• Subscribe

XSEDE: More than just supercomputers — it’s how to use them, too!

Vince Betro. Photo courtesy XSEDE.

To many familiar with the world of high-performance computing, the Extreme Science and Engineering Discovery Environment (XSEDE) means 'supercomputers' and not much more. Often, success stories involve a research team using XSEDE-allocated supercomputers like Stampede at the Texas Advanced Computing Center (TACC) or Comet at the San Diego Supercomputer Center.

But what good are supercomputers without the expertise throughout the community to properly use them? Even worse, what good is training if the community is not aware of it? XSEDE is preparing the current and next generation of computational scientists by providing a full slate of training opportunities across the country. XSEDE's outreach efforts and ability to give users tools to enhance their science are important steps toward breakthrough learning systems coming in the near future.

Fully integrated, established training environments like CI-Tutor (est. 2000) and the Cornell Virtual Workshop (est. 1995) have long been part of the XSEDE landscape. Both of these on-demand resources offer access to specific topics through a modular, asynchronous curriculum and the ability to revisit and review information from massive open online ourses (MOOCs), some for college credit.

XSEDE also offers certification on various HPC tools and skills like OpenACC and Globus Online, and has hosted courses on topics like 'Using R for HPC,' Genesis II, Unicore, GFFS and more. These courses have reached thousands of people, including students and staff at San Francisco State University (US), the University of Puerto Rico and all points between.

In February, XSEDE conducted a Moodle certification pilot alongside a Pittsburgh Supercomputing Center (PSC) monthly workshop, with participants able to receive beginner, intermediate, or advanced badges in OpenACC competency. These PSC seminars recently expanded to 16 simulcast sites and saw their 2,500th user sign up. In all, 17 participants were awarded badges, and another new user training webinar opportunity was instigated in April at TACC.

As another way to engage with those who may take training courses, the XSEDE team used social media as a means to strengthen and extend the conversation surrounding the 'Using R for HPC' event. In addition to the hundreds who attended the seminar, many more followed the hashtag #hpcR on Twitter. Through social media outlets, the team seeks to attract new users and young people who may not yet be fully committed to the importance of science, technology, engineering, and mathematics (STEM).

It's clear that by training the trainers and vetting their services, XSEDE is much more than supercomputers. The XSEDE training team has engaged with personnel from NASA, the US DoE, and PRACE in an attempt to make shorter work of gap analysis in course materials, and to publicize and enhance the value of certification.

The XSEDE team has made it a goal to grow and prepare the community so it has more experts ready to use the computing resources and help others take advantage of them. XSEDE is an important part of the larger HPC ecosystem and computational science cyberinfrastructure. But, XSEDE is not just supercomputers - they are the people who make science happen.

--Vince Betro is a computational scientist with the Joint Institute for Computational Sciences and the lead XSEDE User Services Training Manager in Scientific Computing for the National Institute of Computational Sciences.

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2018 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.