Cormpiler Optimization for Parallelism and Locality Improvement


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 6, No. 2, pp. 307-314, Feb. 1999
10.3745/KIPSTE.1999.6.2.307,   PDF Download:

Abstract

In this paper, we study on the transformation technique of sequential programs for the purpose of 'exploiting parallelism' and 'improving locality'. Based on the analysis of loop procedures of sequential programs with the factor of dependency and locality, two transformation techniques of loop distribution and loop fusion are applied to them. Transformed programs can be easily expressed as a parallel program with thread notation, having coarse-grain parallelism and improved locality. this means that those transformations can be useful tools for optimizing and automatic-paralleling compiler construction. Application of those techniques to SPEC95 on a Solalis machine with four SPARC processors shows an improvement of execution time.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. J. Mee, B. S. Woo, P. C. Woo, L. M. Ho, "Cormpiler Optimization for Parallelism and Locality Improvement," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 6, no. 2, pp. 307-314, 1999. DOI: 10.3745/KIPSTE.1999.6.2.307.

[ACM Style]
Kim Jin Mee, Byun Sug Woo, Pyo Chang Woo, and Lee Mann Ho. 1999. Cormpiler Optimization for Parallelism and Locality Improvement. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 6, 2, (1999), 307-314. DOI: 10.3745/KIPSTE.1999.6.2.307.