TensorRT 8.5.3
nvinfer1::IAlgorithm Class Reference

Describes a variation of execution of a layer. An algorithm is represented by IAlgorithmVariant and the IAlgorithmIOInfo for each of its inputs and outputs. An algorithm can be selected or reproduced using AlgorithmSelector::selectAlgorithms().". More...

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IAlgorithm:
nvinfer1::INoCopy

Public Member Functions

TRT_DEPRECATED IAlgorithmIOInfo const & getAlgorithmIOInfo (int32_t index) const noexcept
 Returns the format of an Algorithm input or output. Algorithm inputs are incrementally numbered first, followed by algorithm outputs. More...
 
IAlgorithmVariant const & getAlgorithmVariant () const noexcept
 Returns the algorithm variant. More...
 
float getTimingMSec () const noexcept
 The time in milliseconds to execute the algorithm. More...
 
std::size_t getWorkspaceSize () const noexcept
 The size of the GPU temporary memory in bytes which the algorithm uses at execution time. More...
 
IAlgorithmIOInfo const * getAlgorithmIOInfoByIndex (int32_t index) const noexcept
 Returns the format of an Algorithm input or output. Algorithm inputs are incrementally numbered first, followed by algorithm outputs. More...
 

Protected Member Functions

virtual ~IAlgorithm () noexcept=default
 
- Protected Member Functions inherited from nvinfer1::INoCopy
 INoCopy ()=default
 
virtual ~INoCopy ()=default
 
 INoCopy (INoCopy const &other)=delete
 
INoCopyoperator= (INoCopy const &other)=delete
 
 INoCopy (INoCopy &&other)=delete
 
INoCopyoperator= (INoCopy &&other)=delete
 

Protected Attributes

apiv::VAlgorithm * mImpl
 

Detailed Description

Describes a variation of execution of a layer. An algorithm is represented by IAlgorithmVariant and the IAlgorithmIOInfo for each of its inputs and outputs. An algorithm can be selected or reproduced using AlgorithmSelector::selectAlgorithms().".

See also
IAlgorithmIOInfo, IAlgorithmVariant, IAlgorithmSelector::selectAlgorithms()
Warning
Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Constructor & Destructor Documentation

◆ ~IAlgorithm()

virtual nvinfer1::IAlgorithm::~IAlgorithm ( )
protectedvirtualdefaultnoexcept

Member Function Documentation

◆ getAlgorithmIOInfo()

TRT_DEPRECATED IAlgorithmIOInfo const & nvinfer1::IAlgorithm::getAlgorithmIOInfo ( int32_t  index) const
inlinenoexcept

Returns the format of an Algorithm input or output. Algorithm inputs are incrementally numbered first, followed by algorithm outputs.

Parameters
indexIndex of the input or output of the algorithm. Incremental numbers assigned to indices of inputs and the outputs.
Returns
a reference to IAlgorithmIOInfo specified by index or the first algorithm if index is out of range.
Deprecated:
Deprecated in TensorRT 8.0. Superseded by IAlgorithm::getAlgorithmIOInfoByIndex().

◆ getAlgorithmIOInfoByIndex()

IAlgorithmIOInfo const * nvinfer1::IAlgorithm::getAlgorithmIOInfoByIndex ( int32_t  index) const
inlinenoexcept

Returns the format of an Algorithm input or output. Algorithm inputs are incrementally numbered first, followed by algorithm outputs.

Parameters
indexIndex of the input or output of the algorithm. Incremental numbers assigned to indices of inputs and the outputs.
Returns
a pointer to a IAlgorithmIOInfo interface or nullptr if index is out of range.

◆ getAlgorithmVariant()

IAlgorithmVariant const & nvinfer1::IAlgorithm::getAlgorithmVariant ( ) const
inlinenoexcept

Returns the algorithm variant.

◆ getTimingMSec()

float nvinfer1::IAlgorithm::getTimingMSec ( ) const
inlinenoexcept

The time in milliseconds to execute the algorithm.

◆ getWorkspaceSize()

std::size_t nvinfer1::IAlgorithm::getWorkspaceSize ( ) const
inlinenoexcept

The size of the GPU temporary memory in bytes which the algorithm uses at execution time.

Member Data Documentation

◆ mImpl

apiv::VAlgorithm* nvinfer1::IAlgorithm::mImpl
protected

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