cuda.bindings.nvml.device_get_topology_nearest_gpus

cuda.bindings.nvml.device_get_topology_nearest_gpus(intptr_t device, unsigned int level)

Retrieve the set of GPUs that are nearest to a given device at a specific interconnectivity level

:param device: The identifier of the first device
:type device: Device
:param level: The level to search for other GPUs
:type level: GpuTopologyLevel

:returns: An array of device handles for GPUs found at level
:rtype: array