The International Journal of High Performance Computing Applications

In November 2000, the government announced a new e-Science initiative in the UK with some £120m funding. In this paper we describe a range of the applications that are now on-going within the e-Science Programme and we detail one of the focuses of the e-Science Core Programme, that of building a UK e-Science Grid. We briefly discuss some of the middleware development activities in the UK and indicate where they sit in the international scene.

A Grid Network monitoring and performance measurement infrastructure is a key component of a large-scale Grid. Requirements for network monitoring with respect to Grid operations as well as performance characteristics and their relevance to Grid context have to be carefully identified before realizing such a system. In this paper we analyze the main issues raised by the design, development, integration in a Grid middleware and deployment of a network monitoring infrastructure in a real Grid environment. Then we present the details of the architecture we proposed in the context of the European DataGRID project and the MapCenter tool we developed to vizualize the Grid status in real time and to give access to our measurement infrastructure.

The use of the Grid for interactive applications imposes new requirements on tools supporting performance analysis, which are not well addressed by tools available in the area of parallel and distributed programming. The two most important demands are an on-line mode of operation, and the ability to measure user-defined, application-specific metrics, such as, for example, the response time of a specific user interaction. The paper starts with an analysis of these requirements, which is based on real-world applications developed in the European CrossGrid project. The most important feature of these applications is the presence of a person in the main computing loop, who inspects intermediate results and controls the further behavior of the application. Based on the results of the requirements analysis, a new performance analysis tool G-PM is currently being implemented. The paper outlines the main ideas as well as some design details of GPM, with a focus on the concept of user-defined metrics, the possible problems of this concept, and some of its implementation aspects.

Over a decade ago, the TOP500 list was started as a way to measure supercomputers by their sustained performance on a particular linear algebra benchmark. Once reserved for the exotic machines and extremely well-funded centers and laboratories, commodity clusters now make it possible for smaller groups to deploy and use high performance machines in their own laboratories. This paper describes a weekend activity where two existing 128-node commodity clusters were fused into a single 256-node cluster for the specific purpose of running the benchmark used to rank the machines in the TOP500 supercomputer list. The resulting metacluster sits on the November 2002 list at position 233. A key differentiator for this cluster is that it was assembled, in terms of its software, from the NPACI Rocks open-source cluster toolkit as downloaded from the public website. The toolkit allows non-cluster experts to deploy and run supercomputer-class machines in a matter of hours instead of weeks or months. With the exception of recompiling the University of Tennessee’s Automatically Tuned Linear Algebra Subroutines (ATLAS) library with a recommended version of the GNU C compiler, this metacluster ran a “stock” Rocks distribution. Successful first-time deployment of the fused cluster was completed in a scant 6 h. Partitioning of the metacluster and restoration of the two 128-node clusters to their original configuration was completed in just over 40 min.

This paper describes early (pre-weekend) benchmark activities to empirically determine reasonably good parameters for the High Performance Linpack (HPL) code on both Ethernet and Myrinet interconnects. It fully describes the physical layout of the machine, the description-based installation methods used in Rocks to re-deploy two independent clusters as a single cluster, and gives the benchmark results that were gathered over the 40-h period allotted for the complete experiment. In addition, we describe some of the on-line monitoring and measurement techniques that were employed during the experiment. Finally, we point out the issues uncovered with a commodity cluster of this size.

The techniques presented in this paper truly bring supercomputers into the hands of the masses of computational scientists.

Coupling grid applications requires code modification and high S/W engineering effort. We propose the Ensemble methodology in which message passing components are developed separately and applications, whether regular, irregular, SPMD or MPMD, are composed without component modification. Composed applications are pure Message Passing Interface programs running on MPICH-G2. We demonstrate our approach by developing two simplified atmospheric and ocean components, which may run on their own or coupled together (climate model) in any required configuration depending on geography or other design issues.

Parallel computing is now popular and mainstream, but performance and ease of use remain elusive to many end-users. There exists a need for performance improvements that can be easily retrofitted to existing parallel applications. In this paper we present MPI process swapping, a simple performance enhancing add-on to the MPI programming paradigm. MPI process swapping improves performance by dynamically choosing the best available resources throughout application execution, using MPI process over-allocation and real-time performance measurement. Swapping provides fully automated performance monitoring and process management, and a rich set of primitives to control execution behavior manually or through an external tool. Swapping, as defined in this implementation, can be added to iterative MPI applications and requires as few as three lines of source code change. We verify our design for a particle dynamics application on desktop resources within a production commercial environment.

In this paper we discuss the design and use of a fault-tolerant MPI (FT-MPI) that handles process failures in a way beyond that of the original MPI static process model. FTMPI allows the semantics and associated modes of failures to be explicitly controlled by an application via a modified functionality within the standard MPI 1.2 API. Given is an overview of the FT-MPI semantics, architecture design, example usage and sample applications. A short discussion is given on the consequences of designing a fault-tolerant MPI both in terms of how such an implementation handles failures at multiple levels internally as well as how existing applications can use new features while still remaining within the MPI standard.

In this paper we examine the topic of writing fault-tolerant Message Passing Interface (MPI) applications. We discuss the meaning of fault tolerance in general and what the MPI Standard has to say about it. We survey several approaches to this problem, namely checkpointing, restructuring a class of standard MPI programs, modifying MPI semantics, and extending the MPI specification. We conclude that, within certain constraints, MPI can provide a useful context for writing application programs that exhibit significant degrees of fault tolerance.

In this paper we presents a tool for the dynamic forecast of performance of linear algebra routine as well as communication between clusters. FAST (Fast Agent’s System Timer) is a software package allowing client applications to obtain an accurate forecast of routine needs in terms of completion time, memory space, and number of communication, as well as current system availability. FAST relies on existing low-level software packages, i.e. network and host monitoring tools, and some of our developments in sequential and parallel computational routines modeling. The FAST internals and user interface are presented, as well as experimental results and validation on different applications.