cuda.bindings._v2.driver.StreamBatchMemOpParams_v1#

class cuda.bindings._v2.driver.StreamBatchMemOpParams_v1(size=1)#

Empty-initialize an array of CUstreamBatchMemOpParams_v1. The resulting object is of length size and of dtype stream_batch_mem_op_params_v1_dtype. If default-constructed, the instance represents a single union.

Parameters:

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

See also

CUstreamBatchMemOpParams_v1

__init__(*args, **kwargs)#

Methods

__init__(*args, **kwargs)

from_buffer(buffer)

Create an StreamBatchMemOpParams_v1 instance with the memory from the given buffer.

from_data(data)

Create an StreamBatchMemOpParams_v1 instance wrapping the given NumPy array.

from_ptr(intptr_t ptr, size_t size=1, ...[, ...])

Create an StreamBatchMemOpParams_v1 instance wrapping the given pointer.

Attributes

atomic_reduction

StreamMemOpAtomicReductionParams:

flush_remote_writes

StreamMemOpFlushRemoteWritesParams:

memory_barrier

StreamMemOpMemoryBarrierParams:

operation

Union[~_numpy.int32, int]:

ptr

Get the pointer address to the data as Python int.

wait_value

StreamMemOpWaitValueParams:

write_value

StreamMemOpWriteValueParams: