Title: Model-guided empirical tuning of loop fusion

Authors: Apan Qasem, Ken Kennedy

Addresses: Department of Computer Science, Texas State University, San Marcos, TX, USA. ' Department of Computer Science, Rice University, Houston, TX, USA

Abstract: Loop fusion is recognised as an effective transformation for improving memory hierarchy performance. However, unconstrained loop fusion can lead to poor performance because of increased register pressure and cache conflict misses. In this paper, we present a cache-conscious analytical model for profitable loop fusion. We use this model to tune fusion parameters for different architectures through empirical search. Experiments on four different platforms for a set of applications show significant speedup over fully optimised code generated by state-of-the-art commercial compilers.

Keywords: automatic tuning; loop fusion; memory hierarchy performance; cache-conscious modelling; empirical tuning.

DOI: 10.1504/IJHPSA.2008.021798

International Journal of High Performance Systems Architecture, 2008 Vol.1 No.3, pp.183 - 198

Published online: 04 Dec 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article