Winter Classic Invitational Student Cluster Competition Specifics
The Winter Classic, now in its second year, is the newest major Student Cluster Competition, fitting nicely between the SC competition in November and the ASC competition in spring. This is a virtual cluster competition, meaning that students will run their benchmarks and HPC applications remotely on systems in their team mentors’ data center.
In this cluster competition, ten student teams will be running their applications remotely on equipment located in national laboratories and other large-scale computing centers. Five of these centers will each pick one application for the student teams to run, teach the students about this application, and help them get it up and running.
The students will be with a particular mentor for about a week, learning about the application and the mentor cluster, then practicing and optimizing the application. Near the end of that week, the students will perform their final scored run of the application and turn in their results to their mentors.
The competition itself will run from mid-January through roughly mid-March and will be capped off with a Gala Virtual Awards Ceremony.
Students will be scored on how well their optimized application performs vs. competing teams. Students will also be scored on how well they present their results to a panel of judges at the end of the competition.
So here’s what all the fuss is about: university students build their own supercomputers – that’s the “cluster” part – for a live face-off to see who can run real HPC workloads the fastest. That’s the “competition” part. They’re given real, scientific workloads to run and a power limit they can’t exceed, and the team with the highest-performing system wins. This is how a traditional event is set up.
These are great programs – chock full of technical challenges, both “book learning” and practical learning, and quite a bit of fun too. There are rules and traditions, just as there are in cricket, soccer, and the Air Guitar World Championships. Whether you’ve been following the competitions obsessively (sponsoring office betting pools, making action figures, etc.) or this is the first time you’ve ever heard of them, you probably have some questions… so here’s everything you need to know. Listen up; we’re only explaining this once.
There are three four major world-wide student cluster events. The United States-based Supercomputing Conference (SC) held the first Student Cluster Competition (SCC) in November 2007. The contest has been included at every subsequent SC conference, usually featuring eight or more university teams from the US, Europe, and Asia. As the first organization to hold a cluster competition, SC pretty much established the template on which the other competitions are based.
The other large HPC conference, the imaginatively named ISC (International Supercomputing Conference), held its first competition at the June 2012 event in Hamburg. This contest, jointly sponsored by the HPC Advisory Council, attracts teams from the US, Europe, and Asia. It has been a big hit with enthusiastic support from conference organizers, competitors and show attendees.
The third entry is the Asia Student Supercomputer Challenge (ASC). These competitions are typically the largest in terms of numbers, with more than 300 teams applying for the finals. The competition, sponsored by Inspur, invites the 20 best applicants to the competition finals, which are hosted in various Chinese cities.
The fourth major competition, the Winter Classic Invitational Student Cluster Competition, was established in 2020 and will run every January starting in 2021. This is a virtual competition where student teams run their workloads remotely on systems in mentor data centers. It is also different in that it exclusively seeks out Historically Black Colleges and Universities and Hispanic Serving Institutions as competitors.
The Winter Classic is adopting a new structure this year. We will have four or five US national laboratories and other major computing centers who will each sponsor an application that will be run on clusters in their data center for about a week.
But before the students start to work with their mentors, they will receive an HPC 101 class that will teach them the concepts behind HPC and give them what they need before they go ‘hands-on’ with mentor clusters. This instruction will be provided by experts in HPC who will also be available for follow-up training and to answer questions.
During their week working on an application, the mentor organization will teach the students how to use their cluster, teach them how to build/run the application, how to profile it, and give them tips on how to optimize the workload. The students will have time to practice on the mentor cluster and will, at the end of the week, do a final optimized run that will count towards their overall competition score.
After a couple days rest, it’s off to the next mentor data center to learn about a new application. All in all, the students will be running two HPC benchmarks (HPL and HPCG) plus four real-world HPC applications selected by the mentoring organizations.
Students will be scored on how their optimized final application run stacks up against their competitors. Points will be awarded for first through tenth place. Students will also be required to turn in an “Application Brief” for each computational task. The application briefs are simple presentations that discuss how the students approached each application, what they found out through profiling the application, what optimizations they tried, and their final results on each application.
Student will turn in their application briefs to the organizers who will in turn pass them on to the judges. Each team will have a 30-40 minutes interview with a panel of competition judges who will score the students on how well they did with each application, how much they learned about the app and HPC, plus the quality of their presentation.
Participating in the Winter Classic won’t be a cake walk. It’s going to require a lot of effort. As a student, you’re going to learn more, in a shorter amount of time, than you probably ever have before. But it will pay off. You’ll have to become a steely eyed time management ninja. At the end of the competition you’ll be able to put on your resume that you can build and run HPC applications, plus profile them, and then optimize them for performance. Furthermore, you can talk about your hands-on experience with large HPC clusters at major computing centers and how you were able to quickly learn how to be productive on every system the competition threw at you.
There aren’t many students who can say this.
Through the competition, you’ll have had interactions with folks from the largest HPC organizations in the world. Organizations who are looking hard for students exactly like you – highly intelligent, motivated, self-starters, who are interested in investigating potential careers in one of the most important fields in any industry.
HPC is where the action is. Every major scientific and industrial innovation in the last 50 years can be traced back to high performance computing. Artificial Intelligence, particularly machine learning and deep learning, begins with HPC. Understanding HPC and being able to work with HPC systems, is your ticket into virtually any industry that matters.
We would strongly encourage you to submit your resume for our Resume Board. This list will be publicized in HPC industry outlets and is where potential employers will be able to find you.
Speaking for myself (and the untold millions of maniacal fans worldwide), these competitions are highly compelling affairs. The one thing I hear time and time again from students is, “I learned sooo much from this…” They’re not just referring to what they’ve learned about systems and clusters, but what they’ve learned about science and research. And they’re so eager and enthusiastic when talking about this new knowledge and what they can do with it – it’s almost contagious.
For some participants, the Student Cluster Competition is a life-changing event. It’s prompted some students to embrace or change their career plans – sometimes radically. These events have led to internships and full-time, career-track jobs. For many of the students, this is their first exposure to the world of supercomputing and the careers paths that are available in industry and research. Watching them begin to realize the range of opportunities open to them is very gratifying; it even penetrates a few layers of my own dispirited cynicism.
The schools sending the teams also realize great value from the contests. Several universities have used the SCC as a springboard to build a more robust computer science and HPC curriculum – sometimes designing classes around the competition to help prepare their teams. The contests also give the schools an opportunity to highlight student achievement, regardless of whether or not they win.
Just being chosen to compete is an achievement. As these competitions receive more attention, the number of schools applying for a slot has increased. Interest is so high in China that annual ‘play-in’ cluster competitions are held to select the university teams that will represent the country at ISC and SC.
With all that said, there’s another reason I find these competitions so compelling: they’re just plain fun. The kids are almost all friendly and personable, even when there’s a language barrier hindering full-bandwidth communications. They’re eager and full of energy. They definitely want to win, but it’s a good-spirited brand of competition. Almost every year we’ve seen teams donate hardware to teams in need when there are shipping problems or when something breaks.
It’s that spirit, coupled with their eagerness to learn and their obvious enjoyment, that really defines these events. And it’s quite a combination.
Yes. There will be fun.