Liquid Cooling Makes a Splash in Enterprise Data Centers

August 12, 2019

Direct liquid cooling is now gaining momentum in mainstream data centers — for many good reasons.

As servers get faster, they generate more heat, and that increases the need for innovative approaches to cooling that go beyond the limitations of conventional air-cooled approaches. One of these innovative approaches that is gaining a lot of traction is direct liquid cooling.

Direct liquid cooling, or DLC, transfers heat away from processors and other heat-generating system components via contact with a liquid-cooled heat sink rather than using just air in the heat-exchange process. In one approach to DLC, used by the company CoolIT, a metal plate, or a cold plate, functions as a heat sink. This plate is placed in direct contact with the processor casing surface. Liquid flows through sealed micro-channels in the plate to capture heat from the processor, and then flows on to a heat exchanger, which dissipates the heat. The cooled liquid coming out of the heat exchanger travels back through the system, and the cycle repeats itself.

While it has been around for decades for various use cases — including supercomputing systems and desktop systems with accelerators — direct liquid cooling is gaining traction in enterprise data centers and service provider environments. The title of a paper by 451 Research pretty much says it all: “The Tide is Turning Toward Liquid Cooling in Datacenters.”[1]

Market research validates this view of the growing momentum for liquid cooling. A report by the research firm Global Market Insights projects that the data center liquid cooling market will jump to $2.5 billion by 2025, up from $750 million in 2018.[2]

A thirst for throughput

So why is direct liquid cooling gaining traction? One reason is an unquenchable thirst for higher throughput for artificial intelligence and high performance computing. To meet to this demand, new generations of technology bring faster Intel® processors and more dense racks, and that equates to more heat with the need for more efficient approaches to cooling.

Over the years, as Moore’s Law played out and the capacity and performance of processors grew, system builders continued to keep things cool with air-based approaches. But now we have reached the point where processor capacities and wattages are starting to bump up against the limits of conventional approaches to cooling. The more we push for higher performance in systems, the more wattage we require in processors, and that equates to more heat. Liquid cooling is one of the ways to deal with that heat in an efficient and cost-effective manner.

Let’s talk watts. Air cooling has worked for systems with CPUs that top out around 150 watts, which is what we have had for the past decade or so. But today, we are seeing more systems with CPUs that run at 200W and above and accelerators that run at 300W, with plans for even higher-wattage processors. These higher-wattage processors will be increasingly important for many computationally intensive artificial intelligence workloads that use hardware accelerators, including machine learning, deep learning and applications like high-frequency training and fraud detection.

Collectively, these trends are causing people to take a closer look at liquid cooling, which is a more efficient way to cool processors. It’s also a more efficient way to cool high-density storage and systems deployed at the network edge, according to 451 Research.

“DLC will largely take off because the existing tech­nology — air cooling — will hit its limitations and inflict pain on major buyers of infrastructure in the form of lost performance or higher costs (or both),” the firm says in its report on the tide turning to DLC. What’s more, the data centers that we build today will likely still be in service in the late 2020s and early 2030s, so they have to be built with future cooling needs in mind. “It is for these reasons that 451 Research views DLC as a must-have in the datacenter operator’s toolset if it wants to keep pace with infrastructure requirements.”1

Liquid cooling in a new supercomputer

Among the organizations that have opted for liquid cooling is the Texas Advanced Computing Center (TACC), with new supercomputer Frontera. The primary system, supplied by Dell EMC, will have more than 8,000 dual-socket Intel® Xeon® nodes with 205W processors. Frontera will also include a small accelerated subsystem, to support molecular dynamics and machine learning applications.[3]

Frontera, which debuted at No. 5 on the latest TOP500 list,[4] leverages DLC-cooled Dell EMC PowerEdge C6420 servers and Dell EMC Isilon unstructured data storage in combination with 2nd-generation Intel® Xeon® Scalable Platinum processors, Intel® Optane™ DC Persistent Memory and a high-performance Mellanox HDR 200Gb/s InfiniBand interconnect.

For the system’s 448,448 cores, the racks leverage DLC technology from CoolIT, a Dell EMC partner. CoolIT’s Direct Contact Liquid Cooling technology uses the exceptional thermal conductivity of liquid to provide dense, concentrated cooling to targeted surface areas. The technology uses warm or room-temperature water to cool CPUs, eliminating the need for chilled water and reducing the cost of cooling by as much as 56 percent over traditional cooling methods.[5]

Dell EMC now offers DCLC technology from CoolIT in the PowerEdge C6420 server, a density-optimized workhorse for artificial intelligence and high performance computing workloads. Liquid cooling allows the server to support higher wattage processors for increased performance and energy efficiency.

Key takeaways

Direct liquid cooling is coming to a data center near you as one of the keys to enabling the use of higher-wattage processors and more powerful computing systems.  As 451 Research notes, “DLC is quickly becoming a relevant consideration for enterprises and service providers, moving beyond the classic supercomputing use case.”1

To learn more

For a closer look at liquid cooling in HPC servers, see the Dell EMC-CoolIT solution brief and watch the Dell EMC video featuring CoolIT Systems CEO/CTO Geoff Lyon.


[1] 451 Research, “The Tide is Turning Toward Liquid Cooling in Datacenters,” July 2018.

[2] Global Market Insights, Inc., “Data Center Liquid Cooling Market worth over $2.5bn by 2025,” February 04, 2019.

[3] HPCwire, “TACC’s ‘Frontera’ Supercomputer Expands Horizon for Extreme-Scale Science,” August 29, 2018.

[4] TOP500, “Frontera – Dell C6420, Xeon Platinum 8280 28C 2.7GHz, Mellanox InfiniBand HDR,” June 2019.

[5] Dell EMC solutions brief, “Improve Power Efficiency with Dell EMC PowerEdge and CoolIT Systems Rack DCLC,” 2017.

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