Adding parallelism to sequential programs – a combined method

Authors

  • Wiktor B. Daszczuk Warsaw University of Technology, Instituteof Computer Science, Warsaw, Poland
  • Denny B. Czejdo Fayetteville State University, Department of Mathematics and Computer Science, Fayetteville, USA
  • Wociech Grześkowiak Warsaw University of Technology, Instituteof Computer Science, Warsaw, Poland

DOI:

https://doi.org/10.24425/ijet.2024.149523

Abstract

The article outlines a contemporary method for creating software for multi-processor computers. It describes the identification of parallelizable sequential code structures. Three structures were found and then carefully examined. The algorithms used to determine whether or not certain parts of code may be parallelized result from static analysis. The techniques demonstrate how, if possible, existing sequential structures might be transformed into parallel-running programs. A dynamic evaluation is also a part of our process, and it can be used to assess the efficiency of the parallel programs that are developed. As a tool for sequential programs, the algorithms have been implemented in C#. All proposed methods were discussed using a common benchmark.

Published

2024-03-23

How to Cite

Daszczuk, Wiktor B., et al. “Adding Parallelism to Sequential Programs – a Combined Method”. International Journal of Electronics and Telecommunications, vol. 70, no. 1, Mar. 2024, doi:10.24425/ijet.2024.149523.

Issue

Section

Artykuły