Aug. 12 — The possibilities of making unprecedented discoveries through data-driven and data-intensive research are based on the existence of reusable, sustainable, accessible, organized and documented Big Data collections. For this reason, data management has taken a center stage in research practices across diverse domains. Even though it is clear that scalable resources and data management workflows are required to attain curated collections in a timely manner, there are significant knowledge barriers in using such scalable high-end resources. This hands-on workshop will (1) introduce the audience to scalable High Performance Computing (HPC) and high-end storage resources, and will (2) provide experience in setting their data management workflows on these resources.
The main target audience of this workshop is researchers, data curators, data managers, librarians and archivists who are in charge of lifecycle management, long-term preservation, and access of data. The key topics that will be covered during the workshop are: TACC resources, data transfer, data integrity, metadata extraction, file-migration, quality control, data classification and reorganization, and data preservation.
Texas Advanced Computing Center (TACC) resources will be used for the hands-on exercises. Participants are not required to have prior knowledge about HPC and will be provided accounts for accessing TACC resources during the workshop. Details regarding the usage of Stampede for the exercises covered during the workshop will be provided at a later date. In order to participate in the hands-on exercises, the workshop participants might want to bring their own laptop with the SSH Shell Client or Terminal available. The Windows OS users might find the instructions in this short video useful for installing and testing an SSH Shell Client on their laptop. The OS/X users should be able to SSH through the “Terminal” application that is already available on their laptop and are not required to do any installations.
This full-day workshop will be held on October 27, at the 2014 IEEE Big Data Conference. The location of the conference/workshop is:
- Hyatt Regency Bethesda
- One Bethesda Metro Center
- 7400 Wisconsin Ave
- Bethesda, Maryland 20814, USA
Morning Session (8:30 AM to 12:10 PM)
- 8:30 AM – 8:45 AM: Opening Remarks
- 8:45 AM – 9:15 AM: Invited Speaker #1 (topic to be announced)
- 9:15 AM – 9:45 AM: Invited Speaker #2 (topic to be announced)
- 9:45 AM – 10:15 AM: Overview of Big Data Management Challenges, by Maria Esteva (TACC)
- 10:15 AM – 10:45 AM: Overview of HPC environment and solutions to mitigate Big Data management challenges, by Ritu Arora (TACC)
- 10:45 AM – 11:00 AM: Break
- 11 AM – 12:10 PM: Introduction to Linux & TACC resources, hands-on session, by Ritu Arora (TACC)
Lunch (12:10 PM – 1:30 PM)
Afternoon Session (1:30 PM to 6:00 PM)
- 1:30 PM – 1:50 PM: Introduction to the test-case to be used for further exercises, by Maria Esteva (TACC)
- 1:50 PM – 2:50 PM: Hands-on exercises on data transfer, calculating checksum, and metadata extraction by Ritu Arora (TACC)
- 2:50 PM – 3:00 PM: Summary and discussion of the exercises and the results, by Ritu Arora (TACC) and Maria Esteva (TACC)
- 3:00 PM – 3:15 PM: Break
- 3:15 PM – 3:35 PM: Design and development of data management workflows on HPC resources, Ritu Arora (TACC)
- 3:35 PM – 6:00 PM: Improv and Hackathon Sessions, Ritu Arora (TACC) and Maria Esteva (TACC)
Ritu Arora received her Ph.D. in Computer and Information Science from the University of Alabama at Birmingham. She works as an HPC researcher and consultant at the Texas Advanced Computing Center (TACC). She also teaches in the Department of Statistics and Scientific Computing at the University of Texas at Austin. She has made significant contributions in the areas of developing abstractions for parallelizing legacy applications and application-level checkpointing. Currently, Ritu is providing consultancy on automating Big Data workflows on national supercomputing resources. Her areas of interest and expertise are HPC, fault-tolerance, domain-specific languages, workflow automation, and big data management.
Maria Esteva has a Ph.D. in Information Science from the University of Texas at Austin. Her research addresses data collections’ lifecycle management and long-term preservation. Her research interests include the use of visual analytics and data analysis methods for the purposes of organizing and assessing the condition of large-scale digital collections and the use of HPC to aid digital collections’ long-term curation. She has presented papers on Digital Curation, Archiving, and Digital Humanities and at the Joint Conference on Digital Libraries. As a member of the Data Management and Collections team at TACC, she works with researchers in many fields, designing and implementing data collection architectures and workflows.
Register for the workshop here. If you are only interested in attending the workshop at the conference, then you can register for just one day at the cost of $300.
With the support from NSF, travel grants are now available to support the participation of students from underrepresented groups in the workshop and in the 2014 IEEE Big Data Conference. Consideration will be given to the applicants from groups that have been traditionally underrepresented in HPC, and Big Data. These groups include women, African Americans, Hispanics, Native Americans, Alaska Natives, Pacific Islanders and people with disabilities. The travel grant will cover air-fare, hotel, workshop/conference registration fees, ground transportation, and per diem for the selected applicants. There are mentoring activities planned for the selected students before and after the workshop/conference. The application deadline is August 26, 2014, 5:00 PM CST. To apply for the travel grant please, click the link for the Google Form or for the interactive pdf form. If you are using the pdf form, please email it to Ritu Arora at email@example.com.
Source: Texas Advanced Computing Center