LRZ-Newsletter Nr. 7/2011 vom 07.07.2011
Unsere Themen:
Impressum, Abbestellen des Newsletters und Archiv
Termine, Veranstaltungen, Allgemeines
Zwei TOP500-Höchstleistungsrechner am Leibniz-Rechenzentrum
Seit Ende Juni 2011 verfügt das Leibniz-Rechenzentrum der Bayerischen Akademie der Wissenschaften (LRZ) über ein weiteres System unter den 500 leistungsfähigsten Rechnern der Welt: „SuperMIG“ wurde installiert, das Migrationssystem für den Wechsel vom bisherigen Höchstleistungsrechner „HLRB II“ auf den nächsten, von IBM entwickelten Höchstleistungsrechner „SuperMUC“. Dieser wird im Frühjahr 2012 in Betrieb gehen.
In der „Top500-Liste“ rangiert SuperMIG auf Platz 166. Der derzeitige Höchstleistungsrechner SGI Altix 4700 lag 2007 auf Rang 10 und ist inzwischen auf Rang 198 zurückgefallen - eine im Höchstleistungsrechnen normale Entwicklung. SuperMIG ist ein IBM Blade Center System mit 8200 Rechenkernen und 52 Terabyte Hauptspeicher. Es wird später in den neuen Höchstleistungsrechner SuperMUC integriert werden, um dauerhaft Anwendern, die hohe Hauptspeicherkapazitäten benötigen, zur Verfügung zu stehen.
Weil SuperMIG wesentlich weniger Strom verbraucht als der HLRB II, soll er diesen so bald wie möglich ablösen. Deshalb wird das Migrationssystem ab Anfang August für die ersten Benutzer zur Verfügung stehen.
LRZ-Video "Grid Computing at LRZ"
Das Grid Computing Team hat ein Video veröffentlicht, das die Grid Tools und deren Benutzung im Forscheralltag vorstellt. Dank der Grid Sicherheitsinfrastruktur (GSI: Grid Security Infrastructure) kann ein Wissenschaftler auch von unterwegs sicher und einfach auf seine Daten zugreifen und die Berechnungen (Simulationsläufe) fernsteuern. Das Grid kümmert sich im Hintergrund um die Sicherheit und Zuverlässigkeit, sodass sich der Forscher ganz auf die Wissenschaft konzentrieren kann.
Autor: Helmut Heller
Vortrag von Christoph Witzig über SWITCHaai am 12.07.2011 am LRZ
Dr. Christoph Witzig (SWITCH, Zuerich) trägt am Dienstag, 12. Juli 2011, 13:00 c.t. im Hörsaal (H.E.009) des LRZ vor über
"SWITCHaai: The national Swiss Authentication and Authorization Infrastructure"
SWITCHaai is the Shibboleth-based identity federation of the Swiss academic and research sector. The project started 10 years ago as a cooperation between SWITCH, the national research and education network, and the Swiss universities. Today, 97% of all academic users and several hundred web-based services are part of the federation. The talk gives a technical overview of federated identity, describes the Shibboleth approach and the current technical, operational as well as organizational setup of SWITCHaai. It provides a perspective into the current development trends of secure access technologies, including extensions to Shibboleth as well as an outlook into other technologies such as OpenID and OAuth.
Christoph Witzig is the team leader of the middleware group at SWITCH, the national research and education network of Switzerland. He holds a degree in high energy physics from ETH Zurich and worked for several years at CERN and Brookhaven National Laboratory in Upton, NY. He held various positions in the commercial sector before joining SWITCH in spring 2005.
Anton Frank
Internet-Mitbegründer Stephen Crocker spricht am 27.09.2011 am LRZ
Stephen D. Crocker, Internet-Koryphäe und einer der Mitbegründer des World Wide Web, und neu gewählter ICANN-Vorsitzender wird am 27. September 2011 um 10:00 Uhr zu Gast sein im Hörsaal (H.E.009) des LRZ in Garching.
Thema seines Vortrags: "History of the Internet and a look at the future"
Stephen Crocker ist der Erfinder der "Request for Comments“ RFC (Internet Standards) und Verfasser des allerersten RFC. Er studierte an der University of California, Los Angeles (UCLA), wo er 1968 den Bachelor- und 1977 den PhD-Grad erwarb. Stephan Crocker hat seit deren Gründung an der Entwicklung der Internet-Community mitgewirkt. Als Student der UCLA in den 1960er Jahren, war Crocker an der Erstellung der ARPANET-Protokolle beteiligt, die den Grundstein für das heutige Internet bildeten.
Für diese Arbeit wurde Crocker 2002 mit dem Internet Award ausgezeichnet.
Nach seinem Studium bekleidete er in zahlreichen Unternehmen leitende Funktionen und betätigte sich als Firmengründer. So war er u.a. Programm-Manager bei der Advanced Research Projects Agency (ARPA), leitender Forscher am Information Sciences Institute der University of Southern California, Gründer und Direktor des Computer Science Laboratory der Firma The Aerospace Corporation und Vice President der Firma Trusted Information Systems. Im Jahr 1994 war er Mitgründer und Chief Technology Officer von CyberCash, Inc. und 1998 gründete er Executive DSL, einen Internet Service Provider. Im Jahr 1999 war er Mitbegründer und CEO der Longitude Systems. Derzeit ist Crocker CEO von Shinkuro Inc., einem Forschungs- und Entwicklungs-unternehmen.
Stephen Crocker war maßgeblich beteiligt an der Schaffung der ARPA "Network Working Group", in deren Umfeld später die IETF entstand. Er war Direktor des IETF-Sicherheitsbereichs, Mitglied des Internet Architecture Board (IAB), Vorsitzender des ICANN Security und Stability Advisory Committee, Mitglied des Vorstandes der ISOC und war in zahlreichen anderen Internet-Gremien vertreten.
Autor: Dieter Kranzlmüller
Am LRZ abzugebende Geräte
Die folgenden, funktionsfähigen Geräte sind am LRZ gegen Abholung abzugeben:
- SUN Fire V880, 8 * 900 MHz CPU, 32 GB RAM, 6 interne FC Platten je 73 GB, mit Einbauschienen und -schublade
- SUN Fire V880, 6 CPUs USIII 750MHz, 12 GB Ram, 12 FC-AL Disks intern mit je 36GB, mit Einbauschienen und -schublade
- SUN Fire V880, 4 CPUs Ultra Sparc III+ 900 MHz, 8MB Cache, 16* 512MB Ram= 8GB, 3 Power Supplies, 6*72 GB interne Platten, mit Einbauschienen und -schublade
- Fujitsu Siemens Blade BX300 mit 13 Blade-Einschüben, die jeweils mit 1 oder 2 GB RAM, 1 oder 2 Pentium-III-Prozessoren und 1 oder 2 Festplatten zu je 55 GB bestückt sind.
- 2 Management-Blades und 2 Switch-Blades
Allgemeine Beschreibung: http://www.fujitsu.com/downloads/AU/BX300_Datasheet.pdf
Bei Interesse wenden Sie sich bitte per E-Mail an sv@bib-bvb.de
Zentrale Systeme und Grid Computing
Joint European DCI Summer School 2011
The summer school will give insights into the distributed computing technologies provided by the European Middleware Initiative, the
Initiative for Globus in Europe, the European Desktop Grid Initiative and StratusLab. Based on the experience of DEGISCO and the European Grid Infrastructure, the school will also address organization, application porting, and user support in production infrastructures based on these technologies.
Date: 11-16 July 2011
Location: Budapest, Hungary
More information can be found here:
http://www.ige-project.eu/news/jointeuropeandcisummerschool2011 .
Autor: Helmut Heller
PRACE Summer School: Taking the Most Out of Supercomputers
PRACE, the Partnership for Advanced Computing in Europe organizes a summer school on 29 August to 1 September 2011 in Espoo, Finland. The school will be hosted by CSC - IT Center for Science Ltd and co-organized together by CSC and the PDC supercomputing centre in Stockholm, Sweden.
In this four-day event the participants will learn advanced parallel programming skills, which are necessary for taking the most out of the largest (Tier-0) supercomputers the PRACE Research Infrastructure is offering for European scientists and engineers.
The speaker list includes William Gropp (University of Illinois Urbana-Champaign), one of the key authors of MPI (Message Passing Interface) programming paradigm, and Rolf Rabenseifner (HLRS), one of the most renowned researchers of hybrid parallel programming models. In addition, the following topics will be covered: programming GPGPU clusters with CUDA+MPI, low-level single-core performance optimization as well as using the Python programming language in supercomputing.
The largest supercomputers in Scandinavia, i.e. the brand new Cray XE6 system at PDC and CSC's Cray XT4/XT5 system Louhi will be in disposal of the participants.
Attendance is free of charge for all academics affiliated to PRACE member countries. For further details and a registration please visit
http://www.csc.fi/courses/archive/prace-summer-school
Compact course: Iterative linear solvers and parallelization
Date: Monday, September 12 - Friday, September 16, 2011, 8:30-17:30
Location: LRZ Building, Garching/Munich, Boltzmannstr. 1
Contents: The focus of this compact course is on iterative and parallel solvers, the parallel programming models MPI and OpenMP, and the parallel middleware PETSc. Different modern Krylov Subspace Methods (CG, GMRES, BiCGSTAB...) as well as highly efficient preconditioning techniques are presented in the context of real life applications. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of iterative solvers, the Message Passing Interface (MPI) and the shared memory directives of OpenMP.
This course is organized by the University of Kassel, the high performance computing centre of Stuttgart (HLRS) and IAG.
For more details and application see our web page.
DEISA European-US Summer School on HPC Challenges
DEISA, Distributed European Infrastructure for Supercomputing Applications, has just announced the second EU/US summer school in computational sciences, to take place from Aug 7-12 at Lake Tahoe, California.
See http://www.deisa.eu/Summer-School
Participation/stay is free of charge, travel funds will be provided by DEISA/PRACE.
The NSF grant is aiming for 60 students, 35 from the US and 25 from Europe (just inverse to the summer school 2010 in Catania).
Applications are all through the US web page. The EU selection will be done by a committee already set up by DEISA and PRACE from six countries.
PRACE 1IP newsletter
The fourth issue of the PRACE 1IP newsletter is published.
Contents:
- A step forward in understanding electron transfer in organic solar cell materials
- HERMIT adds a Cray XE6 based capability machine to the PRACE Tier-0 infrastructure
- PRACE offers access to Europe’s fastest supercomputers
- PRACE grants 400 million compute hours on Tier-0 systems
- DEISA PRACE Symposium 2011 attracted over 200 participants from 26 countries
- 3rd PRACE Industrial Seminar bridges the gap between industry and academia
- PRACE at ISC’11
- Featured project
Link to the newsletter: http://www.prace-project.eu/documents/prace_1ip_nl_4.pdf
Stellenangebote des Leibniz-Rechenzentrums
Stellenangebot Scientific Computing Expert
Leibniz Supercomputing Centre (Leibniz-Rechenzentrum, LRZ) is part of the Bavarian Academy of Sciences and Humanities (Bayerische Akademie der Wissenschaften, BADW). LRZ is a central site for large scale data archiving and backup. It is an active player in the area of high performance computing for over 20 years and provides computing power on several different levels. It offers its services to universities in Germany and to publicly funded research institutions, like Max-Planck and Helmholtz Institutes. LRZ is currently preparing the installation of its new high-end system (SuperMUC) with a peak performance of 3 PetaFlop/s and more than 100,000 cores. When SuperMUC goes into operation it will be a world-leading platform for accelerating open scientific discovery.
For the support of the users and applications on the new system LRZ is looking for a
Scientific Computing Expert
The position is available immediately. Applications will be accepted until July 15th, 2011.
The successful applicant should fill the gap between day-to-day user support and in depth algorithmic research.
Required experience and skills
- PhD or university (post) graduate degree, diploma, master’s degree or equivalent in a scientifically oriented subject (computational science, mathematics, physics, chemistry, life sciences etc.)
- Demonstrated ability to lead scientific and technical efforts in HPC
- Excellent HPC skills, a broad knowledge of massively parallel high-performance algorithms, programming languages and libraries as well as performance analysis tools.
- Initiative, capacity for teamwork, and creativity.
- Excellent oral presentation and writing skills in German and English
Preferred Experiences
- Experience with large-scale parallel application development, debugging and performance tuning
- Experience in managing scientific projects and/or teams
Duties/Responsibilities
- Perform work in the application support team
- Optimization, scaling and performance improvement of strategic large-scale applications
- Performance analysis and benchmarking
- Identification and solution of user problems
- Keeping contact with scientific stakeholders and users
- Promotion and organization of scientific outreach activities through presentations and providing written materials
- Purchasing and maintaining third party applications and tools
- Writing of reports, grant applications, and documentation
- Stimulation of new developments in HPC
Due to its state-of-the-art computing facilities and its proximity to the Munich universities, LRZ offers a very stimulating and innovative environment. Progressive policies such as flexible working hours support the combination of work and family life.
We offer a pleasant and easygoing work environment in an internationally recognized HPC team with many years of experience that you can draw on for support, while also having ample opportunity to work independently and follow individual preferences.
Salary is determined by the German trade agreement for public service „Tarifvertrag für den öffentlichen Dienst der Länder“ (TV-L.) The position is time-limited, initially, to two years with the possibility of prolongation. Qualified women are strongly encouraged to apply. Severely disabled persons will be hired preferentially over others with equal qualifications. Due to export control of supercomputers restrictions for nationality may apply.
Please submit your application with resume (C.V.), ceretificates, reports and letters of recommendation by
July 15th, 2011
To:
Leibniz Supercomputing Centre
Mrs. Hannelore Apel
Keyword: HPC 2011/06
Boltzmannstr. 1
85748 Garching near Munich
Germany
Email: apel@lrz.de
Submissions via email are preferred. We kindly ask you to send your application as a single PDF document.
For further information please contact:
Dr. Horst-Dieter Steinhöfer
Group Leader HPC
Phone: +49 89 35831 8779
Email: steinhoefer@lrz.de
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
Bestellen und Abbestellen des Newsletters
Sie können den LRZ-Newsletter über unsere Webseite bestellen oder abbestellen.
Archiv
Frühere Ausgaben des LRZ-Newsletters finden Sie im Archiv.