A Parallelization Mixing OR-Tools/Gecode Solvers on Top of the Bobpp Framework

Abstract

The novelty of this paper is to propose a parallel solver that mixes two Constraint Programming (CP) solvers, on top of our Bobpp framework, in order to have a parallel CP solver portfolio. The first chosen CP solver is OR-tools which is an open source sequential solver. We propose an external OR-Tools parallelization (partitioning/migration/load balancing) on top of the Bobpp framework, where different instances of the OR-Tools solver are executed on different cores. The second chosen CP solver is Gecode that is also an open source sequential and parallel solver. The Gecode parallelization is internal in a sense that the parallel strategy is included in the library. The advantage of Gecode is that it can be easily interfaced with other software. Bobpp is a parallel framework that provides an interface between: Combinatorial Optimization problems or CP solvers and the parallel machines. Bobpp is designed to propose several parallelizations according to the parallel programming environment and the architecture of a machine. The performances of our solver portfolio are illustrated by solving CP problems modeled in Flat Zinc format.