Automatic Parallelization of ANSI C to CUDA C Programs
Writing efficient general-purpose programs for Graphics Processing Units (GPU) is a complex task. In order to be able to program these processors efficiently, one has to understand their intricate architecture, memory subsystem as well as the interaction with the Central Processing Unit (CPU). The paper presents the GAP - an automatic parallelizer designed to translate sequential ANSI C code to parallel CUDA C programs. Developed and implemented compiler was tested on the series of ANSI C programs. The generated code performed very well, achieving significant speed-ups for the programs that expose high degree of data-parallelism. Thus, the idea of applying the automatic parallelization for generating the CUDA C code is feasible and realistic.
KeywordsAutomatic parallelization GAP compiler Loop transformations Data-parallelism
The authors are grateful to the Czestochowa University of Technology for granting access to GPU platforms provided by the MICLAB project No. POIG.02.03.00.24-093/13.
- 2.Banerjee, U.: Loop Transformations for Restructuring Compilers: Loop Parallelization. Kluwer Academic Publishers, New York (1994)Google Scholar
- 3.Banerjee, U.: Loop Transformations for Restructuring Compilers: Dependence Analysis. Kluwer Academic Publishers, New York (1994)Google Scholar
- 4.Zima, H., Chapman, B.: Supercompilers for Parallel and Vector Computers. ACM Press, New York (1991)Google Scholar
- 5.Midkiff, S.M.: Automatic Parallelization: An Overview of Fundamental Compiler Techniques. Morgan Claypool Publishers, California (2012)Google Scholar
- 6.Allen, R., Kennedy, K.: Automatic loop interchange. In: Proceedings of the SIGPLAN 1984 Symposium on Compiler Construction, Montreal, pp. 233–246 (1984)Google Scholar
- 7.Allen, R.: Dependence analysis for subscripted variables and its application to program transformations. Ph.D. thesis. Department of Mathematical Sciences, Rice University, Houston (1983)Google Scholar
- 8.Wolfe, M.J.: Advanced loop interchange. In: Proceedings of the 1986 International Conference on Parallel Processing, St. Charles, Illinois, pp. 536–543 (1986)Google Scholar
- 11.Bondhugula, U.K.R.: Effective automatic parallelization and locality optimization using the polyhedral model. Ph.D. thesis. The Ohio State University, Ohio (2010)Google Scholar
- 12.Bastoul, C.: Improving data locality in static control programs. Ph.D. thesis. University Paris 6, Pierre et Marie Curie, France (2004)Google Scholar
- 14.Bajgoric, J.: Automatic parallelization of ANSI C to CUDA C programs. Master thesis. Wroclaw University of Science and Technology, Poland (2016)Google Scholar