HP has announced that HP ProLiant servers have accelerated critical research for three leading scientific institutions, enabling them to satisfy unprecedented computational demands at lower cost and with optimal power efficiency.

Tokyo Institute of Technology (Tokyo Tech), Georgia Institute of Technology (Georgia Tech) and MD Anderson Cancer Center looked to HP for high-performance servers to help speed their scientific and medical achievements while advancing to top spots on the TOP500 list of the world’s largest supercomputing installations.

Tokyo Tech needed a supercomputer that could achieve critical performance at maximum power density. To meet its computing needs, HP built its first petascale system, the TSUBAME 2.0, designed to support applications in climate and weather forecasting, tsunami simulations and computational fluid dynamics.

The TSUBAME 2.0 supercomputer took the No. 4 position on the TOP500 list. With power-efficient HP ProLiant servers and the HP Modular Cooling System, TSUBAME 2.0 is one of the most energy-efficient supercomputers in the world.

Georgia Tech’s Keeneland System, which supports scientific discovery, claimed the No. 117 position on the list. The project is funded by a five-year, $12 million Track 2D grant awarded by the National Science Foundation.

Using the HP Unified Cluster Portfolio and HP StorageWorks X9000 Network Storage Systems, MD Anderson Cancer Center at the University of Texas placed at No. 169 on the TOP500 list. HP technology enabled the center to leverage its existing storage area network (SAN) infrastructure to create a flexible, virtual resource pool that can be utilized by researchers regardless of their computational needs.

HP leads the market with standards-based server platforms, including the HP BladeSystem c-Class platform and HP ProLiant servers, that deliver supercomputer-class performance in less space with less power. Its systems enable the scientific community to satisfy unprecedented computational demands at lower cost and maximum density.

The recently introduced HP ProLiant SL390s G7 server now powers 11 of the systems on the TOP500 list. The HP BladeSystem c-Class remains the dominant system architecture in the list with 140 entries.

Tokyo Tech’s multivendor solution places fourth

The TSUBAME 2.0 supercomputer delivered to Tokyo Tech is the result of a multivendor collaboration among HP, NEC Corporation, Microsoft, NVIDIA, Intel, Mellanox, Voltaire and DataDirect Networks.

With only 200 square meters of physical space and 1.8 megawatts of available power, Tokyo Tech built TSUBAME 2.0 with HP ProLiant SL390s G7 servers to achieve supercomputer-class performance, while meeting limited space requirements with a skinless, ultra-lightweight design that eliminates extraneous hardware.

TSUBAME 2.0 is powered by 1,357 HP ProLiant SL390s G7 servers, each with three NVIDIA Tesla M2050 General Purpose Graphics Processing Units, which deliver an eightfold increase in compute power compared to earlier generations.(1) The system achieved a sustained performance of 1.192 petaFLOPS (floating point operations per second) when running the Linpack benchmark on Linux and 1.12 petaFLOPS on Microsoft Windows.

“We needed to increase performance and efficiency thirtyfold, despite limits on available power and data center space,” said Satoshi Matsuoka, project lead and professor, Tokyo Tech. “HP’s expertise and technology coupled with our team’s experience in large-scale deployments, cloud computing and graphics accelerator technology enabled us to push the frontier of energy and space-efficient supercomputing.”

Georgia Tech’s Keeneland Initial Delivery System edges into TOP500

HP enabled Georgia Institute of Technology and its partners, including Oak Ridge National Laboratory and the University of Tennessee at Knoxville, to develop the Keeneland Initial Delivery System.

Consisting of 120 HP ProLiant SL390s G7 servers and 360 NVIDIA Tesla M2070 accelerators, the Keeneland System delivers performance of more than 64 teraFLOPS on the Linpack benchmarks. This combination of HP ProLiant servers with NVIDIA processors accelerated computational science and data-intensive applications, while addressing new challenges of energy efficiency. On Linpack, this initial Keeneland System rates at 677 megaFLOPS per watt. The final delivery of a much larger Keeneland System is scheduled for early 2012.

MD Anderson Cancer Center places on TOP500 List

MD Anderson Cancer Center turned to HP for high-performance computing that addresses the challenges associated with research, including analyzing, storing and managing the large volumes of data generated by genomics research. Today, MD Anderson runs a Converged Infrastructure that is more reliable and robust as well as easier to maintain.

Upgrading their four-year cluster to a new HP Cluster Platform 4000 with 336 HP ProLiant BL465c G7 server blades, MD Anderson researchers were able to increase computing throughput tenfold with the HP StorageWorks X9000 integrated into the cluster. As a result, researchers now have more compute power to simulate proton radiation therapies, toxicity studies due to radiation treatment, and better understand the genes that are responsible for cancer with the eventual goal of helping provide better treatment for cancer patients. MD Anderson also installed several 32-core HP ProLiant DL785 G6 servers with large memory to quickly pre-process genomic data for computational analysis.

“We needed high-performance clusters that could keep pace with our exploding volumes of data, but that could centralize and pool data resources to make them accessible across all research departments,” said Lynn Vogel, Ph.D., vice president and chief information officer, MD Anderson Cancer Center. “HP’s state-of-the-art solutions jump-started our research initiatives, permitting us to map genomes and run billion-particle data sets in a matter of hours instead of days. Our researchers have published over 120 papers in the past few years using our cluster as a resource.”

About the rankings

The TOP500 ranking of supercomputers is released twice a year by researchers at the Universities of Tennessee and Mannheim, Germany, and at NERSC Lawrence Berkeley National Laboratory. The list ranks supercomputers worldwide based on the Linpack N*N Benchmark, a yardstick of performance that is a reflection of processor speed and scalability.