cuda.core.experimental.ProgramOptions#

class cuda.core.experimental.ProgramOptions(
name: str | None = '<default program>',
arch: str | None = None,
relocatable_device_code: bool | None = None,
extensible_whole_program: bool | None = None,
debug: bool | None = None,
lineinfo: bool | None = None,
device_code_optimize: bool | None = None,
ptxas_options: str | List[str] | Tuple[str] | None = None,
max_register_count: int | None = None,
ftz: bool | None = None,
prec_sqrt: bool | None = None,
prec_div: bool | None = None,
fma: bool | None = None,
use_fast_math: bool | None = None,
extra_device_vectorization: bool | None = None,
link_time_optimization: bool | None = None,
gen_opt_lto: bool | None = None,
define_macro: str | Tuple[str, str] | List[str | Tuple[str, str]] | Tuple[str | Tuple[str, str]] | None = None,
undefine_macro: str | List[str] | Tuple[str] | None = None,
include_path: str | List[str] | Tuple[str] | None = None,
pre_include: str | List[str] | Tuple[str] | None = None,
no_source_include: bool | None = None,
std: str | None = None,
builtin_move_forward: bool | None = None,
builtin_initializer_list: bool | None = None,
disable_warnings: bool | None = None,
restrict: bool | None = None,
device_as_default_execution_space: bool | None = None,
device_int128: bool | None = None,
optimization_info: str | None = None,
no_display_error_number: bool | None = None,
diag_error: int | List[int] | Tuple[int] | None = None,
diag_suppress: int | List[int] | Tuple[int] | None = None,
diag_warn: int | List[int] | Tuple[int] | None = None,
brief_diagnostics: bool | None = None,
time: str | None = None,
split_compile: int | None = None,
fdevice_syntax_only: bool | None = None,
minimal: bool | None = None,
)#

Customizable options for configuring Program.

name#

Name of the program. If the compilation succeeds, the name is passed down to the generated ObjectCode.

Type:

str, optional

arch#

Pass the SM architecture value, such as sm_<CC> (for generating CUBIN) or compute_<CC> (for generating PTX). If not provided, the current device’s architecture will be used.

Type:

str, optional

relocatable_device_code#

Enable (disable) the generation of relocatable device code. Default: False

Type:

bool, optional

extensible_whole_program#

Do extensible whole program compilation of device code. Default: False

Type:

bool, optional

debug#

Generate debug information. If –dopt is not specified, then turns off all optimizations. Default: False

Type:

bool, optional

lineinfo#

Generate line-number information. Default: False

Type:

bool, optional

device_code_optimize#

Enable device code optimization. When specified along with ‘-G’, enables limited debug information generation for optimized device code. Default: None

Type:

bool, optional

ptxas_options#

Specify one or more options directly to ptxas, the PTX optimizing assembler. Options should be strings. For example [“-v”, “-O2”]. Default: None

Type:

Union[str, List[str]], optional

max_register_count#

Specify the maximum amount of registers that GPU functions can use. Default: None

Type:

int, optional

ftz#

When performing single-precision floating-point operations, flush denormal values to zero or preserve denormal values. Default: False

Type:

bool, optional

prec_sqrt#

For single-precision floating-point square root, use IEEE round-to-nearest mode or use a faster approximation. Default: True

Type:

bool, optional

prec_div#

For single-precision floating-point division and reciprocals, use IEEE round-to-nearest mode or use a faster approximation. Default: True

Type:

bool, optional

fma#

Enables (disables) the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add operations. Default: True

Type:

bool, optional

use_fast_math#

Make use of fast math operations. Default: False

Type:

bool, optional

extra_device_vectorization#

Enables more aggressive device code vectorization in the NVVM optimizer. Default: False

Type:

bool, optional

Generate intermediate code for later link-time optimization. Default: False

Type:

bool, optional

gen_opt_lto#

Run the optimizer passes before generating the LTO IR. Default: False

Type:

bool, optional

define_macro#

Predefine a macro. Can be either a string, in which case that macro will be set to 1, a 2 element tuple of strings, in which case the first element is defined as the second, or a list of strings or tuples. Default: None

Type:

Union[str, Tuple[str, str], List[Union[str, Tuple[str, str]]]], optional

undefine_macro#

Cancel any previous definition of a macro, or list of macros. Default: None

Type:

Union[str, List[str]], optional

include_path#

Add the directory or directories to the list of directories to be searched for headers. Default: None

Type:

Union[str, List[str]], optional

pre_include#

Preinclude one or more headers during preprocessing. Can be either a string or a list of strings. Default: None

Type:

Union[str, List[str]], optional

no_source_include#

Disable the default behavior of adding the directory of each input source to the include path. Default: False

Type:

bool, optional

std#

Set language dialect to C++03, C++11, C++14, C++17 or C++20. Default: c++17

Type:

str, optional

builtin_move_forward#

Provide builtin definitions of std::move and std::forward. Default: True

Type:

bool, optional

builtin_initializer_list#

Provide builtin definitions of std::initializer_list class and member functions. Default: True

Type:

bool, optional

disable_warnings#

Inhibit all warning messages. Default: False

Type:

bool, optional

restrict#

Programmer assertion that all kernel pointer parameters are restrict pointers. Default: False

Type:

bool, optional

device_as_default_execution_space#

Treat entities with no execution space annotation as __device__ entities. Default: False

Type:

bool, optional

device_int128#

Allow the __int128 type in device code. Default: False

Type:

bool, optional

optimization_info#

Provide optimization reports for the specified kind of optimization. Default: None

Type:

str, optional

no_display_error_number#

Disable the display of a diagnostic number for warning messages. Default: False

Type:

bool, optional

diag_error#

Emit error for a specified diagnostic message number or comma separated list of numbers. Default: None

Type:

Union[int, List[int]], optional

diag_suppress#

Suppress a specified diagnostic message number or comma separated list of numbers. Default: None

Type:

Union[int, List[int]], optional

diag_warn#

Emit warning for a specified diagnostic message number or comma separated lis of numbers. Default: None

Type:

Union[int, List[int]], optional

brief_diagnostics#

Disable or enable showing source line and column info in a diagnostic. Default: False

Type:

bool, optional

time#

Generate a CSV table with the time taken by each compilation phase. Default: None

Type:

str, optional

split_compile#

Perform compiler optimizations in parallel. Default: 1

Type:

int, optional

fdevice_syntax_only#

Ends device compilation after front-end syntax checking. Default: False

Type:

bool, optional

minimal#

Omit certain language features to reduce compile time for small programs. Default: False

Type:

bool, optional