UiT Recycles Supercomputing Power with Asetek’s RackCDU™

June 23, 2014

The University of Tromso (UiT) the “Artic University of Norway” is the world’s northernmost university with four campuses spread out across Norway. UiT is already a leader in High Performance Computing (HPC). In 2007 its STALLO cluster became the most powerful cluster in Norway and reached 63rd position in the Top500. In 2014 STALLO 2 is expected to reach 310 Teraflop in peak performance.UiT

UiT’s innovative thinking includes using supercomputing clusters as a heating plant. Specifically, the waste heat from the High Performance Computing facility is the energy source for building and district heating, reducing overall campus energy demand.

“Recently we have moved our attention from counting how many flops we can get out of the supercomputer to how many watts that can be recycled from the same computer” says Svenn Hanssen, Head of Section Research and Educational IT, University of Tromso

UiT believes that hot water cooling is something that gives the Arctic region an advantage and positions the region as a natural place to establish future datacenters. With an average temperature of 4ºC, UiT is an ideal location for re-use of waste heat from data centers. By cutting millions of krones from the power bill, more money can be spent on computing, software and the actual research. Waste heat recovery is also key in UiT’s goal to become the world’s leader in Green HPC.

During the summer of 2014 UiT will complete the build of a new 2MW data center. Its supercomputing cluster is expected to be around 2/3rds cooled by hot water with the longer term goal to make the entire cluster water cooled. The system will use the exit water from cooling the supercomputer as a heat source for the nearby buildings that will expand in the next phase to also provide heat to the hospital next door. The hot water will be used to heat the structures via both wall and ceiling radiators.

UiT began installing Asetek’s RackCDU D2C™ hot water data center liquid cooling in January 2014with the goal of using the supercomputing cluster as a district heat plant. The RackCDU D2C system consists of two key sub systems: D2C™ server coolers that are drop in replacements for the CPU air heat sinks in each server and a RackCDU extension that mounts of the back of each rack. Asetek D2C server coolers bring low-pressure, hot water inside the computing nodes to directly cool high heat flux components such as CPUs, GPUs and memory.

The RackCDU Extension is a 263mm (10.5 inch) cabinet that contains a zero-U rack level Cooling Distribution Unit (hence RackCDU) that exchanges heat between the cooling liquid running through the servers and the liquid in the larger facilities liquid cooling / waste heat recovery loop. Hot cooling liquid moves Rack CDUbetween RackCDU and server coolers via tubes that attach with dripless quick connectors to the RackCDU and via blind mate connectors to the server coolers. The server cooler, connecting tubes and RackCDU are all delivered pre-filled with coolant. Data center operators never have to deal with server cooling liquid.

RackCDU enables much higher rack densities, reduces the overhead power requirements for data center cooling, lowers acoustic noise and enables the use of waste heat to be recouped for building and district heating.

Hot water cooling is highly effective since the surface temperature of a CPU (case temp) only needs to be maintained between 67°C to 85°C (153°F to 185°F), depending on CPU model. The operating surface temperatures for memory chips, GPUs and co-processors is even higher, in the 90°to 95°C (194°F to 203°F) range. The cooling efficiency of water allows it to maintain the required case temps with a low initial temperature difference between the water and the component being cooled, or a small delta T. This means the water used for cooling the components can be hot.  RackCDU D2C is deployable as part of completely new clusters, in server refresh cycles or even as retrofits of existing servers. In particular, there is the ability to implement D2C in many standard air cooled servers offered by OEMs today just as UiT is doing with its HP SL230 servers.

UiT chose to concentrate on D2C cooling of CPUs in the HP SL230 servers used in their HPC cluster. Air-cooled HP SL230’s are a popular choice in the HPC world and RackCDU D2C allows the leveraging these cost-effective nodes to run more efficiently through liquid cooling while enabling high density deployments and substantial power savings.

To make best use of the waste heat a number of factors must be optimized. UiT is manipulating a range of parameters for optimization: flow rates, amount of hot water needed, the temperature of the water, the delta between the supply and return temperature and the size of the supercomputer in terms of possible production of hot water.

Initial testing has shown it is possible to achieve that greater than 70% waste heat recycling with a delta of 25oC between input and exit temperature of the cooling water. The testingUiTto date has been with a rather cold 12oC supply temperature and performance is expected to be even better at higher input temps. Air temperature in the computer room is also a factor. UiT has found that as they increase the room temperature, the water cooled system performance is not affected. Conversely, the air cooled systems start to spend more power for cooling as room temperature rises.

Because it is an HPC computing cluster, a 100% server load is common. The UiT load is typically greater than 80% 24 hours per day/7 days a week, making it ideal for heat capture and reuse.

One of the side effects of moving to hot water cooling and implementing district heating at UiT is the shift in how the supercomputing resource is viewed. No longer is the supercomputer seen as a multi-million dollar yearly expenditure in terms of variable power costs. It is now actually something the whole university expects to be expanded and integrated into the infrastructure to provide heating as well as power cost savings. Indeed, the visibility has built such enthusiasm that there are even artists trying to hook the supercomputer up to new art installations on campus to give different perspectives to the artwork based on the real-time load of the system.

UiT’s leadership in supercomputing is being matched by its mission to become the world’s leader in green High Performance Computing. Not only greening the data center itself but in recouping energy for district heating and having the supercomputing cluster be viewed as a community asset.

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