Communications between processors and storage devices in automotive predictive maintenance implemented via artificial neural networks

A vehicle, comprising:

• at least one processor;
• at least one sensor configured to generate a sensor data stream;
• and
• a data storage device having a controller, a neural network accelerator, a host interface connected to the at least one processor, and a storage capacity partitioned into at least a first namespace configured to store model data of an artificial neural network, a second namespace configured to store inputs to the artificial neural network, and a third namespace configured to store outputs from the artificial neural network;
• wherein the at least one processor is configured to receive a set of sensor data from the at least one sensor, generate a set of inputs to the artificial neural network based on the sensor data, and write through the host interface the set of inputs to the second namespace in the data storage device;
• wherein the controller and the neural network accelerator in the data storage device is configured to, responsive to the set of inputs being written into the second namespace, perform computation to generate a set of outputs in the third namespace using the model data of the artificial neural network stored in the first namespace in the data storage device and the set of inputs written into the second namespace via the host interface;
• and
• wherein the at least one processor is configured to read via the host interface the set of outputs from the third namespace in the data storage device.

A data storage device, comprising:

• non-volatile memory having a storage capacity partitioned into at least:
• a first namespace configured to store model data of an artificial neural network;
• a second namespace configured to store a set of inputs;
• and
• a third namespace configured to store outputs from the artificial neural network;
• a host interface operable to receive, from at least one processor, commands configured to write to the first namespace the set of inputs;
• a controller;
• a neural network accelerator coupled to the controller to perform computation, responsive to the set of inputs being written in the first namespace, to generate a set of outputs in the third namespace using the model data of the artificial neural network stored in the first namespace and the set of inputs written into the second namespace via the host interface;
• and
• a buffer configured to store the set of outputs in response to commands, received from the at least one processor via the host interface, to read the set of outputs from the third namespace.