Entries filed under “HPC Education and Training”

Pointers to screencasts, tutorials, books, and events that can help get you up to speed on the technologies and techniques of HPC.

MEGWARE Sponsors Local Team at ISC’13 Student Cluster Challenge

When it comes to Student Cluster Competitions, is there such a thing as a home team advantage? A team of six Chemnitz students will battle it out with eight other teams in the ISC’13 Student Cluster Challenge. The team calls themselves “TurboTUC” and their roster includes some students with pure science backgrounds in areas such as chemistry and theoretical physics to go along with their computer-related smarts.

The challenge for us is firstly to create high-performance hardware and then use the right components,” says team member Sebastian Siegert. “In addition, we will only find out about part of the applications at the fair itself – then the task will be to discover whether – and how well – we can adapt these with our supercomputer in order to solve the problem as quickly and with the greatest energy efficiency as possible,” adds Henrik Kretzschmar.

Read the Full Story or check out more Team profiles at the Student Cluster Competition Blog.

Also posted in Events, HPC, ISC13, Student Cluster Competition | Leave a comment

Video: Brent Gorda on the Origins of the Student Cluster Challenge

In this video, Dan Olds from Gabriel Consulting discusses the origins of the Student Cluster Competition with Brent Gorda, who helped found the contest back at SC07. Gorda talks about the goals of the competition and the hurdles they had to go through in the early days.

The Student Cluster Competition has since grown to a series of international events that bring out the best and brightest young people to build the fastest HPC systems they can with limited electrical power. With the ISC’13 Student Cluster Challenge coming up next week in Leipzig, Dan Olds has also posted a complete rundown on the teams, so check it out.

View Part 2 of this video.

Also posted in Events, HPC, ISC13, Student Cluster Competition, Video | Leave a comment

Student Cluster Competition Deep Dive: WRF Weather Code

In this video, Dan Olds from Gabriel Consulting discusses the WRF weather code with Jordan Powers and David Gill from NCAR. As part of the suite of real applications used in the ISC’13 Student Cluster Challenge, WRF optimization could be the key to success for the student teams.

Check out more team and application profiles at the Student Cluster Competition Blog.

Also posted in Events, HPC, HPC Software, ISC13, Student Cluster Competition, Video | Leave a comment

Jeff Layton on Getting Started with HPC Clusters

Generic Cluster Layout

Over at Admin Magazine, Dell’s Jeff Layton has written a wide-ranging primer on Getting Started with HPC Clusters. And while he covers the bases with traditional beowulf topics, Layton says that using virtualization is a great path to understanding.

One of the quickest and easiest ways to really get started is to use virtualization, which is sort of the antithesis of HPC: Virtualization takes a single system and makes it appear to be several separate systems; HPC tries to take several systems and make them appear to be a single system. You can use your laptop or desktop to run a number of VMs and then use them to learn about HPC applications or administering clusters. In doing so, you not only learn about HPC, you learn about virtualization for Linux, which is not a bad skill to have.

Read the Full Story.

Also posted in Cloud HPC, Compute, HPC, HPC Hardware | Leave a comment

OpenFabrics Alliance to Host RDMA Training Courses in New Hampshire

Today the OpenFabrics Alliance (OFA) announced it will host two training classes at the University of New Hampshire Interoperability Lab. The two-day courses, instructed by Dr. Robert D. Russell and Rupert Dance, will provide attendees with hands-on training for managing InfiniBand Fabric in addition to coding applications directly to the VERBS API using OpenFabrics Enterprise Distribution (OFED) and related software tools.

  • InfiniBand Fabric Administration
    • Date: June 5-6, 2013 from 8 a.m. – 6 p.m.
    • Who Should Attend: System Administrators, System Architects, Planners and Technologists. A background in IP-based or Ethernet-based management is helpful and familiarity with the target operating system is assumed. This course does not assume RDMA specific knowledge and programming for RDMA is not a prerequisite.
    • Register now.

Both events will be held at the University of New Hampshire Interoperability Lab in Durham, NH. Read the Full Story.

Also posted in HPC, HPC Software, Open Fabrics | Leave a comment

Student Programming Competition Coming to XSEDE13 this Summer

Students from high school to grad school levels are invited to participate in a programming contest at XSEDE13 high performance computing conference, which takes place in San Diego on July 22-25.

Created as an opportunity to showcase student expertise in a friendly yet spirited competition, the XSEDE13 Student Programming Competition aims to introduce the next generation of students to the high-performance computing community. Over the last couple of years, the competition has drawn teams from around the world, including China, South America, Canada, Africa and Europe. With access to parallel computing resources, teams consisting of up to five students (high school, undergraduate, and/or graduate students) will receive a variety of interesting computational science problems to address at the conference. Awards will recognize creativity, quality of solutions, and good coding practices of the teams who solve the most problems during the daylong competition.

Contest registration will open April 30, 2013 and close May 30, 2013.

Also posted in Events, HPC | Leave a comment

George Michael Fellowship Helps HPC Community Thrive

For doctoral candidates in supercomputing, the George Michael Memorial HPC Fellowship offers a rapid plug-in to the global network of leading high performance computing organizations, from research institutions to industry.

Past recipients report that the fellowship ticket to the annual supercomputing conference (SC) can be a career affirming and life changing experience.

Coupled with the opportunity to display my research at a well-attended conference, the Fellowship has had a tremendous impact on my work future,” said Ryan Gabrys, a 2012 fellow. “The George Michael Fellowship has provided me with more freedom to pursue the areas of research I find the most exciting.”

A doctoral student at UCLA, Gabrys’ HPC specialty is coding for HPC storage systems.

Fellowship candidates are exceptional PhD students whose research focus is on high-performance computing (HPC) applications, networking, storage, or large-scale data analysis using the most powerful computers currently available.
Recipients of the George Michael Memorial HPC Fellowship receive a $5,000 honorarium, travel and registration for SC13, and recognition at the SC13 Awards Ceremony. Past recipients report that the fellowship ticket to the supercomputing conference (SC) can be a career affirming and life changing experience.

The deadline of May 1 to apply for the 2013 fellowship is rapidly approaching. To apply or for more information, see the SC13 website.

Xinyu Que, a 2011 fellow, notes that the fellowship helps students make the most of what can be an “overwhelming” experience at SC. “It provides opportunities to meet other George Michael fellows and make new connections. The profound technical talks helped me better understand research topics and trends.

Not only did I have a chance to present and demonstrate my doctoral research to well-known, senior researchers, but I also learned about future challenges and opportunities in my research areas. It was very stimulating,” said Que, who at the time was a doctoral candidate in Parallel Architecture and System Laboratory in the Department of Computer Science & Software Engineering at Auburn University.
Abhinav Bhatele, a 2009 fellow from the University of Illinois Urbana-Champaign, found the fellowship an effective vehicle for spreading the word about his research. “The fellowship award has been instrumental in disseminating my research and dissertation work on ‘topology aware task mapping’ within the field of HPC,” said Bhatele, who is now a researcher in the Computation Department at Lawrence Livermore National Laboratory. “It also has helped me to connect with others in the field and I have become good friends with other George Michael fellows.”

For Ignacio Laguna Peralta, another 2011 fellow, the fellowship offered the opportunity to get feedback from experts in his field – failure diagnosis and localization in HPC applications.

I received constructive criticism of my work, which I used to improve it. Also, I was able to interact with other students and researchers in my field and to gain valuable professional connections,” said Laguna Peralta, who received his PhD. from Purdue in 2012. “Other benefits of the fellowship include the opportunity to visit and present research to a variety of organizations. This helps in finding collaborators in labs or companies outside your University and in making connections for a future job.”

The fellowship introduced Mark Hoemmen to the Supercomputing Conference (SC) and opened his eyes to the breadth and vitality of the HPC community. Hoemmen, a specialist in architecture-aware iterative linear solvers, currently works at Sandia National Laboratories in New Mexico.

Had I not received the Fellowship, I might not have attended the conference until later in my career, and I might have missed out on seeing how grand and dynamic the field of HPC is,” said Hoemmen, a 2008 fellow from UC Berkeley. “It struck me how much interest industry has in the conference, not just as vendors of HPC technology, but also as consumers. This helped me better understand industry’s interest in HPC, which has served me well in my current responsibility as a central developer of a popular open-source scientific software product.”

Sponsored by the ACM and the IEEE-CS, the George Michael fellowship seeks to address the critical issue of training the next generation of high performance computing scientists and engineers.

The late George Michael, a computational physicist at Lawrence Livermore, was a founder of the annual supercomputing conference (SC), which is now in its 25th year. Michael, who died in 2008, is remembered for his ability to bring together diverse talent from academia, industry and national labs to advance HPC.

To qualify, applicants must be enrolled in a full-time PhD program at an accredited college or university and are expected to have completed at least one year of study in their doctoral program. Women, minorities, and all who contribute to workforce diversity are encouraged to apply.

For more information or to apply, visit the SC13 site. Submissions opened in early March and will close on May 1.

Please send any questions to: [email protected]

Also posted in Events, SC13 | Leave a comment

Sign Up for the Argonne Training Program on Extreme-Scale Computing, July 28-August 9

Computational scientists are invited to register for the upcoming Argonne Training Program on Extreme-Scale Computing (ATPESC). The event will take place in the greater Chicago area from July 28-August 9, 2013.

The program provides intensive hands-on training on the key skills, approaches, and tools to design, implement, and execute computational science and engineering applications on current high-end computing systems and the leadership-class computing systems of the future. As a bridge to that future, this two-week program to be held in suburban Chicago fills the gap that exists in the training computational scientists typically receive through formal education or other shorter courses.

Applications are currently being accepted for the program. The deadline for applying is May 22, 2013. Read the Full Story.

Also posted in Events, HPC, HPC Software | Leave a comment

Asian Students Prep for Cluster Competition Smackdown

Over at The Register, Dan Olds writes that the first annual Asia Student Cluster Challenge (ASCC) culminates this week with a final round of competition that brings 10 university teams to Shanghai for a live cluster-off.

Teams will compete for top benchmark scores on three HPC workloads including the LINPACK benchmark and the Gromacs molecular dynamics package. The third applications, BSDE option pricing (a Monte Carlo calculation), requires students to use Intel’s Phi accelerator to compute results. This competition, which is the first in the student cluster competition triple crown, is jointly sponsored by the Asian Student Supercomputer Challenge (ASC), the HPC Advisory Council, Inspur and Intel. Forty-two universities from far and wide submitted highly detailed competition proposals. The ASC selected the ten best submissions and invited those teams to the final in Shanghai.

ASCC winners will receive cash prizes and a chance to compete at the ISC’13 Student Cluster Competition.


Also posted in Events, HPC, ISC13 | Leave a comment

Bull Opens Centre for Excellence in Parallel Programming

Bull has inaugurated its Centre for Excellence in Parallel Programming, described as the leading European centre of technical and industrial excellence in this field. By working with technology leaders, this centre aims to support engineers and scientists in research centres and industry to overcome the critical technological barrier of “HPC application parallelisation.”

Bull says the Centre will be equipped with the highest levels of expertise, to help research labs and companies optimise their applications so they can be compatible with not only processors available today, but also those in development for the next generation. It will supply a broad portfolio of services, including analysis and consultancy, as well as software parallelisation and optimisation.

The centre will benefit from close cooperation with Intel in the area of supercomputers and parallel computing. It will combine the latest Intel technologies in processing, network and storage technologies with technology from world leaders and players in research and industry specialising in parallel computing software and methodologies. Partners involved the Centre for Excellence in Parallel Programming already include Allinea, CAPS and the Joseph Fourier University.

This story appears here as part of a cross-publishing agreement with Scientific Computing World.


Also posted in HPC | Leave a comment

Update: John West on What’s Missing from HPC?

In this video from the 2013 National HPCC Conference, John West from the DoD HPC Modernization Program presents an Update on What’s Missing from HPC? You can see West’s talk from last year as well.

View the slides on Slideshare.

Also posted in Events, HPC, National HPCC Conference, Video | Leave a comment

Video: Hands-on Training: Know Your Cluster Bottlenecks and Maximize Performance

In this video from the HPC Advisory Council Switzerland Conference, Dan Waxman from Mellanox provides a hands-on training for InfiniBand entitled: Hands-on Training: Know Your Cluster Bottlenecks and Maximize Performance.

Depending on the application of the user’s system, it may be necessary to modify the default configuration of the network adapters and the system/chipset configuration. This slide deck describes common tuning parameters, settings & procedures that can improve performance of the network adapter. Different Server & NIC vendors may have different recommendations for the values to be set – but the general tuning approach should be similar. For the hands-on demo we will utilize Mellanox ConnectX adapters – thus we will implement the recommended settings issued by Mellanox.

Download the Slides (PDF).

Also posted in Events, HPC, HPC Advisory Council Workshop, HPC Hardware, InfiniBand, Network | Leave a comment

Interview: LBNL’s Kathy Yelick on the Importance of STEM Education

The Energy.GOV site is featuring an interview with Kathy Yelick, Associate Laboratory Director for Computing Sciences at Lawrence Berkeley National Laboratory. Yelick is a strong supporter of STEM education efforts around Science, Technology, Engineering and Math, and she offers advice for young people looking to get into science.

I recommend that people explore as many options as they can and try to find something they love to do; I consider myself very fortunate to have such a career. It’s also important to remember that beginning programming courses, just like elementary school arithmetic, start with very basic problems. Large computing systems and software projects involve teams of people working over multiple years, so you may not see the impact of what you can do right away. And while the individual puzzle-solving element of programming never disappears, the opportunity to work with other smart, creative people, often with expertise quite different than your own, is an important characteristic of many computing projects that you can get involved with later in your career.

Read the Full Story.


Also posted in HPC | Leave a comment

Ashlee Ford Versypt Named 2013 Frederick A. Howes Scholar in Computational Science

This week the Krell Institute announced that Ashlee Ford Versypt has been named the 2012 Frederick A. Howes Scholar in Computational Science. The award honors recent doctoral graduates of the Department of Energy Computational Science Graduate Fellowship program for outstanding technical achievements.

Ashlee’s demonstrated excellence in research, leadership and outreach in the computational science community exemplifies the qualities that Fred Howes encouraged in all young scientists. She serves as a role model to her peers and a tireless communicator and advocate for the field of computational science,” the selection committee noted in its award citation.

Read the Full Story.

Leave a comment

OFA Course on Writing Applications for RDMA Using OpenFabrics Software

Over at Open Fabrics, Rupert Dance from the OFA Interoperability Working Group discusses the organization’s RDMA training courses.

The RDMA training courses are delivered in two formats: (1) at the University of New Hampshire Interoperability Lab (UNH-IOL) or (2) at a vendor location using the vendor’s equipment. When we have a group of registrants from different organizations, we host the course at the UNH-IOL and use the university’s cluster for demonstration. The course runs from 8 a.m. to 6 p.m. over two days, and the first 4 hours focus on an architectural overview of RDMA, while the remainder of the day is used for learning programming constructs (programming verbs, writing your own RDMA code). The courses generally consist of an attendance of a small (4-16) group of people as the lessons are hands-on, and all course material, including presentations and code framework built during the course, are available to attendees afterwards.

Read the Full Story.

In related news, the Open Fabrics Alliance will be hosting two workshops this April in Monterey, California:


Also posted in Events, HPC, Open Fabrics Workshop | Leave a comment

Advertisement

Penguin Computing Ad

Video Archive

insideHPC.com is a production of insideHPC, LLC. © 2006-2013 Sitemap