On confident task-accurate performance estimation

Xu Y, Wang B, Rosales R, Hasholzner R, Teich J (2013)


Publication Status: Published

Publication Type: Conference contribution

Publication year: 2013

Pages Range: 25-37

Conference Proceedings Title: Proceedings of the International Conference on Architecture of Computing Systems (ARCS)

Event location: Prague CZ

ISBN: 9783642364235

DOI: 10.1007/978-3-642-36424-2_3

Abstract

Task-accurate performance estimation methods are widely applied for design space exploration at the Electronic System Level (ESL). These methods estimate performance by simulating task-level models annotated with nominal execution time. In early design phases, source code, which is necessary for generating accurate annotations, is usually not available. Instead, extrapolated values or even estimated values are used for performance estimation, which makes the results unreliable and may eventually cause performance violations if used to guide critical design decisions. In this paper, we propose a confident task-accurate performance estimation methodology that uses high-level information available in early design phases and provides confident estimation to guide design space exploration with respect to performance constraints. © 2013 Springer-Verlag.

Authors with CRIS profile

Related research project(s)

Involved external institutions

How to cite

APA:

Xu, Y., Wang, B., Rosales, R., Hasholzner, R., & Teich, J. (2013). On confident task-accurate performance estimation. In Proceedings of the International Conference on Architecture of Computing Systems (ARCS) (pp. 25-37). Prague, CZ.

MLA:

Xu, Yang, et al. "On confident task-accurate performance estimation." Proceedings of the 26th International Conference on Architecture of Computing Systems, ARCS 2013, Prague 2013. 25-37.

BibTeX: Download