Skeleton/Pattern Programming with an Adder Operator for Grid and Cloud Platforms

Pattern operators are extensions to the Pattern/Skeleton parallel programming approach used to apply two types of communication patterns to the same data. The operators are intended to simplify the wide range of possible patterns and skeletons. The abstraction helps manage non-functional concerns on the Grid/Cloud environments. This paper explains how the pattern operators work on synchronous cyclic undirected graph patterns, and it shows examples on how they are used. A prototype was created to test the feasibility of the idea. The example used to show the operator approach is the addition of termination detection to a discrete solution to a PDE. The example can be coded with 27.31% less non-functional code than a similar implementation in MPJ, and its programmability index is 13.5% compared to MPJ’s 9.85%. The overhead for an empty pattern with low communication was 15%. The use of pattern operators can reduce the number of skeletons/patterns developed.