Execution method of CPU (Central Processing Unit) applied to artificial intelligence related program

Abstract

An execution method when a CPU is applied to an artificial intelligence related program comprises the following steps that when TensorFlow is executed on electronic equipment, a corresponding artificial intelligence model is called according to program content; judging and extracting one or more sparse matrixes used by the artificial intelligence model in operation; performing a matrix simplification procedure on the one or more sparse matrixes; performing instruction conversion on an instruction set adopted by the artificial intelligence model; the artificial intelligence model issues an instruction to the weighted value central processing unit through the converted instruction set; and after receiving the instruction, the weighted value central processing unit averagely distributes a plurality of execution threads to execute a plurality of programs indicated by the artificial intelligence model according to the weighted value.

Description

technical field [0001] The present invention relates to a central processing unit, in particular to an execution method for the central processing unit when executing programs related to artificial intelligence. Background technique [0002] In recent years, artificial intelligence technology has developed vigorously, and major companies have invested in the research and development of artificial intelligence-related products. [0003] Generally speaking, software engineers often use TensorFlow developed by Google to develop artificial intelligence related programs. Specifically, TensorFlow is an open source software library applied to machine learning, and TensorFlow provides a variety of artificial intelligence-related models, which are helpful for software engineers to directly use for the development of artificial intelligence. [0004] However, in the prior art, the matrices used by the artificial intelligence-related models to perform calculations are generally not op...

AI Technical Summary

Problems solved by technology

Specifically, the CPU usually simply executes the multiple instructions received in order, so it often happens that one execution thread (Thread) of the CPU cannot complete a program and needs to be handed over to the next execution thread to continue the calculation.

When the above phenomenon occurs, the CPU will increase the time cost of executing SWAP, causing the overall speed to slow down, and a higher-level CPU needs to be replaced, or an additional GPU must be installed.

Images