NVIDIA Scores Green Victory with Italian Supercomputer

By Nicole Hemsoth

February 5, 2013

There must have been a few companies that were a bit put off by the announcement of the Beacon computer as the Green500 champ last November. Everyone, that is, except Intel Corp.

Beacon, developed by the National Institute for Computational Sciences (NICS) at the University of Tennessee, started out as a research project to port software code to small clusters of Intel Many Integrated Core (MIC3) chips. When the group started working with the MICs, now better known as the Xeon Phi processor line, it found some compelling energy-saving possibilities. The NICS group decided to use the technology to create a small HPC cluster.

On Friday Eurotech and NVIDIA announced a new HPC system, called Eurora, that the companies say beats Beacon’s energy efficiency by 26% – using NVIDIA GPUs instead of Intel Xeons, of course. With Eurora pumping out 3.15 gigaflops per watt versus Beacon’s 2.49 gigaflops per watt, NVIDIA executives are happy that they can now claim the most energy-efficient HPC system uses their GPUs.

The most powerful supercomputer in the world, the Titan system at Oak Ridge National Lab, uses the same K20 GPUs as Eurora. Titan, however, finished third on the Green500 list. Eurora is NVIDIA’s chance to take the title back from Intel.

Even with the advent of multicore CPUs, accelerators seem to be critical to creating today’s most efficient HPC systems. NVIDIA technology, in particular, has made its presence felt on recent Green500 lists. “GPUs have been the biggest innovation in energy efficiency in the last five years,” says Sumit Gupta, NVIDIA’s general manager for Tesla GPU Accelerated Computing.

Eurora’s efficiency was not just about GPUs, though. Everything about the system was created with the intention of optimizing power draw. The machine is part of Eurotech’s latest Aurora Tigon line of HPC systems. Aurora was designed to decrease energy cost by using Eurotech’s custom-built hot-water cooling system, enabling a datacenter PUE as low as 1.05.

To create Eurora, Eurotech replaced older generation NVIDIA GPUs in its previous Aurora systems with the latest Tesla K20 processors. NVIDIA’s K20 Kepler generation GPU for the HPC market was also designed specifically to increase FLOPS per watt.

Next >>

The Eurora system was delivered to Cineca, an Italian non-profit consortium of universities and a member of the Partnership for Advanced Computing in Europe (PRACE). Cineca provides access to HPC systems for research institutions across Europe and prides itself as usually having one of the most powerful supercomputers in the world. Now, it seems, it can add energy efficiency to its boast. It’s an important consideration in Europe, where energy prices tend to be much higher than those in the U.S., and where governments are increasingly demanding green technology.

Still, Eurora is essentially a prototype upon which to build. NVIDIA says it shipped a special version of its GPU to Eurotech. And Eurora, with a Linpack rating of 110 teraflops, is a small system compared to Titan at 17 petaflops. That makes the Oak Ridge machine 150 times more powerful than Cineca’s.

NVIDIA’s Gupta says it’s not really fair to compare the reported energy efficiency for Beacon with that of other systems like Titan and Eurora. “Beacon was measured only for the Green500,” he points out. “You can always create the ideal situation for that. Cineca is doing what they would do in production. Cineca is government funded and has regulations. They have to be mindful of the data they report.”

Gupta notes that paradoxically, the energy-efficiency gains in HPC have been driven in large part by consumer products, not the need to cut energy costs for supercomputers or datacenters. The GPUs built to run electronic game graphics have to get by on as little energy as possible because of short battery life. Those same GPUs then started going into HPC systems, both to boost performance and to cut down on energy use.

NVIDIA’s Kepler generation, released a couple years ago for the gaming market, is the processor that was really designed to reduce energy consumption as much as possible. The company streamlined the design by eliminating a lot of registers and logic that were not really needed, and increased the number of cores dramatically. With more cores working, the company could cut the clock speed of the processors by almost half. “Frequency has a bigger impact on power efficiency” than almost any other change one can make, says Gupta. “The simple trick is to increase the number of cores and decrease the frequency.”

Still, Eurora is noticeably more energy efficient than the Titan, which uses the same generation of NVIDIA GPUs. So why the difference? A lot of it is due to Eurotech’s on-board cooling system. That system delivers 50 degree C water to a heat exchanger – flat metal plates with water-flow systems attached. The plates sit directly in contact with the components on a circuit board to uniformly draw away heat. That’s why NVIDIA had to provide a special version of its GPUs to Eurotech. They don’t have the usual heat sinks attached, but accommodate a plate instead.

Still, given the efficiency of Beacon, there will be an ongoing contest between NVIDIA’s GPUs and Intel’s Xeon Phi coprocessors for the best performance per watt. The Intel Phi processors are not yet shipping beyond a few test systems such as Beacon, but will be more generally available within a few months. As these technologies move beyond their testing stages and into real production systems, supercomputers and datacenters should see real benefits.

And, of course everyone will be watching to see whose accelerators show up on top of the next Green500 list.

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