Document acties

First International Workshop on HPC User Support Tools (HUST-14)

General information

Friday 21 November 2014

New Orleans, LA, USA

In cooperation with ACM Special Interest Group on High Performance Computing (SIGHPC)

Held in conjunction with SC14: The International Conference on High Performance Computing, Networking, Storage and Analysis

SIGHPC logo SC14 logo

Scope

Researchers pushing the boundaries of science and technology are an existential reason for supercomputing centres. In order to be productive, they heavily depend on HPC support teams, who often struggle to adequately support the researchers.

Recent surveys have pointed out that there is an abundant lack of collaboration between HPC support teams all around the world, even though they are frequently facing very similar problems in order to provide end users with the tools and services they require.

The first International Workshop on HPC User Support Tools (HUST-14) aims to bring together all parties involved, i.e., system administrators, user support team members, tool developers, policy makers and end users, to discuss these issues and bring forward solutions, either existing ones or new ones the community should come up with. The workshop provides a platform to present tools, share best practices and exchange ideas that help streamline HPC user support. This in turn can prevent HPC support teams from re-inventing (existing) solutions time and again.

Program

HUST-14 is held in conjunction with SC'14 in New Orleans (USA), on Friday Nov 21st 2014, 8.30am - 12.00pm.

Detailed program:

  • 8.30am - 9.00am: Parallel Post-processing with MPI-Bash - Scott Pakin (LANL) [PDF: paper - slides]
  • 9.00am - 9.30am: Comprehensive Resource Use Monitoring for HPC Systems with TACC Stats - Richard Evans (TACC), Bill Barth (TACC), James Browne (UT Austin), Robert Deleon (Univ. at Buffalo), Thomas Furlani (Univ. at Buffalo), Steven Gallo (Univ. at Buffalo), Matthew Jones (Univ. at Buffalo) and Abani Patra (Univ. at Buffalo) [PDF: paper - slides]
  • 9.30am - 10.00am: Self-Service Queue and User Management in Shared Clusters - Kevin Colby (Purdue Univ.), Daniel Dietz (Purdue Univ.), Preston Smith (Purdue Univ.) and Donna Cumberland (Purdue Univ.) [PDF: paper - slides]

(10.00am - 10.30am: coffee break)

  • 10.30am - 11.00am: User Environment Tracking and Problem Detection with XALT - Kapil Agrawal (UT Knoxville), Mark R. Fahey (NICS), Robert McLay (TACC) and Doug James (UT Austin) [PDF: paper - slides]
  • 11.00am - 11.30am: Modern Scientific Software Management Using EasyBuild and Lmod - Markus Geimer (JSC), Kenneth Hoste (HPC-UGent) and Robert McLay (TACC) [PDF: paper - slides]
  • 11.30am - 12.00pm: interactive discussion on topics concerning user support

Topics

Topics of interest include, but are not limited to:

  • defining and customising the user environment
  • software build and installation tools
  • performance analysis tools
  • workflow and pipeline tools
  • novel environments: cloud, etc.
  • supporting Hadoop or other Big Data tools and frameworks
  • establishing baseline configuration efforts for HPC
  • software development/system testing
  • documentation: creating, maintaining and updating

Submissions

We invite authors to submit original, high-quality work with sufficient background material to be clear to the HPC community. Papers should be submitted in PDF format and should not exceed 10 pages including tables, figures and appendices, but excluding references. They should be formatted according to the standard SC14 format, i.e., the double-column IEEE format for Conference Proceedings (IEEEtran LaTeX Class (template) V1.8 packages and IEEEtran V1.12 BibTeX (bibliography)). Similar to the SC14 policy, margins and font sizes should not be modified. We kindly refer authors to the necessary templates.

All submissions should be made electronically through the Easychair website. Submissions must be double blind, i.e., authors should remove their names, institutions or hints found in references to earlier work. When discussing past work, they need to refer to themselves in the third person, as if they were discussing another researcher's work. Furthermore, authors must identify any conflict of interest with the PC chair or PC members.

Proceedings will be published in both IEEE Xplore and the ACM Digital library through collaboration with ACM SIGHPC.

Important dates

  • Call for papers: Wednesday May 14th 2014
  • Submission open: Sunday June 1st 2014
  • Workshop papers due: Sunday August 17th 2014 (AOE) (extended deadline, no further extensions!)
  • Notification of acceptance: Wednesday October 1st 2014
  • Camera-ready papers due: Monday October 13th 2014
  • Workshop date: Friday November 21st 2014

Contact

For questions and remarks related to the HUST workshop, please contact kenneth.hoste@ugent.be .

Organizers

  • Christopher Bording, iVEC, Australia
  • Andy Georges, HPC Infrastructure Unit at Ghent University, Belgium
  • Kenneth Hoste, HPC Infrastructure Unit at Ghent University, Belgium

General Chair

Christopher Bording

Program Chair

Andy Georges

Program Committee

  • Jordi Blasco, New Zealand eScience Infrastructure (NeSI), New Zealand
  • Christopher Bording, iVEC, Australia
  • Koen De Bosschere, Ghent University & HiPEAC network of excellence, Belgium
  • Todd Gamblin, Lawrence Livermore National Laboratory (LLNL), USA
  • Markus Geimer, Jülich Supercomputing Centre (JSC), Germany
  • Vera Hansper, Victorian Life Sciences Computing Initiative (VLSCI), Australia
  • Kenneth Hoste, Ghent University, Belgium
  • Olli-Pekka Lehto, CSC — IT Center for Science Ltd, Finland
  • John Linford, ParaTools, USA
  • Robert McLay, Texas Advanced Computing Center (TACC), USA
  • Dane Skow (Dane Skow Associates), USA