A parallel Quantized State System Solver for ODEs

JOAQUIN FERNANDEZ; ERNESTO KOFMAN; FEDERICO BERGERO

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING

ACADEMIC PRESS INC ELSEVIER SCIENCE

Lugar: Amsterdam; Año: 2017

0743-7315

This work introduces novel parallelization techniques for Quantized State System (QSS) simulation of continuous time and hybrid systems and their implementation on a multi-core architecture. Exploiting the asynchronous nature of QSS algorithms, the novel methodologies are based on the use of non?strict synchronization between logical processes. The fact that the synchronization is not strict allows to achieve large speedups at the cost of introducing additional numerical errors that, under certain assumptions, are bounded depending on some given parameters.Besides introducing the parallelization techniques, the article describes their implementation on a software tool and it presents a theoretical analysis of the aforementioned additional numerical error. Finally, the performance of the novel methodology and its implementation is deeply evaluated on four large scale models.