NVIDIA NvNeural SDK  2022.2
GPU inference framework for NVIDIA Nsight Deep Learning Designer
nvneural::PrototypeDesc Struct Reference

This structure represent a prototype layer version (backend, tensor format and kernel type), it should be passed to ClassRegistry using registerPrototype. More...

#include <nvneural/CoreTypes.h>

Public Attributes

NetworkBackendId backend
 This is the backend identifier supported by this instance of the prototype layer. More...
 
CompilationLevel compilationLevel
 This is the compilation level of the contained kernel.
 
const char * pDisplayName
 An optional human-readable prototype name. More...
 
const char * pObjectClass
 This is the programmatic class name used to instantiate the prototype object through the IPlugin::createObject interface. More...
 
const char * pSerializedName
 This is the name used to represent the prototype type in serialized form. More...
 
std::size_t structSize
 This is the sizeof() this struct. More...
 
TensorFormat tensorFormat
 This is the tensor format supported by this prototype layer.
 

Detailed Description

This structure represent a prototype layer version (backend, tensor format and kernel type), it should be passed to ClassRegistry using registerPrototype.

The same remarks from LayerDesc regarding struct packing, ABI and struct versions applies.

Member Data Documentation

◆ backend

NetworkBackendId nvneural::PrototypeDesc::backend

This is the backend identifier supported by this instance of the prototype layer.

Prototype supporting multiple backends should expose multiple PrototypeDesc instances.

◆ pDisplayName

const char* nvneural::PrototypeDesc::pDisplayName

An optional human-readable prototype name.

Generally used in host editor. If this is not defined (nullptr) then pSerializedName will be used. String should be treated as UTF-8.

◆ pObjectClass

const char* nvneural::PrototypeDesc::pObjectClass

This is the programmatic class name used to instantiate the prototype object through the IPlugin::createObject interface.

Example: "com.nvidia.prototype.cuda.nchw.fp32"

◆ pSerializedName

const char* nvneural::PrototypeDesc::pSerializedName

This is the name used to represent the prototype type in serialized form.

String should be treated as UTF-8.

Examples: "cuda_nchw_fp32", "cubin_nhwc_fp16"

◆ structSize

std::size_t nvneural::PrototypeDesc::structSize

This is the sizeof() this struct.

It is used for versioning, for instance, one plugin could have an earlier version of this struct and the host a later version and thus, their structSize would be different.


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