An SOA Approach to High Performance Scientific Computing: Early Experiences

Abstract

Service Oriented Architecture (SOA) has been embraced in enterprise computing for several years. The scientific community always felt the need of an SOA infrastructure not only with the convenience of enterprise SOA but also with expected level of high performance capabilities. Our research has produced an SOA middleware (ANU-SOAM) which supports an already popular enterprise SOA middleware API (Platform Symphony API) with the desired level of performance for scientific computations such as a Conjugate Gradient Solver. We have extended the compute services of ANU-SOAM with a common data service (CDS) between client and the service instances. The aim is to improve performance of applications by reducing communications or communication cost between the client and the service instances with the help of CDS. This is achieved by enabling tasks to perform a deferred put operation to the common data their service instances, with the results of the put operation only being visible to the next generation of tasks. These updates can be synchronised (committed) at CDS at the direction of the client. This property enables applications on ANU-SOAM to overcome latency of poor networks (or 'cloud') between client and service instances. Experimental results on a small Gigabit ethernet cluster show that, for the Conjugate Gradient Solver, the ANU-SOAM version suffers no appreciable performance loss over MPI versions and the CDS enhances N-Body Solver performance, with good scalability in both cases.