Struct CudaEGraphStructuralEquivalenceKernelResult 

pub struct CudaEGraphStructuralEquivalenceKernelResult {
    pub emitted_pair_count: u64,
    pub unique: Vec<Equivalence>,
    pub device_reported_count: u64,
    pub overflowed_output_capacity: bool,
}

Result produced by launching the structural-equivalence CUDA kernel.

Fields

emitted_pair_count: u64

Raw emitted e-class pair count before host deduplication and excluding device-side overflow beyond the planned output capacity.

unique: Vec<Equivalence>

Unique sorted e-class pairs after host compaction.

device_reported_count: u64

Number of pairs reported by the device atomic counter before capping to the planned output capacity.

overflowed_output_capacity: bool

Whether device output exceeded the planned output-pair capacity.

Trait Implementations

impl Clone for CudaEGraphStructuralEquivalenceKernelResult

fn clone(&self) -> CudaEGraphStructuralEquivalenceKernelResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CudaEGraphStructuralEquivalenceKernelResult

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

Formats the value using the given formatter.

impl PartialEq for CudaEGraphStructuralEquivalenceKernelResult

fn eq(&self, other: &CudaEGraphStructuralEquivalenceKernelResult) -> 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 Eq for CudaEGraphStructuralEquivalenceKernelResult

impl StructuralPartialEq for CudaEGraphStructuralEquivalenceKernelResult