In this article, some instances of well known combinatorial optimization NP-Hard problems are solved by using Koopmans and Beckmann formulation of the quadratic assignment problem (QAP). These instances are solved by using an Embarrassingly Parallel Genetic Algorithm or by using an Island Parallel Genetic Algorithm; in both cases, the implementation is carried out on Graphics Processing Units (GPUs).

The Grisland model is a Parallel Genetic Algorithm designed to find optimal solutions close to the Travelling Salesman Problem. This algorithm combines the classical fine-grained parallel models (grid models) and the coarsemodels (island models) with the 2-opt local search heuristics. This article implements on Grisland some assignment problems, which result in particular cases of the Symmetric Euclidian Problem of the Travelling Salesman.