Managing Compilation Overheads in a Runtime Specializer for OpenMP

M. Burcea and M.J. Voss (Canada)


OpenMP API, Runtime Optimization, Program Specializa tion, Hyperthreading


While runtime compilation has in practice been largely restricted to programming languages that execute on vir tual machines, such as Java and C#, parallel OpenMP pro grams show many promising traits for efficient and effec tive runtime optimization. The stOMP system for the run time optimization of OpenMP applications is currently un der development at the University of Toronto. One of the key issues in making stOMP successful is to minimize the overheads incurred when invoking compilers at runtime. This paper focuses on two techniques that have been de veloped to manage these overheads: a two-level, context based hot-spot detector and a pruning mechanism that elim inates poorly behaved variables as specialization targets. A detailed presentation of both techniques is presented along with evaluations of the techniques on a subset of the SPEC OMP benchmark suite.

Important Links:

Go Back