On Using Volume Computation to Estimate the Work Distribution for Parallel Programs

In this paper we describe a performance parameter which models the work contained in a parallel program and the corresponding work distribution. The work distribution is modeled at the program level which carefully distinguishes between useful and redundant work. We achieve high accuracy due to aggressive exploitation of compiler knowledge such as loop iteration spaces, array access patterns and data distributions. The underlying algorithm is based on the intersection and volume computation of n-dimensional linear and convex polytopes. The performance parameter has been implemented under the P 3 T, which is a static parameter based performance prediction tool under the Vienna Fortran Compilation System (VFCS).