Reality Check on Liquid Cooling in the Data Center

December 9, 2013

Evaluating liquid cooling for a data center requires an understanding of both the technical approach and ability of the solution to address the business and operational concerns of the data center.

To be practical, it must not only be technically sound but must provide reduced operational costs (OpEx) and/or capital expenditures (CapEx) and must satisfy other metrics such as serviceability,  monitoring, redundancy, failure isolation and even server warranty coverage.

Approaches to Liquid Cooling

Nearly every data center is liquid cooled today.  Most data centers bring liquid into Computer Room Air Handlers (CRAH) or Computer Room Air Conditioning (CRAC) units to cool the air in the data center.  CRAH units bring chilled water in to cool the air. The refrigerant comes into CRAC units as a liquid.  It is not a question of should we liquid cool? It’s a question of how to liquid cool most efficiency?  How to get server heat into liquid to reduce energy costs, mitigate expansion costs and enable increased density?

There are three significant drawbacks with CRAC and CRAH units. The first is that to produce cold enough air to cool servers, the liquid coolant coming to the data center (facilities liquid) must be refrigerated to a temperature colder than ambient (outdoor) air. Chilling is expensive. The second is CRAC and CRAH units produce cold air at the periphery of the data center and considerable effort is needed to move it to the racks. Third, considerable effort is needed move it through the servers via server fans.

Rear door, in-row and over-row liquid coolers focus on reducing the cost of moving air about the data center by placing the air-cooling unit as closer to the servers. For example, Rear Door Coolers replace rear doors on the rack with a liquid cooled heat exchanger that transfers server heat into liquid as hot air leaves the servers. The servers are still air-cooled and facilities liquid must be brought into the computer room at the same temperatures as is needed for CRAH units, <65 degrees F and that liquid exits at <80 degrees F.  While air handling is simplified expensive chillers are still required and server fans still consume the same amount of energy.

“Direct Touch” cooling replaces air heat sinks with ‘Heat Risers’ which transfer heat to skin of server chassis where cold plates between servers transfer heat to refrigerant so the heat can be removed from the building. This eliminates fans in the server and the need to move air around the data center for server cooling.  However facilities are still needed to cool the refrigerant to <61°F and cold plates between the servers reduce the capacity of a 42U rack to ~35 RUs.

Immersion cooling uses an all liquid path to remove server heat by placing servers in tanks of dielectric fluid or filling custom servers with dielectric fluid.  Key concerns with this technology are the maintenance of servers, large quantities of oil-based coolant in the data center, modification of servers with non-stand parts and poor space utilization as in effect the “racks” are lying on their backs.

The most significant advancement in practical liquid cooling can be seen in Asetek’s RackCDU™ Direct-to-Chip (D2C™) hot water cooling system.

D2C hot water liquid cooling brings cooling liquid directly to the server components that generate the most heat within a server and cools the remaining components with air. This solution removes 60% to 80% of the heat generated by servers with an all-liquid path. Pumps replace fan energy in the data center and server, and hot water eliminates the need for chilling the coolant. The air-cooled side of the solution is also more efficient as lower volumes of warmer air are sufficient to cool the remaining components. D2C liquid cooling dramatically reduces chiller use, CRAH fan energy and server fan energy, delivers energy savings of up to 80% and server rack density increases of 2.5x-5x times compared to air-cooled data centers.

Addressing the Business and Operational Concerns of Data Centers

Cost Containment be it CapEx or OpEx is a necessity for data centers.  30+ Kw/racks enabled by Asetek’s RackCDU D2C enable consolidation and mitigate the need for build-outs.  Cost is further reduced by the use of hot water for cooling. CPUs run quite hot (153°F to 185°F) and hotter for memory and GPUs.  The cooling efficiency of water (4000x air) allows it to cool the components with a much smaller temperature difference than air.  This also reduces the power required for server fans.

The data center does not need all the CRACs or CRAHs normally required and rather than needing an extensive chiller plant outside the data center can use cheap dry coolers.  This is a major impact on both CapEx and OpEx.

Monitoring and Alarming is essential for any technology in the contemporary data center.  Asetek’s RackCDU system includes a software suite that provides monitoring, alerts, including temperatures, flow, pressures and leak detection and importantly can report into data center management software suites.

Failure Isolation is a key metric for data centers. Servers using Asetek’s RackCDU use very low pressure and are insolated in closed loops that exchange heat in the CDU with the facilities water loop.  This is an important difference to cooling systems that use a centralized pumping system. Centralized systems require high pressures and hence the risk of high pressure leaks and wide “blast radius.”

Redundancy is one of sacred cows of data centers.  Asetek’s RackCDU D2C CPU and GPU pump /cold plates are drop in replacements for air heat sinks.  One pump is sufficient to drive the required cooling for the server.  Hence a dual CPU, dual GPU or CPU + GPU server contains its own redundant pumping.

Serviceability is a key requirement for any data center hardware system.  Because the Asetek RackCDU is an extension to a standard rack and has independent quick connects for each server, data center facilities teams can remove or replace servers for repair or upgrade as they do today.

Warranty is an issue with installing after market liquid cooling solutions in that it can void the server manufacture’s warranties.  Asetek as also addressed this issue by teaming up with Signature Technology Group (STG), a warranty service and support firm that will maintain coverage for systems that have been upgraded with Asetek’s liquid-cooling technology.

The reality check on data center liquid cooling is that Asetek has moved liquid cooling from an exotic technology to a practical option for data center operators.

asetek.com

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!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues 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 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…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion 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…

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