Summary: A Unified Framework for Schedule and Storage Optimization #
William Thies + , Fr’ed’eric Vivien § , Je#rey Sheldon + , and Saman Amarasinghe +
+ Laboratory For Computer Science
Massachusetts Institute of Technology
Cambridge, MA 02139
{thies,jeffshel,saman}@lcs.mit.edu
§ ICPS/LSIIT
Universit’e Louis Pasteur
Strasbourg, France
vivien@icps.u­strasbg.fr
Abstract
We present a unified mathematical framework for analyz­
ing the tradeo#s between parallelism and storage allocation
within a parallelizing compiler. Using this framework, we
show how to find a good storage mapping for a given sched­
ule, a good schedule for a given storage mapping, and a
good storage mapping that is valid for all legal schedules.
We consider storage mappings that collapse one dimension
of a multi­dimensional array, and programs that are in a sin­
gle assignment form with a one­dimensional schedule. Our

Source: Amarasinghe, Saman - Computer Science and Artificial Intelligence Laboratory & Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)
Vivien, Frédéric - INRIA & Laboratoire de l'Informatique du Parallélisme, Ecole Normale Supérieure de Lyon

Collections: Computer Technologies and Information Sciences