Marketplace enthusiasm for HP Unified Cluster Portfolio

The HP supercomputer is a 1,024-node Cluster Platform 4000 based on HP ProLiant DL145 servers with AMD Opteron™ processors running the Linux operating system. A high-speed Voltaire InfiniBand interconnect is used with HP's XC System Software providing cluster management capability.

» Press Announcement (March 2006)
» Press Release (July 2005)

Aeronautical Systems Center (ASC) Major Shared Resource Center (MSRC)

"HP's Unified Cluster Portfolio will enable us to capitalize on the tremendous advances in price/performance provided by industry-standard technologies, while providing a fully supported, robust production system for our critical workload."

Steve Wourns,
Director, ASC MSRC

The utility computing facility at HP Labs and the installation of a new HP Cluster platform 4000 Supercomputer system as WilliamsF1's primary computing resource at their Grove, UK headquarters have increased the team's computer modeling capabilities in 2005 by more than a factor of three.

» Press Release (February 2005)

BMW Williams F1

"Prediction, using computational fluid dynamics, was our main tool to assess the implications of the new FIA rules for the 2005 season, and to consider a wide range of potential solutions. Together with our partner HP, we have scaled up our computational resource by a factor of three. We augmented our in-house capability with the use of HP's Bristol Labs utility computing facility, which allows us to run computations using external resource at peak load times, such as during the new car design phase."

Sam Michael,
Technical Director, WilliamsF1

To improve productivity and process jobs quicker, Boeing engineers installed Windows® Compute Cluster Server 2003 on an HP Cluster Platform 4000 for use with their finite element analysis and intelligent graphics applications.

» Case study (April 2007)

Boeing

"We found the HP Cluster Platform very useful because it provided defined cluster configurations with the flexibility to choose types of server, number of servers, and interconnects. In addition, the flexibility to preload Windows CCS at HP provided significant advantages in deployment."

Dr. J.S. Hurley,
Senior Manager,
Distributed Software and Systems Integration, Boeing

Borsa Italiana, the Italian stock exchange, deployed a 130-node HP Cluster Platform 4000 based on HP ProLiant blade servers to reliably distribute trading information to financial institutions, consolidate its server systems and lower energy costs.

» Case study (November 2007)
» Press release (May 2007)

Borsa Italiana

Alessandro Pelosi, senior engineer, ICT Department, Borsa Italiana

Callaway Golf installed an HP Cluster Platform 3000 system based on HP ProLiant DL140 G3 and DL380 G5 servers running Microsoft® Windows® Computer Cluster Server (CCS) software. The installation also included HP StorageWorks 70 Modular Storage Array (MSA) and HP ProCurve switches. HP configured and installed this turnkey solution running in one hour and Callaway has seen performance increased by 2-3 times.

"Callaway Golf earned its reputation as a club design innovator by embracing technology. Today, our HP high performance computing cluster lets us model critical aspects of club design faster than ever. We're able to test more ideas and design permutations, which in turn enables us to meet ever-higher standards of innovation without impacting design lead times."

John Loo, Senior Manager,
Design Systems, Callaway Golf

The CCRC has deployed 2 clusters:

• An 8-node HP Cluster Platform 6000 system based on HP Integrity rx2600 servers with Intel® Itanium® processors and Myrinet interconnects, running Linux. Scali Manage provides cluster management. A 2 TB StorageWorks RAID array is also included.
• A 64-node HP Cluster Platform 3000 system based on HP ProLiant DL360 servers with dual Intel® Xeon® processors and both Myrinet and Gigabit Ethernet interconnects. Scali Manage provides cluster management.

"Our simulations require huge computing capacity combined with low latency. HP was one of only two vendors that offered a suitable solution. And in the end, HP offered superior value and good system management tools for the total solution we needed."

Dr. Robert Woods
Complex Carbohydrate Research Center (CCRC)
University of Georgia

CSC's M-grid project consists of clusters located on their premises and at eight universities. They are based on 200 HP ProLiant DL145 and 585 servers with 381 processors. The combined computing capacity of the clusters is approximately 1.5 teraflop/s.

» Press announcement (October 2006)
» Press announcement (January 2006)

"We found HP clearly to be the best and most cost effective choice. HP clearly had the best understanding of what type of equipment we were looking for. Performance, large memory and good network connections are the most important features in servers and computers used in research."

Kai Nordlund
M-grid Project Coordinator
Professor of Computational Physics
CSC

The IGIB supercomputer, which is expected to deliver four teraflop/s of performance, is a 288-node HP Cluster Platform 3000 based on HP ProLiant servers with Intel® Xeon™ processors and running Linux with XC System Software. The Voltaire ISR 9288 provides the high-speed InfiniBand 10 Gbps cluster interconnect and HP's XC System Software provides cluster management capability.

» HP Press Release
» HP's supercomputer will greatly aid research at IGIB (May 2006)

"HP's Cluster Platform provides a scalable architecture that allows us to complete large, complex simulation experiments such as molecular interactions and dynamics, virtual drug screening, protein folding and so forth much more quickly. This technology, combined with HP's experience and expertise in life sciences, helps IGIB speed access to information, knowledge and new levels of efficiency, which we hope will ultimately culminate in the discovery of new drug targets and predictive medicine for complex disorders with minimum side effects."

Dr. Samir Brahmachari
Director, Institute of Genomics
and Integrative Biology

The Institute of Statistical Mathematics (ISM) is Japan's leading statistical science institution. ISM recently deployed a 128 node HP Cluster Platform 4000, with XC Software and integrated with HP StorageWorks Scalable File Share. The solution supports inter-university research and advanced projects requiring statistical analysis.

" Building clusters takes time, but with the HP XC4000 cluster system, the operating system, middleware and overall optimization were all included...It's great to be able to put something in place and deploy immedately....It supported Lustre-based HP StorageWorks Scalable File Share which could relieve I/O bottlenecks."

Professor Tamura Yoshiyasu,
Deputy Director, ISM

Taiwan's NCHC 192-node, 2 teraflop/s HP Cluster Platform 6000 system, based on HP Integrity rx2600 servers with Intel® Itanium® processors, is one of the largest Linux clusters in Asia Pacific. HP's XC System Software provides cluster management capability, and the HP StorageWorks Scalable File Share delivers high bandwidth, high capacity, shared storage to all nodes on the cluster.

"We are pleased to partner with HP on this important project. With our firm commitment to research and innovation, we needed a computing environment to meet our scalability, sustainability and performance requirements. HP was able to deliver accurately what we needed to stay on course with our high-performance computing strategy. HP's industry-standard architecture, competitive pricing and customized on-site engineering service made HP an excellent choice to help us stay ahead in today's fast-changing IT industry."

Dr. Joe Juang Director, NCHC

Orbital wanted a distributed memory system that was also powerful and reliable so they chose the HP Cluster Platform 4000BL (CP4000BL) based on the HP BladeSystem c7000 infrastructure, which consolidates and packages all supporting computing elements - compute, storage, network, and power - into a single cabinet that smoothes data center integration and optimization.

» Case study (April, 2008)

“From a technical standpoint, the CP4000BL cluster is by far the best piece of hardware I have ever worked with.“ I’ve been a system administrator for more than twelve years, and I’ve managed hardware from all of the big names in the industry. The HP CP4000BL cluster is one of my favorite platforms.”

Don Collins
Orbital’s East Coast IT

PNNL's 11.8-teraflop/s, Linux-based HP supercomputer was designed specifically for computational biology and chemistry research, and is one of the fastest in the world for those applications. It boasts power of nearly 2,000 Intel® Itanium® processors and also has 6.8 terabytes of local memory.

» Press Release (April 2005)
» Press Release (June 2004)

"The HP and PNNL collaboration is a good example of how industry and research laboratories can partner to create unique solutions to national problems. Our collaboration has resulted in building a supercomputer that will enable scientists to integrate and access data at an unprecedented rate, transforming their ability to do detailed computer modeling on a whole host of subjects. Research scientists from around the world will be able to make use of its power."

Dr. George Michaels
Director, Computational and Information
Sciences Directorate
Pacific Northwest National Laboratory

HPCGG has installed a 64-node HP Cluster Platform 4000 managed by HP's Linux-based XC System Software, integrating Linux, Platform Computing's LSF software, HP's MPI (message passing interface), as well as open source components. Gigabit Ethernet connectivity is used.

» Case study (June 2007)
» Press Release (February 2005)
» Press Release (September 2003)

"With this system, analysis that used to take a month to run will only take days. It opens up an exciting new world of opportunities for collaborative healthcare research here in the Boston area."

Isaac Kohane, M.D., Ph.D.
Director of Bioinformatics, HPCGG
Principal Investigator, I2B2 National Center for Biomedical Computing

To Deploy maximum computing power within tightening space, power, cooling, and administration-time requirments, Pharmasset deployed the HP ProLiant c-Class Server Blades in an HP BladeSystem c3000 enclosure.

"I evaluated the various solutions on a number of criteria, but in the end it all really came down to processor speed and density" Anuth says. "The HP Bladesystem met our speed, density, power, space and cooling requirement best."

Jim Anuth,
Director of Information Technology,
Paramasset

SHARCNET's new HP clusters, which are collectively expected to deliver 25 teraflop/s of performance and total 1900 nodes, will consist of HP Cluster Platform 4000 systems based on HP ProLiant servers with AMD Opteron processors running HP's Linux-based XC System Software. Cluster interconnection will be delivered by GbE, Quadrics ELAN4, Myrinet and Voltaire's InfiniBand. The upgrade will integrate a total of 480 terabytes in HP StorageWorks Scalable File Share (HP SFS) systems.

» Press Release
» Research website

"The HP Unified Cluster Portfolio provides us an integrated, open-source based supercomputing utility to support distributed, high-performance computing, data management and visualization. Our researchers will be able to use as much, or as little, of the processing and data capacity as they require, and seamlessly access it from anywhere on the network. Such technology is critical to Canada's competitiveness as a world-class research community and our ability to accelerate the production of results that are of benefit to our economy, health, environment, scientific knowledge and culture."

Hugh Couchman
Scientific Director, SHARCNET

SPACI maintains a grid comprised of three clusters (two have 68-nodes and one has 13-nodes) of HP Cluster Platform 6000 systems based on HP Integrity rx2600 servers with Intel® Itanium® processors. HP's Linux-based XC System Software provides cluster management capability. High performance Quadrics Elan 4 interconnects are used at each cluster site.

» Press Release (June 2004)

"Our decision to select HP in favor of a major competitor was based on a number of critical factors. HP Italy's obvious commitment to the project and our access to HP's technical computing team (HPC) at an EMEA level, provided invaluable support and consultancy, and demonstrated their belief in the strategic importance of the project."

Professor Giovanni Aloisio
President, SPACI Consortium
Professor, University of Lecce

SSCK's 1.87 TFLOP/s, 312 processor supercomputer is an HP Cluster Platform 6000 system based on HP Integrity rx2600 and rx8620 servers with Intel® Itanium® processors. HP's XC System Software provides cluster management capability. By early 2006, the overall system will be upgraded to a total of 340 nodes. An HP SFS system will provide 40 terabytes of storage in its final configuration.

» Press release (April 2007)
» Case study (January 2006)
» Press Release

"The HP high performance supercomputing system is significantly advancing research and development work at the universities and research institutes in the state of Baden-Württemberg, Germany. In addition, the HP Cluster Platform 6000 provides a powerful, reliable, and easy to manage system for industrial users."

-- Prof. Dr. Wilfried Juling, Director of the Computing Center, University of Karlsruhe
SSCK

SIB promotes research, the development of databanks and computer technologies, teaching and service activities in the field of bioinformatics. SIB’s Vital-IT Computer Center has 2 production clusters (one 32 node HP Cluster Platform 6000 and one 32 node HP Cluster Platform 4000) and 2 development clusters, sharing a Voltaire InfiniBand fabric, and connected to a 13 TB HP Scalable File Share (SFS). The clusters utilize Red Hat Linux and HP-MPI, along with Platform LSF.

» Voltaire Case Study
» Press announcement (June 2003)

SIB has found that the combination of Voltaire Grid Director and HP SFS give researchers I/O performance comparable to locally-attached disks.

And..”overall, the HP and Voltaire cluster has increased our file system throughput by 10 times, and our researchers have doubled their productivity”

C. Victor Jongeneel, Ph.D, Director of Vital-IT Center, Swiss Institute of Bioinformatics

TIFR is implementing a 78-node HP Cluster Platform 6000 system, based on HP Integrity rx2600 servers with Intel® Itanium® processors. HP's XC System Software provides cluster management capability.

» Mumbai Press Coverage
» PUNE press coverage

"TIFR is very pleased to partner with HP - a global technology leader - for high-end research in the field of computational mathematics. These technologies will help us in our research on the fundamental problems in mathematics and optimization techniques. With the implementation of this Itanium cluster, we have reached yet another milestone in technology adoption to help scientific discoveries using world-class algorithmic research in computational mathematics."

Narendra Karmarkar
Head of Computational Mathematics Laboratory TIFR

Universidad de Chile installed an HP Cluster Platform 6000 with Scali Manage cluster management software to provide high performance computing power for scientific applications and meet research project deadlines. The system provides a platform to collaborate with other universities in South America and the Pacific Rim through a Supercomputer Grid.

» Case study

Universidad de Chile

The C&I consultant’s ability to interact and communicate with the HP engineers and HP’s great partnership with Sali to deliver Scali Manage™ was very impressive. It drove home the added value HP brings to High Performance Computing.”

Juan Carlos Maureira, Center for Mathematical Modeling Systems Engineer, Universidad de Chile

“Our primary research goal is to use computer modeling and simulation to better analyze and understand coastal hydroscience. HP helps us achieve this goal by providing us with a powerful system that can effectively handle the extraordinary computational demands of our research.”

Director of the CHAMPS Lab

The University of Houston's TLC² has a 154-node Linux cluster based on HP Itanium® 2 systems. Three interconnects are used - Myrinet, Gigabit Ethernet and fast Ethernet.

"Thanks to HP and its commitment to open standards and software and the power of Itanium solutions, we are firmly convinced that our choice maximizes the impact of our research in addition to providing a cost effective solution to our needs."

Dr. Lennart Johnsson
Director, ACRL and TLC²

The University of Tromsø has installed a Linux cluster of 49 HP Integrity servers with a total of 196 Intel® Itanium® processors.

» Case study

"Our chemistry and biotechnology researchers say that installing Norway's first teraflop/s cluster from HP has completely changed the way they work, because they no longer have to wait weeks for results."

Tor Johansen
Project Manager, High Performance Computing University of Tromsø

"With HP's XC Cluster, we have a complete and supported cluster solution, with single system features for management and familiar user interfaces. It is what we needed to quickly deploy and support the round-the-clock needs of our university community."

Akinori Kidera
Graduate School of Integrated Science
Yokohama City University