Abstract

Executing multi-threaded programs on multiprocessors can exploit the inherent paral-lelism among threads. However I the load imbalance and frequent remote data access factors may degrade the performance in distributed-memory parallel systems. To cope with these problems, one of the solutions is to enhance threads with dynamic migration capability. This paper describes our experiences with the design and implementation issues of thread migration in the Xthreads library, which is currently running on the nCUBE2 and iPSC860 machines. Performance measurements of the current implementation are also included.