An intercontinental network of supercomputers spanning more than 10 000 mil
es and running challenging scientific applications was realized at the Supe
rcomputing '99 (SC99) conference in Portland, OR using PACX-MPI and ATM PVC
s. In this paper, we describe how we constructed the heterogeneous cluster
of supercomputers, the problems we confronted in terms of multi-architectur
e and the way several applications handled the specific requirements of a m
etacomputer. (C) 2001 Elsevier Science B.V. All rights reserved.