Mapping parallelism to multi-cores: a machine learning based approach

Wang, Zheng and O'Boyle, Michael F.P. (2009) Mapping parallelism to multi-cores: a machine learning based approach. In: Proceedings of the 14th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming (PPoPP '09). ACM, USA, pp. 75-84. ISBN 978-1-60558-397-6

Abstract

The efficient mapping of program parallelism to multi-core processors is highly dependent on the underlying architecture. This paper proposes a portable and automatic compiler-based approach to mapping such parallelism using machine learning. It develops two predictors: a data sensitive and a data insensitive predictor to select the best mapping for parallel programs. They predict the number of threads and the scheduling policy for any given program using a model learnt off-line. By using low-cost profiling runs, they predict the mapping for a new unseen program across multiple input data sets. We evaluate our approach by selecting parallelism mapping configurations for OpenMP programs on two representative but different multi-core platforms (the Intel Xeon and the Cell processors). Performance of our technique is stable across programs and architectures. On average, it delivers above 96% performance of the maximum available on both platforms. It achieve, on average, a 37% (up to 17.5 times) performance improvement over the OpenMP runtime default scheme on the Cell platform. Compared to two recent prediction models, our predictors achieve better performance with a significant lower profiling cost.