SGI Cyclone Offers HPC in the Cloud

SGI has launched a new side to its business: cloud computing for the HPC crowd. SGI, which was formed through Rackable’s acquisition of Silicon Graphics, launched SGI Cyclone on Friday, joining a number of high performance computing (HPC) providers now offering cloud services.

For a list billing price of $0.95 per HPC core hour, SGI Cyclone is offered in two service models: Software as a service (SaaS) and infrastructure as a service (IaaS). Cyclone will initially support five technical domains: computational fluid dynamics, finite element analysis, computational chemistry and materials, computational biology, and ontologies.

HPC applications are a growing niche in the cloud computing universe. Last August, Linux cluster provider Penguin Computing announced Penguin On Demand. This month, Microsoft boosted its HPC cloud profile by giving away Azure compute time for free to engineers and scientists supported by the National Science Foundation.

The entry of SGI and Penguin into the cloud points to the high level of interest by the scientific and research communities in on-demand computing.

“More and more organizations that rely on HPC resources are investigating clouds for solutions that offer additional computing capacity and flexibility, and reduce or eliminate the need to make additional long-term investments in hardware,” said Earl Joseph, IDC program vice president for high performance computing.

Scientists Offered Free Access to Azure Cloud

Microsoft is giving scientists and researchers supported by the National Science Foundation free access to its Azure cloud computing platform for three years. The deal would potentially, in one fell swoop, give Microsoft access to research projects that the NSF funds in nearly 2,000 universities and institutions in all 50 states.

The agreement would also give Microsoft access to computer scientists who could help the software giant to develop new ways to simplify the use of cloud computing for the scientific and research community.

Microsoft formed the eXtreme Computing Group in June 2009 as part of its Microsoft Research arm. Its goal is to develop “radical new approaches to ultrascale and high-performance computing hardware and software,” specifically for computer security, cloud computing, and data center architecture, among other areas.

“I am very excited about this, as it is the fruit of nearly two years of planning and collaboration across Microsoft product and research teams, as well as many discussions with researchers, university leaders and government agencies,” wrote Dan Reed, corporate vice president for Microsoft’s eXtreme Computing Group, in his blog.

‘More Than Adequate’ Horsepower
Microsoft didn’t detail how much Azure capacity it would give away, but during a conference call announcing the deal, Reed said the compute power would be “more than adequate” for researchers’ needs.

HPC Customers Get a Cloud Computing Option

Six months after launching its Penguin on Demand (POD) cloud computing service, high-performance Linux cluster provider Penguin Computing said up to 200 of its 2,000-strong customer base are using its on-demand offering, including some new customer wins in the life-sciences sector.

POD is a complete high-performance computing (HPC) system in the cloud, but no virtualization technology is used because Penguin wanted to offer each of its HPC customers dedicated servers to ensure optimum performance.

HPC users, particularly academic researchers, are naturally drawn to the cost benefits of dynamic compute environments, as illustrated by the many shared networks of academic and research organizations, such as ESnet, a high-speed network managed by Lawrence Berkeley National Laboratory that’s used by thousands of Department of Energy scientists and collaborators worldwide. Some researchers have also been drawn to public clouds, including Amazon Web Services, which offers free usage credits to educators, academic researchers and students.

HPC on Azure, Too
Microsoft is reporting HPC customers using traditional HPC systems in conjunction with its Azure hosted platform. RiskMetrics, a financial risk management firm used Azure to help it measure and model complex financial instruments. According to Microsoft, RiskMetrics “anticipates developing increasingly seamless and scalable applications that span Windows Azure and Windows HPC Server 2008 … to deliver both on-premises and cloud computing capacity as needed.”

Princeton U. to Build New HPC Data Center

Princeton University will build a new data center to house its high performance computing operations, the university said last week. The new High-Performance Research Computing Center facility will be a two-story, 40,000 square foot facility located on the university’s Forrestal Campus in Plainsboro, N.J.,

The facility will be the home of the university’s supercomputer, TIGRESS – the Terascale Infrastructure for Groundbreaking Research in Engineering and Science Center. It also will also enable greater research collaboration between the university and the neighboring Geophysical Fluid Dynamics Laboratory (GFDL) and Princeton Plasma Physics lab. The GFDL is part of the U.S. National Oceanic and Atmospheric Administration and develops sophisticated prediction models for the path of hurricanes. The Princeton Plasma Physics Lab is funded by the U.S. Department of Energy and managed by the University, and conducts fusion energy research.

Verari ‘Reboots’ With Focus on Partners

Verari confirmed Tuesday that an investment group led by founder David Driggers has acquired the company’s assets and will ”re-start the Verari engine” with a focus on working through partners. In a statement on its web site, Verari announced the “successful acquisition of substantially all of Verari Systems’ corporate and intellectual property assets by an Investment Group led by Driggers.”

The high-performance computing company will change its name from Verari Systems to Verari Technologies. On Dec. 11 Verari halted most operations and laid off most of its staff, and its assets were placed for sale in an auction. Driggers’ group purchased all of Verari’s inventory, equipment and technologies and said it will support past Verari Systems’ customers.

Driggers said Verari Technologies will focus on blade-based servers and storage for high-performance computing, as well as data center containers.

‘Back to our Roots’
“We have the opportunity to go back to our roots of being a consulting company that heavily partners to deliver custom solutions for our customers,” says David Driggers. “The ‘new Verari’ is going to build stronger partnerships with our customers while delivering the solutions they require. I’m a strong believer that companies are more successful when they listen and collaborate with their customers.”

The Data-Crunching Powerhouse Behind ‘Avatar’

A look at some of the high-density server and networking gear inside the Weta Digital data center used to render the animation for the new James Cameron movie "Avatar." (Photo: Foundry Networks Inc.)

It takes a lot of data center horsepower to create the stunning visual effects behind blockbuster movies such as King Kong, X-Men, the Lord of the Rings trilogy and most recently, James Cameron’s $230 million Avatar.  Tucked away in Wellington, New Zealand are the facilities where visual effects company Weta Digital renders the imaginary landscapes of Middle Earth and Pandora at a campus of studios, production facilities, soundstages and a purpose-built data center.

The 10,000 square foot server farm manages thousands of work orders and a serious amount of data. Information Management magazine reports on the creative artists and rendering done for the movie, as well as the thoroughbred data center supporting it.

The Weta data center got a major hardware refresh and redesign in 2008 and now uses more than 4,000 HP BL2×220c blades (new BL2×220c G6 blades announced last month), 10 Gigabit Ethernet networking gear from Foundry and storage from BluArc and NetApp. The system now occupies spot 193 through 197 in the Top 500 list of the most powerful supercomputers.

Blue Waters and the Supercomputing Frontier

A look at progress at the $72 million Petascale Computing Facility at the University of Illinois, which is scheduled to open next year.

My 7 year old daughter anxiously anticipates seeing who will win the top spot on “Dancing with the Stars.”  I know the feeling – twice a year I revel in reading about the fastest and most powerful supercomputers in the world. Supercomputers are built to enormous scale in order to tackle some of the most compute-intense applications and needs of  science.

The Top 500 list for November 2009 features two supercomputers now in the petaflop per second performance speed range. A petaflop is one quadrillion calculations per second. The Roadrunner system at Los Alamos was the world’s first petaflop supercomputer in 2008, but was edged out in the last round by the Department of Energy’s Jaguar supercomputer, posting a 1.75 petaflop/second Linpack benchmark.

Petascale Computing
A petascale computer is one that is capable of reaching performance speeds in excess of one petaflop. Additionally, it could refer to storage capacity in excess of one Petabyte. The potential for petascale computers has been discussed since 2006, as shown by this Google news timeline, and this Google trends depiction of search trends for the term.

One quadrillion calculations per second would seem to be enough power to tackle the most demanding applications and scientific or research queries, but Network World reports that discussions at the November SC09 supercomputer conference focused on the need for Exascale computers. An example of applications requiring exaflop level calculations are high resolution climate models and energy studies such as the International Thermonuclear Experimental Reactor. An exaflop is one quintillion floating point operations per second.

What Happens to Verari’s Technology?

The Verari data center container housing the NASA Nebula cloud computing application arrives at Ames Research Center in Mountain View, Calif.

There has been speculation about the financial health of high performance computing specialist Verari Systems ever since the company failed to show at the SC09 conference, where it had purchased a booth. Most employees have been let go, and reports Friday on Twitter and Inside HPC indicated Verari had shut down.

On Monday the company issued a statement, saying it is reorganizing. “Verari has initiated a process that will protect our customers investment and benefit our creditors as we restructure the business,” the company said on its web site. “The intention is to safeguard customers investment and provide an ongoing support capability. There are several options that are being considered to provide solutions to our customers. We expect to have the new plan in place soon.”

Earlier Monday, Verari CEO David Wright told InsideHPC that the company is in a “controlled reorganization” and won’t file for Chapter 11 or Chapter 7 bankruptcy. Wright says Verari is still open for business and working on a support plan for existing customers.

Wild New Design: Data Center in A Silo

A diagram of the design of the CLUMEQ Colossus supercomputer, from a recent presentation by Marc Parizeau of CLUMEQ.

Here’s one of the most unusual data center designs we’ve seen. The CLUMEQ supercomputing center in Quebec has worked with Sun Microsystems to transform a huge silo into a data center. The cylindrical silo, which is 65 feet high and 36 feet wide with two-foot thick concrete walls, previously housed a Van de Graaf particle accelerator. When the accelerator was decommissioned, CLUMEQ decided to convert the facility into a high-performance computing (HPC) cluster known as Colossus.

We first noted the development of the CLUMEQ site earlier this year when Marc Hamilton of Sun discussed its unique design, but offered scant details. Additional information about the design of the facility and its cooling system were discussed at the Sun HPC Consortium last month in Portland, Oregon.

The CLUMEQ Colossus cylinder features an interior “hot core” (as opposed to a hot aisle) in the center of the building and uses the outside ring of the facility as the cold air plenum. The cabinets are arranged in a ring on each floor, facing the outside of the silo. The floors supporting each ring of cabinets are comprised of grates rather than solid flooring to facilitate airflow through the facility.

The cooling coils and air handlers are located in the basement. Chilled air flows upward through the outside cold aisle and through the racks of servers. The waste heat exits the rear of the racks into the hot core, and is returned to the basement via the cold aisle.