Håkan Lundvall
PELAB – Programming Environment Lab, Dept. Computer Science, Linköping University, Sweden
Peter Fritzson
PELAB – Programming Environment Lab, Dept. Computer Science, Linköping University, Sweden
Ladda ner artikel
Ingår i: The 48th Scandinavian Conference on Simulation and Modeling (SIMS 2007); 30-31 October; 2007; Göteborg (Särö)
Linköping Electronic Conference Proceedings 27:1, s. 1-7
Publicerad: 2007-12-21
ISBN:
ISSN: 1650-3686 (tryckt), 1650-3740 (online)
In this work we report preliminary results of automatically generating parallel code from equation-based models together at two levels: Performing inline expansion of a Runge-Kutta solver combined with finegrained automatic parallelization of the resulting RHS opens up new possibilities for generating high performance code; which is becoming increasingly relevant when multi-core computers are becoming common-place.
We have introduced a new way of scheduling the task graph generated from the simulation problem which utilizes knowledge about locality of the simulation problem. The scheduling is also done in a way that limits communication; to the greatest extent possible; to neighboring processors thus avoiding expensive global synchronization. Preliminary tests on a PC-cluster show speedup that is better than what was achieved in previous work where parallelization was done only at the equation system level.
Inga referenser tillgängliga
