Hermann Mierendorff

Europort-1: Porting industrial codes to parallel architectures

Europort is a European initiative (within the ESPRIT III programme) the goal of which is to demonstrate the benefit of parallel computer technology for industry by porting a vast range of real industrial applications to parallel platforms. This porting action will serve as an exemplar for industry to increase the awareness of parallel high performance computing (HPC) within industry at large and demonstrate the cost-effectiveness of parallel systems. Europort as a whole is subdivided into two projects, Europort-1 and Europort-2. This paper gives an overview of the Europort-1 project, namely, those activities dealing with fluid dynamics and structural mechanics. Europort-1 is partially funded by the European Commission under contract EP 8421.

Performance estimations for SUPRENUM systems

Abstract A SUPRENUM system consists of many independent processors connected by a hierarchical bus system. Application problems are usually parallelized by decomposition into processes which are mapped onto the processors. Standard multigrid methods for the Poisson equation are considered as a model problem. An abstract model of the SUPRENUM system is developed consisting of five essential components. Their performance is approximated by linear functions. The efficiency and speedup of the considered parallel algorithms are estimated for several system and problem sizes. Parameter studies show the influence of the most important system parameters. The results are extended to some other multigrid algorithms.

Industrial parallel computing with real codes

Abstract The significant amount of work required to move large commercial application programs to parallel architectures in a portable way has stalled the take up of parallel technology in industry, thereby preventing the extra competitiveness of this technology from being fully utilized. Therefore, the European Commission has decided to promote European industry through the Europort initiative (within the ESPRIT III programme) by partially funding the porting of 38 industrially relevant codes to parallel computers. The goal is to demonstrate the benefit and cost-effectiveness of such systems and foster their industrial use. This paper presents current trends and first official benchmark results in the area of fluid dynamics and structural mechanics (Europort-1). These clearly show that it is not necessary to develop new codes in order to be able to gain essential benefit from the power of parallel architectures. In spite of serious constraints which come along with the porting of commercial codes in an industrial environment, all parallel codes will outperform their sequential counterpart at a considerably better price-performance ratio.

Working with MPI Benchmarking Suites on ccNUMA Architectures

Four different benchmarking suites for testing the performance of MPI routines have been considered on an SGI Origin2000. Special properties of these benchmarking suites which are mostly hidden to the user turned out as being of considerable influence on the benchmarking results for ccNUMA systems such as number and location of buffers, warm-up of the cache before running the benchmark, or procedure of measuring the time. In addition, we consider interpretation of results and their approximation by piecewise linear curves.

- WINPAR -: Windows-Based Parallel Computing

Personal computers are todays most widely used technology. They can be found in almost any company, office, university and school. Those PCs are usually connected to local area networks (LANs). Due to the high performance of modern off-the-shelf microprocessors, PCs can reach the processing power of workstations. However, even when using state-of-the-art software packages, most of a PCs processing power still remains unused. In particular, most PCs are unused during off-work hours. During the last few years, a number of research projects aimed at utilizing networked workstations as parallel computing systems. Standard communication libraries were ported to workstations, low-communication algorithms were developed, and various parallel programming tools were ported to workstation clusters. These activities utilized workstation clusters as an alternative to expensive parallel computers for a wide variety of application domains. The WINPAR project aims at transfering selected concepts and technologies with high quality and proven usability from parallel computers and workstation clusters to PC networks. The projects visions are to operate networked PCs as parallel computers, and to make parallel computing available for the PC mass market.

Europort: Parallel CFD for industrial applications

Publisher Summary During the past decade, computer scientists have largely demonstrated the high potential of parallel computing technology. Computer scientists were convinced of the importance of parallel technology for the future development of high-performance computing. For the general purpose CFD code PHOENICS, each time step requires updates of velocity components as well as updates of the pressure. The first is accomplished by Gauss-Seidel-like iterations of the velocity components and the second by solving the so-called pressure-correction equation, which is, roughly, a Poisson equation for the pressure. The major emphasis in benchmarking was on comparing the performance of the parallel codes run on standard parallel platforms, with that of their sequential analogs run on traditional systems. Europort has shown that an essential benefit is obtainable even under these constraints some of which, clearly, are in conflict with the goal of obtaining the highest parallel efficiency. In addition, this is achievable in a reasonable time frame and with a reasonable amount of work. It is not necessary to develop new codes to be able to exploit the power of parallel architectures.

Parallel Industrial Fluid Dynamics and Structural Mechanics Codes

The European Commission has promoted European industry through the Europort initiative (within the ESPRIT III programme) by partially funding the porting of 38 industrially relevant codes to parallel computers. The goal was to demonstrate the benefit and cost-effectiveness of such systems at large and foster their industrial use. Europort has finished end of February 1996 and this paper presents an overview on results in the areas of fluid dynamics and structural mechanics which were treated in the subproject Europort-1.

Automatic model generation for performance estimation of parallel programs

Abstract A hybrid method for performance modeling of parallel programs is considered where the runtime of large sequential segments is estimated statically and the parallel program structure is evaluated by simulation. The present paper describes a way to generate a model of a given program automatically from the source code where the user has to provide only values for a small number of variables. This model contains the control structure of the original program and timing information for generalized basic blocks. We consider Fortran programs which are parallelized using the message passing paradigm. A prototype of a tool for automatic model generation has been developed which is able to treat examples of moderate size.

Definition of control variables for automatic performance modeling

Automatic model generation is studied as part of a hybrid modeling strategy using simulation for performance analysis. Two major steps have to be carried out in this context. The program which is being investigated has to be translated into a model. During the translation, runtime has to be estimated for numerous computational blocks of statements which are replaced by simple delays. For performance estimation, the model has finally to be analyzed by an evaluation tool. Model evaluation as well as runtime estimation of computational blocks requires values of some variables, the control variables. We discuss the problem of automatic definition of control variables in general and consider some important cases. For the implementation of a model generating tool, we concentrate on parallel Fortran programs using message passing primitives for process communication.

Generation of Performance Models

A hybrid method for performance modeling of parallel programs is presented, where the runtime of large sequential segments is estimated statically and the parallel program structure is evaluated by simulation. AUGUR (automatic model generation with user response) is a tool that assists the user during performance model generation starting from the source of a parallel Fortran program. The resulting model can be simulated by MODARCH.