Distributed storage structure-oriented handling method

Abstract

The invention discloses a distributed storage structure-oriented handling method. An intensive computing-oriented five-layer parallel compiling frame is adopted and comprises an intensive computing application compiling layer for generating a redundancy-removed multi-atom application parallel area, an atom application layer based on a data parallel model, a data parallel compiling layer used for translating an application instruction set of the atom application layer into SPMD parallel codes based on a multi-core runtime system, a parallel runtime layer for finishing task scheduling and data flow scheduling, and a local compiling layer and an operating system layer for supporting the parallel runtime layer. Based on a model of the handling method, embedded type multi-core MATLAB can be developed, a programming effect of 'what you see is what you get' is implemented, and a simple and efficient multi-core programming platform is provided for complex algorithms such as matrix operation, pattern recognition and machine learning for rapid R&D and deployment of new-generation cruise missiles, air defense missiles and smart unmanned aerial vehicles and the like.

Description

technical field [0001] The invention belongs to the technical field of multi-core embedded storage structure design, and in particular relates to a processing method oriented to a distributed storage structure. Background technique [0002] As digital signal processing technology has been widely used in communication, image recognition, radar, electronics, medical imaging and other fields, the performance requirements of digital signal processors (DSP, Digital Signal Processor) in various fields have also surged. However, the computing performance of traditional single-core DSP is close to the bottleneck under the existing technological conditions, so multi-core DSP will become an important development direction in the future. However, the multi-core DSP programming environment is complex, and software personnel need to consider the allocation of core tasks, resources, and data, as well as the collaborative work between cores, etc., resulting in long programming cycles and h...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to provide a processing method for a distributed storage structure in view of the deficiencies in the above-mentioned prior art. By making full use of the data locality principle of the distributed storage structure, the present invention improves the multi-core acceleration ratio, At the same time, it also solves the problems caused by complex calculation expressions under the distributed storage model, such as extremely cumbersome data flow transmission control logic and difficulties in automatic scheduling.

Images