The PVM system, a software framework for heterogeneous concurrent computing in networked environments, has evolved in the past several years into a viable technology for distributed and parallel processing in a variety of disciplines. PVM supports a straightforward but functionally complete message passing model, and is capable of harnessing the combined resources of typically heterogeneous networked computing platforms to deliver high levels of performance and functionality. In this paper, we describe the architecture of PVM system, and discuss its computing model, the programming interface it supports, auxiliary facilities for process groups and MPP support, and some of the internal implementation techniques employed. Performance issues, dealing primarily with communication overheads, are analyzed, and recent findings as well as experimental enhancements to are presented. In order to demonstrate the viability of PVM for large scale scientific supercomputing, the paper incl...

This paper describes an X-window based software environment called HeNCE (Heterogeneous Network Computing Environment) designed to assist scientists in developing parallel programs that run on a network of computers. HeNCE is built on top of a software package called P M which supports process management and communication between a network of heterogeneous computers. HeNCE is based on a parallel programming paradigm where an application program can be described by a graph. Nodes of the graph represent subroutines and the arcs represent data dependencies. HeNCE is composed of integrated graphical tools for creating, compiling, executing, and analyzing HeNCE programs.

Abstract-A collective communication library for parallel computers includes frequently used operations such as broadcast, reduce, scatter, gather, concatenate, synchronize, and shift. Such a library provides users with a convenient programming interface, efficient communication operations, and the advantage of portability. A library of this nature, the Collective Communication Library (CCL), intended for the line of scalable parallel amputer products by IBM, has been designed. CCL is pact of the parallel application programming interface of the recently announced IBM 9076 Scalable POWERparallel System 1 (SP1). In this paper, we examine several issues related to the functionality, correctness, and performance of a portable collective communication library while focusing on three novel aspects in the design and implementation of CCL: 1) the introduction of process groups, 2) the definition of semantics that ensures correctness, and 3) the design of new and tunable algorithms based on a realistic point-to-point communication model. Index Terms- Collective communication algorithms, collective communication semantics, message-passing parallel systems, portable library, process group, tunable algorithms. I.

We present a systematic performance assessment of the hardware and software that provides the interface between applications and emerging high-speed networks. Using LogP as a conceptual framework and Active Messages as the communication layer, we devise a set of communication microbenchmarks. These generate a graphical signature from which we extract the LogP performance parameters of latency, overhead, and bandwidth. The method is illustrated on three diverse platforms: Intel Paragon, Meiko CS-2, and a cluster of SparcStations with Myrinet. The study provides a detailed breakdown of the differences in communication performance among the platforms. While the details of our microbenchmark depend on Active Messages, the methodology can be applied to conventional communication layers. Introduction 2 LogP Performance Assessment of Fast Network Interfaces 1.Introduction In recent years, we have seen dramatic advances in scalable, low-latency interconnection networks for parallel machine...

This paper describes the design of the Fortran90D/HPF compiler, a source-to-source parallel compiler for distributed memory systems being developed at Syracuse University. Fortran 90D/HPF is a data parallel language with special directives to specify data alignment and distributions. A systematic methodology to process distribution directives of Fortran 90D/HPF is presented. Furthermore, techniques for data and computation partitioning, communication detection and generation, and the run-time support for the compiler are discussed. Finally, initial performance results for the compiler are presented. We believe that the methodology to process data distribution, computation partitioning, communication system design and the overall compiler design can be used by the implementors of compilers for HPF.

Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data alignment and distributions. This paper describes the design and implementation of a Fortran90D/HPF compiler. Techniques for data and computation partitioning, communication detection and generation, and the run-time support for the compiler are discussed. Finally, initial performance results for the compiler are presented which show that the code produced by the compiler is portable, yet efficient. We believe that the methodology to process data distribution, computation partitioning, communication system design and the overall compiler design can be used by the implementors of HPF compilers. This work was supported in part by NSF under CCR-9110812 (Center for Research on Parallel Computation) and DARPA under contract # DABT63-91-C-0028. The content of the information does not necessarily reflect the position or the policy of the Government and no official endorsement should be inferr...

This paper presents a distributed architecture for the visualization of large steady and transient data-sets. Because one of the goals is to not have to store away the 10s to 100s of Gigabytes necessary to perform a post-processing animation of the data, this system must be able to run concurrently with the task producing the data. This requirement forces portions of the visualization system to run on the same hardware where the data is generated. What follows is a discussion of current computer architectures used for CFD calculations and how these systems affect the model selected for the visualization software. Also data and data movement considerations must be an integral part of any project that requires the distribution of a compute task. 1 Introduction Scientific visualization is an area that has grown greatly in size and importance in the last five years. This growth has been driven by a number of factors. One is the change in the types of calculations that are being done by Co...

The minimum rectilinear Steiner tree (MRST) problem arises in global routing and wiring estimation, as well as in many other areas. The MRST problem is known to be NP-hard, and the best performing MRST heuristic to date is the Iterated 1-Steiner (I1S) method recently proposed by Kahng and Robins. In this paper we develop a straightforward, efficient implementation of I1S, achieving a speedup factor of three orders of magnitude over previous implementations. We also give a parallel implementation that achieves near-linear speedup on multiple processors. Several performance-improving enhancements enable us to obtain Steiner trees with average cost within 0.25% of optimal, and our methods produce optimal solutions in up to 90% of the cases for typical nets. We generalize I1S and its variants to three dimensions, as well as to the case where all the pins lie on k parallel planes, which arises in, e.g., multi-layer routing. Motivated by the goal of reducing the running times of our algorith...

We propose a new visual structured programming language, GRAPNEL (GRAphical Process's NEt Language) for designing distributed parallel programs. This language is a part of a complex software environment for parallel programming which includes tools for design, mapping, visualization, optimization, monitoring and debugging of parallel systems. For design we use a hybrid language where the main internal structure of the processes and the communication between processes are described using graphical representaion, meanwhile the sequential parts and code fragments without communication are described using textual representation. 2 Introduction Parallel processing is emerging as a promising way of computation as powerful new multiprocessor computers are becoming available at reduced cost. Also, there is a need to exploit a collection of machines joined by a fast interconnection network. However, if we use a distributed system instead of a single--processing one, it raises new difficulties ...

Network computing seeks to utilize the aggregate resources of many networked computers to solve a single problem. In so doing it is often possible to obtain supercomputer performance from an inexpensive local area network. The drawback is that network computing is complicated and error prone when done by hand, especially if the computers have different operating systems and data formats and are thus heterogeneous. HeNCE (Heterogeneous Network Computing Environment) is an integrated graphical environment for creating and running parallel programs over a heterogeneous collection of computers. It is built on a lower level package called PVM. The HeNCE philosophy of parallel programming is to have the programmer graphically specify the parallelism of a computation and to automate, as much as possible, the tasks of writing, compiling, executing, debugging, and tracing the network computation. Key to HeNCE is a graphical language based on directed graphs that describe the parallelism and dat...