@inproceedings{2df770e1bc9a46a0911c4cb6422d47c3,
title = "A loop transformation algorithm based on explicit data layout representation for optimizing locality",
abstract = "We present a cache locality optimization technique that can optimize a loop nest even if the arrays referenced have different layouts in memory. Such a capability is required for a global locality optimization framework that applies both loop and data transformations to a sequence of loop nests for optimizingl ocality. Our method finds a nonsingular iteration-space transformation matrix such that in a given loop nest spatial locality is exploited in the innermost loops where it is most useful. The method builds inverse of a non-singular transformation matrix column-by-column startingfrom the rightmost column. In addition, our approach can work in those cases where the data layouts of a subset of the referenced arrays is unknown. Experimental results on an 8-processor SGI Origin 2000 show that our technique reduces execution times by up to 72%.",
author = "M. Kandemir and J. Ramanujam and A. Choudhary and P. Banerjee",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 1999.; 11th International Workshop on Languages and Compilers for Parallel Computing, LCPC 1998 ; Conference date: 07-08-1998 Through 09-08-1998",
year = "1999",
doi = "10.1007/3-540-48319-5_3",
language = "English (US)",
isbn = "3540664262",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "34--50",
editor = "Siddhartha Chatterjee and Prins, {Jan F.} and Larry Carter and Jeanne Ferrante and Zhiyuan Li and David Sehr and Pen-Chung Yew",
booktitle = "Languages and Compilers for Parallel Computing - 11th International Workshop, LCPC 1998, Proceedings",
}