Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/21550
Title: Validation of parallelizing transformations of sequential programs
Authors: Dutta, Sudakshina
Published in: Concurrency and Computation: Practice and Experience
Abstract: Transformations for high-performance superscalar, vector, and parallel processors maximize parallelism and memory locality. Often parallelizing compilers apply transformations, such as loop parallelization and loop vectorization, to convert a sequential array-handling program into a parallel program. Validation of such transformations is extremely useful in the prevalent high-performance computing environment. This paper proposes a novel algorithm for construction of the dependence graph of the generated parallel programs. These transformations are validated by checking equivalence of the dependence graphs of the original sequential program and the transformed parallel program using a standard algorithm reported in the literature. The above equivalence checker works even when the above parallelizing transformations are preceded by various enabling transformations except for loop collapsing transformation that changes the dimensions of the arrays. In the present paper, the scope of the equivalence checker has been expanded to handle this special case by informing it of the correspondence between the index spaces of the corresponding of input and output arrays in the sequential and the parallel programs. The proposed methods are implemented and tested against a set of available benchmark programs that are parallelized by the polyhedral auto-parallelizer LooPo and the auto-vectorizer Scout. Copyright ¬© 2017 John Wiley & Sons, Ltd.
Citation: Concurrency and Computation: Practice and Experience, 29(8)
URI: https://doi.org/10.1002/cpe.3958
http://repository.iitr.ac.in/handle/123456789/21550
Issue Date: 2017
Publisher: John Wiley and Sons Ltd
Keywords: conflict access
dependence graphs
loop parallelization
loop vectorization
validation
ISSN: 15320626
Author Scopus IDs: 55098724900
Author Affiliations: Dutta, S., Indian Institute of Technology Kharagpur, Afghanistan
Funding Details: I sincerely thank Dr. Dipankar Sarkar for helping me with his valuable suggestions towards improving the content of this paper.
Corresponding Author: Dutta, S.; Indian Institute of Technology KharagpurAfghanistan; email: sudakshina@cse.iitkgp.ernet.in
Appears in Collections:Journal Publications [CE]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.