Paper Details
Reference:
Dattatraya Kulkarni, Michael Stumm, and Ronald C. Unrau,
"Implementing flexible computation rules with subexpression-level loop transformations",
In Proceedings EUROPAR Conference on Parallel Processing, Stockholm, Sweden, Springer Verlag Lecture Notes in Computer Science Volume 966, Springer Verlag, Berlin, Germany, August, 1995, pp. 327–338.
Download:
Abstract:
Computation Decomposition and Alignment (CDA) is a new loop transformation framework that extends the linear loop transformation framework and the more recently proposed Computation Alignment frameworks by linearly transforming computations at the granularity of subexpressions. It can be applied to achieve a number of optimization objectives, including the removal of data alignment constraints, the elimination of ownership tests, the reduction of cache conflicts, and improvements in data access locality. In this paper we show how CDA can be used to effectively implement flexible computation rules with the objective of minimizing communication and, whenever possible, eliminating intrinsics that test whether computations need to be executed or not. We describe CDA, show how it can be used to implement flexible computation rules, and present an algorithm for deriving appropriate CDA transformations.
Keywords:
Compiler optimization, loop transformations, computation decomposition and alignment
Reference Info:
DOI: 10.1007/BFb0020475
ISBN: 978-3-540-44769-6
ISSN: 0302-9743
BibTeX:
@inproceedings(Kulkarni-EuroPar95, author = {Dattatraya Kulkarni and Michael Stumm and Ronald C. Unrau}, title = {Implementing flexible computation rules with subexpression-level loop transformations}, booktitle = {Proceedings EUROPAR Conference on Parallel Processing}, location = {Stockholm, Sweden}, volume = {Springer Verlag Lecture Notes in Computer Science Volume 966}, publisher = {Springer Verlag}, address = {Berlin, Germany}, month = {August}, year = {1995}, pages = {327-338}, doi = {10.1007/BFb0020475}, isbn = {978-3-540-44769-6}, issn = {0302-9743}, keywords = {Compiler optimization, loop transformations, computation decomposition and alignment} )