Spatiotemporal Partitioning Strategies

Spatiotemporal Partitioning Strategies are a new set of design patterns strategyoverviewand accompanying selection methodology for developing parallel computations. The patterns are based on the idea that programs can be partitioned by data or instructions and these partitionings can occur in time or space. This project presents the patterns and describes many case studies which demonstrate the selection methodology.

The partitioning strategies project explores design patterns of parallel software development as a tool for both software engineering and teaching. Existing parallel patterns have tremendous descriptive power, but it is often unclear to non-experts how to choose a pattern based on the specific performance goals of a given application. This work addresses the need for a pattern selection methodology by presenting four patterns and an accompanying decision framework for choosing from these patterns given an application’s throughput and latency goals.

The patterns are based on recognizing that one can partition an application’s data or instructions and that these partitionings can be done in time or space, hence we refer to them as spatiotemporal partitioning strategies. This work introduces a taxonomy that describes each of the resulting four partitioning strategies and presents a three-step methodology for selecting one or more given a throughput and latency goal.