NVRTC defines the following enumeration type and function for API call error handling.

NVRTC defines the following function for general information query.

NVRTC defines the following type and functions for actual compilation.

NVRTC supports the compile options below. Option names with two preceding dashs (--) are long option names and option names with one preceding dash (-) are short option names. Short option names can be used instead of long option names. When a compile option takes an argument, an assignment operator (=) is used to separate the compile option argument from the compile option name, e.g., "--gpu-architecture=compute_20". Alternatively, the compile option name and the argument can be specified in separate strings without an assignment operator, .e.g, "--gpu-architecturend""compute_20". Single-character short option names, such as -D, -U, and -I, do not require an assignment operator, and the compile option name and the argument can be present in the same string with or without spaces between them. For instance, "-D=<def>", "-D<def>", and "-D <def>" are all supported.

The valid compiler options are:

• Compilation targets

  • --gpu-architecture=<arch> (-arch)

    Specify the name of the class of GPU architectures for which the input must be compiled.

    • Valid <arch>s:

      • compute_20

      • compute_30

      • compute_35

      • compute_50

      • compute_52

      • compute_53

    • Default: compute_20

• Separate compilation / whole-program compilation

  • --device-c (-dc)

    Generate relocatable code that can be linked with other relocatable device code. It is equivalent to --relocatable-device-code=true.

  • --device-w (-dw)

    Generate non-relocatable code. It is equivalent to --relocatable-device-code=false.

  • --relocatable-device-code={true|false} (-rdc)

    Enable (disable) the generation of relocatable device code.

    • Default: false

• Debugging support

  • --device-debug (-G)

    Generate debug information.

  • --generate-line-info (-lineinfo)

    Generate line-number information.

• Code generation

  • --maxrregcount=<N> (-maxrregcount)

    Specify the maximum amount of registers that GPU functions can use. Until a function-specific limit, a higher value will generally increase the performance of individual GPU threads that execute this function. However, because thread registers are allocated from a global register pool on each GPU, a higher value of this option will also reduce the maximum thread block size, thereby reducing the amount of thread parallelism. Hence, a good maxrregcount value is the result of a trade-off. If this option is not specified, then no maximum is assumed. Value less than the minimum registers required by ABI will be bumped up by the compiler to ABI minimum limit.

  • --ftz={true|false} (-ftz)

    When performing single-precision floating-point operations, flush denormal values to zero or preserve denormal values. --use_fast_math implies --ftz=true.

    • Default: false

  • --prec-sqrt={true|false} (-prec-sqrt)

    For single-precision floating-point square root, use IEEE round-to-nearest mode or use a faster approximation. --use_fast_math implies --prec-sqrt=false.

    • Default: true

  • --prec-div={true|false} (-prec-div)

    For single-precision floating-point division and reciprocals, use IEEE round-to-nearest mode or use a faster approximation. --use_fast_math implies --prec-div=false.

    • Default: true

  • --fmad={true|false} (-fmad)

    Enables (disables) the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add operations (FMAD, FFMA, or DFMA). --use_fast_math implies --fmad=true.

    • Default: true

  • --use_fast_math (-use_fast_math)

    Make use of fast math operations. --use_fast_math implies --ftz=true--prec-div=false--prec-sqrt=false--fmad=true.

• Preprocessing

  • --define-macro=<def> (-D)

    <def> can be either <name> or <name=definitions>.

    • <name>

      Predefine <name> as a macro with definition 1.

    • <name>=<definition>

      The contents of <definition> are tokenized and preprocessed as if they appeared during translation phase three in a #define directive. In particular, the definition will be truncated by embedded new line characters.

  • --undefine-macro=<def> (-U)

    Cancel any previous definition of <def>.

  • --include-path=<dir> (-I)

    Add the directory <dir> to the list of directories to be searched for headers. These paths are searched after the list of headers given to nvrtcCreateProgram.

  • --pre-include=<header> (-include)

    Preinclude <header> during preprocessing.

• Language Dialect

  • --std=c++11 (-std=c++11)

    Set language dialect to C++11.

  • --builtin-move-forward={true|false} (-builtin-move-forward)

    Provide builtin definitions of std::move and std::forward, when C++11 language dialect is selected.

    • Default: true

  • --builtin-initializer-list={true|false} (-builtin-initializer-list)

    Provide builtin definitions of std::initializer_list class and member functions when C++11 language dialect is selected.

    • Default: true

• Misc.

  • --disable-warnings (-w)

    Inhibit all warning messages.

  • --restrict (-restrict)

    Programmer assertion that all kernel pointer parameters are restrict pointers.

  • --device-as-default-execution-space (-default-device)

    Treat entities with no execution space annotation as __device__ entities.