Name
Abstract | ||
|---|---|---|
The goal of this work is the efficient parallel execution of loops with indirect array accesses, in order to be embedded in a parallelizing compiler framework. In this kind of loop pattern, dependences can not always be determined at compile-time as, in many cases, they involve input data that are only known at run-time and/or the access pattern is too complex to be analyzed. In this paper we propose run-time strategies for the parallelization of these loops. Our approaches focus not only on extracting parallelism among iterations of the loop, but also on exploiting data access locality to improve memory hierarchy behavior and, thus, theoverall program speedup. Two strategies are proposed: one based on graph partitioning techniques and other based on a block-cyclic distribution. Experimental results show that both strategies are complementary and the choice of the best alternative depends on some features of the loop pattern. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1109/ICPP.2002.1040856 | ICPP |
Keywords | Field | DocType |
parallelising compilers,program control structures,access pattern,block-cyclic distribution,efficient parallel execution,graph partitioning techniques,indirect array accesses,loop pattern,memory hierarchy behavior,parallelizing compiler framework,program speedup | Locality,Memory hierarchy,Computer science,Parallel computing,Theoretical computer science,Compiler,Loop tiling,Graph partition,Data access,Speedup,Distributed computing | Conference |
ISSN | ISBN | Citations |
0190-3918 | 0-7695-1677-7 | 10 |
PageRank | References | Authors |
0.62 | 17 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| María J. Martín | 1 | 174 | 27.68 |
| David E. Singh | 2 | 191 | 23.13 |
| Juan Touriño | 3 | 424 | 43.66 |
| Francisco F. Rivera | 4 | 177 | 26.17 |