensorDesc const *	in,
		int32_t	nbInputs,
		DynamicPluginTensorDesc const *	out,
		int32_t	nbOutputs
	)

pure virtualnoexcept

Configure the plugin.

configurePlugin() can be called multiple times in both the build and execution phases. The build phase happens before initialize() is called and only occurs during creation of an engine by IBuilder. The execution phase happens after initialize() is called and occurs during both creation of an engine by IBuilder and execution of an engine by IExecutionContext.

Build phase: IPluginV2DynamicExt->configurePlugin is called when a plugin is being prepared for profiling but not for any specific input size. This provides an opportunity for the plugin to make algorithmic choices on the basis of input and output formats, along with the bound of possible dimensions. The min and max value of the DynamicPluginTensorDesc correspond to the kMIN and kMAX value of the current profile that the plugin is being profiled for, with the desc.dims field corresponding to the dimensions of plugin specified at network creation. Wildcard dimensions will exist during this phase in the desc.dims field.

Execution phase: IPluginV2DynamicExt->configurePlugin is called when a plugin is being prepared for executing the plugin for a specific dimensions. This provides an opportunity for the plugin to change algorithmic choices based on the explicit input dimensions stored in desc.dims field.

IBuilder will call this function once per profile, with desc.dims resolved to the values specified by the kOPT field of the current profile. Wildcard dimensions will not exist during this phase.

IExecutionContext will call this during the next subsequent instance enqueue[V2]() or execute[V2]() if:

The batch size is changed from previous call of execute()/enqueue() if hasImplicitBatchDimension() returns true.
The optimization profile is changed via setOptimizationProfileAsync().

An input execution binding is changed via setInputShape().

Warning: The execution phase is timing critical during IExecutionContext but is not part of the timing loop when called from IBuilder. Performance bottlenecks of configurePlugin won't show up during engine building but will be visible during execution after calling functions that trigger layer resource updates.

Parameters

in	The input tensors attributes that are used for configuration.
nbInputs	Number of input tensors.
out	The output tensors attributes that are used for configuration.
nbOutputs	Number of output tensors.

◆ enqueue()

virtual int32_t nvinfer1::IPluginV2DynamicExt::enqueue	(	PluginTensorDesc const *	inputDesc,
		PluginTensorDesc const *	outputDesc,
		void const const	inputs,
		void const	outputs,
		void *	workspace,
		cudaStream_t	stream
	)

pure virtualnoexcept

Execute the layer.

Parameters

inputDesc	how to interpret the memory for the input tensors.
outputDesc	how to interpret the memory for the output tensors.
inputs	The memory for the input tensors.
outputs	The memory for the output tensors.
workspace	Workspace for execution.
stream	The stream in which to execute the kernels.

Returns: 0 for success, else non-zero (which will cause engine termination).

◆ getOutputDimensions()

virtual DimsExprs nvinfer1::IPluginV2DynamicExt::getOutputDimensions	(	int32_t	outputIndex,
		DimsExprs const *	inputs,
		int32_t	nbInputs,
		IExprBuilder &	exprBuilder
	)

pure virtualnoexcept

Get expressions for computing dimensions of an output tensor from dimensions of the input tensors.

Parameters

outputIndex	The index of the output tensor
inputs	Expressions for dimensions of the input tensors
nbInputs	The number of input tensors
exprBuilder	Object for generating new expressions

This function is called by the implementations of IBuilder during analysis of the network.

Example #1: A plugin has a single output that transposes the last two dimensions of the plugin's single input. The body of the override of getOutputDimensions can be:

DimsExprs output(inputs[0]);
std::swap(output.d[output.nbDims-1], output.d[output.nbDims-2]);
return output;

Example #2: A plugin concatenates its two inputs along the first dimension. The body of the override of getOutputDimensions can be:

DimsExprs output(inputs[0]);
output.d[0] = exprBuilder.operation(DimensionOperation::kSUM, *inputs[0].d[0], *inputs[1].d[0]);
return output;

◆ getTensorRTVersion()

int32_t nvinfer1::IPluginV2DynamicExt::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.

◆ getWorkspaceSize()

virtual size_t nvinfer1::IPluginV2DynamicExt::getWorkspaceSize	(	PluginTensorDesc const *	inputs,
		int32_t	nbInputs,
		PluginTensorDesc const *	outputs,
		int32_t	nbOutputs
	)		const

pure virtualnoexcept

Find the workspace size required by the layer.

This function is called after the plugin is configured, and possibly during execution. The result should be a sufficient workspace size to deal with inputs and outputs of the given size or any smaller problem.

Returns: The workspace size.

◆ supportsFormatCombination()

virtual bool nvinfer1::IPluginV2DynamicExt::supportsFormatCombination	(	int32_t	pos,
		PluginTensorDesc const *	inOut,
		int32_t	nbInputs,
		int32_t	nbOutputs
	)

pure virtualnoexcept

Return true if plugin supports the format and datatype for the input/output indexed by pos.

For this method inputs are numbered 0..(nbInputs-1) and outputs are numbered nbInputs..(nbInputs+nbOutputs-1). Using this numbering, pos is an index into InOut, where 0 <= pos < nbInputs+nbOutputs.

TensorRT invokes this method to ask if the input/output indexed by pos supports the format/datatype specified by inOut[pos].format and inOut[pos].type. The override should return true if that format/datatype at inOut[pos] are supported by the plugin. If support is conditional on other input/output formats/datatypes, the plugin can make its result conditional on the formats/datatypes in inOut[0..pos-1], which will be set to values that the plugin supports. The override should not inspect inOut[pos+1..nbInputs+nbOutputs-1], which will have invalid values. In other words, the decision for pos must be based on inOut[0..pos] only.

Some examples:

A definition for a plugin that supports only FP16 NCHW:

  return inOut[pos].format == TensorFormat::kLINEAR && inOut[pos].type == DataType::kHALF;

A definition for a plugin that supports only FP16 NCHW for its two inputs, and FP32 NCHW for its single output:

  return inOut[pos].format == TensorFormat::kLINEAR && (inOut[pos].type == (pos < 2 ? DataType::kHALF :
  DataType::kFLOAT));

A definition for a "polymorphic" plugin with two inputs and one output that supports any format or type, but the inputs and output must have the same format and type:
```
  return pos == 0 || (inOut[pos].format == inOut.format[0] && inOut[pos].type == inOut[0].type);
```
Warning: TensorRT will stop asking for formats once it finds kFORMAT_COMBINATION_LIMIT on combinations.

Member Data Documentation

◆ kFORMAT_COMBINATION_LIMIT

constexpr int32_t nvinfer1::IPluginV2DynamicExt::kFORMAT_COMBINATION_LIMIT = 100

staticconstexpr

Limit on number of format combinations accepted.

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

NvInferRuntime.h

Public Member Functions

Static Public Attributes

Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ ~IPluginV2DynamicExt()

Member Function Documentation

◆ clone()

◆ configurePlugin()

◆ enqueue()

◆ getOutputDimensions()

◆ getTensorRTVersion()

◆ getWorkspaceSize()

◆ supportsFormatCombination()

Member Data Documentation

◆ kFORMAT_COMBINATION_LIMIT