As workstation clusters gain popularity as a parallel computing platform,there is an increasing need for performance tools that support these platforms. Performance prediction is important for performance analysis of scalable parallel applications. Although there are several performance tools available that work with PVM programs,none are capable of performance prediction. We have developed the...

* Dr. Rosen is with the Naval Air Warfare Center, Aircraft Division, Warminster, PA Abstract This paper describes the SCI-based workstation cluster system being developed at the HCS Research Lab and the parallel processing and network experiments that have been conducted and the results achieved. Using several different input sizes and degrees of partitioning and granularity for the parallel pr...

In this paper, a case study is presented which is aimed at investigating the performance of several parallel versions of the POV{Ray raytracing package implemented on a workstation cluster using the MPI message passing library. Based on a manager/worker scheme, variants of workload partitioning and message scheduling strategies, in conjunction with diierent task granular-ities, are evaluated wi...

Highly scalable parallel computers, e.g. SCI-coupled workstation clusters, are NUMA architectures. Thus good static locality is essential for high performance and scalability of parallel programs on these machines. This paper describes novel techniques to optimize static locality at compilation time by application of data transformations and data distributions. The metric which guides the optim...

Processes Barrier Figure 6.1 Processes reaching the barrier at different times. Time Active Waiting Synchronous Computations In a (fully) synchronous application, all the processes are synchronized at regular points. A barrier, a basic mechanism for synchronizing processes-inserted at the point in each process where it must wait. All processes can continue from this point when all the processes...

The growing importance of networked workstations as a computing milieu has created a new modality of parallel computing, namely, the possibility of having one workstation \steal cycles" from another. In a typical episode of cycle-stealing, the owner of workstation B allows the owner of workstation A to take control of B's processor whenever it is idle, with the promise of relinquishing control ...

In this paper the conservative Chandy-Misra parallel simulation algorithm is discussed. The basic algorithm is improved by using null message cancellation, simulation loop optimization and multicasting techniques. The algorithms are used for the simulation of a GSM mobile network application in a distributed workstation environment, Diworse. In the simulation results, special attention is paid ...

Parallel workstations, each comprising a 10-100 processor shared memory machine, promise cost-e ective general-purpose multiprocessing. This thesis explores the coupling of such smallto medium-scale shared memory multiprocessors through software over a local area network to synthesize larger shared memory systems. Multiprocessors built in this fashion are called Distributed Scalable Shared memo...

Workstation networks are an underutilized yet valuable resource for solving large-scale parallel problems. In this paper, we present \idle-initiated" techniques for eeciently scheduling large-scale parallel computations on workstation networks. By \idle-initiated," we mean that idle computers actively search out work to do rather than wait for work to be assigned. The idle-initiated scheduler o...