Struct ReduceTensorDescriptor 

pub struct ReduceTensorDescriptor { /* private fields */ }

A reduce-tensor descriptor: reduction op + compute dtype.

Implementations

impl ReduceTensorDescriptor

pub fn new(op: ReduceOp, compute: DType) -> Result<Self>

Build a reduce-tensor descriptor for op with compute as the accumulation dtype. NaN propagation defaults to PropagateNan; indices are not returned (use the lower-level cuDNN API directly for arg-reductions).

pub fn workspace_size( &self, handle: &Handle, a: &TensorDescriptor, c: &TensorDescriptor, ) -> Result<usize>

Workspace bytes required to run reduce_tensor reducing a into c.

pub fn as_raw(&self) -> cudnnReduceTensorDescriptor_t

Raw descriptor.

Trait Implementations

impl Debug for ReduceTensorDescriptor

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

Formats the value using the given formatter.

impl Drop for ReduceTensorDescriptor

fn drop(&mut self)

Executes the destructor for this type.

fn pin_drop(self: Pin<&mut Self>)

🔬This is a nightly-only experimental API. (pin_ergonomics)

Execute the destructor for this type, but different to Drop::drop, it requires self to be pinned.

impl Send for ReduceTensorDescriptor