Sun Cofounder Evangelizes Liquid Blade Server

By Michael Feldman

May 4, 2011

What does a Sun Microsystems cofounder do with his spare time? Well, if you’re Scott McNealy, you spend some if it lending your expertise to promising tech vendors that are looking to break into the IT big leagues. One such company that he has taken a personal interest in is Hardcore Computer, which recently introduced a line of servers that use liquid submersion technology. HPCwire spoke with McNealy to get his take on the technology and to ask him why he thinks the company deserves the spotlight.

McNealy signed on as a non-paid advisor and consultant with Hardcore in January at the behest of longtime friend and former Stanford classmate Doug Burgum. Burgum’s venture firm, Kilbourne Group, has invested in Hardcore, a Rochester, Minnesota-based computer maker that specializes in high performance gear based on the company’s patented liquid submersion cooling technology.

“This is one of the few companies innovating on top of the Intel architecture — rather than just strapping a power supply on and porting Linux,” McNealy told HPCwire.

Hardcore makes a range of liquid-cooled offerings, including desktops, workstations, and servers. Its latest offering is the “Liquid Blade,” a server line the company announced in May 2010 and launched in November at the Supercomputing Conference in New Orleans (SC10). The new blade is more or less a standard dual-socket x86-based blade using Intel Xeon 5500 and 5600 Xeon parts. It sports eight DDR3 memory slots per CPU, six SATA slots for storage, and a PCIe x16 slot for a GPU card or other external device.

Liquid Blade’s secret sauce — and in this case it literally is a sauce — is Hardcore’s patented liquid submersion technology. The company uses a proprietary dielectric fluid, called Core Coolant, to entirely submerge the blades within a specially-built 5U rack-mounted chassis. The coolant is inert, biodegradable, and most importantly non-conductive, so all of the electrical components inside the server are protected.

As with any liquid coolant, the idea is to draw off the excess heat much more efficiently than an air-cooled setup and ensure all the server components are keep comfortably cool even under maximum load. According to the company literature, the Core Coolant has 1,350 times the cooling capacity of air. Since the coolant is so effective at heat dissipation and the internal fans have been dispensed with, the server components can be packed rather densely. In this case the 5U Hardcore chassis can house up to seven of the dual-socket blades.

The company launched its liquid-dipped server at SC10 last November to get the attention of the HPC community, but the offering is suitable for any installation where the datacenter is constrained by power and space. Besides HPC centers, these include DoD facilities, telco firms, and Internet service providers. “You have to look at the users who think at scale and have a huge electric bill,” explains McNealy.

The datacenter cooling problem is well-known, of course. As servers get packed with hotter and faster chips and datacenters scale up to meet growing demand, getting enough power and space has become increasingly challenging. Datacenter cooling has traditionally relied on air conditioning, but air makes for a poor heat exchange medium, and it’s hard to direct it where it’s most needed. “Air goes everywhere but where you want it to,” laughs McNealy. Cooling a hot server, he says is “like trying to blow a candle out from the other side of the room.”

Because of the density of the Hardcore solution, you need about 50 percent fewer racks to deliver the same compute. And since the blades essentially never overheat, one can expect better reliability and longevity. As any datacenter administrator knows, heat is a major cause of server mortality, especially in facilities filled to capacity.

But the really big savings is on the power side. Since cooling and the associated equipment take up such a large chunk of a datacenter energy budget, any effort to reduce these costs tends to pay for itself in just a few years. An independent study found that a Liquid Blade setup could reduce datacenter cooling costs by up to 80 percent and operating costs by up to 25 percent.

Hardcore isn’t alone in the liquid submersion biz. Other companies, most notably Austin-based Green Revolution, are providing these types of products. In the case of Green Revolution, they offer a general-purpose solution for all sorts of hardware — rack servers, blades, and network switches. The company will strip down the gear to its essentials and immerse the components in a specially-built 42U enclosure filled with an inert mineral oil.

But since Hardcore is dunking its own servers, it has the option to build high performance gear that would be impractical to run in an air-cooled environment. As McNealy points out, the efficient liquid cooling is a natural for the highest bin x86 chips running the fastest clocks. For example, the company could stuff Intel’s latest 4.4 GHz Xeon 5600 processors into its blades, and offer a special-purpose product for high frequency traders (as Appro has done, sans immersive liquid cooling, with its HF1 servers). Hardcore has never talked about such a setup for HFT, but it does tout the servers outfitted with high wattage graphics cards for GPGPU type computation. Applications using such capabilities include medical imaging, CGI rendering, engineering simulation and modeling and web-based gaming.

One the things McNealy has been working with the Hardcore people on is getting an apples-to-apples comparison of their liquid cooled gear versus conventional air-cooled servers. To do this, he says, you have come up with a higher level analysis that takes into account the service cost over the entire datacenter.

According to the company, the cost of a Liquid Blade setup is on par with a comparably equipped air-cooled product since all the fans are eliminated and the chassis design is simpler. If a user opted for Liquid Blade when it came time to upgrade their servers, they could start to realize energy costs savings immediately. But the big savings occur when a datacenter can be built from scratch with liquid submersion in mind.

In that case, the datacenter can dispense with a lot of the CRAC units, use 12-foot ceilings instead of 16-foot ones (no overhead air ductwork is needed), and use less UPS units thanks to reduced power requirements. The only extra cost comes with the chilled water to oil heat exchangers used to draw the heat from the chassis coolant. Also, since you can fit more servers into the same space, the datacenter floor space can be reduced by about 30 percent for a given compute capacity.

So why isn’t everyone flocking to liquid submersion? Customer inertia, says McNealy. According to him, he’s spent most of his career knowing the right thing to do and trying to get others to realize it themselves.

With Hardcore, the challenge is that most organizations are already set up with their existing air-cooled facilities, so a lot of the cost incentives for the big switch aren’t there. He thinks if a large Internet service provider bought into this technology for a new datacenter, the business could quickly take off. For McNealy’s Sun, that tipping point was in the late 80s when Computervision made a big deal to go with his company’s Unix-based workstations. Hardcore, no doubt would love to repeat history, this time with the likes of Google, Amazon, or Facebook.

“Their biggest challenges is the barrier to exit from the old strategy, not the barrier to entry to the new one,” says McNealy.

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