Paper Info
Title
Run-Time Characterization of Irregular Accesses Applied to Parallelization of Irregular Reductions
Abstract
Abstract: Irregular reduction operations are the core of many large scientific and engineering applications. There are, in the literature, different methods to solve these operations in parallel. In this paper we discuss a new technique which improves performance significantly, both in terms of execution time and memory overhead. These improvements are achieved in the preprocessing as well as in the resulting parallel code. Our proposal is based on the use of the Irregular Access Region Descriptor (IARD). This data structure is a compact characterization of indirectly accessed arrays that can be used for the efficient parallelization of a wide spectrum of irregular codes. In this paper we present its application to parallelize irregular reduction operations.
Year
DOI
Venue
2001
10.1109/ICPPW.2001.951841
ICPP Workshops
Keywords
Field
DocType
irregular code,engineering application,irregular accesses applied,irregular reductions,irregular access region descriptor,accessed array,compact characterization,data structure,efficient parallelization,different method,parallel code,irregular reduction operation,run-time characterization,application software,spectrum,data structures,indexation,polarization,sparse matrices,kernel,parallelization,parallel algorithms,computer science
Data structure,Parallel algorithm,Computer science,Irregular Z-buffer,Parallel computing,Preprocessor,Execution time,Sparse matrix,Distributed computing
Conference
ISSN
Citations 
PageRank 
1530-2016
2
0.41
References 
Authors
9
3
Name
Order
Citations
PageRank
David E. Singh119123.13
Francisco F. Rivera217726.17
María J. Martín317427.68