ARC/ICOS Big Data Summer Camp — June 1-4 & 11

This year, the Interdisciplinary Committee on Organizational Studes (ICOS) and ARC are again offering a one-week “big data summer camp” for doctoral students in the social sciences interested in organizational research, with a combination of detailed examples from researchers; hands-on instruction in Python, SQL, and APIs; and group work to apply these ideas to organizational questions.

The dates of the camp are all day June 1-4 and the afternoon of June 11 for group project presentations. Enrollment is free, but students must commit to attending all day for each day of camp, and be willing to work in interdisciplinary groups.

To sign up for camp, visit the registration page.  Please note that space is limited, and we will be accepting people on a first-come, first-served basis. There are no pre-requisites, but we will expect all participants to complete some online instruction prior to camp and to bring a laptop to class with all the relevant programs and files loaded and ready.

A summary of last year’s boot camp is available on the ARC web site.

SC15 conference seeks student volunteers — June 1 application deadline

The SC15 conference in Austin, Texas, in November is taking applications for student volunteers. The deadline to apply is June 1.

Conference organizers say they are accepting an increased number of students from the U.S. and internationally. Student volunteers can attend tutorials, technical talks, panels, poster sessions, and workshops.

For information on how to apply, visit the SC15 Student Volunteer web page, or email student-vols@info.supercomputing.org

Registration open for NCSA Blue Waters Symposium for Petascale Science and Beyond — May 10-13

The Third Annual NCSA Blue Waters Symposium will bring together leaders in petascale computational science and engineering and will be a tremendous opportunity for sharing successes and challenges in large-scale heterogeneous computing. Along with presentations from the Blue Waters science teams, the symposium will feature keynotes from innovative thinkers in science and will provide opportunities to share and discuss specific topics of interest.

The symposium will take place at the Sunriver Resort in Sunriver Oregon. For more information, visit the Symposium Web site.

Info sessions: Graduate Studies in Computational and Data Sciences at U-M — April 14 & 15

Learn about graduate programs that will prepare you for success in computationally intensive fields — and enjoy pizza and pop! Presentations will describe the following programs:

  • The Ph.D. in Scientific Computing is open to all Ph.D. students who will make extensive use of large-scale computation, computational methods, or algorithms for advanced computer architec- tures in their studies. It is a joint degree program, with students earning a Ph.D. from their current departments, “… and Scientific Computing” — for example, “Ph.D. in Aerospace Engineering and Scientific Computing.”
  • The Graduate Certificate in Computational Discovery and Engineering trains graduate students in computationally intensive research so they can excel in interdisciplinary HPC-focused research and product development environments. The certificate is open to all students currently pursuing Master’s or Ph.D. degrees at the University of Michigan.
  • The new Graduate Certificate in Data Science is focused on developing core proficiencies in data analytics: 1) Modeling — Understanding of core data science principles, assumptions and applications; 2) Technology — Knowledge of basic protocols for data management, processing, computation, information extraction, and visualization; 3) Practice — Hands-on experience with real data, modeling tools, and technology resources.

Interested students should attend ONE of these sessions:

Tuesday, April 14, 5-6 p.m., 3100 North Quad (Ehrlicher Room)

OR

Wednesday, April 15, 5-6 p.m., Cooley G906

Presenters:

  • Ken Powell, Arthur F. Thurnau Professor of Aerospace Engineering
  • Eric Michielssen, Professor of Electrical Engineering and Computer Science
  • Ivo Dinov, Associate Professor of Bioinformatics and Leadership and Effectiveness Science.

There will be time for questions and discussion.

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

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.

XSEDE15 Call for Participation deadline extended to April 6

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.

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

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.

Flux, Nyx outage scheduled for March 28

The ARC cluster Flux and Engineering cluster Nyx will be unavailable for jobs March 28th at 10:00pm. There is an emergency update to the ITS Value Storage systems on that date.
http://status.its.umich.edu/outage.php?id=93178

Flux and Nyx rely on Value Storage and thus will also not be available during that time.  We expect the outage to be finished quickly and any queued jobs will run as expected once the service is completed.

At the start of the outage, login and transfer nodes will be rebooted.  Users will be unable to login until after the service is restored.

Any jobs that request more walltime than remains until the start of the outage will be held and started after the systems return to service.

To find the maximum walltime you can request and have your job start prior to the outage can be found with our walltime calculator.

module load flux-utils
maxwalltime

Allocations that are active on that date will be extended by one day at no cost.

If you have any questions feel free to ask us at hpc-support@umich.edu
For immediate updates watch: https://twitter.com/umcoecac

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

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.

 

REMINDER: MICDE fellowships available — March 27 deadline

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.