Automatic parallelization of canonical loops

This paper presents a compilation technique that performs the automatic parallelization of canonical loops. Canonical loops are a recurring pattern that we have observed in many well known algorithms, such as frequent itemset, K-means and K nearest neighbors. Our compiler translates C code to sequen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Science of computer programming Jg. 78; H. 8; S. 1193 - 1206
Hauptverfasser: da Mata, Leonardo Luiz Padovani, Pereira, Fernando Magno Quintão, Ferreira, Renato
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.08.2013
Schlagworte:
Automatic parallelization
Compiler
Map-reduce
Stream-programming
Automatic parallelization
Compiler
Stream-programming
Map-reduce
ISSN:0167-6423, 1872-7964
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents a compilation technique that performs the automatic parallelization of canonical loops. Canonical loops are a recurring pattern that we have observed in many well known algorithms, such as frequent itemset, K-means and K nearest neighbors. Our compiler translates C code to sequences of stream filters that communicate through a variety of channel types. We analyze code containing canonical loops, separate the data over a cluster of processors and determine suitable communication strategies between these processors. Experiments performed on a cluster of 36 computers show that, for the three algorithms described above, our method produces speed-ups that are almost linear on the number of available processors. These experiments also show that the code automatically generated is competitive when compared to hand tuned programs.
ISSN:0167-6423
1872-7964
DOI:10.1016/j.scico.2012.09.006