Thursday, April 30, 2015

10 Questions with SC17 General Chair Bernd Mohr

Bernd Mohr is the first SC chair from outside the U.S.
In November 2014, Bernd Mohr was announced as the general chair for the SC17 conference, marking the first time that someone from outside the United States was selected as conference chair. Mohr attended his first SC conference more than 20 years ago and has held a number of positions on the SC planning committee over the years. He is also internationally known for his work as a performance analyst for HPC systems and has given invited talks at conferences and workshops around the globe.

He is currently responsible for user support and training in regard to performance tools at the Jülich Supercomputing Centre (JSC) in Germany. Mohr started to design and develop tools for performance analysis of parallel programs as a graduate student at the University of Erlangen in Germany, and continued this in his Ph.D. work, which he finished in 1992. During a three year postdoc position at the University of Oregon, he designed and implemented the original TAU performance analysis framework

In 1996, he joined the Forschungszentrum Jülich, Germany's largest multidisciplinary research center and home of one of Europe's most powerful HPC systems, a 28-rack BlueGene/Q. In addition to leading several projects at Jülich aimed at improving system performance, including the Scalasca toolset effort, he is an active member in the International Exascale Software Project (IESP/BDEC) and work package leader in the European (EESI2) and Jülich (EIC, ECL) exascale efforts. He is the author of several dozen conference and journal articles about performance analysis and tuning of parallel programs.

Looking ahead to the task of organizing SC17, Mohr said he intends to combine his work in performance analysis with the well-known German focus on efficiency. Now five months into this role, Mohr took time to answer 10 questions from the SC15 Communications Committee about his experiences, expectations and ideas as he looks ahead to chairing a conference that will draw more than 10,000 attendees from all around the world.

Congratulations – you’re the first person from outside the U.S. to chair the SC conference. As you start to plan SC17, do you feel the weight of the world on your shoulders? 
Since I learned that I had been elected chair for SC17, I’ve felt very excited one moment and then the next moment I I think, “Oh my God, why are you doing this?” Sometimes I can’t sleep because I’m thinking of all these great ideas of what I want to add to the conference and what I’m thinking of changing. And the next night I can’t sleep because I’m wondering why I accepted this responsibility. It’s kind of strange.

But what’s comforting is knowing that I have enormous support from my home organization. For example, the conference requires that my home institution pays travel support so I can attend all the necessary SC planning meetings. So I had to get a letter from my manager, the director of our computing center, stating this. But he also got me a support letter from the chairman of the Board of Directors of the entire Jülich Research Center pledging his full support. It shows they really value this. And after the decision was announced, a lot of my friends and colleagues congratulated me, and that was also very comforting.

But it’s a big job: I am currently selecting my executive committee to get everything started. Next year, we will need to build up the whole 500-member volunteer committee and create the SC17 brand, which means designing the logo and setting up the initial website. I’ve been told by past chairs that in the last year leading up to the conference, it will be a halftime job for nine months and for the last three months it will be full time. I will move to the U.S. at that time to make sure I am available around the clock to solve last minute issues and to make sure SC17 is the best SC conference ever.

A scene from the SC14 exhibition floor that featured 121 international exhibitors from 26 countries.
Both on the SC exhibition floor and in the Tech Program sessions, there’s a very strong international presence and the number of international attendees is steadily growing. Your thoughts on this?
It just shows that SC is THE international conference on HPC now. It’s funny, when I go to SC, I meet more Germans than I do at any event in Germany and more Europeans than I do at a European meeting. At SC14, 25 percent of the attendees were from outside the U.S. Sixty different countries were represented in New Orleans.

I have a two-part theory about this growth, but I can’t really prove it. First, the countries outside the U.S. that have a tradition of HPC, like England, France, Germany, Japan and Taiwan, are now sending more people who are not only from the major centers. This includes staff from the regional centers and more universities. Second, those countries that don’t have such a long HPC tradition, like the other European countries or China, India, and several countries in South America, are now also participating. HPC is everywhere and they all go to SC.

Aerial view of the Jülich Research Center in Germany.
Your home institution, the Jülich Research Center, is a longtime SC exhibitor with a significant booth space. What value do you see in this?
Well, you would really need to ask my center’s director this question. For me, it’s really a brand-building exercise to help establish an image of our center. We are the leading HPC center in Europe and having a large booth allows us to showcase our results, our accomplishments and current projects. And at SC, we can show this to the whole community worldwide – the exposure is amazing.

We also want to demonstrate that there are a lot of amazing things in HPC coming from outside the U.S. – as I said, it’s a very international activity. But I’ve talked to a lot of SC attendees who have  never been to an HPC conferences outside the country, even big and well-known ones like ISC. That’s surprising to me. But by attending SC, they can learn a lot about things happening outside the U.S. and Jülich is a big player in that arena.

On his way to SC12 in Salt Lake City, Mohr and his colleagues spent a couple days exploring Arches National Park and other parks in Utah. Spending a few days relaxing before the conference can help international attendees beat jet lag.
Do you remember your first SC? What was your impression?
Oh yes. It was at SC93 in Portland. I was a young postdoc and had just moved to the University of Oregon in Eugene with my wife and our two kids, who were still little at this time. Because Portland was so close, Allen Malony at the university took a bunch of us students and postdocs to SC. The secretary found a small furnished apartment downtown for us and we slept in sleeping bags on the couch, in the beds, and on the floor. It was my first large conference – I think about 2,000 people were there.

I had only been to smaller academic conferences in Europe before that. It was amazing. This was really at the start of massively parallel computing, so besides big companies like Cray, IBM, Intel and SGI, Thinking Machines, KSR, Meiko and others were there too. You really could feel this excitement on the show floor. It was so exciting, I didn’t sleep much that week. I was immediately hooked. It was also the 25th anniversary of Intel and they held a big birthday party downtown and everyone from SC was invited. I remember, they gave out harmonicas with SC and Intel printed on them. I still have mine.

How important has your participation at SC been to your career development?
The whole activity has helped my career in two aspects. When you go to SC, there are paper and poster presentations, tutorial lessons, demonstrations on the show floor and dozens of other activities and you really learn a lot about new things, new ideas and the latest state-of-the-art developments in HPC all in one place.

And then of course, it’s the biggest networking event in the HPC space. There is no better place to build your personal network – and on an international scale! You meet people from places like Chile, Brazil, South Africa, Japan and China.

And as you know more people, you will get ideas for new project proposals and potential partners, and this can help you get funding. And all of these connections come down to SC. These connections can really help boost your career and I don’t know what I would do without them. You can’t claim to work in HPC and not go to SC.

How did you get involved with the SC conference planning committee? 
After I attended a few conferences, I began to participate by organizing a BoF (Birds-of-a-Feather session) or a workshop and it grew from there. Over the years I actually have presented over 14 tutorials at SC. You learn more about the conference and meet more people. In 2003 I was invited to be a Tech Papers reviewer. What’s different about SC is that all the reviewers, not just the chairs, meet face-to-face at a meeting in June, which exposes you to both the process and other committee members. And you often get asked to do more. We have a saying in German that you offer them a little finger and they take the whole hand. I did get pulled in, but it was my choice to accept.

What committee positions have you held over the years?
I have helped out in the Tech Paper, BoFs and Poster committees and once I’ve been a judge for the Student Cluster Competition. Over the years, I have been the Panels Chair, Tech Papers Area Chair, Posters Chair, Awards Chair, Tutorials Chair, Invited Speakers Chair and at SC13, I was Student Job Fair Chair. I was very honored in 2011 to be elected as the first European to the SC Steering Committee.

Mohr advises that those new to the conference spend time understanding the website and taking advantage of onsite resources like orientation sessions or stopping at the help desk (which is always staffed by SC veterans).
What advice would you give to someone who’s attending SC for the first time?
The first thing is to check out the resources on the SC website. There is a guide for first-time attendees and additional information for international visitors. But remember that the conference is amazingly large and has so much to offer that you can feel lost. If you are part of a larger group attending, talk to others who have been there before. If you’re on your own, try to find someone from an organization near yours and see if you can walk around with them. Talk to them before the conference on what to expect and things to look out for.

Look over the program in advance so you understand the difference between workshops, BoFs, papers, posters and panels. Also look to see if there is an orientation session for newcomers – it’s usually held on the Monday afternoon.

And here’s some advice for international visitors. If your budget and travel rules allow it, come in a few days earlier and do some sightseeing; for example, visit a nearby national park. This is fun, but it will help you too. Since the meeting is in November, it will be dark when you get up in the morning and dark when you leave the convention center at the end of the day, which doesn’t help you to get over your jet lag. If you can get outside during the day for a few days, maybe do some hiking or a lot of walking, you get tired and sleep well, and this way adjust much more quickly to the time zone. This will help you relax and beat jet lag. Just before SC12 in Salt Lake City, we went to Bryce Canyon, Zion, Arches and Canyonlands national parks in Utah and we had a great time. In 2006, in Tampa, we went to see the Everglades and did an airboat ride.

You’ve actually worked in the U.S. at the University of Oregon and toured around the western U.S. with your family. What were your favorite places to visit?
I love the outdoors and hiking. The western U.S. and Oregon have amazing landscapes. In Europe, there are people and cars everywhere, but the western U.S. has these big, wide open landscapes. So far, I’ve been to 33 national parks in the U.S. But my favorites are some lesser-known areas in Oregon.

We went cross-country skiing around the rim of Crater Lake and rode a jet boat through Hell’s Canyon on the Snake River, North America’s deepest river gorge – even deeper than the Grand Canyon. Many times we hiked to a hidden hot spring in Oregon’s old-growth forests and sat in this natural hot tub surrounded by 2,000-year-old trees. While I was there, I actually took a community college course to become a whitewater rafting captain -- you can’t do such things in Europe!

We knew we would be there three years, so every weekend we took our kids and went somewhere. After two years, the locals began asking me about things to do and places to go! One of the most unusual was Steens Mountain in southeast Oregon. You drive on a gravel road for about three or four hours and the road suddenly stops at a more than 5000-foot drop where there is this structural fault. It’s said to be the farthest place from an interstate highway in the continental U.S.

Bernd Mohr relaxes at his home in Germany with his two beagles, Buddy and Troy.
When you’re not thinking about computing and conferences, what do you like to do in your free time?
I do a lot of traveling for my job – meetings, invited talks, quarterly reviews, conferences and workshops, so when I’m at home I really enjoy just sitting on the couch and doing nothing. I often sit there with our two beagles, Buddy and Troy. At home, they are kind of like cats because they like to be near us and sit with us on the couch or on the bed. But they are bred to be hunting dogs and follow scents, so when I take them for a walk they are always sniffing things. Other people walk or jog by with their dogs by their sides, but I have one dog on a leash pulling on my left arm and the other pulling on my right.

As you probably realize, I also like to visit remote and quiet places where I can get away from everything. Sometimes it’s nice to not have to talk with anyone unless I want to.

Tuesday, April 28, 2015

Call for Interest in SC Leadership Roles

SC18 Conference General Chair
Nominations for the SC18 General Chair are now open and will close on June 9, 2015. To nominate someone, or to nominate yourself, for the general Chair position, send an email giving the candidate’s name, a short paragraph describing how the candidate meets the following criteria, and a recent curriculum vitae (CV) that highlights professional and SC experience.
  • Experience managing large, complex projects in which the people executing the project do not all report directly to the manager
  • SC or equivalent experience, for example, head of two or more previous committees
  • Visionary in our community
  • Able to set strategic direction (and delegate its execution)
  • Willing and able to make the conference her/his top priority for the year of the conference
  • Experience managing a multimillion dollar budget

Member of the SC Steering Committee
Nominations for two openings on the SC Steering committee are now open and will close on  September 8, 2015. To nominate someone, or to nominate yourself, for a position on the Steering Committee, send an email giving the candidate¹s name, a short paragraph describing how the candidate meets the following criteria, and a recent curriculum vitae (CV) that highlights professional and SC experience.
  • Visionary in our community
  • Familiarity with, and passion for, the SC conference
  • Willingness to be an active and engaged advocate for the SC Conference community
  • Willing and able to commit time to attend three one-day in-person meetings and monthly one-hour teleconferences.
Please send nominations for either position to nominations@info.supercomputing.org.

Monday, April 27, 2015

ACM/IEEE-CS George Michael Memorial HPC Fellowship Applications due May 1, 2015

The ACM/IEEE-CS George Michael Memorial HPC Fellowship is seeking applications from exceptional Ph.D. students whose research focus is on high performance computing applications, networking, storage, or large-scale data analysis using the most powerful computers currently available.

Fellowship winners are selected based on overall potential for research excellence, the degree to which technical interests align with those of the HPC community, academic progress to date, recommendations by their advisor and others, and a demonstration of current and anticipated use of HPC resources. The Fellowship includes a $5,000 honorarium, plus travel and registration to receive the award at the annual SC conference.

The Fellowship reflects the two societies’ (ACM and IEEE-CS) long-standing commitment to workforce diversity and encourages applications from women, minorities, international students, and all who contribute to diversity.

Applications due: May 1, 2015

Web submissions: https://submissions.supercomputing.org/

Email contact: awards@info.supercomputing.org

Click here for more on the ACM IEEE-CS George Michael Memorial HPC Fellowship.

Wednesday, April 22, 2015

Eight Questions with "HPC Matters" Chair Wilf Pinfold from Intel

Wilf Pinfold
Wilf Pinfold has a PhD in Computational Fluid Dynamics and Studied Business at Stanford.  He serves as the HPC (High Performance Computing) Matters Chair as well as the Chair of the ACM SIGHPC Advisory Board.

What is your role in the “HPC Matters” program?
SC conference organizers launched the “HPC Matters” program in 2013 with support to develop it over a three-year period. I am honored to have been asked to chair the program through this three-year launch period.
   
SC15: How/when did this get started?
My first conversation with the SC Steering committee about a program that reaches beyond the technical community and communicates the importance of high performance computing to politicians and the general public was in 2006. Since then there have been several programs such as “masterworks”, but they have not had multi-year support. We believe this multi-year program will be a breakthrough.

What are the goals?
Starting in November 2013, the SC conference organizers launched “HPC Matters” to encourage members of the computational sciences community to share their thoughts, vision, and experiences with how High Performance Computers are used to improve the lives of people all over the world. Four pillars provide structure to the program:
1.    Influencing Daily Lives
2.    Science and Engineering
3.    Economic
4.    Education

The inaugural HPC Matters Plenary opened to a packed house
What were some of the highlights from last year?
The SC14 launch was excellent with a Video Challenge, a Plenary and a 
speaker program called the Impact Showcase.

The HPC Matters video challenge had four award winners:

o    Micron Technology for the Funniest Video
o    Texas Advanced Computing Center (TACC) for the Most Creative Video
o    Ohio Supercomputer Center (OSC) for the Most Inspiring
o    National Center for Supercomputing Applications (NCSA) for the Most Likes/Views

The conference also created four videos highlighting the ways in which supercomputers benefit society via health/consumer products, entertainment, weather forecasting, and climate modeling.

The HPC Matters Plenary was given by Dr Eng Lim Goh, CTO of SGI, who discussed the vital role HPC plays in helping researchers and organizations create a better world. Dr. Goh explained what HPC makes possible across industry with real-world examples. He invited Dr. Piyush Mehrotra, chief, from NASA Advanced Supercomputing Division, to speak on HPC-based research that is leading us to revolutionary insights about the world.

The Impact Showcase, launched  in 2013, is designed to introduce attendees to the many ways that HPC matters in our world, through testimonials from companies large and small who many times are clients of exhibitors on the show floor.  Their stories relate real-world experiences of what it took to embrace HPC to better compete and succeed in their line of endeavor.

What can attendees expect this year?
These programs will be back along with new programs for Technical Program, Exhibitors, and Students. Stay tuned as these get rolled out in 2015.
     
How can organizations or individuals get involved?
There will be a call for participation in May 2015 looking for parties interested in the HPC Matters Plenary, the Video Challenge and Impact Showcase.

Why is this important?
For the whole HPC community it is important because we need the politicians and their electorate to understand the value of HPC so our scientists and researchers continue to have the best equipment to keep doing the analyses that make the world a better place.

As a veteran of the HPC industry, what keeps you motivated?
In HPC there is always something new to learn, some new discovery or some significant advance. Each day you can see how HPC makes the world better and that is highly motivating.

Monday, April 13, 2015

Students: Increase Your Application Speed – Student Cluster Competition Deadline is April 17, 2015

SC14 SCC Participants
The clock is ticking down for teams to submit their applications for the SC15 Student Cluster Competition. The deadline to apply for a spot in this year’s competition is Friday, April 17.

Launched at SC07 to showcase student expertise in a friendly yet spirited competition, the Student Cluster Competition aims to introduce the next generation of students to the high-performance computing community. Over the years, the competition has drawn teams from Australia, Canada, China, Costa Rica, Germany, Russia, Taiwan and the United States.

Team proposals must be submitted via the SC15 submission site by clicking here.

Team applications due: April 17, 2015
Email Contact: student-cluster-competition@info.supercomputing.org
Click here for more on the Student Cluster Competition

Thursday, April 9, 2015

U.S. Department of Energy Awards $200 Million for Next- Generation Supercomputer at Argonne National Laboratory

From a U.S. Government Press Release:

Under Secretary for Science and Energy Orr Announces Next Steps in Pursuit of Exascale Supercomputing to Accelerate Major Scientific Discoveries and Engineering Breakthroughs.

Argonne, Ill. – Today, U.S. Department of Energy Under Secretary for Science and Energy Lynn Orr announced two new High Performance Computing (HPC) awards that continue to advance U.S. leadership in developing exascale computing.  The announcement was made alongside leaders from Argonne National Laboratory and industry partners at Chicago’s tech start-up hub, 1871.

Under the joint Collaboration of Oak Ridge, Argonne, and Lawrence Livermore (CORAL) initiative, the U.S. Department of Energy (DOE) announced a $200 million investment to deliver a next-generation supercomputer, known as Aurora, to the Argonne Leadership Computing Facility (ALCF). When commissioned in 2018, this supercomputer will be open to all scientific users – drawing America’s top researchers to Argonne National Laboratory. Additionally, Under Secretary Orr announced $10 million for a high-performance computing R&D program, DesignForward, led by DOE’s Office of Science and National Nuclear Security Administration (NNSA).

“Argonne National Laboratory’s announcement of the Aurora supercomputer will advance low-carbon energy technologies and our fundamental understanding of the universe, while maintaining United States' global leadership in high performance computing,” said Under Secretary Orr. “This machine – part of the Department of Energy’s CORAL initiative – will put the United States one step closer to exascale computing.”

Today’s $200 million award is the third, and final, supercomputer investment funded as part of the CORAL initiative, a $525 million project announced by Department of Energy Secretary Moniz in November 2014.  CORAL was established to leverage supercomputers that will be five to seven times more powerful than today’s top supercomputers and help the nation accelerate to next-generation exascale computing.  DOE earlier announced a $325 million investment to build state-of-the-art supercomputers at its Oak Ridge and Lawrence Livermore laboratories.

“Few national investments have the potential to demonstrate dramatic progress and capability across many scientific disciplines and domains with real-world benefits,” said Peter Littlewood, Director, Argonne National Laboratory. “Advanced computing is a lever that drives transformational change in science and technology, accelerating discovery and shortening the time for technology to reach market.”

Key research goals for the Aurora system, expected to be commissioned in 2018 and to which the entire scientific community will have access, include:

  • Materials science: Designing new classes of materials that will lead to more powerful, efficient and durable batteries and solar panels.
  • Biological science: Gaining the ability to understand the capabilities and vulnerabilities of organisms that can result in improved biofuels and more effective disease control.
  • Transportation efficiency: Collaborating with industry to improve transportation systems with enhanced aerodynamics features, as well as enable production of better, more highly-efficient and quieter engines.
  • Renewable energy: Engineering wind turbine design and placement to greatly improve efficiency and reduce noise.
The new system, Aurora, will use Intel’s HPC scalable system framework to provide a peak performance of 180 PetaFLOP/s.  The system will help ensure continued U.S. leadership in high-end computing for scientific research while also cementing the nation's position as global leader in the development of next-generation exascale computing systems.  Aurora, in effect a “pre-exascale” system, will be delivered in 2018.  Argonne and Intel will also provide an interim system, called Theta, to be delivered in 2016, which will help ALCF users transition their applications to the new technology.

“The future of high performance computing will require significant innovations on multiple fronts and Argonne's Aurora and Theta supercomputers represent successive generations of the transformation required in future HPC system architectures” said Raj Hazra, Vice President, Data Center Group and General Manager, Technical Computing Group, Intel Corporation. “Working together with Cray, these systems provide a highly flexible and adaptable industry design based on Intel’s HPC scalable system framework that will deliver breakthrough performance, power efficiency and application compatibility through an integrated and balanced system architecture – paving the way for new scientific discoveries and far-reaching benefits on a global scale. Intel is honored to have been awarded the Aurora contract as part of the CORAL program.”

Intel will work with Cray Inc. as the system integrator sub-contracted to provide its industry-leading scalable system expertise together with its proven supercomputing technology and HPC software stack. Aurora will be based on a next-generation Cray supercomputer, code-named “Shasta,” a follow-on to the Cray® XC™ series.

“Cray is honored to partner with Argonne and Intel as we develop our next-generation Shasta system to build one of the fastest supercomputers on the planet for the Department of Energy,” said Peter Ungaro, president and CEO of Cray. “Shasta will be a powerful combination of Intel’s new technologies and Cray’s advanced supercomputing expertise, creating a single, flexible system that will enable huge advances in computing and analytics. Aurora will be the first system in our Shasta family and we couldn’t be more excited.”

In addition to procuring systems like Aurora, the Office of Science and the National Nuclear Security Administration are making longer-term investments in exascale computing under the DesignForward high-performance computing R&D program, designed to accelerate the development of next-generation supercomputers. The program recently awarded $10 million in contracts to AMD, Cray, IBM and Intel Federal, complementing the $25.4 million already invested in the first round of DesignForward. Under this public-private partnership, the four technology firms will work with DOE researchers to study and develop software and hardware technologies aimed at maintaining our nation’s lead in scientific computing.

ACM Gordon Bell Prize Applications Due April 24, 2015

Gordon Bell
The ACM Gordon Bell Prize is awarded each year to recognize outstanding achievement in high performance computing. The purpose of the award is to track the progress over time of parallel computing, with particular emphasis on rewarding innovation in applying high performance computing to applications in science, engineering, and large-scale data analytics. Prizes may be awarded for peak performance or special achievements in scalability and time-to-solution on important science and engineering problems.

Last year, the ACM Gordon Bell Prize for best performance of a high performance application went to “Anton 2: Raising the Bar for Performance and Programmability in a Special-Purpose Molecular Dynamics Supercomputer,” from author David E. Shaw and collaborators at D.E. Shaw Research.

Applications due: April 24, 2015
Email contact: acm-awards@acm.org
Web Submissions: click here.
Click here for more information on the ACM Gordon Bell Prize


Wednesday, April 8, 2015

Deadline Approaching: Submit Your Full Technical Papers by April 10, 2015

Full paper submissions for Technical Papers need to be submitted by April 10, 2015.  A traditional one week extension will be granted until April 17, 2015, end of day AoE (Anywhere on Earth time zone).

This year the submissions need to be in the ACM format (http://www.acm.org/sigs/publications/proceedings-templates) and are limited to 10 pages. The 10-page limit includes figures, tables, and appendices, but does not include references, for which there is no page limit.

To find out more about the submission and review processes, please click here

Full papers due: April 10, 2015
Email contact: papers@info.supercomputing.org
Web submissions: click here.

Click here for more on Tech Papers.

Monday, April 6, 2015

Panel and SC Tutorial Submissions Due April 24, 2015

The submission deadline for Panels and Tutorials is quickly approaching.
Panels bring a rare opportunity for mutual engagement of community leaders and broad mainstream contributors in a face-to-face exchange through audience participation and questioning.

This year, panel committee members at SC15 will prepare a series of challenging questions to be revealed to panelists only during the panel. You just have to be there to see how they will have to defend themselves in real-time!

Panels due: April 24, 2015
Email Contact: panels@info.supercomputing.org
Web Submissions: https://submissions.supercomputing.org/

Click here for more on Panels Tutorial Submissions due April 24, 2015

The SC Tutorials Program is one of the highlights of the SC Conference series, and it is one of the largest tutorial programs at any computing-related conference in the world. It offers attendees the chance to learn from and to interact with leading experts in the most popular areas of high performance computing (HPC), networking, and storage.

The tutorials committee is soliciting proposals for full-day (six hours) or half-day (three hours) tutorials that cover a wide range of topics.

Tutorials due: April 24, 2015 (automatic 1-week extension to May 1)
Email Contact: tutorials@info.supercomputing.org
Web Submissions: https://submissions.supercomputing.org/

Click here for more on Tutorials

Wednesday, April 1, 2015

Students: Increase Your Application Speed – Student Cluster Competition Deadline is April 17

Students hard at work during the SC14 Student Cluster Competition.
The clock is ticking down for teams to submit their applications for the SC15 Student Cluster Competition. The deadline to apply for a spot in this year’s competition is Friday, April 17. The Student Cluster Competition is a high energy event featuring young supercomputing talent from around the world competing to build and operate powerful cluster computers during the conference.

Launched at SC07 to showcase student expertise in a friendly yet spirited, the Student Cluster Competition aims to introduce the next generation of students to the high-performance computing community. Over the years, the competition has drawn teams from Australia, Canada, China, Costa Rica, Germany, Russia, Taiwan and the United States.

How the Challenge Works
In this real-time, non-stop, 48-hour competition, teams of undergraduate and/or high school students assemble small cluster computers on the SC15 exhibit floor and race to complete a real-world workload across a series of applications and impress HPC industry judges. Prior to the competition, teams work with their advisor and vendor partners to design and build a cutting-edge cluster from commercially available components that does not exceed a 3120-watt power limit (26-amp at 120-volt), and work with application experts to tune and run the competition codes.

Team proposals must be submitted via the SC15 submission site available by clicking here.