This year we again report Live! from Europe's main supercomputing event. See the issues for each day:

• Wednesday June 23, 2004 .
• Thursday June 24, 2004 .
• Friday June 25, 2004 .

This year we start each issue with an experimental "blog" giving you some personal impressions. The next sections provide traditional reporting. The last section "Company news" provides mainly press release type of information from the companies. Hence, a few items are brought to you from three different view points.

Late afternoon yesterday, I arrived at the conference centre in Heidelberg. The tutorial on supercomputing benchmarking was well underway as was the building of the booths for the exhibtition. Always interesting to watch the people who will be explaining in suit next day why their product is the best, rolling up the sleeves and putting equipment and machinery together. The "democratisation" process that is taking place in the supercomputer arena - reflected by the fact that a lot of manufacturers are producing one or two TOP500 class supercomputers - also resulted in a rush on booth space. The organisers had 50 booths which were sold out with a number of companies eager to exhibit still on the waiting list. At the opening session, conference chair Hans Meuer said there where close to 500 participant from close to 25 countries. (AE)

The TOP500 of the world's fastest supercomputer is getting bluer. In the June 2004 list IBM has 224 entries. Second is HP which has 140 entries - down from 165 last year. SGI and Sun are again in third and fourth position. More and more clusters are finding their way into the TOP500. This is reflected by a large number of integrator companies having one or two entries in the TOP500.

Two years after Quadrics helped build the fastest Linux cluster of the day, called MCR, Quadrics and Lawrence Livermore National Laboratory (LLNL) have done it again. This time the system, called Thunder, is not only the fastest Linux cluster in the world, but also the fastest computer system in the US and the number 2 system in the world, surpassing the previous number 2 system (ASCI-Q), also based on Quadrics QsNet.

At the ISC 2004 Conference, Dr. Simon White described the research done at the Max Planck Institute for Astrophysics on how the structure in the Universe is constantly growing since the Big Bang. To provide an idea on the evolution from these origins, sophisticated simulations are being performed.

In the first day afternoon session at ISC 2004 Keith Gray, BP Manager from Houston, Texas held a presentation on the support of computing needs to perform subsalt seismic imaging. He talked about the Thunder Horse GOM development and about the HPC computing architecture and application infrastructure to perform complex seismic research.

Frieder Seible from the Jacobs School of Engineering at the University of California in San Diego showed the dependence on the physical infrastructure of roads, bridges, dams, water supply pipelines/aqueducts, ports and harbours, etc., in a lot of interesting pictures. Mostly we are unaware of its existence and problems as long as functionality is provided. The ageing of structures, natural hazards such as earthquakes, floods, and fires, as well as man-made hazards including terrorist attacks and accidents, threaten the functionality of the physical infrastructure and extraordinary expenditures are required to just maintain the status quo.

This talk was given by Bernd F. Lober, Vice President, and Wolfgang Becker, Chief Architect, SAP AG. The topic of adaptive computing deals with the enterprise service architecture, the performance and scalability, and the adaptive computing infrastructure. Centralised computing is replaced, the client server architecture is now leveraged. The new dimension is focusing on service oriented architectures with adaptable business.

The Cray X1 supercomputer once again had the most powerful processors and the highest efficiencies in the latest rankings of the "World's TOP500 Supercomputers". The company also recently announced that overall customer-reported scores for the Cray X1 supercomputer system were the best for any high-performance computing (HPC) system on the new U.S. government-sponsored HPC Challenge benchmark tests.

PathScale, developer of software and hardware solutions to acceleratef Linux clusters, and Absoft , specialized in software development tools, have announced the results of a collaborative engineering initiative to assure optimum compatibility and interoperability between the PathScale EKO compiler suite for Linux-based AMD64 compatible systems and the Absoft Fx2 Fortran/C/C++ debugging solution.