Enum MathType 

pub enum MathType {
    Default,
    TensorOp,
    TensorOpAllowConversion,
    FmaOnly,
}

Math-type selector for ConvolutionDescriptor::set_math_type — controls tensor-core eligibility.

Variants

Default

Standard FMA-only math; tensor cores not used.

TensorOp

Allow tensor-core math (Volta+).

TensorOpAllowConversion

Allow tensor-core math with implicit half-precision conversion.

FmaOnly

Strict FMA-only.

Trait Implementations

impl Clone for MathType

fn clone(&self) -> MathType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for MathType

impl Debug for MathType

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

Formats the value using the given formatter.

impl Default for MathType

fn default() -> MathType

Returns the “default value” for a type.

impl Eq for MathType

impl PartialEq for MathType

fn eq(&self, other: &MathType) -> 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 MathType