New advances in reconfigurable optical interconnect technologies will allow the fabrication of cheap, fast and run-time adaptable networks for connecting processors and memory modules in large shared-memory multiprocessor machines. Since, in some technologies, the switching times of these components are high compared to the memory access time, reconfiguration can only take place on a time scale significantly above individual memory accesses. In this paper, we present preliminary results of our investigation into the exploitability of the space and time locality of address streams by a reconfigurable network.