HOMEBREW SUPERCOMPUTER COMPUTES AT BARGAIN PRICES

October 6, 2000

FEATURES & COMMENTARY

San Diego, CALIF. — In mid-April a group of 20 Vanderbilt University physicists, biologists and computer technicians held a two-and-a-half day pizza party. At its end they had assembled a powerful supercomputer from off-the-shelf PC parts for a bargain-basement price.

“When they told me what they planned to do, I was skeptical,” admits Chip Cox, Vanderbilt’s Internet 2 director who helped bring together faculty members from the campus and medical center who need supercomputer-level number crunching. “But I was wrong. They did it, and it works!”

They named their new number cruncher VAMPIRE, which stands for Vanderbilt Multiple Processor Integrated Research Engine. It was constructed with a parallel architecture. That is, it uses a large number of processing units, or nodes, that work at the same time and are connected by a high-speed network.

Such a design can achieve tremendous speed and power by processing information simultaneously at many nodes.

Parallel processing requires users to break down their problems into small pieces that can be processed by individual nodes and then reassembled to provide the final result. This is easier to do with some problems than with others. Fortunately, a number of science problems lend themselves to such an approach and the tremendous cost-advantage is motivating many researchers to adapt their methods to take advantage of it.

The Vanderbilt group is not alone in such an effort. Scientists, engineers and computer technicians at a number of universities around the country are building similar homebrew systems. “The average university system currently is about 16 to 32 nodes,” says Alan Tackett, the Information Technology Services (ITS) administrator who manages the new machine. “So VAMPIRE is considerably larger than average.”

Parallel computers built from off-the-shelf hardware have been dubbed Beowulfs, after the name of one of the first computers of this type built in the early 1990s at NASA’s Goddard Space Flight Center in Greenbelt, Md. The University of New Mexico has constructed a 500-node Beowulf and recently the University of Pittsburgh received funding for a 1,000-node machine, Tackett reports.

“Of course, we’d like to grow VAMPIRE to that size,” says Paul Sheldon expansively. Sheldon, an associate professor of physics and astronomy, has spearheaded the project along with Jason Moore, an assistant professor of molecular biology and biophysics, and Will Johns, an assistant professor of physics and astronomy.

The new Vanderbilt supercomputer was declared operational Sept. 11, following a several-month period of installing and debugging the software. The last element added was a “gateway server” that controls access to the processor array and allocates the computer resources to different jobs in an equitable fashion.

For the April party, boxes containing dozens of processors, motherboards, hard drives, network cards, and memory cards were set out in a small conference room in a campus building like techie party favors.

“It was amazing to see thousands of dollars worth of memory chips in a box the size of a toaster,” says Tim Miller, a physics graduate student. “It was like being a kid in a candy shop.”

The party-goers’ task was to assemble more than 50 stripped-down personal computers. The researchers and technicians plugged in two 600 megahertz Pentium III processors and 256 megabytes of Random Access Memory or RAM and connected a 10 gigabyte hard drive and a networking card to each motherboard. Each motherboard was installed in a metal cabinet about the size, quite appropriately, of a pizza box.

The components installed in each cabinet act as a single processing unit, or node, in the finished supercomputer. The nodes are all networked to each other and to the gateway server. The remaining part of the supercomputer is a server that operates a bank of hard drives with a total capacity of 350 gigabytes that serves as a central data storage area.

It took the group a little more than two days to assemble the 54 nodes. Individuals came and went as their schedules dictated. There were about 10 people working in the room at any given time. One of their biggest problems, they agree, was a shortage of screwdrivers.

In its current configuration, VAMPIRE cost about $90,000 to build. That is less than the price of a single node for IBM’s least expensive supercomputer, the SP-1. In addition, two VAMPIRE nodes are more powerful than one SP-1 node, says Tackett.

Homebrew projects like this are possible because computer components have become standardized commodities, Sheldon points out. “That allows us to shop around for the best price on individual components with the confidence that the pieces will all work together.”

Another critical element has been the development of Linux, an operating system that is particularly suited to this kind of application. Linux is an “open source” version of Unix, a scientific operating system originally developed by AT&T that is the standard for basic research applications. Open source software is developed, distributed, and upgraded for free by independent programmers. Using Linux saved the project thousands of dollars in software licenses, according to the researchers.

In 1994, Sheldon and his colleagues in the physics and astronomy department built a smaller “workstation farm” with a $250,000 grant from the National Science Foundation to perform the computations required by their projects, such as an experiment that Sheldon is participating in at the Fermi National Accelerator Laboratory in Batavia, Ill. that studies the behavior of quarks, the tiny particles that make up the protons and neutrons that reside in the nucleus of the atom. With the prospect of new experiments that will produce even more data, the physicists were looking for a way to boost their computer power.

Last year, Moore, whose research also requires a large amount of data processing, received a campus grant to finance the purchase of a larger, faster computer. He learned about the physics department’s workstation farm, contacted Sheldon and the impetus for VAMPIRE was born.

After their initial success, the VAMPIRE team would like to grow the system into one of the largest Beowulf computer arrays in the country. They envision doubling, tripling, quadrupling the number of nodes and linking them with new, high-speed networking capabilities that should significantly jump up the system’s performance.

“VAMPIRE provides campus investigators with an invaluable research tool,” says Sheldon. “It will allow them to compete successfully for research projects that involve intensive computation, as well as bringing increased funding specifically targeted to support computer facilities to campus.” Visit http://www.vampire.vanderbilt.edu for more information.

============================================================

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire