Abstract
This paper differentiates between vectorization (and also concurrentization) and vector optimization (or concurrency optimization). Vectorization (concurrentization) is the process of translating serial DO (or FOR) loops into vector code for a vector computer (concurrent code for a multiprocessor computer). Vector optimization (concurrency optimization) uses vectorization (concurrentization) but adds some intelligence to decide which loop(s) to run in parallel. Loop interchanging and generation of multiple versions of a loop are discussed as vector optimization tools.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
Bibliography
John R. Allen and Ken Kennedy. Automatic Loop Interchange. SIGPLAN Notices, 19(6):233–246, June 1984. Proc. of the ACM SIGPLAN '84 Symp. on Compiler Construction.
C. N. Arnold. Vector Optimization on the Cyber 205. in H. J. Siegel and Leah Siegel, editor, Proc. of the Int'l Conf. for Parallel Pricessing, pages 530–536, IEEE Computer Society Press, Aug. 23–26 1983.
Mark Byler, James Davies, Christopher Huson, Bruce Leasure, and Michael Wolfe. Multiple Version Loops. Proceedings of the 1987 Int'l Conf. for Parallel Pricessing, St. Charles, Illinois, Aug. 18–20 1987. To appear.
Control Data Corporation. Fortran 200 Reference Manual, Control Data Corporation, March 1984. Pub. No. 60480200, rev. D.
Cray Research, Inc. Fortran (CFT) Reference Manual, Cray Research, Inc., August 1981. Pub. No. SR-009, rev. H.
James Davies, Christopher Huson, Tom Macke, Bruce Leasure, and Michael Wolfe. The KAP/S-1: An Advanced Source-to-Source Vectorizer for the S-1 Mark IIa Supercomputer. Proc. of the 1986 Int'l Conf. on Parallel Processing, pages 833–835, IEEE Computer Press, St. Charles, Illinois, Aug. 19–22 1986.
A. Dickinson. Optimizing Numerical Weather Forcasting Models for the Cray-1 and Cyber 205 Computers. Int'l Symp. on Vector Processing Algorithms, Colorado State University, Boulder, Colorado, August 1982.
Christopher Huson, Tom Macke, James Davies, Michael Wolfe, and Bruce Leasure. The KAP/205: An Advanced Source-to-Source Vectorizer for the Cyber 205 Supercomputer. Proc. of the 1986 Int'l Conf. on Parallel Processing, pages 827–832, IEEE Computer Press, St. Charles, Illinois, Aug. 19–22 1986.
D. Loveman. Program Improvement by Source to Source Transformation. Journal of the ACM, 20(1):121–145), January 1977.
David A. Padua and Michael J. Wolfe. Advanced Compiler Optimizations for Supercomputers. Communications of the ACM, 29(12):1184–1201, December 1986.
Constantine D. Polychronopoulos. On Program Restructuring, Scheduling, and Communication for Parallel Processor Systems, U. of Il. Center for Supercomputing Res. & Dev., August 1986. CSRD Rpt. No.595.
W. A. Abu-Sufah, D. J. Kuck, and D. H. Lawrie. On the Performance Enhancement of Paging Systems Through Program Analysis and Transformations. IEEE Trans. on Computer, C-30(5):341–356, May 1981.
Michael Wolfe. Advanced Loop Interchanging. Proc. of the 1986 Int'l Conf. on Parallel Processing, pages 536–543, IEEE Computer Society Press, St. Charles, Illinois, Aug. 19–22 1986.
Michael J. Wolfe. Optimizing Supercompilers for Supercomputers, PhD thesis, University of Illinois at Urbana-Champaign, Urbana, Illinois 1982. Report No. UIUCDCS-R-82-1105.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wolfe, M. (1988). Vector optimization vs. vectorization. In: Houstis, E.N., Papatheodorou, T.S., Polychronopoulos, C.D. (eds) Supercomputing. ICS 1987. Lecture Notes in Computer Science, vol 297. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-18991-2_18
Download citation
DOI: https://doi.org/10.1007/3-540-18991-2_18
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-18991-6
Online ISBN: 978-3-540-38888-3
eBook Packages: Springer Book Archive