COMPUTATIONAL RESEARCH in BOSTON and BEYOND (CRIBB)

Date	Dec. 6, 2013
Speaker	Alex Kogan (Oracle Labs)
Topic	Message Passing or Shared Memory: Evaluating the Delegation Abstraction for Multicores
Abstract:	Even for small multi-core systems, it has become harder and harder to support a simple shared memory abstraction. Processors access some memory regions more quickly than thers, which is a phenomenon called "non-uniform memory access" (NUMA). These trends have prompted researchers to investigate alternative programming abstractions based on message passing rather than cache-coherent shared memory. To advance a pragmatic understanding of these models' respective strengths and weaknesses, we have explored a range of different message passing and shared memory designs, for a variety of concurrent data structures, running on different multi-core architectures. Our goal was to evaluate which combinations perform best and where simple software or hardware optimizations might have the most impact. We observe that different approaches perform best in different circumstances, and that the communication overhead of message passing often can outweigh its benefits. Nonetheless, we discuss ways in which this balance may shift in the future. Overall, we conclude that, by emphasizng high-level shared data abstractions, software should be designed to be largely independent of the choice of low-level communication mechanism.

Acknowledgements

We thank the generous support of MIT IS&T, CSAIL, and the Department of Mathematics for their support of this series.