NVIDIA NvNeural SDK
2022.2
GPU inference framework for NVIDIA Nsight Deep Learning Designer
|
Params struct describing a compilation request. More...
#include <nvneural/CudaTypes.h>
Public Attributes | |
IStringList * | pAdditionalCompilerOptions = nullptr |
List of additional flags to pass to the compiler. More... | |
IStringList * | pHeaderContents = nullptr |
List of header contents to provide to the compiler. More... | |
IStringList * | pHeaderNames = nullptr |
List of header filenames to provide to the compiler. More... | |
const char * | pModuleEntryPoint = nullptr |
Name of the entry point; must be a global function. | |
const char * | pModuleName = nullptr |
Translation unit filename to report in compiler diagnostics (e.g., 'mykernel.cu') | |
const char * | pModuleSource = nullptr |
Source code of the translation unit to compile. | |
Params struct describing a compilation request.
IStringList* nvneural::ICudaRuntimeCompiler::CompilationDetails::pAdditionalCompilerOptions = nullptr |
List of additional flags to pass to the compiler.
See nvrtc for more details. If null, no additional compiler flags are passed.
IStringList* nvneural::ICudaRuntimeCompiler::CompilationDetails::pHeaderContents = nullptr |
List of header contents to provide to the compiler.
If null, no headers are provided.
IStringList* nvneural::ICudaRuntimeCompiler::CompilationDetails::pHeaderNames = nullptr |
List of header filenames to provide to the compiler.
If null, no headers are provided.