Struct HipTensorLinalgBackend 

pub struct HipTensorLinalgBackend;

Marker type for the HIP tensor linalg backend.

Examples

let _backend = tenferro_linalg_prims::backend::HipTensorLinalgBackend;

Trait Implementations

impl Clone for HipTensorLinalgBackend

fn clone(&self) -> HipTensorLinalgBackend

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for HipTensorLinalgBackend

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

Formats the value using the given formatter.

impl Default for HipTensorLinalgBackend

fn default() -> HipTensorLinalgBackend

Returns the “default value” for a type.

impl<T: KernelLinalgScalar> TensorLinalgPrims<T> for HipTensorLinalgBackend

type Context = RocmContext

fn has_linalg_support(_op: LinalgCapabilityOp) -> bool

fn solve_ex( _ctx: &mut Self::Context, _a: &Tensor<T>, _b: &Tensor<T>, ) -> Result<SolveTensorExResult<T>>

Solve a square linear system while returning per-batch numerical status.

fn solve( _ctx: &mut Self::Context, _a: &Tensor<T>, _b: &Tensor<T>, ) -> Result<Tensor<T>>

fn lu_solve( _ctx: &mut Self::Context, _factors: &Tensor<T>, _pivots: &Tensor<i32>, _b: &Tensor<T>, ) -> Result<Tensor<T>>

fn solve_triangular( _ctx: &mut Self::Context, _a: &Tensor<T>, _b: &Tensor<T>, _upper: bool, ) -> Result<Tensor<T>>

fn qr(_ctx: &mut Self::Context, _a: &Tensor<T>) -> Result<QrTensorResult<T>>

fn thin_svd( _ctx: &mut Self::Context, _a: &Tensor<T>, ) -> Result<SvdTensorResult<T>>

fn svdvals(_ctx: &mut Self::Context, _a: &Tensor<T>) -> Result<Tensor<T::Real>>

fn lu_factor_ex( _ctx: &mut Self::Context, _a: &Tensor<T>, ) -> Result<LuTensorExResult<T>>

Compute an LU factorization while returning per-batch numerical status.

fn lu_factor( _ctx: &mut Self::Context, _a: &Tensor<T>, ) -> Result<LuTensorResult<T>>

fn lu_factor_no_pivot( _ctx: &mut Self::Context, _a: &Tensor<T>, ) -> Result<LuTensorResult<T>>

Compute an LU factorization without pivoting.

fn cholesky_ex( _ctx: &mut Self::Context, _a: &Tensor<T>, ) -> Result<CholeskyTensorExResult<T>>

Compute a Cholesky factorization while returning per-batch numerical status.

fn cholesky(_ctx: &mut Self::Context, _a: &Tensor<T>) -> Result<Tensor<T>>

fn eigen_sym( _ctx: &mut Self::Context, _a: &Tensor<T>, ) -> Result<EigenTensorResult<T>>

fn eig(_ctx: &mut Self::Context, _a: &Tensor<T>) -> Result<EigTensorResult<T>>

impl Copy for HipTensorLinalgBackend