Dynamic detection of parallelism in Pascal-like program
Yong Zheng, Jiahua Qian · 1988
The execution time of Pascal-like programs can be decreased by putting solutions to problems in their maximally parallel forms. In this study Pascal-like programs are considered, and analysis of parallelism is performed by using a dynamic recent data dependency graph (DDG). The means taken in this paper is able to derive maximally parallel versions of the programs and to minimize the execution time. The advantage of this means is not only to save the effort in implementation but also to possess generality and high-efficiency resulting from dynamically locating parallelism in program. The study shows that the maximally parallel program can run in considerably less time than that needed to run the original sequential Pascal-like program.