ASC19: NTHU Returns to Glory

By Dan Olds

May 11, 2019

As many of you Student Cluster Competition fanatics know by now, Taiwan’s National Tsing Hua University (NTHU) won the gold medal at the recently concluded ASC19 cluster competition in Dalian, China.

But what you don’t know is how they won and just how close the final scores were…so here’s the rest of the story.

On the first day, Beihang University came off the top rope and laid a big flying elbow on the rest of the field by posting a 50.21 teraflops Linpack score. The next closest team, cluster competition newcomer Jinan U, was well behind Team Beihang, notching a score of 39.68. Beihang more than doubled the field average result of 24.28, putting them firmly in the driver’s seat after the first benchmark. NTHU was third in Linpack, giving them some points and keeping them in the race.

NTHU came roaring back with a near record-breaking score of 2004.96 gigaflops on the HPCG benchmark — grabbing all 18 points for the first-place finish. Beihang shared second with SUSTech, which at this point in the competition, was enough to keep Beihang virtually tied with NTHU for first place. Traditional student cluster powerhouse Tsinghua kept themselves in the game by taking fourth on both Linpack and HPCG.

Coming at the end of day one, CESM was a real game changer. This application, written in the early 1980’s, almost drove teams insane with compiler errors, hot spots, and inability to parallelize with anything less than an entire rewrite or alien intervention. It was absolutely the most difficult application in the ASC19.

From a scoring standpoint, CESM was a nightmare application that wrecked some dreams of student cluster competition glory. However, a few teams were able to tame CESM and ride it, giving them a vehicle to take them from mid-pack player to real contender.

Sun Yat-Sen took down the rest of the field by a wide margin on CESM, with Shanghai Jaio Tong pulling down second place. Tsinghua strengthened their championship hopes by grabbing third place while NTHU had to make do with a distant fourth. Beihang stumbled on CESM and it nearly took them out of the race for the top slot.

ASC19 Day Two

Going into day two, there were four teams vying for the lead:  NTHU, Tsinghua, Sun Yat-Sen, and Beihang. These teams were in control of their own destinies. Other teams still had a chance for an upset victory, but they had to rely on the top teams making mistakes or being off their game.

This was a very busy day for the competitors. Their first task was to get genome assembler WTDBG2 to scale to more than one node – which had been problematic for most teams during the warm ups.

NTHU put the lumber to the ball and hit WTDGB2 out of the park with a perfect 100 percent score. Beihang stayed in contention with a score of 93 percent and Tsinghua swiped a third-place finish from SUSTech by a mere three percentage points. At this point, NTHU has a great chance to run the table for the championship, but Tsinghua was still lurking in second place, ready to pounce.

Faces SR was the next application up for the student teams. This is the app where the students are presented with blurred faces and have to use AI and other tools to get the highest resolution possible in the shortest amount of time.

Team Beihang put on a masterful performance, pounding Faces SR for a perfect score of 100 percent. Jinan took second place, with NTHU and Tsinghua third and fourth respectively. According to the official referee score cards, NTHU was still clinging to their first-place position, but Tsinghua was less than a point behind them with Sun Yat-Sen and Beihang closing in.

ShengBTE, an application used for solving the hugely popular Boltzmann Transport Equation, was the mystery app at ASC19. SUSTech threw down a big 100 percent score and vaulted themselves up a few spots while Sun Yat-Sen mounted a valiant charge with their score of 96.6 percent — but would it be enough to get them on the podium? NTHU and Tsinghua remained deadlocked with their scores of 70.97 percent and 68.13 percent.

With only the interview to go, NTHU was holding onto a vanishingly thin margin over Tsinghua, with Sun Yat-Sen and Beihang still banging on the door.

ASC19 Day Three

The ASC19 interview room is a scary place. Students are confronted by genuine HPC experts, including some of the biggest names in the game. The teams have to put on a short presentation and then brace themselves for the questioning that is sure to follow.

Peking University did an outstanding job on the interview with a perfect 100 percent score. Tsinghua also nailed the interview with a 100 – was this enough for them to catch up with and surpass NTHU? Sun Yat-Sen continued their furious comeback with a 96 percent and Team Beihang kept it close with their score of 84. NTHU stumbled a bit in the interview, uncharacteristically taking ninth place with a score of 83 percent. Would this spell disaster for the kids from Taiwan? Could they possibly still hold onto their slim lead?

Yes, they could. By the slenderest of margins, NTHU took home the championship, topping arch-rival Tsinghua by just over a percentage point. Sun Yat-Sen University took home the Bronze Medal with their overall score of 70.99 percent. Beihang took fourth and newcomer Jinan turned in a fifth-place final score.

NTHU was one of the very first teams to participate in a Student Cluster Competition. They can trace their lineage all the way back to 2007, when the first competition was held in Reno. This marks the 15th competition for NTHU and gives them their first Gold medal since 2011. The team has won a total of three Gold medals, plus four Highest LINPACK prizes.

With their first-place finish, NTHU gets their ticket punched for the ISC19 finals which will take place in Frankfurt, Germany, next month. Tsinghua was already invited to this important event, so they receive a bye into the ISC competition. This means that third-place finisher Sun Yat-Sen will take the second ISC slot reserved for the ASC winners and make the trip to Germany.

E-Prize & Application Innovation

Sun Yat-Sen University took home the prestigious E-Prize for their outstanding performance on the troublesome CESM application. As we saw above, Sun Yat-Sen topped the 20 team field by a wide margin on this application.

Jinan University earned one of the two Application Innovation awards, which is an impressive accomplishment in their first competition. There was another first as well – EAFIT also earned an Application Innovation Award, their first major award. SUSTech was the third Application Innovation award winner, good job to all three teams.

So What Have We Learned?

There are several takeaways from this ASC19 cluster competition event. The first is that it is totally AWESOME to hold a cluster competition in a real stadium. There’s plenty of room, great heat dispersion, and massive scoreboards for the power meters.

The second thing we’ve learned is that CESM is a either a horrible application (if you’re a student) or a great test of student optimizing abilities (if you’re a judge).

The results from ASC19 also reinforce something that I’ve been telling every cluster competition team:  you don’t have to win every benchmark and application to become the champion – but you do have to turn in a result for every application.

NTHU won the HPCG benchmark and WTDBG2 application outright, but only finished in the top handful of teams on the other tasks. Tsinghua, the second-place winner, didn’t win any of the benchmarks or tasks, but they turned in competitive results on every challenge. That’s the key to being competitive in these events – consistent performance.

Final Note

I would be remiss if I didn’t recognize Inspur for sponsoring yet again another fantastic ASC Student Cluster Competition. Inspur is the only vendor to put on an entire competition on their own, providing all of the equipment, facilities, translators, and other support for 20 teams — which is probably close to 150 people. A sincere thank you to Inspur, plus the legion of volunteers from Dalian University, for putting on the competition, making it a great experience for the student teams and easy for me to cover.

The next big event on the Student Cluster Competition calendar is the ISC19 competition, which kicks off in the middle of June. You’ll see many of these ASC19 teams competing at this tourney and we’ll be covering it with our typical OCD depth and breadth. I hope this coverage has converted some of you to Student Cluster Competition fans and supporters. If not, try harder, ok?

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!

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…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a 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…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi 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