Struct PtxRegisterUsage 

pub struct PtxRegisterUsage { /* private fields */ }

Register-file usage of a single PTX kernel, derived from its .reg directives.

Implementations

impl PtxRegisterUsage

pub fn registers_per_thread(&self) -> u32

Registers consumed per thread, as ptxas would report under the no-coalescing (-O0) lower bound.

This is the value to pass to the CUDA occupancy model and to cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags.

pub fn predicate_registers(&self) -> u32

Number of predicate registers declared by the kernel.

Predicates are tracked separately because they do not draw from the general-purpose register file that bounds occupancy.

pub fn directive_count(&self) -> u32

Number of .reg directives that contributed to this usage.

Trait Implementations

impl Clone for PtxRegisterUsage

fn clone(&self) -> PtxRegisterUsage

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for PtxRegisterUsage

impl Debug for PtxRegisterUsage

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for PtxRegisterUsage

fn default() -> PtxRegisterUsage

Returns the “default value” for a type.

impl Eq for PtxRegisterUsage

impl PartialEq for PtxRegisterUsage

fn eq(&self, other: &PtxRegisterUsage) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for PtxRegisterUsage