Method for high-efficiency task scheduling of heterogeneous multi-core processor

Abstract

The invention provides a method for high-efficiency task scheduling of a heterogeneous multi-core processor. The method comprises the following steps of: clustering certain special tasks which are large in communication overhead and easy to cluster in a task image to a precursor node of the tasks by adopting a linear task clustering method; starting from a topological structure of the whole task image, selecting parameters capable of comprehensively reflecting the importance of the task in the whole task image as priority weights; selecting a free critical path node to perform allocation first, and if multiple free critical path nodes exist, allocating the free critical path nodes in a sequence from high to low according to the node priority weights, and allocating all non-critical path free nodes in a sequence from high to low according to the priority weights; performing redundancy judgment, and deleting redundant tasks in a scheduling result; and performing adjustment according to the scheduling result after deleting the redundant tasks, and recalculating the earliest finish time of each task. According to the method, the efficiency of the task scheduling of the heterogeneous multi-core processor is improved, the power consumption of the processor is reduced, and the performance of the multi-core processor is promoted.

Description

Technical field [0001] The invention relates to a method for improving processor performance. Specifically, it is an efficient task scheduling method based on heterogeneous multi-core. Background technique [0002] With people's endless pursuit of high-performance microprocessors, in the past few decades, relying on traditional methods of increasing the processor clock frequency, the frequency of single-core processors has been greatly increased, and has now reached 4GHz. At the same time, due to the continuous improvement of processor frequency and the increase of chip integration, the power consumption and heat dissipation of single-core processors are becoming more and more serious. The traditional technology of developing processor parallelism through superscalar and super pipeline makes processing The design cost of the processor is getting higher and higher, and it is overwhelmed, and the performance of the single-core processor encounters a bottleneck. However, the ever-...

AI Technical Summary

Problems solved by technology

However, the task scheduling efficiency of heterogeneous multi-core processors is still not ideal, and there are problems such as excessive communication overhead, low priority of key tasks, and too many redundant tasks, which seriously affect the task scheduling performance of multi-core processors.

Images