OPTIMIZATION METHOD OF NEURAL NETWORK FOR MULTI-GPU SYSTEM AND OPTIMIZATION SYSTEM USING THE SAME

摘要

The present application relates to a method of optimizing a neural network for a multi-GPU system including a main GPU and a secondary GPU, and the optimization method according to an aspect of the present specification includes: obtaining the neural network including a plurality of layers; a profiling step of collecting base information for optimizing the neural network, wherein the base information includes GPU information of the multi-GPU system and neural network information about the structure of the neural network; A first tree structure including a first main neural network processed by the main GPU and a first auxiliary neural network processed by the auxiliary GPU to branch the neural network at a first branch point that is one of the points between the plurality of layers converting to a neural network; and optimizing the first tree-structured neural network based on the base information.