Enum TensorArg

Source
pub enum TensorArg<'a, R: Runtime> {
    Handle {
        handle: TensorHandleRef<'a, R>,
        vectorization_factor: u8,
    },
    Alias {
        input_pos: usize,
    },
}
Expand description

Argument to be used for tensors passed as arguments to kernels.

Variants§

§

Handle

The tensor is passed with a tensor handle.

Fields

§handle: TensorHandleRef<'a, R>

The tensor handle.

§vectorization_factor: u8

The vectorization factor.

§

Alias

The tensor is aliasing another input tensor.

Fields

§input_pos: usize

The position of the input tensor.

Implementations§

Source§

impl<'a, R: Runtime> TensorArg<'a, R>

Source

pub unsafe fn from_raw_parts<E: CubePrimitive>( handle: &'a Handle, strides: &'a [usize], shape: &'a [usize], factor: u8, ) -> Self

Create a new tensor argument specified with its vectorization factor.

§Safety

If you provide wrong strides or shapes, it might create undefined behavior caused by out-of-bound reads and writes.

Source

pub unsafe fn from_raw_parts_and_size( handle: &'a Handle, strides: &'a [usize], shape: &'a [usize], factor: u8, elem_size: usize, ) -> Self

Create a new tensor argument specified with its vectorization factor with a manual element size in bytes.

§Safety

If you provide wrong strides or shapes, it might create undefined behavior caused by out-of-bound reads and writes.

Source

pub fn alias(position: usize) -> Self

Create an alias argument.

Trait Implementations§

Source§

impl<R: Runtime> ArgSettings<R> for TensorArg<'_, R>

Source§

fn register(&self, launcher: &mut KernelLauncher<R>)

Register the information of an argument to the KernelLauncher.
Source§

impl<'a, R: Debug + Runtime> Debug for TensorArg<'a, R>

Source§

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

Formats the value using the given formatter. Read more

Auto Trait Implementations§

§

impl<'a, R> Freeze for TensorArg<'a, R>

§

impl<'a, R> RefUnwindSafe for TensorArg<'a, R>
where R: RefUnwindSafe,

§

impl<'a, R> Send for TensorArg<'a, R>

§

impl<'a, R> Sync for TensorArg<'a, R>

§

impl<'a, R> Unpin for TensorArg<'a, R>
where R: Unpin,

§

impl<'a, R> UnwindSafe for TensorArg<'a, R>
where R: UnwindSafe,

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V