HP Targets HPC with New Approach to Water Cooling

By Nicole Hemsoth

June 10, 2014

HP has announced a new family of high performance computing systems that target a balance between high density, energy efficiency, and raw performance. The line, called “HP Apollo” is divided in half for key workloads and needs, with the air-cooled Apollo 6000 system aimed at enterprise users and the liquid-cooled Apollo 8000 focused on large-scale supercomputing sites.

As many remember, last year we followed the announcement of the new Peregrine supercomputer at the National Renewable Energy Laboratory (NREL). The warm water-cooled system set the bar for efficiency, but little did we know then that HP would roll out an entire line to replicate that success. HP saw the value of the approach while completing the system for NREL and has since learned lessons about expanding the same system for both new and existing air-cooled datacenters. They’re hoping the balanced push of high density and big energy savings will speak both to the national lab set and commercial datacenter operators who don’t have the luxury of, say a Facebook, to build as big as they wish with the comfort of cheap power that they can blow back into the sky as waste heat.

The Apollo system features a scalable rack design that allows for 144 servers in a rack, which HP says means “four times the teraflops per rack compared to air-cooled designs.” HP’s Ed Turkel said that this translates into the elimination of over 3.800 tons of carbon dioxide waster from a datacenter over the course of a year. Further, the Apollo 8000 features a patented, novel warm water cooling system that HP’s Ed Turkel provides “liquid cooling without the risk.” HP’s approach avoids the use of dripless connectors and other safeguards against water touching any of the components. The cooled components release hot water, which can be recirculated to provide building heat. In fact, one of the prime sites to see the Apollo 8000 line in action is where it was conceptualized—at the NREL Peregrine supercomputer site.

The Apollo 8000 at its base starting line consists of an Apollo 8000 standard-sized rack and the Apollo 8000 iCDU rack.

HPSpecs1

These are outfitted with the HP Proliant XL730f server and HP’s InfiniBand switch.

HPSpecs2

As Turkel told us, when NREL set forth designing the type of system that would showcase their position as both an energy efficient research leader as well as practitioner of efficient practices, they knew that part of their design would incorporate warm water cooling. This initial RFP set HP’s development wheels in motion as the team tried to find a way to integrate risk-free, high-density water-cooled supercomputing capabilities at NREL within space and budget limitations.

Luckily, NREL was able to design the center from the ground up to accommodate the plumbing and other infrastructure to support both a water cooled supercomputer and the ability to carry the waste heat in water form throughout the building, but Turkel says that his team is confident that retrofitting an air-cooled datacenter for the same environment NREL has is also practical and affordable, especially after their work in making some of the piping and other components more “modular” in nature so user facilities can circumvent some of the custom pipe cutting that had to go on at the first NREL site.

Turkel said that one testament to the success of the datacenter waste heat’s potential to heat the area is the fact that the sidewalk leading up to the NREL supercomputing site is always free of ice and snow during the cold Colorado winter. NREL extended the pipes that carry heat from the servers to just under the pavement.

But for NREL, the project means more than recycling supercomputer heat—it has lead to close to a million dollars in energy savings, both in heating costs and in overall efficiency of the supercomputers themselves. Further, since the components run at a stable temperature, they’re able to operate their Xeon Phi in ongoing turbo mode.

This is a huge improvement in how NREL has designed and implemented new supercomputing facilities. Steve Hammond, director of Computational Sciences at NREL, compared the current trend of air cooling to setting a glass of lemonade on a kitchen counter during a hot summer day and keeping it cold by cranking up the air conditioning in the room. “It’s incredibly wasteful—it just doesn’t make sense,” he told us.

“For us, warm water cooling was the key approach to making the efficiency targets work. As a cooling medium, liquids have about 1,000 times the efficiency of air,” said Hammond. “A juice glass full of water has the cooling capacity of a room full of air. And the pump energy needed to move that juice glass of water, to eject the heat from the system, is less than the fan energy needed to move that room full of air—much less.”

A great deal of the decision to move to hot water cooling was fed by existing problems, both because of efficiency or safety, with current solutions on the liquid and air-cooling fronts. As Hammond explained, making the decision to circulate past the air cooling decision was simple because the inefficiencies and waste are clear.

While many of the hyperscale datacenter giants tend to use air cooling, their greenfield facilities are placed where space and power are cheap and plentiful. Although certainly not the most efficient or carbon-aware, many HPC datacenters, including the new high performance computing facility where the Peregrine supercomputer is housed at NREL, are limited all around—space is a precious commodity and the thought of wasting all of the heat generated by their constant research by blowing it up into the sky would be completely counter to their center’s mission of “practicing what is preached” in terms of energy research.

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!

Weekly Wire Roundup: July 8-July 12, 2024

July 12, 2024

HPC news can get pretty sleepy in June and July, but this week saw a bump in activity midweek as Americans realized they still had work to do after the previous holiday weekend. The world outside the United States also s Read more…

Nvidia, Intel not Welcomed in New Apple AI and HPC Development Tools

July 12, 2024

New Mac developer tools will leverage Apple's homegrown chips, limiting HPC users' ability to use parallel programming frameworks from Intel or Nvidia. Apple's latest programming framework, Xcode 16, was introduced at Read more…

Virga: Australia’s New HPC and AI Powerhouse

July 11, 2024

Australia has officially added another supercomputer to the TOP500 list with the implementation of Virga. Officially coming online in June 2024, Virga is the newest HPC system to come out of the Australian Commonwealth S Read more…

NSF Issues Next Solicitation and More Detail on National Quantum Virtual Laboratory

July 10, 2024

After percolating for roughly a year, NSF has issued the next solicitation for the National Quantum Virtual Lab program — this one focused on design and implementation phases of the Quantum Quantum Science and Technolo Read more…

NCSA’s SEAS Team Keeps APACE of AlphaFold2

July 9, 2024

High-performance computing (HPC) can often be challenging for researchers to use because it requires expertise in working with large datasets, scaling the software, and selecting the best user interface. The National Read more…

Anders Jensen on Europe’s Plan for AI-optimized Supercomputers, Welcoming the UK, and More

July 8, 2024

The recent ISC24 conference in Hamburg showcased LUMI and other leadership-class supercomputers co-funded by the EuroHPC Joint Undertaking (JU), including three of the 10 highest-ranking Top500 systems, but some other ne Read more…

Shutterstock 2203611339

NSF Issues Next Solicitation and More Detail on National Quantum Virtual Laboratory

July 10, 2024

After percolating for roughly a year, NSF has issued the next solicitation for the National Quantum Virtual Lab program — this one focused on design and imple Read more…

NCSA’s SEAS Team Keeps APACE of AlphaFold2

July 9, 2024

High-performance computing (HPC) can often be challenging for researchers to use because it requires expertise in working with large datasets, scaling the softw Read more…

Anders Jensen on Europe’s Plan for AI-optimized Supercomputers, Welcoming the UK, and More

July 8, 2024

The recent ISC24 conference in Hamburg showcased LUMI and other leadership-class supercomputers co-funded by the EuroHPC Joint Undertaking (JU), including three Read more…

Generative AI to Account for 1.5% of World’s Power Consumption by 2029

July 8, 2024

Generative AI will take on a larger chunk of the world's power consumption to keep up with the hefty hardware requirements to run applications. "AI chips repres Read more…

US Senators Propose $32 Billion in Annual AI Spending, but Critics Remain Unconvinced

July 5, 2024

Senate leader, Chuck Schumer, and three colleagues want the US government to spend at least $32 billion annually by 2026 for non-defense related AI systems.  T Read more…

Point and Click HPC: High-Performance Desktops

July 3, 2024

Recently, an interesting paper appeared on Arvix called Use Cases for High-Performance Research Desktops. To be clear, the term desktop in this context does not Read more…

IonQ Plots Path to Commercial (Quantum) Advantage

July 2, 2024

IonQ, the trapped ion quantum computing specialist, delivered a progress report last week firming up 2024/25 product goals and reviewing its technology roadmap. Read more…

Shutterstock_1687123447

Nvidia Economics: Make $5-$7 for Every $1 Spent on GPUs

June 30, 2024

Nvidia is saying that companies could make $5 to $7 for every $1 invested in GPUs over a four-year period. Customers are investing billions in new Nvidia hardwa Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Everyone Except Nvidia Forms Ultra Accelerator Link (UALink) Consortium

May 30, 2024

Consider the GPU. An island of SIMD greatness that makes light work of matrix math. Originally designed to rapidly paint dots on a computer monitor, it was then Read more…

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…

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…

Shutterstock_1687123447

Nvidia Economics: Make $5-$7 for Every $1 Spent on GPUs

June 30, 2024

Nvidia is saying that companies could make $5 to $7 for every $1 invested in GPUs over a four-year period. Customers are investing billions in new Nvidia hardwa Read more…

Nvidia Shipped 3.76 Million Data-center GPUs in 2023, According to Study

June 10, 2024

Nvidia had an explosive 2023 in data-center GPU shipments, which totaled roughly 3.76 million units, according to a study conducted by semiconductor analyst fir Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top 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…

Leading Solution Providers

Contributors

AMD Clears Up Messy GPU Roadmap, Upgrades Chips Annually

June 3, 2024

In the world of AI, there's a desperate search for an alternative to Nvidia's GPUs, and AMD is stepping up to the plate. AMD detailed its updated GPU roadmap, w Read more…

Intel’s Next-gen Falcon Shores Coming Out in Late 2025 

April 30, 2024

It's a long wait for customers hanging on for Intel's next-generation GPU, Falcon Shores, which will be released in late 2025.  "Then we have a rich, a very Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l 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…

IonQ Plots Path to Commercial (Quantum) Advantage

July 2, 2024

IonQ, the trapped ion quantum computing specialist, delivered a progress report last week firming up 2024/25 product goals and reviewing its technology roadmap. Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh 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…

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…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire