News

Mar 23
0

MICDE Seminar: Henry Neeman, University of Oklahoma Supercomputing Center: “Why Storage for Big Data is Hard” — March 26

By | Educational, Events

Henry Neeman is Director of the OU Supercomputing Center for Education and Research (OSCER); Assistant Vice President, Information Technology – Research Strategy Advisor; Associate Professor, College of Engineering; and Adjunct Associate Professor, School of Computer Science; University of Oklahoma. He received a Ph.D and M.S. in Computer Science from the University of Illinois at Urbana-Champaign, and did doctoral and post-doc work at the National Center for Supercomputing Applications at UIUC.

 

Mar 23
0

Open meeting for HPC users at U-M — March 27

By | Educational, Events

Users of high performance computing resources are invited to meet Flux operators and support staff in person at an upcoming user meeting:

  • March 27th, 1 – 5 p.m., 2001 LSA

There is not a set agenda; come at anytime and stay as long as you please. You can come and talk about your use of any sort of computational resource, Flux, Nyx, XSEDE, or other.

Ask any questions you may have. The Flux staff will work with you on your specific projects, or just show you new things that can help you optimize your research.

This is also a good time to meet other researchers doing similar work.

This is open to anyone interested; it is not limited to Flux users.

Examples potential topics:

  • What Flux/ARC services are there, and how to access them?
  • How to make the most of PBS and learn its features specific to your work?
  • I want to do X, do you have software capable of it?
  • What is special about GPU/Xeon Phi/Accelerators?
  • Are there resources for people without budgets?
  • I want to apply for grant X, but it has certain limitations. What support can ARC provide?
  • I want to learn more about the compiler and debugging?
  • I want to learn more about performance tuning, can you look at my code with me?
  • Etc.

For more information, contact Brock Palen (brockp@umich.edu) at the College of Engineering; Dr. Charles Antonelli (cja@umich.edu) at LSA; Jeremy Hallum (jhallum@umich.edu) at the Medical School; or Vlad Wielbut (wlodek@umich.edu) at SPH.

Mar 22
0

REMINDER: MICDE fellowships available — March 27 deadline

By | Educational, Events, Funding Opportunities

Applications are now being accepted for Michigan Institute for Computational Discovery and Engineering (MICDE) Fellowships for the 2015-2016 academic year. Applicants should be graduate students enrolled in either the CDE certificate program, or the Ph.D. program in Scientific Computing. Students not yet enrolled in one of those programs but planning on doing so may simultaneously submit program and fellowship applications.

Fellows will receive a $4,000 research fund that can be used to attend a conference, to buy a computer, or for any other advisor-approved activity that enhances the Fellow’s graduate experience.  We also ask that Fellows present a poster at the MICDE Symposium in Fall 2015.

Interested students should download and complete the application form, have it signed by their advisor, and submit it with a one-page resume to MICDE-apps@umich.edu. The due date for applications is March 27, 2015.

Mar 21
0

MICDE Seminar: Hossam Metwally, ANSYS Inc., “Role of Multi-Physics Computational Discovery in Product Development” — March 30

By | Educational, Events

The presentation will start by highlighting the industry current trends in the product development  process in general; PLM-CAE integration, multi-disciplinary optimization, democratization, and finally the need for speed. Examples from different industries will be shared and discussed to highlight how each of the trends has been implemented. The examples will cover a wide range of industries namely, automotive, consumer products, chemicals, medical, electromechanical, and civil engineering to stress  on the wide applicability and potential use of computational discovery across the different disciplines. Finally, a high level vision for running such an organization within an academic setting with business/industrial background will be shared.

Role of Multi-Physics Computational Discovery in Product Development

2:30 – 3:30 p.m., Monday, March 30, 2015
1210 Lurie Engineering Center

Dr. Hossam Metwally obtained his Ph.D. from the University of Cincinnati in 2002 from the department of Mechanical, Industrial, and Nuclear Engineering. He joined the consulting group in Fluent Inc. (now part of ANSYS Inc.) a year prior. Currently Dr. Metwally holds the position of principal engineer at ANSYS Inc. where he is involved in technical support, advanced training, technical marketing, testing, documentation revisions, and business & product development. Dr. Metwally has also wide consulting experience across different engineering disciplines that utilize simulation; e.g. chemicals processing, aerospace, mechanical, and HVAC. Currently, Dr. Metwally is specifically active in the plastics processing area where he is continuously publishing and attending various conferences (ANTEC, Annual blow Molding Conference, Thermoforming Conference). He has received best paper award in 2006 from the Society of Plastics Engineering (SPE) Extrusion Division. Dr. Metwally has also authored several white papers on the role of simulation across different disciplines that are currently posted on ansys.com.

Mar 20
0

XSEDE15 Call for Participation deadline extended to April 6

By | Events

The XSEDE15 Call for Participation, covering all aspects of participation in the conference, has been extended to April 6.

The XSEDE15 Conference, to be held in St. Louis on July 26-30, will showcase the discoveries, innovations, and achievements of those who use, build, and support XSEDE resources and services, as well as those involved in related digital resources endeavors around the world. This year’s theme is Scientific Advancements Enabled by Enhanced Cyberinfrastructure.

The annual XSEDE conference is designed to engage and directly benefit diverse communities, including students, educators, researchers, and practitioners across all fields of study and scholarly research with particular emphasis placed on engaging under-represented minorities, women, and people with disabilities. Last year’s XSEDE14 conference saw more than 600 attendees from 49 states and 10 countries.

Full papers will be included in the Conference Proceedings and submitted to the ACM Digital Library.

XSEDE15 seeks high-quality submissions—including papers, posters, visualizations, and more—in four thematic tracks. The original deadline of March 30 has been extended to April 6.

To find out more information on the Call for Participation and full sponsorship prospectus details, please visit the conference Web site.

If you are planning to submit after the original March 30 deadline, please consider submitting an abstract in advance and adding the full paper by the new deadline. This is not required, but will help us gauge the level of interest in each track. All other dates, including poster submission deadlines and author notifications will remain the same. Submissions must be made through Easy Chair.

Mar 18
0

MIDAS seminar: Shuo Xiang, Pinterest data scientist, “Data Engineering on Spark” — March 27

By | Educational, Events

Shuo Xiang, a data scientist at Pinterest, will deliver a seminar titled “Data Engineering on Spark.”

Date: Friday, March 27

Time: 1 p.m.

Location: Henderson Room, Michigan League

Abstract: We are collecting and processing vast amount of data nowadays and we have witnessed how data-driven R&D could fundamentally change various aspects of our life. In this talk, Shuo Xiang will first introduce common data engineering tasks and the associated challenges that are faced by both industrial companies and academic researchers. Powered by Apache Spark, an emerging data processing engine, he will show how to deliver and scale up data engineering services such as data preprocessing, machine learning and real-time analytics. Finally, he will give examples on parallelizing specific machine learning algorithms on top of Spark.

Bio: Shuo Xiang is a Data Scientist of Pinterest, where he works on data pipeline, machine learning service and visualization. He obtained his PhD from Arizona State University in 2014 for research on feature selection modeling and optimization algorithm. He is a contributor of multiple open-source projects including Apache Spark.

Pinterest is a visual bookmarking tool that helps users discover and save creative ideas. Its mission is “to help people discover the things they love, and inspire them to go do those things in their daily lives.”

This event is sponsored by the Michigan Institute for Data Science and the Department of Electrical & Computer Engineering.

 

Mar 18
0

Big Data workshop simulcast at U-M will focus on Hadoop, Spark — April 7

By | Educational, Events
XSEDE along with the Pittsburgh Supercomputing Center are pleased to announce a one day Big Data workshop, to be held April 7, 2015.This workshop will focus on topics such as Hadoop and Spark. Please bring your laptop to work on the exercises. Access accounts will be provided at the training site.

Agenda – Tuesday, April 7 (All times given are Eastern)

11:00 Welcome
11:30 Intro to Big Data
12:15 Hadoop
1:00 Lunch break
2:00 Hadoop(cont)
2:30 Exercises
3:15 Spark
4:15 Exercise 2
5:00 AdjournUniversity of Michigan

Ehrlichler Room 3rd floor, Room 3100 of North Quad
Ann Arbor, MI 48109
Registration is required to attend this event.
Mar 18
0

XSEDE accepting research allocation requests — April 15 deadline

By | Educational, Events

XSEDE, the Extreme Science and Engineering Discovery Environment, is accepting research allocation requests for the period July 1, 2015 to June 30, 2016. The submission deadline is April 15, 2015. Requests must be submitted through the XSEDE user portal.

Before submitting a request, please review the description of new XSEDE resources, allocation request procedures, and policy changes posted on the XSEDE website.

Mar 18
0

Webcast: Writing a Successful XSEDE Allocation Proposal — March 25

By | Educational, Events

This short webinar will introduce users to the process of writing a proposal to secure an allocation on XSEDE, the Extreme Science and Engineering Discovery Environment, and cover the elements that make a proposal successful. This webinar is recommended for users making the jump from a startup allocation to a research allocation, and is highly recommended for new campus champions.

Registration:
https://www.xsede.org/web/xup/course-calendar/-/training-user/class/379/session/637

Please submit any questions you may have via the Consulting section of the XSEDE User Portal.
https://portal.xsede.org/help-desk

Time: 1-3 p.m., Eastern

Date: Wednesday, March 25

Mar 17
0

REMINDER: MICDE Seminar: David Keyes, KAUST, “Algorithmic Adaptations to Extreme Scale” — March 19

By | Educational, Events

Algorithmic adaptations to use next-generation computers closer to their potential are underway throughout scientific computing. Instead of squeezing out flops – the traditional goal of algorithmic optimality, which served as a reasonable proxy for all associated costs – algorithms must now squeeze synchronizations, memory, and data transfers, while extra flops on locally cacheable data typically represent only small costs in time and energy. Today’s scalable solvers, in particular, exploit frequent global synchronizations. After decades of programming model stability with bulk synchronous processing (BSP), new programming models and new algorithmic capabilities (to make forays into, e.g., data assimilation, inverse problems, and uncertainty quantification) must be co-designed with the hardware. This talk will briefly recap the architectural constraints, mention some related work at KAUST, and outline future directions.

Algorithmic Adaptations to Extreme Scale

1 – 2:30 p.m., Thurs., March 19
1010 Herbert H. Dow Building

David Keyes directs the Extreme Computing Research Center at the King Abdullah University of Science and Technology (KAUST). He earned a BSE in Aerospace and Mechanical Sciences from Princeton in 1978 and PhD in Applied Mathematics from Harvard in 1984. Keyes works at the interface between parallel computing and the numerical analysis of PDEs, with a focus on scalable implicit solvers. Newton-Krylov-Schwarz (NKS), Additive Schwarz Preconditioned Inexact Newton (ASPIN), and Algebraic Fast Multipole (AFM) methods are methods he helped name and is helping to popularize.  Before joining KAUST as a founding dean in 2009, he led scalable solver software projects in the ASCI and SciDAC programs of the US DOE, headed university collaboration programs at NASA’s ICASE and the LLNL’s ISCR, and taught at Columbia, Old Dominion, and Yale Universities.  He holds a Gordon Bell Prize and a Sidney Fernbach Award, is a Fellow of AMS and SIAM, and was the recipient of the 2011 SIAM Prize for Distinguished Service to the Profession.