Real-time compilation of programs using the NVIDIA libraries. More...

Namespaces
	compilation_output
	Definitions relating to and supporting the compilation_output_t class.

	program
	Definitions relating to source-code programs to be compiled.

Classes
struct	common_ptx_compilation_options_t
	A subset of the options for compiling PTX code into SASS, usable both with the CUDA driver and with NVIDIA's PTX compilation library. More...

struct	compilation_options_base_t
	Compilation options common to all kinds of JIT-compilable programs. More...

class	compilation_options_t
	Options to be passed to one of the NVIDIA JIT compilers along with a program's source code. More...

class	compilation_options_t< cuda_cpp >
	Options for JIT-compilation of CUDA C++ code. More...

class	compilation_options_t< ptx >
	Options for JIT-compilation of CUDA PTX code. More...

class	compilation_output_base_t
	The result of the compilation of an {rtc::program_t}, whether successful or failed, with any related byproducts. More...

class	compilation_output_t
	The output produced by a compilation process by one of the CUDA libraries, including any byproducts. More...

class	compilation_output_t< cuda_cpp >
	Output of CUDA C++ code JIT-compilation. More...

class	program_t

class	program_t< cuda_cpp >
	Wrapper class for a CUDA runtime-compilable program. More...

class	runtime_error
	A (base?) class for exceptions raised by CUDA code; these errors are thrown by essentially all CUDA Runtime API wrappers upon failure. More...

Typedefs
using	ptx_register_count_t = int16_t
	The type used to specify the maximum number of SM registers to use, to the PTX compiler.

using	optimization_level_t = int
	The type used to specify the intensity, and extent of allowed implication, of optimization efforts, for the PTX compilation.

using	const_cstrings_span = span< const char *const >
	A span of C-style strings the contents of which must not be modified.

template<source_kind_t Kind>
using	status_t = typename detail_::types< Kind >::status_type
	Status values returned by the NVIDIA run-time compilation libraries's API calls: The NVRTC library for CUDA C++, and the PTX compiler library.

Enumerations
enum	cpp_dialect_t { cpp03 = 0, cpp11 = 1, cpp14 = 2, cpp17 = 3, last = cpp17 }

enum	: rtc::optimization_level_t { O0 = 0, no_optimization = O0, O1 = 1, O2 = 2, O3 = 3, maximum_optimization = O3 }
	Commonly-used phrases regarding the optimization level (e.g. More...

Functions
template<typename CompilationOptions >
inline ::std::string	render (const CompilationOptions &opts)

Variables
struct {
optimization_level_t minimum

optimization_level_t maximum

}	valid_optimization_level_range
	The range of optimization level values outside of which the compiler is certain not to support.

Detailed Description

Real-time compilation of programs using the NVIDIA libraries.

Enumeration Type Documentation

Commonly-used phrases regarding the optimization level (e.g.

from GCC's command-line arguments), translated into the numeric levels the RTC compilation actually accepts