Key Considerations in the Cooling of AI and HPC Systems

November 19, 2018

The critical driver for any AI or HPC cluster is the ability to fit to a usage model that requires continuous computing throughput across the entire system.   HPC and the latest AI architectures are characterized by clusters and their nodes running at 100% utilization for sustained periods. Further, as any such application is always compute limited, cutting edge AI and HPC requires the highest performance versions of the latest CPUs and GPUs. This means the highest frequency offerings of processors such as NVIDIA’s V100 GPUs and Intel’s Xeon Scalable Processors (Skylake).   Indeed, the highest performance versions also means the highest wattages.

The wattages for NVIDIA’s Volta V100 GPU are currently at 300 watts and both Intel’s Xeon Scalable Processors (Skylake) CPU and Xeon Phi (KNM) MIC-styled GPU & have been publicly announced at 205 and 320 watts, respectively.

These chip wattages translate into substantially higher wattage densities at both the node-level and rack-level not simply because of the component wattages alone but also due to the requirement for the shortest possible signal distance between processors, GPUs, switches both in and between cluster racks.  For HPC workloads, overall computing throughput is also constrained by signal delay both in the spatial and time domains.  These factors are driving cluster racks well beyond 50kW to 80kW or higher.

Racks with air heat sinks struggle to handle the heat to maintain this maximum throughput and CPU throttling occurs due to inefficient air cooling. Particularly for HPC sites, reducing rack densities can mean increasing interconnect distances resulting in greater latency and lower cluster throughput.  As a result, liquid cooling is required for the highest performance AI and HPC systems.

Implementation of liquid cooling at its best requires an architecture that is highly reliable, flexible to a variety of heat rejection scenarios, adaptable to the underlying compute and interconnect architecture and is not cost prohibitive.  All of these factors must be addressed by the liquid cooling architecture so that compromises need not be made in the compute architecture.

From a reliability standpoint, there are a number of cooling elements to consider.  The most important factor is to have very low pressures throughout the system (e.g. 4psi) both in the node and at the rack level which also addresses the cost issue in not requiring high-pressure components and allows for higher densities. Additionally, redundancy in the cooling architecture is needed to mitigate any impact of single point failure and to allow for component replacement during normal scheduled down-time.  Finally, a robust monitoring and alarming system is needed to monitor the cooling system and anticipate potential issues over time.

Adaptability of the cooling architecture is often overlooked largely due to the historical approach of liquid cooling related to the use of high-pressure pumping systems that take a one-size-fits-all approach.  With Asetek’s distributed architecture in contrast, coolers (integrated pumps/cold plates) are placed within server or blade nodes, and these coolers replace CPU/GPU air heat sinks in order to remove heat with warm water.   This has numerous advantages.

Heat capture with distributed pumping liquid cooling combined with options for heat rejection into either data centre air or facilities liquid seen in Asetek’s architecture provides a flexibility to address high-wattage on an as-needed basis. The Asetek architecture heat rejection options provide adaption to existing air-cooled data centers and to liquid-cooled facilities.

Adding liquid cooling with no impact on data center infrastructure can be done with Asetek’s InRackLAAC™, a server-level Liquid Assisted Air Cooling (LAAC) option.   With InRackLAAC the redundant liquid pump/cold plates are paired with a shared HEX (radiator) in the rack.   Via the HEX the captured heat is exhausted into the data center. InRackLAAC places a shared HEX with a 6kW 2U chassis that is connected to a “block” of up to 12 servers.   Existing data center HVAC systems handle the heat.

Multiple such computing blocks can be used in a rack. InRackLACC allows incorporation of the highest wattage CPUs/GPUs and additionally racks can contain a mix of liquid-cooled and air-cooled nodes.

When facilities water is routed to the racks, Asetek’s 80kW InRackCDU™ D2C (Direct-to-Chip) can capture 60 to 80 percent of server heat into liquid, reducing data center cooling costs by over 50 percent and allowing 2.5x-5x increases in data center server density.  Because hot water (up to 40ºC) is used to cool, it does not require expensive HVAC systems and can utilize inexpensive dry coolers

With InRackCDU the heat collected is moved via a sealed liquid path to heat exchangers for transfer of heat into facilities water.  InRackCDU is mounted in the rack along with servers.  Using 4U, it connects to nodes via Zero-U PDU style manifolds in the rack.

Asetek’s distributed pumping architecture at the server, rack, cluster and site levels delivers flexibility in the areas of heat capture, coolant distribution and heat rejection that other approaches do not.

Visit Asetek.com to learn more.

 

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Is Data Science the Fourth Pillar of the Scientific Method?

April 18, 2019

Nvidia CEO Jensen Huang revived a decade-old debate last month when he said that modern data science (AI plus HPC) has become the fourth pillar of the scientific method. While some disagree with the notion that statistic Read more…

By Alex Woodie

At ASF 2019: The Virtuous Circle of Big Data, AI and HPC

April 18, 2019

We've entered a new phase in IT -- in the world, really -- where the combination of big data, artificial intelligence, and high performance computing is pushing the bounds of what's possible in business and science, in w Read more…

By Alex Woodie with Doug Black and Tiffany Trader

Google Open Sources TensorFlow Version of MorphNet DL Tool

April 18, 2019

Designing optimum deep neural networks remains a non-trivial exercise. “Given the large search space of possible architectures, designing a network from scratch for your specific application can be prohibitively expens Read more…

By John Russell

HPE Extreme Performance Solutions

HPE and Intel® Omni-Path Architecture: How to Power a Cloud

Learn how HPE and Intel® Omni-Path Architecture provide critical infrastructure for leading Nordic HPC provider’s HPCFLOW cloud service.

powercloud_blog.jpgFor decades, HPE has been at the forefront of high-performance computing, and we’ve powered some of the fastest and most robust supercomputers in the world. Read more…

IBM Accelerated Insights

Bridging HPC and Cloud Native Development with Kubernetes

The HPC community has historically developed its own specialized software stack including schedulers, filesystems, developer tools, container technologies tuned for performance and large-scale on-premises deployments. Read more…

Interview with 2019 Person to Watch Michela Taufer

April 18, 2019

Today, as part of our ongoing HPCwire People to Watch focus series, we are highlighting our interview with 2019 Person to Watch Michela Taufer. Michela -- the General Chair of SC19 -- is an ACM Distinguished Scientist. Read more…

By HPCwire Editorial Team

At ASF 2019: The Virtuous Circle of Big Data, AI and HPC

April 18, 2019

We've entered a new phase in IT -- in the world, really -- where the combination of big data, artificial intelligence, and high performance computing is pushing Read more…

By Alex Woodie with Doug Black and Tiffany Trader

Interview with 2019 Person to Watch Michela Taufer

April 18, 2019

Today, as part of our ongoing HPCwire People to Watch focus series, we are highlighting our interview with 2019 Person to Watch Michela Taufer. Michela -- the Read more…

By HPCwire Editorial Team

Intel Gold U-Series SKUs Reveal Single Socket Intentions

April 18, 2019

Intel plans to jump into the single socket market with a portion of its just announced Cascade Lake microprocessor line according to one media report. This isn Read more…

By John Russell

BSC Researchers Shrink Floating Point Formats to Accelerate Deep Neural Network Training

April 15, 2019

Sometimes calculating solutions as precisely as a computer can wastes more CPU resources than is necessary. A case in point is with deep learning. In early stag Read more…

By Ken Strandberg

Intel Extends FPGA Ecosystem with 10nm Agilex

April 11, 2019

The insatiable appetite for higher throughput and lower latency – particularly where edge analytics and AI, network functions, or for a range of datacenter ac Read more…

By Doug Black

Nvidia Doubles Down on Medical AI

April 9, 2019

Nvidia is collaborating with medical groups to push GPU-powered AI tools into clinical settings, including radiology and drug discovery. The GPU leader said Monday it will collaborate with the American College of Radiology (ACR) to provide clinicians with its Clara AI tool kit. The partnership would allow radiologists to leverage AI techniques for diagnostic imaging using their own clinical data. Read more…

By George Leopold

Digging into MLPerf Benchmark Suite to Inform AI Infrastructure Decisions

April 9, 2019

With machine learning and deep learning storming into the datacenter, the new challenge is optimizing infrastructure choices to support diverse ML and DL workfl Read more…

By John Russell

AI and Enterprise Datacenters Boost HPC Server Revenues Past Expectations – Hyperion

April 9, 2019

Building on the big year of 2017 and spurred in part by the convergence of AI and HPC, global revenue for high performance servers jumped 15.6 percent last year Read more…

By Doug Black

The Case Against ‘The Case Against Quantum Computing’

January 9, 2019

It’s not easy to be a physicist. Richard Feynman (basically the Jimi Hendrix of physicists) once said: “The first principle is that you must not fool yourse Read more…

By Ben Criger

Why Nvidia Bought Mellanox: ‘Future Datacenters Will Be…Like High Performance Computers’

March 14, 2019

“Future datacenters of all kinds will be built like high performance computers,” said Nvidia CEO Jensen Huang during a phone briefing on Monday after Nvidia revealed scooping up the high performance networking company Mellanox for $6.9 billion. Read more…

By Tiffany Trader

ClusterVision in Bankruptcy, Fate Uncertain

February 13, 2019

ClusterVision, European HPC specialists that have built and installed over 20 Top500-ranked systems in their nearly 17-year history, appear to be in the midst o Read more…

By Tiffany Trader

Intel Reportedly in $6B Bid for Mellanox

January 30, 2019

The latest rumors and reports around an acquisition of Mellanox focus on Intel, which has reportedly offered a $6 billion bid for the high performance interconn Read more…

By Doug Black

It’s Official: Aurora on Track to Be First US Exascale Computer in 2021

March 18, 2019

The U.S. Department of Energy along with Intel and Cray confirmed today that an Intel/Cray supercomputer, "Aurora," capable of sustained performance of one exaf Read more…

By Tiffany Trader

Looking for Light Reading? NSF-backed ‘Comic Books’ Tackle Quantum Computing

January 28, 2019

Still baffled by quantum computing? How about turning to comic books (graphic novels for the well-read among you) for some clarity and a little humor on QC. The Read more…

By John Russell

IBM Quantum Update: Q System One Launch, New Collaborators, and QC Center Plans

January 10, 2019

IBM made three significant quantum computing announcements at CES this week. One was introduction of IBM Q System One; it’s really the integration of IBM’s Read more…

By John Russell

Deep500: ETH Researchers Introduce New Deep Learning Benchmark for HPC

February 5, 2019

ETH researchers have developed a new deep learning benchmarking environment – Deep500 – they say is “the first distributed and reproducible benchmarking s Read more…

By John Russell

Leading Solution Providers

SC 18 Virtual Booth Video Tour

Advania @ SC18 AMD @ SC18
ASRock Rack @ SC18
DDN Storage @ SC18
HPE @ SC18
IBM @ SC18
Lenovo @ SC18 Mellanox Technologies @ SC18
NVIDIA @ SC18
One Stop Systems @ SC18
Oracle @ SC18 Panasas @ SC18
Supermicro @ SC18 SUSE @ SC18 TYAN @ SC18
Verne Global @ SC18

IBM Bets $2B Seeking 1000X AI Hardware Performance Boost

February 7, 2019

For now, AI systems are mostly machine learning-based and “narrow” – powerful as they are by today's standards, they're limited to performing a few, narro Read more…

By Doug Black

The Deep500 – Researchers Tackle an HPC Benchmark for Deep Learning

January 7, 2019

How do you know if an HPC system, particularly a larger-scale system, is well-suited for deep learning workloads? Today, that’s not an easy question to answer Read more…

By John Russell

Arm Unveils Neoverse N1 Platform with up to 128-Cores

February 20, 2019

Following on its Neoverse roadmap announcement last October, Arm today revealed its next-gen Neoverse microarchitecture with compute and throughput-optimized si Read more…

By Tiffany Trader

France to Deploy AI-Focused Supercomputer: Jean Zay

January 22, 2019

HPE announced today that it won the contract to build a supercomputer that will drive France’s AI and HPC efforts. The computer will be part of GENCI, the Fre Read more…

By Tiffany Trader

Intel Launches Cascade Lake Xeons with Up to 56 Cores

April 2, 2019

At Intel's Data-Centric Innovation Day in San Francisco (April 2), the company unveiled its second-generation Xeon Scalable (Cascade Lake) family and debuted it Read more…

By Tiffany Trader

Oil and Gas Supercloud Clears Out Remaining Knights Landing Inventory: All 38,000 Wafers

March 13, 2019

The McCloud HPC service being built by Australia’s DownUnder GeoSolutions (DUG) outside Houston is set to become the largest oil and gas cloud in the world th Read more…

By Tiffany Trader

Intel Extends FPGA Ecosystem with 10nm Agilex

April 11, 2019

The insatiable appetite for higher throughput and lower latency – particularly where edge analytics and AI, network functions, or for a range of datacenter ac Read more…

By Doug Black

UC Berkeley Paper Heralds Rise of Serverless Computing in the Cloud – Do You Agree?

February 13, 2019

Almost exactly ten years to the day from publishing of their widely-read, seminal paper on cloud computing, UC Berkeley researchers have issued another ambitious examination of cloud computing - Cloud Programming Simplified: A Berkeley View on Serverless Computing. The new work heralds the rise of ‘serverless computing’ as the next dominant phase of cloud computing. Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This