Exploiting Monotone Convergence Functions in Parallel Programs

Scientific codes which use iterative methods are often difficult to parallelize well. Such codes usually contain while loops which iterate until they converge upon the solution. Problems arise since the number of iterations cannot be determined at compile time, and tests for termination usually require a global reduction and an associated barrier. We present a method which allows us avoid performing global barriers and exploit pipelined parallelism when processors can detect nonconvergence from local information.