cuda.bindings.nvml.device_get_memory_affinity#

cuda.bindings.nvml.device_get_memory_affinity( intptr_t device, unsigned int node_set_size, unsigned int scope, )#

Retrieves an array of unsigned ints (sized to node_set_size) of bitmasks with the ideal memory affinity within node or socket for the device. For example, if NUMA node 0, 1 are ideal within the socket for the device and node_set_size == 1, result[0] = 0x3.

Parameters:

device (intptr_t) – The identifier of the target device.
node_set_size (unsigned int) – The size of the nodeSet array that is safe to access.
scope (unsigned int) – Array reference in which to return a bitmask of NODEs, 64 NODEs per unsigned long on 64-bit machines, 32 on 32-bit machines.