• Subscribe

At Science Node, we need your help. We have ALMOST reached our fund-raising goal. In order to maintain our independence as a source of unbiased news and information, we don’t take money from big tech corporations. That’s why we’re asking our readers to help us raise the final $10,000 we need to meet our budget for the year. Donate now to Science Node's Gofundme campaign. Thank you!

iSGTW Roaming mike - Voices from the OSG Great Plains Summer School


Roaming mike - Voices from the OSG Great Plains Summer School


Cristy Burne, iSGTW editor
Three months in to the job and I still understood only a fraction of the three-letter acronyms required to have an ordinary conversation about grids. It was time for me to study up, and what better place than the University of Nebraska in Lincoln, Nebraska, home of the mighty Huskers and center of activity for this year's Open Science Grid Great Plains Summer School.

As a grid novice I found this school a real eye-opener. What an opportunity to learn and create: we had 40 enthused scientists and academics, an endless supply of hot coffee, and an intensive schedule of lectures and hands-on grid computing. Anything was possible.

Three days later I am shattered, but come away knowing more about the guts of grid computing than I thought there was to know. How it all fits together and does what it does is a wonder to me, and a credit to everyone involved.

But what did everyone else think? I was keen to find out...

I've trained more than 500 people in grid schools all over the globe, and every school is different.

Of course Wednesday night's microbrewery tour was all a part of the curriculum...you never know where grid computing might find application next.

Alina Bejan, Open Science Grid Coordinator for Education, Outreach and Training
I only recently joined the OSG team, and already, all around me, I find people with great ideas involved in the development of cutting-edge technologies. This was my first grid workshop, both as a student and as an organizer, and it has been an excellent experience.

I have been able to meet many interesting people from different universities, representing a large pool of disciplines. My job now is to make sure that these participants receive the proper support to start or continue their work on projects that utilize grid resources and technologies, adding to the growing community of grid users interacting and collaborating to take advantage of the grid.

Estelle M. Huff, Ph. D. Candidate, University of Arkansas, Department of Chemistry and Biochemistry
The grid school has been rather intensive. Some of the information is familiar, but other portions have been completely foreign.

Since a lot of my work is computer-based, access to more processing power is very appetizing. The main question remains: how to package my software such that it can be send along with jobs?

I don't have as much experience in programming as many of the other participants so I feel like I need to do a little bit of catch-up. If I can get a script together to submit jobs with chemistry software I'm sure that other chemists would join the grid. I'm looking forward to being able to use the resources I've learned about here, both human and technological.

Sanjiv Bhatia, University of Missouri, Department of Math and Computer Science
This was an excellent workshop, in terms of format, content, and enthusiasm of presenters. I came in with no knowledge of grid computing and am leaving with enough to be dangerous.

My main concern with the grid computing tools is that they are being built in a non-optimal fashion. We are trying to drive computation with the thinking that more teraflops, more petabytes and more CPUs are better when solving large problems. However, we are losing touch with bare metal and not bothering to write code that is optimal. And this seems to be a problem with computer science in general.

We now have a generation of programmers who think that time spent shaving microseconds off code execution time is time wasted, and think of the solution in terms of bigger hardware. Hence, we have Vista that takes gigabytes of memory to run on multicore CPUs, and we have Office that requires 24KB to store 13 bytes of Hello World.

I think we need to educate our high performance computer scientists to take advantage of issues like cache management and loop unrolling before we put them on the grid, and that will create a better use of the grid than just trying to divide up problems that may not have been optimized very well to begin with.

Brian Bockelman, Ph. D. Candidate and Tier 2 site system administrator for the Compact Muon Solenoid experiment, University of Nebraska
I have been working with grids since the summer of 2005, when the CMS site at Nebraska consisted of me, four servers, and not a clue in the world. Since then, I've helped our local site grow and participate in the CMS and OSG communities.

Here at the grid school, I'm volunteering as a teaching assistant. We have encouraged grid usage through the Great Plains Network, and are excited to host this event.

Hopefully, our local users can now utilize even more resources and start out with an advantage I lacked when I began: advice and knowledge from the experts!

Rebecca Ryan, Center for Research, University of Kansas
It's been great. The team is excellent. The lectures were clear, explanations excellent. The labs were great in terms of providing hands-on experience with the concepts presented. Everyone was helpful. No one talked down, even when I asked stupid questions. It was a great learning environment. I'm very glad I came.

I want to go back and finish bringing our Condor pools up, bring up a campus scheduler using Condor-G, and try to offer carrots so existing clusters on campus might want to allow those resources to be scheduled through Condor-G. I'd also like to implement a program like this one, where we offer classes to our faculty to make use of the grid easier and not so intimidating.

Mike Wilde, Argonne National Laboratory, University of Chicago Computation Institute and director of the OSG education program.
I enjoy working on grids because it's a great laboratory for computer science.
But more than this I love this work because of the great people I meet, and the chance to make a positive difference for people doing intriguing and vital science.

The grid schools give us a great opportunity to bring this excitement to a wide and fresh audience. This is our sixth grid school-our third this year-and each time I'm inspired by the excitement of our students, who range from undergraduates to faculty and program directors, and the joy of helping them discover new possibilities to extend their research through computation.

Join the conversation

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

Copyright © 2019 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.