cuda.core.experimental.LaunchConfig¶

class cuda.core.experimental.LaunchConfig(grid: tuple | int = None, block: tuple | int = None, stream: Stream = None, shmem_size: int | None = None)¶

Customizable launch options.

grid¶

Collection of threads that will execute a kernel function.

Type:: Union[tuple, int]

block¶

Group of threads (Thread Block) that will execute on the same multiprocessor. Threads within a thread blocks have access to shared memory and can be explicitly synchronized.

Type:: Union[tuple, int]

stream¶

The stream establishing the stream ordering semantic of a launch.

Type:: Stream

shmem_size¶

Dynamic shared-memory size per thread block in bytes. (Default to size 0)

Type:: int, optional