Search

We are now seeing governments and funding agencies looking at ways to increase the value and pace of scientific research through increased or open access to both data and publications. In this point of view article, we wish to look at another aspect of these twin revolutions, namely, how to enable developers, designers and researchers to build intuitive,multimodal, user-centric, scientific applications that can aid and enable scientific research.

The study of Quantum Chromodynamics (QCD) remains one of the most challenging topics in elementary particle physics. The lattice formulation of QCD, in which space–time is treated as a four-dimensional hypercubic grid of points, provides the means for a numerical solution from first principles but makes extreme demands upon computational performance. High Performance Computing (HPC) offers us the tantalising prospect of a verification of QCD through the precise reproduction of the known masses of the strongly interacting particles. It is also leading to the development of a phenomenological tool capable of disentangling strong interaction effects from weak interaction effects in the decays of one kind of quark into another, crucial for determining parameters of the Standard Model of particle physics. The 1980s saw the first attempts to apply parallel architecture computers to lattice QCD. The SIMD and MIMD machines used in these pioneering efforts were the ICL DAP and the Cosmic Cube, respectively. These were followed by the Connection Machine, the Meiko i860 Computing Surface and the Intel Hypercube. The end of the decade witnessed a rise in the development of special purpose dedicated parallel systems, notably the APE machines in Rome, the Columbia machines, the GF-11 system at IBM Research and the QCDPAX project in Tsukuba. The state-of-the-art is represented by the CP–PACS machine at Tsukuba, and QCDSP, the latest Columbia machine. We give a brief pedagogic review of lattice QCD, outline the computational methodology used and discuss the sources of systematic error that arise in numerical calculations. We outline some of the early calculations and discuss parallel architectures and their application to QCD, giving examples of both commercial and special purpose machines. After a short section on recent developments, we describe state-of-the-art machines and conclude with the prospects for the future.

In the desktop networked PC age, does high performance computing have a future? Drawing on the history of the computer and the present state of the art, the article concludes that HPC is alive and well, with healthy prospects for many years to come.

I well remember my arrival at Caltech on a sunny October morning in 1970. Fresh from the University of Oxford where even graduate students at that time wore ties and shirts, I was unsure what to wear for my first meeting with Murray Gell‐Mann. I gambled, wrongly, on a suit, and arrived at the office of the theory group secretary, Julie Curcio, feeling more and more overdressed and as if I had a large label dangling from my collar saying “New PhD from Oxford.” I had seen Gell‐Mann once before in England but was unsure if the bearded individual dressed in an open‐necked shirt and sitting in Julie's office was indeed the eminent professor, A moment after I had introduced myself, my doubts were dispelled by the man putting out his hand and saying “Hi, I'm Murray.” This episode illustrates only a small part of the healthy culture shock I experienced in California. Six years in Oxford had left me used to calling my professor “Professor Dalitz, sir.” At that time, I would certainly not have dared to address Richard Dalitz as “Dick.” A ‘new’ set of lectures—on computation—by one of the more colorful characters in modern physics, gives rise to these reminiscences by an Englishman in Richard's court.

Unlike single-processor benchmarks, multiprocessor benchmarks can yield tens of numbers for each benchmark on each computer, as factors such as the number of processors and problem size are varied. A graphical display of performance surfaces therefore provides a satisfactory way of comparing results. The University of Southampton has developed the Graphical Benchmark Information Service (GBIS) on the World Wide Web (WWW) to display interactively graphs of user-selected benchmark results from the GENESIS and PARKBENCH benchmark suites.

High Performance Fortran (HPF) is an informal standard for extensions to Fortran 90 to assist its implementation on parallel architectures, particularly for data-parallel computation. Among other things, it includes directives for specifying data distribution across multiple memories, and concurrent execution features. This article provides a tutorial introduction to the main features of HPF.