Abstract
Virtual execution is a method to reduce the prohibitive overhead of the execution step on adaptive compilation systems. Nevertheless it may fail to identify the best compiler optimizations set, reducing the speedup that could be achieved by the adaptive compilation system. We discuss the shortcomings of the virtual execution method and propose a hybrid mechanism, which leverages the virtual execution method to select a few optimizations sets before performing the execution step to select the best set of optimizations.
Chapter PDF
Similar content being viewed by others
References
Cavazos, J., Fursin, G., Agakov, F., Bonilla, E., O’Boyle, M.F.P., Temam, O.: Rapidly selecting good compiler optimizations using performance counters. In: Proceedings of the International Symposium on Code Generation and Optimization, CGO 2007, pp. 185–197. IEEE Computer Society, Washington, DC (2007)
Cooper, K.D., Grosul, A., Harvey, T.J., Reeves, S., Subramanian, D., Torczon, L., Waterman, T.: ACME: Adaptive compilation made efficient. SIGPLAN Not. 40(7), 69–77 (2005)
de Lima, E.D., de Souza Xavier, T.C., da Silva, A.F., Ruiz, L.B.: Compiling for performance and power efficiency. In: 2013 23rd International Workshop on Power and Timing Modeling, Optimization and Simulation (PATMOS), pp. 142–149 (September 2013)
Henning, J.L.: Spec cpu2006 benchmark descriptions. SIGARCH Computer Architecture News 34(4), 1–17 (2006)
Pan, Z., Eigenmann, R.: Fast and effective orchestration of compiler optimizations for automatic performance tuning. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO), pp. 319–332 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Bertazi, G.K., da Silva, A.F., Borin, E. (2014). A Hybrid Framework to Accelerate Adaptive Compilation Systems. In: Quintão Pereira, F.M. (eds) Programming Languages. SBLP 2014. Lecture Notes in Computer Science, vol 8771. Springer, Cham. https://doi.org/10.1007/978-3-319-11863-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-11863-5_10
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11862-8
Online ISBN: 978-3-319-11863-5
eBook Packages: Computer ScienceComputer Science (R0)