Legacy HPC System Seeds Supercomputing Excellence at UT Dallas

By Aaron Dubrow

September 16, 2020

What happens to supercomputers after their productive life at an academic research center ends?

The question often arises when people hear that the average age of a top supercomputer at retirement is about five years. Rest assured — systems aren’t simply scrapped. Instead, they’re donated to organizations and institutions that can make use of their still-high-performance hardware.

A recent example is Stampede1, one of the most powerful supercomputers in the U.S. for open science research from 2013 to 2017. Stampede1 ran more than eight million jobs and delivered more than three billion core hours of computation to the national research community.

An Intel/Dell system that at one time was the 6th fastest in the world, Stampede1 was retired from the Texas Advanced Computing Center (TACC) at The University of Texas at Austin in 2017 and donated to a number of institutions. Among those was The University of Texas at Dallas (UT Dallas) — recently designated an “R1” research university — which sought to grow its advanced computing capacity and expertise.

Chris S. Simmons, director of cyberinfrastructure and research services in the Office of Information Technology at UT Dallas.

Research computing resources had historically been almost non-existent on campus. In 2017, when Frank Feagans joined UT Dallas as Chief Information Officer, he started building a central cyberinfrastructure team and investing in core technologies. Then, in 2018, through the UT Research Cyberinfrastructure (UTRC) initiative — a program that provides advanced computing capabilities across all 14 University of Texas System institutions — UT Dallas received 20 Stampede1 racks.

These formed the compute backbone of Ganymede — a 4,786-core cluster that significantly augmented high performance computing (HPC) expertise at UT Dallas. Chris S. Simmons was hired as UT Dallas’ director of cyberinfrastructure researcher support in 2018. He had used supercomputers at UT Austin since 1997, “before TACC was TACC,” and in short order made Stampede1 useful for campus researchers again.

If you Build It

In addition to building the system, Simmons led a public relations campaign to get researchers who were not previously using advanced computing in their research to do so.

“When I joined UT Dallas, the campus had a few dozen supercomputing users,” Simmons recalled. “As of January 1, 2020, we had 500 users on Ganymede and another 500 across other research group-specific systems.”

Ganymede helped users who might have been intimidated by TACC transition to larger-scale resources. “Once they’ve used Ganymede, nine times out of 10 they can copy their code to TACC and run without modification,” Simmons said. “They use Ganymede as a training tool and eventually a springboard to TACC or other national resources.”

The data supports this: UT Dallas is the second-largest consumer of cycles among the 14 institutions in the UT system and has more TACC users than any university in Texas besides UT Austin. In total, UT Dallas researchers used 30 million node hours in 2019.

Projects using Ganymede spanned efforts to teach data science to business students in the Naveen Jindal School of Management to research into seismic imaging.

Georgia Stuart, a Ph.D. student in Math studying geophysics, said it would take her desktop computer 1,000 days of computation to solve one problem.

“On Ganymede, I’m able to reduce the computation time to a mere 10 seconds per velocity field — or only 5 days of computation time — and I can run multiple parts of the experiment at once. Ganymede makes a hugely time-consuming problem, and my Ph.D. work, possible.”

Building on Success

Based on the widespread use of Ganymede, UT Dallas recently announced they are building a second system, Ganymede 2, an Intel based system that is still in early development. UT Dallas has committed to the new system and formed an advisory council to start making plans for long-term investment into research computing. UT System will contribute free power and cooling at the UT System/UTRC datacenter.

UT Dallas geoscientists used earthquake data and a computationally intensive technique on the Ganymede cluster to create 3D images of the geometry of subducting slabs (green bodies) and induced mantle flows (yellow arrows) under Central America and the Caribbean Sea at a depth of 500 kilometers. (Credit: Hejun Zhu, UT Dallas)

Ganymede 1’s Stampede racks will go into a “new” resource called Europa. Europa will be a high-throughput computing cluster with 12,800 cores that will provide web-based access to researchers and students from UT Dallas, UT Arlington and UT San Antonio.

“All three universities will have access to Europa and, longer-term, we plan to use Europa as a pipeline for TACC to retire systems that will then get re-inserted into the UT System research computing ecosystem,” Simmons said.

That’s not all. After seeing the impact of local HPC via Ganymede, Natural Sciences and Mathematica along with UT Dallas will be investing heavily into a Ganymede refresh that will bring GPGPU and machine learning/AI systems to campus.

“Before Ganymede and the Stampede1 donations, UT Dallas did not have HPC on our radar,” said Simmons. “Our approach was just to send everyone to TACC. By building Ganymede and showing a need on campus, we have built enough word-of-mouth and have made the case for more dedicated resources on campus.”

UT Dallas will hold its first research computing advisory committee meeting in August to develop a sustainable plan for UT Dallas research computing and establish goals for five and 10 years. “Without TACC and the legacy of Stampede1, that would not have been possible,” Simmons said.

Seeding HPC Leaders

Simmons’ vision for advancing computing excellence at UT Dallas, and improving the pipeline of computational scientists, goes further.

He recently received a $1.4 million grant from the National Science Foundation to develop a new post-doctoral program to train computational research facilitators — individuals who understand the needs of domain scientists and of top-tier HPC centers like TACC.

“There are not enough cyberinfrastructure professionals to fill the national need,” Simmons said. “TACC and other centers always have openings.”

The reason for this is simple. Research computing has not been around for long as a distinct discipline. Simmons counts himself among the first generation of PhD students to use HPC in their dissertations. Parallel computing, he notes, is still not taught as a formal discipline except in a handful of institutions.

Simmons hopes to identify HPC-savvy students in graduate school who do not want to go into academia and grab them before they join industry. His “Cyberteam” will hire three postdoctoral fellows from three domain areas: computational chemistry, computational biology, and data science/machine learning. These postdocs will be embedded into multiple research groups and will be part of a multi-campus effort to provide deeper levels of research facilitation and support. Instead of writing science papers, they will develop tutorial content for leading supercomputing conferences and contribute to open source science projects.

The effort is part of TRECIS, the Texas Research and Education Cyberinfrastructure Services cloud. Over the next three years, it aims to couple older, capacity resources from TACC with postdoctoral research facilitators and provide it as a service to all of UT system.

With additional TACC systems like Lonestar5 and Wrangler being decommissioned in the coming years, Simmons hopes to build up even greater capacity to enable and train computational scientists throughout the state.

“The goal is to develop the next generation of advanced cyberinfrastructure research facilitators for the nation, while addressing our short-term support needs on multiple campuses in key domain areas,” he said.

Header image caption: Europa, a “new” high-throughput computing cluster at UT Dallas with 12,800 cores, will provide web-based access to researchers and students from UT Dallas, UT Arlington and UT San Antonio.

About the Author

Aaron Dubrow is a Science And Technology Writer with the Communications, Media & Design Group at the Texas Advanced Computing Center.

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!

The Present and Future of AI: A Discussion with HPC Visionary Dr. Eng Lim Goh

November 27, 2020

As HPE’s chief technology officer for artificial intelligence, Dr. Eng Lim Goh devotes much of his time talking and consulting with enterprise customers about how AI can benefit their business operations and products. Read more…

By Todd R. Weiss

SC20 Panel – OK, You Hate Storage Tiering. What’s Next Then?

November 25, 2020

Tiering in HPC storage has a bad rep. No one likes it. It complicates things and slows I/O. At least one storage technology newcomer – VAST Data – advocates dumping the whole idea. One large-scale user, NERSC storage architect Glenn Lockwood sort of agrees. The challenge, of course, is that tiering... Read more…

By John Russell

Exscalate4CoV Runs 70 Billion-Molecule Coronavirus Simulation

November 25, 2020

The winds of the pandemic are changing – for better and for worse. Three viable vaccines now teeter on the brink of regulatory approval, which will pave the way for broad distribution by April or May. But until then, COVID-19 cases are skyrocketing across the U.S. and Europe... Read more…

By Oliver Peckham

Azure Scaled to Record 86,400 Cores for Molecular Dynamics

November 20, 2020

A new record for HPC scaling on the public cloud has been achieved on Microsoft Azure. Led by Dr. Jer-Ming Chia, the cloud provider partnered with the Beckman Institute for Advanced Science and Technology at the Universi Read more…

By Oliver Peckham

Gordon Bell Special Prize Goes to Massive SARS-CoV-2 Simulations

November 19, 2020

2020 has proven a harrowing year – but it has produced remarkable heroes. To that end, this year, the Association for Computing Machinery (ACM) introduced the Gordon Bell Special Prize for High Performance Computing-Ba Read more…

By Oliver Peckham

AWS Solution Channel

Introducing AWS ParallelCluster as an Intel Select Solution

High performance computing (HPC) system owners can spend weeks or months researching, procuring, and assembling components to build HPC clusters to run their workloads. Understanding and managing the complexities of compute, storage, networking, and software requirements can be confusing and time-consuming, slowing innovation and results. Read more…

Intel® HPC + AI Pavilion

Intel Keynote Address

Intel is the foundation of HPC – from the workstation to the cloud to the backbone of the Top500. At SC20, Intel’s Trish Damkroger, VP and GM of high performance computing, addresses the audience to show how Intel and its partners are building the future of HPC today, through hardware and software technologies that accelerate the broad deployment of advanced HPC systems. Read more…

Gordon Bell Prize Winner Breaks Ground in AI-Infused Ab Initio Simulation

November 19, 2020

The race to blend deep learning and first-principle simulation to speed up solutions and scale up problems tackled is one of the most exciting research areas in computational science today. This year’s ACM Gordon Bell Prize winner announced today at SC20 makes significant progress in that direction. Read more…

By John Russell

The Present and Future of AI: A Discussion with HPC Visionary Dr. Eng Lim Goh

November 27, 2020

As HPE’s chief technology officer for artificial intelligence, Dr. Eng Lim Goh devotes much of his time talking and consulting with enterprise customers about Read more…

By Todd R. Weiss

SC20 Panel – OK, You Hate Storage Tiering. What’s Next Then?

November 25, 2020

Tiering in HPC storage has a bad rep. No one likes it. It complicates things and slows I/O. At least one storage technology newcomer – VAST Data – advocates dumping the whole idea. One large-scale user, NERSC storage architect Glenn Lockwood sort of agrees. The challenge, of course, is that tiering... Read more…

By John Russell

Exscalate4CoV Runs 70 Billion-Molecule Coronavirus Simulation

November 25, 2020

The winds of the pandemic are changing – for better and for worse. Three viable vaccines now teeter on the brink of regulatory approval, which will pave the way for broad distribution by April or May. But until then, COVID-19 cases are skyrocketing across the U.S. and Europe... Read more…

By Oliver Peckham

Azure Scaled to Record 86,400 Cores for Molecular Dynamics

November 20, 2020

A new record for HPC scaling on the public cloud has been achieved on Microsoft Azure. Led by Dr. Jer-Ming Chia, the cloud provider partnered with the Beckman I Read more…

By Oliver Peckham

Gordon Bell Special Prize Goes to Massive SARS-CoV-2 Simulations

November 19, 2020

2020 has proven a harrowing year – but it has produced remarkable heroes. To that end, this year, the Association for Computing Machinery (ACM) introduced the Read more…

By Oliver Peckham

Gordon Bell Prize Winner Breaks Ground in AI-Infused Ab Initio Simulation

November 19, 2020

The race to blend deep learning and first-principle simulation to speed up solutions and scale up problems tackled is one of the most exciting research areas in computational science today. This year’s ACM Gordon Bell Prize winner announced today at SC20 makes significant progress in that direction. Read more…

By John Russell

SC20 Keynote: Climate, Exascale & the Ultimate Answer

November 19, 2020

SC20’s keynote was delivered by renowned meteorologist and climatologist Bjorn Stevens, a director at the Max Planck Institute for Meteorology since 2008 and a professor at the University of Hamburg. In his keynote, Stevens traced the history of climate science from its earliest days through... Read more…

By Oliver Peckham

EuroHPC Exec. Dir. Talks Procurement, EPI, and Europe’s Efforts to Control its HPC Destiny

November 19, 2020

While much of the HPC community’s attention is fixed on SC20’s flood of news and new product announcements, Anders Dam Jensen, the newly-minted executive di Read more…

By Steve Conway

Nvidia Said to Be Close on Arm Deal

August 3, 2020

GPU leader Nvidia Corp. is in talks to buy U.K. chip designer Arm from parent company Softbank, according to several reports over the weekend. If consummated Read more…

By George Leopold

Supercomputer-Powered Research Uncovers Signs of ‘Bradykinin Storm’ That May Explain COVID-19 Symptoms

July 28, 2020

Doctors and medical researchers have struggled to pinpoint – let alone explain – the deluge of symptoms induced by COVID-19 infections in patients, and what Read more…

By Oliver Peckham

Azure Scaled to Record 86,400 Cores for Molecular Dynamics

November 20, 2020

A new record for HPC scaling on the public cloud has been achieved on Microsoft Azure. Led by Dr. Jer-Ming Chia, the cloud provider partnered with the Beckman I Read more…

By Oliver Peckham

Google Hires Longtime Intel Exec Bill Magro to Lead HPC Strategy

September 18, 2020

In a sign of the times, another prominent HPCer has made a move to a hyperscaler. Longtime Intel executive Bill Magro joined Google as chief technologist for hi Read more…

By Tiffany Trader

HPE Keeps Cray Brand Promise, Reveals HPE Cray Supercomputing Line

August 4, 2020

The HPC community, ever-affectionate toward Cray and its eponymous founder, can breathe a (virtual) sigh of relief. The Cray brand will live on, encompassing th Read more…

By Tiffany Trader

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

NICS Unleashes ‘Kraken’ Supercomputer

April 4, 2008

A Cray XT4 supercomputer, dubbed Kraken, is scheduled to come online in mid-summer at the National Institute for Computational Sciences (NICS). The soon-to-be petascale system, and the resulting NICS organization, are the result of an NSF Track II award of $65 million to the University of Tennessee and its partners to provide next-generation supercomputing for the nation's science community. Read more…

Is the Nvidia A100 GPU Performance Worth a Hardware Upgrade?

October 16, 2020

Over the last decade, accelerators have seen an increasing rate of adoption in high-performance computing (HPC) platforms, and in the June 2020 Top500 list, eig Read more…

By Hartwig Anzt, Ahmad Abdelfattah and Jack Dongarra

Leading Solution Providers

Contributors

Aurora’s Troubles Move Frontier into Pole Exascale Position

October 1, 2020

Intel’s 7nm node delay has raised questions about the status of the Aurora supercomputer that was scheduled to be stood up at Argonne National Laboratory next year. Aurora was in the running to be the United States’ first exascale supercomputer although it was on a contemporaneous timeline with... Read more…

By Tiffany Trader

European Commission Declares €8 Billion Investment in Supercomputing

September 18, 2020

Just under two years ago, the European Commission formalized the EuroHPC Joint Undertaking (JU): a concerted HPC effort (comprising 32 participating states at c Read more…

By Oliver Peckham

At Oak Ridge, ‘End of Life’ Sometimes Isn’t

October 31, 2020

Sometimes, the old dog actually does go live on a farm. HPC systems are often cursed with short lifespans, as they are continually supplanted by the latest and Read more…

By Oliver Peckham

Texas A&M Announces Flagship ‘Grace’ Supercomputer

November 9, 2020

Texas A&M University has announced its next flagship system: Grace. The new supercomputer, named for legendary programming pioneer Grace Hopper, is replacing the Ada system (itself named for mathematician Ada Lovelace) as the primary workhorse for Texas A&M’s High Performance Research Computing (HPRC). Read more…

By Oliver Peckham

Top500: Fugaku Keeps Crown, Nvidia’s Selene Climbs to #5

November 16, 2020

With the publication of the 56th Top500 list today from SC20's virtual proceedings, Japan's Fugaku supercomputer – now fully deployed – notches another win, Read more…

By Tiffany Trader

Nvidia and EuroHPC Team for Four Supercomputers, Including Massive ‘Leonardo’ System

October 15, 2020

The EuroHPC Joint Undertaking (JU) serves as Europe’s concerted supercomputing play, currently comprising 32 member states and billions of euros in funding. I Read more…

By Oliver Peckham

Microsoft Azure Adds A100 GPU Instances for ‘Supercomputer-Class AI’ in the Cloud

August 19, 2020

Microsoft Azure continues to infuse its cloud platform with HPC- and AI-directed technologies. Today the cloud services purveyor announced a new virtual machine Read more…

By Tiffany Trader

Nvidia-Arm Deal a Boon for RISC-V?

October 26, 2020

The $40 billion blockbuster acquisition deal that will bring chipmaker Arm into the Nvidia corporate family could provide a boost for the competing RISC-V architecture. As regulators in the U.S., China and the European Union begin scrutinizing the impact of the blockbuster deal on semiconductor industry competition and innovation, the deal has at the very least... Read more…

By George Leopold

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