cuda.bindings.nvml.ProcessDetail_v1

class cuda.bindings.nvml.ProcessDetail_v1(size=1)

Empty-initialize an array of nvmlProcessDetail_v1_t.

The resulting object is of length size and of dtype process_detail_v1_dtype. If default-constructed, the instance represents a single struct.

Parameters:

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

See also

nvmlProcessDetail_v1_t

__init__(*args, **kwargs)

Methods

__init__(*args, **kwargs)
from_buffer(buffer)	Create an ProcessDetail_v1 instance with the memory from the given buffer.
from_data(data)	Create an ProcessDetail_v1 instance wrapping the given NumPy array.
from_ptr(intptr_t ptr, size_t size=1, ...)	Create an ProcessDetail_v1 instance wrapping the given pointer.

Attributes

compute_instance_id	If MIG is enabled, stores a valid compute instance ID.
gpu_instance_id	If MIG is enabled, stores a valid GPU instance ID.
pid	Process ID.
ptr	Get the pointer address to the data as Python int.
used_gpu_cc_protected_memory	Amount of used GPU conf compute protected memory in bytes.
used_gpu_memory	Amount of used GPU memory in bytes.