A Parallel Scheduler for Block Iterative Solvers in Heterogeneous Computing Environments.
Mario Arioli, Anthony Drummond, Iain Duff, Daniel Ruiz · 1995
We present a parallel scheduler for distributing work to a group of processors in a heterogeneous computing environment. Some of the processors in the heterogeneous computing environment can be clustered to take advantage of particular communication networks. Here, the scheduler has been used in the implementation of a parallel block iterative solver based on the Cimmino method. We have used PVM 3 to implement the communication between the heterogeneous processors. 1 Introduction Nowadays with the help of different programming tools, it is easier to develop parallel applications that run in heterogeneous environments. From the advantages of these environments, we are interested in the ability of combining different computing capabilities into a single metacomputer to provide a way of reusing resources that are already available at our computing sites. We introduce a scheduler for distributing a set of tasks among a set of processors contained in a metacomputer. We study a case for the...