Project updates


Exascale OS/R Technical Council Position Papers

posted Jul 27, 2012, 6:00 PM by Eric Van Hensbergen

All submitted position papers are posted at https://blizzard.mcs.anl.gov/display/exaosr/Position+Papers

OS/R Call For Position Papers

posted Jun 21, 2012, 12:52 PM by Eric Van Hensbergen

The Department of Energy Office of Science and the National Nuclear Security Administration has asked a technical council to develop a research agenda to address the challenges of Operating Systems and Runtime Software (OS/R) for next-generation, Exascale systems. The research challenges associated with Exascale systems have been articulated in numerous reports.  It is clear that new approaches are needed to address these tremendous challenges. The OS/R technical council will produce a report in November 2012 that summarizes the key challenges and important research topics that must be addressed.  As part of the process, the council solicits community input, in the form of position papers that describe novel research approaches for exascale OS/R. Responsive submissions will be made public via the OS/R TC website (http://collab.mcs.anl.gov/display/exaosr) and portions may be included in the final report. The technical council will review submitted position papers and invite selected contributors to participate in a workshop to be held in October 2012.

Short 2 page papers are due July 13, 2012.  For more information, please see the website: http://collab.mcs.anl.gov/display/exaosr and follow the call for position papers link on the left.

ROSS 2012 Call For Participation

posted Jan 31, 2012, 8:20 AM by Eric Van Hensbergen

International Workshop on Runtime and Operating Systems for Supercomputers 

In collaboration with ACM SIGHPC 
-------------------------------- 
Held in conjunction with ICS 2012, Venice, Italy, June 25-29, 2012 

==================================
http://www.mcs.anl.gov/events/workshops/ross/2012/ 
==================================

The complexity of node architectures in supercomputers increases as we 
cross petaflop milestones on the way towards Exascale. Increasing 
levels of parallelism in multi- and many-core chips and emerging 
heterogeneity of computational resources coupled with energy and memory 
constraints force a reevaluation of our approaches towards operating 
systems and runtime environments. 

The ROSS workshop, to be held as a full-day meeting at the ICS 2012 
conference in Venice, Italy, focuses on principles and techniques to 
design, implement, optimize, or operate runtime and operating systems 
for supercomputers and massively parallel machines. 

TOPICS OF INTEREST: 
------------------- 

- OS and runtime system scalability on many-node and multi/many-core 
systems 
- specialized OSs for Supercomputing 
- distributed/hybrid/partitioned OSs and runtime systems for 
Supercomputing 
- fault tolerance 
- system noise analysis and prevention 
- interaction between middleware, runtime system, and the OS 
- I/O resource management and forwarding 
- parallel job startup 
- memory management and emerging memory technologies 
- real-time considerations for Supercomputing 

SCHEDULE AND SUBMISSION PROCEDURE: 
---------------------------------- 

Submission deadline: March 30, 2012 
Author notification: May 7, 2012 
Final papers due: May 25, 2012 
Workshop date: To be announced (held between June 25-29, 2012) 

The ROSS workshop proceedings will be published electronically along 
with the ICS conference proceedings via the ACM Digital Library. 
Submitted manuscripts should be formatted using the ACM SIG proceedings 
alternate format. Extensive documentation can be found at the ACM site 
(http://www.acm.org/sigs/publications/proceedings-templates). The 
maximum length is 8 pages. All papers must be in English. Please visit 
the workshop website for further instructions and the submission link. 

The best papers of the workshop will be considered for inclusion in a 
special issue of International Journal of High Performance Computing 
Applications (IJHPCA). 

WORKSHOP CHAIRS: 
---------------- 

Torsten Hoefler, University of Illinois at Urbana-Champaign, USA 
Kamil Iskra, Argonne National Laboratory, USA 

PROGRAM COMMITTEE: 
------------------ 

George Almasi, IBM Research, USA 
Henri Bal, Vrije Universiteit Amsterdam, Netherlands 
Pete Beckman, Argonne National Laboratory, USA 
Patrick Bridges, University of New Mexico, USA 
Ron Brightwell, Sandia National Laboratories, USA 
Franck Cappello, INRIA, France / UIUC, USA 
Bronis R. de Supinski, Lawrence Livermore National Laboratory, USA 
Christian Engelmann, Oak Ridge National Laboratory, USA 
Markus Geimer, Juelich Supercomputing Centre, Germany 
Roberto Gioiosa, Barcelona Supercomputing Center, Spain 
Yutaka Ishikawa, University of Tokyo, Japan 
Larry Kaplan, Cray, Inc., USA 
Ron Minnich, Google, Inc., USA 
Bernd Mohr, Juelich Supercomputing Centre, Germany 
Raymond Namyst, University of Bordeaux 1, France 
Rob Ross, Argonne National Laboratory, USA 
Pascale Rosse-Laurent, Bull, France 
Martin Schulz, Lawrence Livermore National Laboratory, USA 
Jesper Larsson Traeff, University of Vienna, Austria 
Robert Wisniewski, IBM Research, USA 

Contact us at ross-2012@easychair.org if you have any questions.

New Xstack Programming Challenges, Runtime Systems and Tools FOA Announced

posted Nov 22, 2011, 6:04 PM by Eric Van Hensbergen   [ updated Nov 22, 2011, 6:23 PM ]

"The Office of Advanced Scientific Computing Research (ASCR) of the Office of Science (SC), 
U.S. Department of Energy (DOE), hereby invites applications for basic research that represents 
significant advances in programming models, languages, compilers, runtime systems and tools 
that address fundamental challenges related to the system software stack for Exascale computing 
platforms (X-Stack).   

Programming models, languages, and related technologies that have sustained High Performance 
Computing (HPC) application software development for the past decade are inadequate for 
Exascale era computers. The significant increase in complexity of Exascale platforms due to 
energy-constrained, billion-way parallelism, with major changes to processor and memory 
architecture, requires new energy-efficient and resilient programming techniques that are 
portable across multiple future machine generations. We expect to make research investments 
that address fundamental Exascale challenges, while offering a transition path for existing 
scientific applications to fully explore the challenges and rewards of Exascale platforms. 
Exascale programming challenges and strategies were identified in the ASCR Exascale 
Programming Challenges Workshop and carefully captured in the workshop report
Challenges and strategies related to tools for Exascale platforms were identified in the ASCR 

Sought are complete solutions that will address multiple components of the system software 
stack and that will have the following characteristics: 
• Scalability: enable applications to strongly scale to Exascale levels of parallelism;  
• Programmability: clearly reduce the burden we are placing on high performance 
programmers; 
• Performance Portability:  eliminate or significantly minimize requirements for porting to 
future platforms; 
• Resilience: properly manage fault detection and recovery at all components of the 
software stack; and 
• Energy Efficiency:  maximally exploit dynamic energy saving opportunities, leveraging 
the tradeoffs between energy efficiency, resilience, and performance.  
We encourage solutions that involve radically new approaches to programming Exascale 
applications and algorithms. New approaches are required in order to address the complexities of 
Exascale systems.   It is important to demonstrate the viability of such solutions in a broad high 
performance programming context by showing how the proposed solution: 
• interoperates with existing programming environments based on the MPI+X model, so 
that a smooth migration path is enabled, and/or 
• enables the automatic transformation of applications (possibly with users in the loop) 
from the “old” programming environment to the “new” one, such that the transformations 
are semantics and performance preserving." 

Computer Science Notices: (Link to the ASCR CS web page)
 •  2012 X-Stack: Programming Challenges, Runtime Systems, and Tools
   ·Issued: 11/22/2011
   ·Letter of Intent (Strongly Encouraged) Due Date: December 19, 2011
   ·Application Due Date: February 6, 2012, 11:59pm Eastern Time
   ·Universities, Industry, etc. Announcement: DE-FOA-0000619.  
   ·Laboratories Announcement: LAB 12-619

ASCR Exascale Research PI Meeting 10/11/11-10/13/11

posted Aug 31, 2011, 7:57 AM by Eric Van Hensbergen   [ updated Sep 19, 2011, 7:09 AM ]

http://exascaleresearch.labworks.org/ascrOct2011/ascr

Goals & Expected Outcomes

  1. Participants understand the DOE Exascale vision and preliminary plans.
  2. Participants are aware of what was learned during the summer workshops on Programming Challenges and Advanced Architectures and they understand the impact of that information on their own research efforts.
  3. Participants have greater understanding of the outcomes from the NNSA Exascale Roadmapping Workshops and the potential for collaboration between the ASCR and NNSA research communities.
  4. Participants understand the role of the ASCR Co-Design Centers in the development of Exascale systems, their respective individual roles in the Exascale co-design process, and how that process will affect their ASCR-supported research.
  5. Participating computer scientists and application scientists have greater understanding about the topic of uncertainty quantification and research in this area.

General Discussion Mailing List

posted Apr 26, 2011, 11:17 AM by Eric Van Hensbergen   [ updated Apr 26, 2011, 11:26 AM ]

I've created a general discussion mailing list for the x-stack program.  Everyone is welcome to subscribe.

You can self-subscribe here:

Call for Papers - ROSS 2011

posted Feb 4, 2011, 7:45 AM by Eric Van Hensbergen   [ updated Feb 4, 2011, 7:52 AM ]

The ROSS (International Workshop on Runtime and Operating Systems for Supercomputers) workshop, to be held as a full-day meeting at the ICS 2011 conference in Tucson, Arizona, focuses on principles and techniques to design, implement, optimize, or operate runtime and operating systems for supercomputers and massively parallel machines.

TOPICS OF INTEREST:

- OS and runtime system scalability on many-node and multi/many-core systems
- specialized OSs for Supercomputing
- distributed/hybrid/partitioned OSs and runtime systems for Supercomputing
- fault tolerance
- system noise analysis and prevention
- interaction between middleware, runtime system, and the OS
- I/O resource management and forwarding
- parallel job startup
- memory management and emerging memory technologies
- real-time considerations for Supercomputing

SCHEDULE AND SUBMISSION PROCEDURE:

Submission deadline:    March 21, 2011
Author notification:    April 18, 2011

The ROSS workshop proceedings will be published electronically along with
the ICS conference proceedings via the ACM Digital Library. Submitted
manuscripts should be formatted using the ACM SIG proceedings alternate
format. Extensive documentation can be found at the ACM site
(http://www.acm.org/sigs/publications/proceedings-templates). The maximum
length is 8 pages. All papers must be in English. Please visit the workshop
website for further instructions and the submission link.

The best papers of the workshop will be considered for inclusion in a
special issue of International Journal of High Performance Computing
Applications (IJHPCA).

WORKSHOP CHAIRS:

Kamil Iskra          Argonne National Laboratory, USA
Torsten Hoefler      University of Illinois at Urbana-Champaign, USA

PROGRAM COMMITTEE:

Henri Bal, Vrije Universiteit Amsterdam, Netherlands
Pete Beckman, Argonne National Laboratory, USA
Patrick Bridges, University of New Mexico, USA
Ron Brightwell, Sandia National Laboratories, USA
Luiz De Rose, Cray, Inc., USA
Christian Engelmann, Oak Ridge National Laboratory, USA
Yutaka Ishikawa, University of Tokyo, Japan
Ron Minnich, Sandia National Laboratories, USA
Rob Ross, Argonne National Laboratory, USA
Martin Schulz, Lawrence Livermore National Laboratory, USA
Thomas Sterling, Louisiana State University, USA
Bronis de Supinski, Lawrence Livermore National Laboratory, USA
Jesper Larsson Traeff, University of Vienna, Austria
Robert Wisniewski, IBM Research, USA


Contact us at ross2011@easychair.org if you have any questions.

ASCR Exascale Kickoff Meeting

posted Feb 4, 2011, 7:34 AM by Eric Van Hensbergen   [ updated Feb 4, 2011, 7:48 AM ]

Project teams have been invited to the ASCR Exascale Research Kickoff Meeting in San Diego, March 7-11.

Information about the upcoming kickoff meeting can be found at http://exascaleresearch.labworks.org.   Please note that our group lodging block is being held by the hotel through THURSDAY, FEBRUARY 10, so be sure to make your lodging reservations soon.  Additional materials will continue to be added to the website as they become available (e.g., detailed agenda, online registration, research project team handouts and presentations, etc.).

More Content Soon (with your help)

posted Jun 15, 2010, 8:48 AM by Eric Van Hensbergen   [ updated Feb 4, 2011, 7:55 AM ]

We are busy trying to set up this site as a nexus for information on exascale software research.  Please bear with us.

If any x-stack project would like edit access to this site or would like to hang a project web site off of the xstack.org room domain, please contact ericvh@gmail.com.

1-9 of 9