MatmulHeuristicResult

class nvmath.bindings.cublasLt.MatmulHeuristicResult(size=1)

Empty-initialize an array of cublasLtMatmulHeuristicResult_t.

The resulting object is of length size and of dtype matmul_heuristic_result_dtype. If default-constructed, the instance represents a single struct.

Parameters:

size (int) – number of structs, default=1.

See also

cublasLtMatmulHeuristicResult_t

Attributes

algo

matmul_algo_dtype:

ptr

Get the pointer address to the data as Python int.

state

Union[~_numpy.int32, int]:

waves_count

Union[~_numpy.float32, float]:

workspace_size

Union[~_numpy.uint64, int]:

Methods

static from_buffer(buffer)

Create an MatmulHeuristicResult instance with the memory from the given buffer.

static from_data(data)

Create an MatmulHeuristicResult instance wrapping the given NumPy array.

Parameters:

data (_numpy.ndarray) – a 1D array of dtype matmul_heuristic_result_dtype holding the data.

static from_ptr(

intptr_t ptr,

size_t size=1,

bool readonly=False,

)

Create an MatmulHeuristicResult instance wrapping the given pointer.

Parameters:

• ptr (intptr_t) – pointer address as Python int to the data.

• size (int) – number of structs, default=1.

• readonly (bool) – whether the data is read-only (to the user). default is False.