On Generalizing Divide and Conquer Parallel Programming Pattern

(1) Background: Structuring is important in parallel programming order to master its complexity, and this structuring could be achieved through patterns skeletons. Divide-and-conquer computation essentially defined by a recurrence relation that links the solution of problem solutions subproblems same type, but smaller sizes. This pattern allows specification different types computations, so it provide general comprises all cases. We intend prove divide-and-conquer generalized such comprise many other patterns, this, we formulation it. (2) Methods: Starting from proposed pattern, analyzed based on stages: decomposition, base-case composition. Examples are provided, execution models analyzed. (3) Results: functional provided for it, specialized parameters’ instantiating into classical patterns. Based specific stages divide-and-conquer, three classes computations emphasized. In context, an equivalent efficient bottom-up formally proved. Associated executions emphasized computations. (4) Conclusion: A more definition includes arity list decomposition degrees, level recursion, also alternative cases not trivial allow approaches (sequential or parallel) lead better performance. Together with associated analysis equivalence optimized models, provides useful both at semantic implementation level.