US 2023/0053575 A1 · PARTITIONING AND PLACEMENT OF MODELS

Abstract

This disclosure describes techniques and mechanisms for enabling a user to run heavy deep learning workloads on standard edge networks without off-loading computation to a cloud, leveraging the available edge computing resources, and efficiently partitioning and distributing a Deep Neural Network (DNN) over a network. The techniques enable the user to split a workload into multiple parts and process the workload on a set of smaller, less capable compute nodes in a distributed manner, without compromising on performance, and while meeting a Service Level Objective (SLO).

Claims20

Dependent claims

A method implemented by an orchestration system, the method comprising:

identifying a neural network model configured to process data generated by a computing device in a network;
analyzing the neural network model to determine a location in the neural network model at which to split the neural network model;
identifying a first computing device in the network at which to run a first workload associated with a first portion of the neural network model;
identifying a second computing device in the network at which to run a second workload associated with a second portion of the neural network model;
splitting the neural network model at the location to create the first workload and the second workload;
deploying the first workload to the first computing device;
and
deploying the second workload to the second computing device.

5 more elements

Dependencies are inferred from the claim text.

Partitioning and placement of models

Life of this patent

Partitioning and placement of models

Life of this patent

Abstract

Claims20