INTERCONNECTS
CINECA In Italy Selects Cray XD1
Cray announced that CINECA, Italy's national supercomputing center, has selected the new Cray XD1 supercomputer to advance scientific and engineering research across a broad spectrum of disciplines. The 144-processor system is the largest ordered by a European customer since the Cray XD1 supercomputer began shipping to Europe in November 2004. CINECA will make the innovative Cray XD1 supercomputer available to researchers at its 25 affiliated Italian universities for advanced work in mathematics, engineering, physics, chemistry, statistics, climate science, biomedicine and human sciences. CINECA will also exploit the Cray XD1 system's field programmable gate array (FPGA) capabilities for acceleration of key applications.
"We look forward to giving Italy's research community access to the latest Cray technology and to expanding our long-standing, beneficial relationship with Cray," said CINECA Director Marco Lanzarini. In 2004, CINECA hosted the successful Cray Advanced Technical Workshop in Europe.
"Cray is excited that CINECA, a national supercomputing center with a strong worldwide reputation, has chosen the Cray XD1 supercomputer as a powerful new tool for its users. We will collaborate closely with Marco Lanzarini and his staff to ensure that CINECA's ambitious goals for this system are met," said Ulla Thiel, vice president responsible for Cray Europe.
More About the Cray XD1 Supercomputer
The Cray XD1 is rapidly winning customers around the world. This exciting new system lets users experience the performance and reliability of Cray supercomputing technology in systems that scale from small to highly parallel. The Cray XD1 provides scientists and engineers with a platform purpose-built to meet their high performance computing challenges, and is an attractive alternative to the challenge of managing clusters assembled from general-purpose business servers.
The Cray XD1 supercomputer features the direct connect processor (DCP) architecture, which removes PCI bottlenecks and memory contention to deliver superior sustained performance. The Cray XD1 system has the lowest latency of any current HPC system, with MPI latency of 1.8 microseconds in measured tests conducted using the Ohio State MPI benchmark.