Enum kn_cuda_sys::bindings::cublasLtMatrixLayoutAttribute_t

#[non_exhaustive]
#[repr(u32)]
pub enum cublasLtMatrixLayoutAttribute_t {
    CUBLASLT_MATRIX_LAYOUT_TYPE = 0,
    CUBLASLT_MATRIX_LAYOUT_ORDER = 1,
    CUBLASLT_MATRIX_LAYOUT_ROWS = 2,
    CUBLASLT_MATRIX_LAYOUT_COLS = 3,
    CUBLASLT_MATRIX_LAYOUT_LD = 4,
    CUBLASLT_MATRIX_LAYOUT_BATCH_COUNT = 5,
    CUBLASLT_MATRIX_LAYOUT_STRIDED_BATCH_OFFSET = 6,
    CUBLASLT_MATRIX_LAYOUT_PLANE_OFFSET = 7,
}

Attributes of memory layout

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

CUBLASLT_MATRIX_LAYOUT_TYPE = 0

Data type, see cudaDataType.

uint32_t

CUBLASLT_MATRIX_LAYOUT_ORDER = 1

Memory order of the data, see cublasLtOrder_t.

int32_t, default: CUBLASLT_ORDER_COL

CUBLASLT_MATRIX_LAYOUT_ROWS = 2

Number of rows.

Usually only values that can be expressed as int32_t are supported.

uint64_t

CUBLASLT_MATRIX_LAYOUT_COLS = 3

Number of columns.

Usually only values that can be expressed as int32_t are supported.

uint64_t

CUBLASLT_MATRIX_LAYOUT_LD = 4

Matrix leading dimension.

For CUBLASLT_ORDER_COL this is stride (in elements) of matrix column, for more details and documentation for other memory orders see documentation for cublasLtOrder_t values.

Currently only non-negative values are supported, must be large enough so that matrix memory locations are not overlapping (e.g. greater or equal to CUBLASLT_MATRIX_LAYOUT_ROWS in case of CUBLASLT_ORDER_COL).

int64_t;

CUBLASLT_MATRIX_LAYOUT_BATCH_COUNT = 5

Number of matmul operations to perform in the batch.

See also CUBLASLT_ALGO_CAP_STRIDED_BATCH_SUPPORT

int32_t, default: 1

CUBLASLT_MATRIX_LAYOUT_STRIDED_BATCH_OFFSET = 6

Stride (in elements) to the next matrix for strided batch operation.

When matrix type is planar-complex (CUBLASLT_MATRIX_LAYOUT_PLANE_OFFSET != 0), batch stride is interpreted by cublasLtMatmul() in number of real valued sub-elements. E.g. for data of type CUDA_C_16F, offset of 1024B is encoded as a stride of value 512 (since each element of the real and imaginary matrices is a 2B (16bit) floating point type).

NOTE: A bug in cublasLtMatrixTransform() causes it to interpret the batch stride for a planar-complex matrix as if it was specified in number of complex elements. Therefore an offset of 1024B must be encoded as stride value 256 when calling cublasLtMatrixTransform() (each complex element is 4B with real and imaginary values 2B each). This behavior is expected to be corrected in the next major cuBLAS version.

int64_t, default: 0

CUBLASLT_MATRIX_LAYOUT_PLANE_OFFSET = 7

Stride (in bytes) to the imaginary plane for planar complex layout.

int64_t, default: 0 - 0 means that layout is regular (real and imaginary parts of complex numbers are interleaved in memory in each element)

Trait Implementations

impl Clone for cublasLtMatrixLayoutAttribute_t

fn clone(&self) -> cublasLtMatrixLayoutAttribute_t

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for cublasLtMatrixLayoutAttribute_t

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

Formats the value using the given formatter.

impl Hash for cublasLtMatrixLayoutAttribute_t

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for cublasLtMatrixLayoutAttribute_t

fn eq(&self, other: &cublasLtMatrixLayoutAttribute_t) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for cublasLtMatrixLayoutAttribute_t

impl Eq for cublasLtMatrixLayoutAttribute_t

impl StructuralPartialEq for cublasLtMatrixLayoutAttribute_t