The Community for Technology Leaders
2011 International Conference on Parallel Architectures and Compilation Techniques (2011)
Galveston, Texas USA
Oct. 10, 2011 to Oct. 14, 2011
ISSN: 1089-795X
ISBN: 978-0-7695-4566-0
pp: 383-392
Program optimization on multi-core systems must preserve the program memory consistency. This paper studies TSO-preserving binary optimization. We introduce a novel approach to formally model TSO-preserving binary optimization based on the formal TSO memory model. The major contribution of the modeling is a sound and complete algorithm to verify TSO-preserving binary optimization with O(N2) complexity. We also developed a dynamic binary optimization system to evaluate the performance impact of TSO-preserving optimization. We show in our experiments that, dynamic binary optimization without memory optimizations can improve performance by 8.1%. TSO-preserving optimizations can further improve the performance by 4.8% to a total 12.9%. Without considering the restriction for TSO-preserving optimizations, the dynamic binary optimization can improve the overall performance to 20.4%.
Total Store Ordering, Binary Optimization, TSO-preserving optimization

C. Wang and Y. Wu, "Modeling and Performance Evaluation of TSO-Preserving Binary Optimization," 2011 International Conference on Parallel Architectures and Compilation Techniques(PACT), Galveston, Texas USA, 2011, pp. 383-392.
183 ms
(Ver 3.3 (11022016))