Several techniques have been developed to increase the performance of parallel computers. Recon®gurable networks can be used as an alternative to increase the performance. Network recon®guration can be carried out in di erent ways. Our research has focused on distributed memory systems with dynamic recon®guration of node location. Brie¯y, this technique consists of positioning the processors in the network depending on the existing communication pattern among them, to suit the requirements of each computation.In this article, we present a dynamic recon®guration technique for wormhole networks. We have used both a crossbar and a multistage interconnection network to implement a recon®gurable logical two-dimensional (2-D) torus topology. The recon®guration mechanism is based on a distributed recon®guration algorithm. The algorithm is based on a cost function that requires only local information. We discuss recon®guration features and adjust the di erent parameters of the recon®guration algorithm. We have also studied the deadlock problem in recon®gurable wormhole networks, and give details of our solution. Finally, we have evaluated the performance of this technique under several workloads. Ó