Foresight thread particles for restart optimization and construction method thereof

Abstract

The invention discloses foresight thread particles for restart optimization and a construction method thereof. The particle includes an input parameter identification part, an execution part and a result storage part. The method has the following steps: A. constructing a symbol set of the foresight thread particles; B. distributing the program statements in a foresight thread into the corresponding foresight thread particles of step A according to the generative rule of the symbol set of the foresight thread particles; C. adjusting the order of the program statements of step B in the foresight thread particles; and D. filling out the structure which controls the restart optimization of the foresight thread particles. According to the influence of the input parameter of the foresight thread on the foresight thread particles, the method can design the structure for controlling the restart optimization of the foresight thread particles, thereby reducing the unnecessary execution of the program statements during effectiveness failure and reducing the cost of time and the resources for the operation of thread restart. When the thread suffers foresight failure, only a plurality of parts of the thread needs to be restarted, and the cost of restart of the thread during foresight failure is reduced.

Description

technical field [0001] The invention relates to the computer field, and proposes a forward-looking thread particle for restart optimization and a construction method thereof. Background technique [0002] The continuous development of computer technology and the extensive and in-depth application fields have higher requirements for processor performance. However, traditional methods for improving processor performance, such as increasing the integration of processor transistors and increasing processor clock frequency, are greatly limited. These limitations include that the processor technology and clock frequency are close to the limit, and its improvement becomes more and more difficult; with the increase of the clock frequency, the power consumption of the processor is increasing, and the heat dissipation problem has also become a problem that affects the stable performance of the processor. The key issue. [0003] Under such a background, the single-chip multi-core pro...

AI Technical Summary

Problems solved by technology

The results inferred by the forward-looking technology are not always correct. When the inference of the forward-looking technology fails, the failed thread must be restarted, but the time and resource overhead of restarting the thread are extremely large, and even offset the parallelism of the serial program. Benefits, therefore, optimizing thread restart is known as one of the key technologies for serial program parallelization, it is necessary to further refine threads and reduce thread granularity

Images