LRZ-Newsletter Nr. 1/2010 vom 12.01.2010
Unsere Themen:
-
Termine, Veranstaltungen, Allgemeines
-
Zentrale Systeme und Grid Computing
- Courses and Tutorials for High Performance Computing (Winter 2009/2010)
- DECI-6 Call for HPC project proposals is open
- Call for Proposals for PRACE Prototype testing
- The eighth issue of the PRACE newsletter has been published
- 5th VI-HPS Tuning Workshop
- HPC Software: Allinea DDT workshop on April 13, 2010
-
Impressum, Abbestellen des Newsletters und Archiv
Termine, Veranstaltungen, Allgemeines
Hinweise zur Verwendung von Thunderbird 3
Seit dem 09.12.2009 ist der Mozilla-Mailclient Thunderbird in der Version 3.0 freigegeben. Die neue Version bietet zwar einige nützliche neue Funktionen, hat aber teilweise fragwürdige Voreinstellungen, die bei der Umstellung für Probleme sorgen können. Wenn Sie beabsichtigen, die Version 3.0 zu verwenden, lesen Sie bitte vorher unsere Hinweise zur Verwendung von Thunderbird 3.
Autor: Ado Haarer
LRZ in Garching bietet künftig keine verlängerten Öffnungszeiten am Abend mehr an
Die am alten Standort in der Innenstadt bewährten Abendöffnungszeiten haben wir zunächst auf den neuen Standort Garching übertragen. Nach gut 3 Jahren stellen wir fest, dass die Nutzung der Arbeitsplätze im LRZ-Gebäude ab etwa 17 Uhr nur noch sehr gering ist. Das LRZ stellt angesichts der Aufwände für diese wenig nachgefragte Dienstleistung dieses Angebot daher probeweise ein.
Ab dem neuen Jahr 2010 ist das LRZ-Gebäude am Standort Garching daher nur noch
von 7:30 Uhr bis 18:00 Uhr (freitags bis 17:00 Uhr) geöffnet.
Es gibt dann keine Abendöffnungszeit mehr.
Der Betrieb in den Nutzerräumen und -anlaufstellen endet jeweils bereits eine Viertelstunde vor der angegebenen Schließung des Gebäudes.
Wir bitten um Ihr Verständnis für diese Maßnahme, die wir auch im Interesse sparsamen Wirtschaftens ergreifen müssen. Unsere Kunden haben die Möglichkeit, sich an den Arbeitsplatzrechner-Pools ihres Instituts Rechen- und Präsenzberechtigung geben zu lassen.
Talk: How can Tools Keep up with the Growing Size of HPC Systems?
Several high-end HPC cluster systems have already surpassed the 100,000 core mark and machines with over 1,000,000 cores are on the horizon. While this promises unprecedented compute power and opens the door for new scientific discovery through advanced simulation, it comes at the price of increased complexity in both hardware and software. To deal with this complexity, users will require programming environments that scale with the machine. This includes performance analysis and debugging tools, which need to be capable of collecting, analyzing, and presenting data from all cores in a system. To satisfy these requirements we can not simply scale existing tool solutions that work on few hundred nodes; instead we require a set of new techniques that are explicitly designed and optimized for scale.
In this talk it will be shown how this challenge is addressed in the ADEPT project at LLNL. In particular, focus will be on three tool sets that demonstrate different aspects necessary to achieve scalable tools:
- the use of hierarchical communication and online analysis in the Stack Trace Analysis Tool (STAT),
- the need for application specific rapid tool prototyping, as supported by the P^nMPI infrastructure; and
- the design of a component infrastructure based on the OpenSpeedShop tool set.
Lecturer: Dr. Martin Schulz, CASC@Lawrence Livermore National Laboratory (LLNL), Livermore, USA
Date: Fri, Jan 15, 2010, 13:00 s.t.
Location: LRZ, Boltzmannstr. 1, Seminarraum 1 (H.E.008)
Short Bio of Dr. Martin Schulz
Autor: Matthias Brehm
Talk: QPACE - A massively parallel supercomputer based on PowerXCell 8i processors and network FPGAs
QPACE (QCD Parallel Computing on the Cell) is the most energy-efficient supercomputer in the world. QPACE was developed by an academic consortium of universities and research centers as well as the German IBM research and development center in Böblingen within the framework of a state-sponsored research association. Within the consortium, the development effort was led by the University of Regensburg, while the research centers DESY and Jülich also assumed central responsibilities.
Prof. Tilo Wettig will explain in his talk the background of the project as well as the QPACE architecture its unique features.
Date: Feb 2, 2010.
Time: 14:00 s.t.
Location: LRZ H.0.008 (Hörsaal)
Zentrale Systeme und Grid Computing
Courses and Tutorials for High Performance Computing (Winter 2009/2010)
Introduction to the PGAS languages UPC and CAF
Wed Jan 20, 2010 9:00-18:00
Einführung in Virtual Reality
Fri Jan 22, 2010, 10:00-12:00
Programming with Fortran
Mon Feb 8 - Fri Feb 12, 2010, 9:00-18:00
Scientific 3D Animation with Blender
Thu Feb 18, 2010 – Fri Feb 19, 2010
Parallel Programming of High Performance Systems
Mon March 8 - Fri Mar 12, 2010, 9:00-18:00
Advanced Topics in High Performance Computing
Mon Mar 22 - Wed Mar 24, 2010, 9:00-18:00
Introduction to Molecular Modeling on Supercomputers
Wed Apr 14 – Thu Apr 15, 2010
See details and link to regisgtration see:
http://www.lrz-muenchen.de/services/compute/courses
Autor: Matthias Brehm
DECI-6 Call for HPC project proposals is open
The DEISA Extreme Computing Initiative (DECI) is a scheme through which European computational scientists can apply for single-project access to world-leading computational resources in the European HPC infrastructure, operated by DEISA, for a period of up to 10 months. DECI enables European researchers to obtain access to the most powerful national computing resources in Europe, regardless of their country of origin or work and to enhance DEISA's impact on European science and technology at the highest level.
Through an open, competitive call, a number of capability computing projects will be selected on the basis of innovation and scientific excellence. These projects must deal with complex, demanding, innovative simulations that would not be possible without the DEISA infrastructure, and which would benefit from the exceptional resources of the Consortium. The closing date of this call is February 16th, 2010. Proposals selected under this call will be given access to the infrastructure for applications enabling from 1 July 2010 and for production runs from October 1st, 2010 to April 30th, 2011.
The official announcement of the call is found under www.deisa.eu/science/deci/deci-call-for-proposals2010.
For an overview of DEISA and DECI, see the HPCWire article "DEISA Call for HPC Proposals Is Now Open" from Dec. 4th, 2009. For a full view of background information, including the Applications Task Force (including a list of centers involved; note the contributions from Garching also in terms of platforms), all running and completed projects, benchamrking and other issues, start from www.deisa.eu/science.
In addition to offering access to computing resources, DEISA offers applications-enabling assistance from experts at the leading European HPC centres to enable projects to be run on the most appropriate platforms in the DEISA consortium. For advice and assistance on proposal preparation and submission please contact deisa-support@lrz.de.
Projects supported by DECI will be chosen on the basis of innovation potential, scientific excellence and relevance criteria. Priority will be given to proposals that promote collaborative research, either at a cross- national or cross-disciplinary level. Further, proposals from researcher who have yet to benefit from DECI compute and applications enabling resources may be given preference.
Autor: Kamen Beronov
Zurück zum Inhaltsverzeichnis
Call for Proposals for PRACE Prototype testing
PRACE, the Partnership for Advanced Computing in Europe, invites researchers from academia and industry to test applications on prototypes of potential future HPC Petascale systems. PRACE partners have installed six systems of different architectures that are now available for assessment. For more details, please see the complete Call for Proposals for PRACE Prototype testing
The eighth issue of the PRACE newsletter has been published
Please find the newsletter at:
http://www.prace-project.eu/documents/prace_nl_8.pdf
5th VI-HPS Tuning Workshop
Date: Monday, March 8, 9:00 - Wednesday, March 10, 2010, 15:00
Location:
Technische Universität München
Fakultät für Mathematik und Informatik
Boltzmannstr. 3 (next building to LRZ)
85748 Graching
Contents:
The Chair of Computer Architecture (LRR) of the Techische Universität München and the VI-HPS (Virtual Institute - High Productivity Supercomputing) organize a workshop on tuning of parallel programs using tools developed by the VI-HPS.
The workshop aims at experienced users who develop, optimize, and port larger programs. It is expected that these users can pass the obtained knowledge to their working groups.
Classroom capacity is limited, therefore priority will be given to applicants with codes already running on HPC systems. Participants are therefore encouraged to prepare their own MPI, OpenMP and hybrid OpenMP/MPI parallel application code(s) for analysis.
Participants are expected to use their own notebook computers for the first day tutorial using a Live-DVD for hands-on exercises: it may be possible to arrange alternatives for those who don't have access to an x86-compatible notebook computer with DVD drive, if the organizers are informed in advance.
The workshop covers the following tools:
MARMOT is a free correctness checking tool for MPI programs developed by TUD-ZIH and HLRS.
PAPI is a free library interfacing to hardware performance counters developed by UTK-ICL, used by Periscope, Scalasca, VampirTrace, and multiple other tools.
Periscope is a prototype automatic performance analysis tool using a distributed online search for performance bottlenecks being developed by TUM.
Scalasca is an open-source toolset developed by JSC that can be used to analyze the performance behaviour of parallel applications and automatically identify inefficiencies.
Vampir is a commercial framework and graphical analysis tool developed by TUD-ZIH to display and analyze trace files.
VampirTrace is an open-source library for generating event trace files which can be analyzed and visualized by Vampir.
Language: English
More information: see: http://www.vi-hps.org/vi-hps-tw5/
Contact for Registration: petkovve_at_in.tum.de
Autor: Matthias Brehm
HPC Software: Allinea DDT workshop on April 13, 2010
A workshop on debugging serial and parallel applications with the DDT debugger by Allinea (www.allinea.com) has been scheduled for April 13, 2010. LRZ thanks Allinea for sponsoring this event and in particular for delegating Mark O'Connor as a tutor.
More details on the event are available on the HPC course page.
Since only a limited number of seats (32) are available in the course room, we must ask you to register for this workshop. Please choose the link for HDDT1S10); deadline for registration is March 29, 2010.
Autor: Reinhold Bader
Impressum
Herausgeber:
Leibniz-Rechenzentrum der Bayerischen Akademie der Wissenschaften
Anschrift:
Leibniz-Rechenzentrum der Bayerischen Akademie der Wissenschaften
Boltzmannstraße 1
D-85748 Garching
Telefon: +49-89-35831-8000
Telefax: +49-89-35831-9700
E-Mail: lrzpost_AT_lrz.de
Redaktion: Dr. Ludger Palm
Abbestellen des Newsletters
Wenn Sie diese Informationen nicht mehr erhalten wollen, tragen Sie sich aus dieser Liste aus, indem Sie
- die URLhttp://www.lrz-muenchen.de/majordomo?LIST=newsletter&CMD=unsubscribe aufrufen und dann die Mailadresse angeben, mit der Sie in die Liste eingetragen sind oder
- eine Email an majordomo@lists.lrz-muenchen.de schicken, in deren Body folgendes Kommando enthalten ist: unsubscribe newsletter <Mailadresse> .
Bei Problemen mit dem Austragen wenden Sie sich bitte an den Listenverwalter newsletter-owner@lists.lrz-muenchen.de .
Archiv
Frühere Ausgaben des LRZ-Newsletters finden Sie im Archiv.