CONSTRUCTION OF DO LOOPS FROM SYSTEMS OF AFFINE CONSTRAINTS
Parallel Processing Letters · 1995-09 · 05 (03) · 421-436
DOI: 10.1142/s0129626495000394 ↗Kurz gefasst
Fachartikel in der Zeitschrift Parallel Processing Letters, online erschienen am 21.11.2011. Verfasst von JEAN-FRANÇOIS COLLARD und 2 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref).
Abstract (Originalsprache)
Most parallelization techniques for [Formula: see text] loop nests are based on reindexation. Reindexation yields a new iteration space, which is a convex integer polyhedron defined by a set of affine constraints. Parallel code generation thus needs to scan all the integer points of this convex, thereby requiring the construction of a new [Formula: see text] loop nest. We detail an algorithm to this purpose, which relies on a parametrized version of the Dual Simplex. We show how the resulting loop nest and especially the loop bounds can be kept simple, thus reducing the control overhead of parallelization to a minimum.
Zitieren
APA
COLLARD, J., RISSET, T., & FEAUTRIER, P. (1995). CONSTRUCTION OF DO LOOPS FROM SYSTEMS OF AFFINE CONSTRAINTS. Parallel Processing Letters, 05(03), 421-436. https://doi.org/10.1142/s0129626495000394
Vancouver
COLLARD J, RISSET T, FEAUTRIER P. CONSTRUCTION OF DO LOOPS FROM SYSTEMS OF AFFINE CONSTRAINTS. Parallel Processing Letters. 1995;05(03):421-436. doi:10.1142/s0129626495000394
BibTeX
@article{COLLARD1995,
author = {COLLARD, JEAN-FRANÇOIS and RISSET, TANGUY and FEAUTRIER, PAUL},
title = {CONSTRUCTION OF DO LOOPS FROM SYSTEMS OF AFFINE CONSTRAINTS},
journal = {Parallel Processing Letters},
year = {1995},
volume = {05},
number = {03},
pages = {421--436},
doi = {10.1142/s0129626495000394}
}
EUVIMED