CUDA-NoCollectives

Do not use warp collective operations

Required inputs: IR, StaticSemanticAnalysis

This rule can be used to ensure that warp collective operations are not used and that the CUDA 2.x guidelines are thus trivially met. It should be regarded as an alternative to enabling these rules.

Possible Messages

Key	Text	Severity	Disabled
forbidden_call	Call to warp collective operation.	None	False

Options

• This rule shares the following common options: exclude_in_macros, exclude_messages_in_system_headers, excludes, extend_exclude_to_macro_invocations, includes, justification_checker, languages, post_processing, provider, report_at, severity

• The following places define options that affect this rule: Stylechecks, Analysis-GlobalOptions

only_reachable_calls

only_reachable_calls : bool = True

Do not report findings for unreachable calls (e.g., in library code that is never called).