Struct TensorDescriptor 

pub struct TensorDescriptor { /* private fields */ }

Implementations

impl TensorDescriptor

pub fn create_for<T: DataTypeLike>( ctx: &Context, shape: &[u64], alignment_requirement: u32, ) -> Result<Self>

pub fn create( ctx: &Context, shape: &[u64], data_type: DataType, alignment_requirement: u32, ) -> Result<Self>

pub fn create_with_strides( ctx: &Context, shape: &[u64], strides: Option<&[u64]>, data_type: DataType, alignment_requirement: u32, ) -> Result<Self>

Creates a tensor descriptor.

This allocates a small amount of host memory.

The descriptor frees the associated cuTENSOR resources when dropped.

This non-blocking call is thread-safe but not reentrant.

Errors

Returns an error if the context cannot be bound, shape and strides have different ranks, an extent or stride cannot be represented for cuTENSOR, the data type or descriptor layout is unsupported, or cuTENSOR returns a null descriptor handle.

pub fn create_with_strides_for<T: DataTypeLike>( ctx: &Context, shape: &[u64], strides: Option<&[u64]>, alignment_requirement: u32, ) -> Result<Self>

pub fn shape(&self) -> &[u64]

pub fn strides(&self) -> Option<&[u64]>

pub fn rank(&self) -> u32

pub fn data_type(&self) -> DataType

pub fn alignment_requirement(&self) -> u32

pub const fn as_raw(&self) -> cutensorTensorDescriptor_t

Trait Implementations

impl Debug for TensorDescriptor

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

Formats the value using the given formatter.

impl Drop for TensorDescriptor

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.