LRZ-Newsletter Nr. 05/2018 vom 03.05.2018

Unsere Themen:


Termine, Veranstaltungen, Allgemeines


Doppelerfolg beim Deutschen Rechenzentrumspreis

Das Leibniz-Rechenzentrum (LRZ) war beim Deutschen Rechenzentrumspreis doppelt erfolgreich: In der Kategorie "Datacenter Klimatisierung und Kühlung" konnte das LRZ mit zwei Lösungen aus dem Bereich der Wasserkühlung punkten und gemeinsam mit den Partnern Fahrenheit und MEGWARE die Plätze 1 und 2 für sich verbuchen. Das LRZ setzte sich damit in der meistumkämpften Kategorie beim diesjährigen Wettbewerb mit insgesamt 51 Einreichungen durch. Fahrenheit und Megware haben für das LRZ Lösungen entwickelt, mit denen sich deutlich effizienter kühlen lässt und die die bestehenden Wasserkühltechnologien ergänzen und weiterentwickeln. Bei Fahrenheit handelt es sich um ein Adsorptionskühlsystem zur Nutzung der Rechnerabwärme. Dies wird z.B. eingesetzt beim künftigen nationalen Höchstleistungsrechner SuperMUC-NG (Next Generation). CoolMUC-3, realisiert von Megware, überzeugte mit seiner 100% Warmwasserkühlung auch von Komponenten wie Switches oder Netzteilen.

Weitere Informationen finden Sie hier: BAdW Pressemitteilung: Leibniz-Rechenzentrum erneut für Energieeffizienz ausgezeichnet

Kontakt: Sabrina Eisenreich (eisenreich_AT_lrz.de )

Zurück zum Inhaltsverzeichnis


LRZ Mitglied im VI-HPS

Seit April 2018 ist das Leibniz-Rechenzentrum (LRZ) offizielles Mitglied des Virtual Institutes – High Productivity Supercomputing (VI-HPS). Das VI-HPS Konsortium hat sich zum Ziel gesetzt, Entwicklern von komplexen Simulationscodes Werkzeuge an die Hand zu geben, mit denen die Codes auf ihre Qualität überprüft werden können und Wege aufgezeigt werden, um die Leistungsfähigkeit kontinuierlich zu steigern. Mit seiner Mitgliedschaft möchte das LRZ seinen Beitrag in dieser Community weiter steigern und seine Expertise noch aktiver einbringen. Derzeit fokussieren die LRZ-Aktivitäten vorrangig auf das Tool “Callgrind”, das seit kurzem am LRZ gepflegt und weiterentwickelt wird. Callgrind hilft insbesondere, Flaschenhälse beim Zugriff auf Daten zu identifizieren und zu beseitigen. Die beliebten Workshops und Trainings in diesem Bereich, wie z.B. die Ausrichtung der VI-HPS "Tuning Workshops", bietet das LRZ natürlich weiterhin an.

Über VI-HPS: www.vi-hps.org

Kontakt: Josef Weidendorfer (Josef.Weidendorfer_AT_lrz.de)

Zurück zum Inhaltsverzeichnis


Prof. Dr. Xiaoxiang Zhu wins the 2018 PRACE Ada Lovelace Award for HPC

We are delighted to announce that Prof. Dr. Xiaoxiang Zhu, German Aerospace Center (DLR) and Technical University of Munich (TUM), Germany, is the winner of the 2018 PRACE Ada Lovelace Award for HPC for her outstanding contributions and impact on HPC in Europe. She is the professor for Signal Processing in Earth Observation (SiPEO) at TUM and head of Department EO Data Science at the Remote Sensing Technology Institute of DLR. Sinead Ryan, Chair of the PRACE Scientific Steering Committee will present the award to Xiaoxiang Zhu on 31 May 2018 at PRACEdays18, the central event of the European HPC Summit Week in Ljubljana, Slovenia. Prof. Zhu currently uses two allocations of 26 and 20 million core hours, respectively, on SuperMUC of the Leibniz Supercomputing Centre (LRZ). More details can be found under http://www.prace-ri.eu/httpwinner-3rd-prace-ada-lovelace-award-hpc/.

Zurück zum Inhaltsverzeichnis


Fortran Modernisation Workshop

We are very happy to host a Workshop on Fortran Code Modernisation offered by the Numerical Algorithms Group (NAG) at LRZ in June 2018.

This two-day practical hands-on workshop - open and free of charge for all - is aimed at Fortran programmers who want to write modern code, or to modernise existing code, to make it more readable and maintainable by encouraging good engineering practices. The workshop will also present how to integrate tools and techniques for Fortran codes to help you develop sustainable software for your scientific and academic research particularly in a collaborative environment.

Date: Monday, June 4 - Tuesday, June 5 2018, 9:00-17:00
Location
: Leibniz Supercomputing Centre (LRZ), Boltzmannstr. 1, D-85748 Garching bei Muenchen, Germany
Lecturer
: Dr. Wadud Miah, Numerical Algorithms Group (NAG)

Topics:

  • Modern Fortran standards and how to write optimised and efficient Fortran;
  • NetCDF and HDF5 scientific file formats for data sharing in Fortran;
  • GNU Automake to automate the build process;
  • pFUnit unit testing framework for testing Fortran codes;
  • Fortran Documenter tool for Fortran code documentation;
  • Git version control for collaborative code development;
  • In-situ visualisation using PLplot in Fortran;
  • IEEE Floating Point Exception Handling;
  • Software verification and portability using the NAG Fortran Compiler;
  • Fortran interoperability with C, Python and R;
  • Introduction to parallelism for Fortran;
  • Fortran code verification using the CamFort tool;
  • Introduction to the NAG Fortran library.

Further details and a link to the registration form can be found under https://www.lrz.de/services/compute/courses/2018-06-04_hnag1s18/ .
For more information on the successful series of Fortran Modernisation Workshops offered by the Numerical Algorithms Group (NAG), see https://www.nag.co.uk/content/fortran-modernization-workshop

Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


2nd Call for Papers EnviroInfo 2018 extended

We invite you to the EnviroInfo 2018, to see how state of the art in research, current IT-supported environmental decision-making, and visions of the future benefit each other. The conference takes place in Garching near Munich, on September 5th – 7th 2018 at Leibniz Supercomputing Centre (LRZ).

The EnviroInfo 2018 is the 32nd edition of the long standing and established international and interdisciplinary conference series on leading environmental information and communication technologies. Combining and shaping national and international activities in the field of applied informatics and environmental informatics in making the world a better place for living, the EnviroInfo conference series aims at presenting and discussing the latest state-of-the-art development on ICT and environmental related fields.

This years’ focus will be on five key topics and their relevant to Environmental Informatics:

  •     Efficient Computing
  •     Virtual Discoveries
  •     Managing Disruption
  •     Big Data
  •     Open Science
  •     Distributed Processing and Sensing

Topics of special interest will be covered in special workshops or within topic centred sessions/tracks within the conference’s schedule. Some of the special topics of this year’s conference are:

  •     Disaster Management for Resilience and Public Safety
  •     Sustainable Mobility
  •     Environmental Health Informatics
  •     Earthquakes and Tsunamis
  •     Energy Aware Software-Engineering and Development
  •     Environmental Information Systems

These core topics are intended to provide continuity with previous EnviroInfo issues and topics that have long been close to  the heart of the specialist community. On the other hand, we would also like to pick up the new hot topics that have not been around the area for so long.

This years' edition of the conference is organized by Prof. Dr. Volker Wohlgemuth, Prof. Dr. Dieter Kranzlmüller and Prof. Dr. Hans-Joachim Bungartz (general chairs), Dr. Volker Weinberg (publication chair), Dr. Jens Weismüller (program chair), Natalie Vogel (local chair) and Sabrina Eisenreich (communication chair).

In the name of the committee we invite contributions in the form of short papers, full papers or posters. The submission deadline for full papers will be deadline for full papers will be May 15, 2018, for short contributions it will be June 1st, 2018. Full papers should be 8-20 pages and will be published in a Springer book, short papers should be 4-6 pages and will appear in a Shaker proceedings.

Please submit your contributions via the Conference Tool linked on

http://www.enviroinfo2018.eu/

Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


CADFEM Campus Technologietag am 17. Mai am LRZ

Der 5. Technologietag von CADFEM Academic zeigt, wie mit Hilfe der Finite Volumen Methode (FVM) und der leistungsfähigen Solvertechnologie von ANSYS komplexe Strömungen präzise vorhergesagt werden können.

Wann: 17. Mai 2018, 13:00 bis 16:30 Uhr
Wo: Leibniz-Rechenzentrum, Garching b. München

Weitere Einzelheiten entnehmen Sie bitte der Ankündigung von CADFEM (PDF-Datei). Melden Sie sich bitte formlos an bei academic@cadfem.de

Zurück zum Inhaltsverzeichnis

SuperMUC Status and Results Workshop July 24-25

All users and project managers of SuperMUC projects are hereby cordially invited to the SuperMUC Status and Results Workshop at the LRZ in Garching July 24-25, 2018
During the last two years of operation SuperMUC has hosted many high level projects from a broad range of scientific communities. To share their experience we kindly invite all users of SuperMUC to present the scientific results of their projects with a special focus on the alogrithms and utilization of SuperMUC. We plan for 25-30 oral presentations of 15min plus 5min for Q & A. Additionally, we will have an exhhibition of posters and electronic presentations. We hope that the talks ignite fruitful discussions on the usage and challenges of HPC systems. During the planned User Forum you can directly discuss your current and future needs with experts from LRZ.

  • Each SuperMUC project is cordially invited to submit a 15min talk.
  • Additionally, users can bring posters and scientific visualisation showcases that will be displayed in the foyer throughout the workshop and the poster session.
  • Bring in your feedback, future requirements, and directly discuss with experts from LRZ during the user forum (Tuesday afternoon). After the user forum, we will have the poster session and get together event with Bavarian beer and food.
  • Please register before July 10 if you plan to attend the workshop.
All details can be found here: https://www.lrz.de/services/compute/courses/2018-07-24_hprw1s18/.

Autor: Helmut Brüchle

Zurück zum Inhaltsverzeichnis


Am LRZ abzugebende Geräte

Die folgenden Geräte werden an Interessenten aus dem Hochschulbereich oder aus anderen Behörden kostenlos abgegeben.
Senden Sie bitte bei Interesse bis spätestens 20.05.2018 eine Nachricht an die E-Mail-Adresse: Hardware_AT_lrz.de.
Wir werden dann mit Ihnen Kontakt aufnehmen.

Anzahl Modell Baujahr CPU RAM GB DISK GB Bemerkung
1 Dell Optiplex GX620 2005 Pentium 4 2 Nein
1 Dell Precision 690 2006 Xeon 4 250
7 Dell Precision T3400 2009 Core 2 Quad 8 500
1 Dell Precision T1500 2010 Core i5 4 500
6 Dell Optiplex 990 2011 Core i5 4 500
16 Dell Optiplex 980 2011 Core i5 4 250
10 Dell Optiplex 790 2011 Core i5 4 250
17 Zotac ID12 2012 Atom D525 4 Nein
1 PowerMac G5/1800DP 2004 Dual G5 8 Nein
2 MacBook Pro 15" 2007 Core 2 Duo 4 Nein
2 iMac 24" 2008 Core 2 Duo 4 Nein
1 iMac 27" 2009 Core 2 Duo 4 Nein
1 iMac 27" 2009 Core 2 Duo 4 Nein Tempsensor fehlt
1 MacBook Pro 13" 2009 Core 2 Duo 4 Nein
4 MacBook Pro 15,4" 2009 Core 2 Duo 8 Nein
1 MacBook Pro 15,4" 2009 Core 2 Duo 8 Nein
1 MacMini 2010 Core 2 Duo 4 Nein
10 iPad 2 - 16GB 2011 teilweise fehlen Netzteile
2 iMac 21" 2012 Quad-Core i5 8 Nein
28 DELL 19" Monitore 2005 - 2008

Autor: Thomas Niedermeier

Zurück zum Inhaltsverzeichnis


Zentrale Systeme und Compute Dienste


New Course: Introduction to GASPI - Scalability in HPC

There are still free places available for the upcoming GASPI Workshop @ LRZ. The registration deadline has been extended until Friday, 4 May 2018. Don't miss this chance!

  • The GASPI programming model represents a powerful and highly scalable alternative to the one-sided communication of MPI in accessing the global memory address space (across many compute nodes).
  • LRZ invited two experts from Fraunhofer Institute for Industrial Mathematics ITWM as teachers.
  • The workshop will cover both lectures and hands-on sessions.

As scalable and flexible computing on massively parallel HPC systems based on distributed memory architectures becomes more important, we are happy to host the course on

"Introduction to GASPI - Scalability in HPC"


in cooperation with the Fraunhofer Institute for Industrial Mathematics (ITWM).

The course will take place on

Tuesday, May 8 and Wednesday, May 9, 2018, 9:00 - 16:30

at the Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities at Garching b. München, Germany.

Overview

GASPI (Global Address Space Programming Interface) offers a small, yet powerful API for scalable HPC applications following a single program multiple data (SPMD) approach. Single-sided communication primitives are supplemented by a light weight synchronization mechanism (notifications).

Agenda

The course aims to provide an introduction to the GASPI API as well as to discuss typical use cases.

On the Linux cluster CoolMUC-2 the attendees will have the chance to apply the acquired skills.

Teachers

Daniel Grünewald, Martin Kühn (Fraunhofer Institute for Industrial Mathematics ITWM, Kaiserslautern)

Details about the course can be found at https://www.lrz.de/services/compute/courses/2018-05-08_hpcg1s18/.

Autor: Dr. Andre Kurzmann / Dr. Volker Weinberg

Zurück zum Inhaltsverzeichnis


NEW PRACE Workshop: HPC code optimisation workshop

In the ever-growing complexity of computer architectures, code optimization has become the main route to keep pace with hardware advancements and effectively make use of current and upcoming High Performance Computing systems.

Have you ever asked yourself:

  • Where does the performance of my application lay?
  • What is the maximum speed-up achievable on the architecture I am using?
  • Is my implementation matching the HPC objectives?

In this workshop, two leading experts, from Intel and our Intel Parallel Computing Center team at LRZ, will answer these questions and provide a unique opportunity to learn techniques, methods and solutions on how to improve code, how to enable new hardware features and how to use the roofline model to visualize the potential benefits of an optimization process.

Date: Thursday, 21 June - Friday, 22 June 2018, 9:00-17:00
Lecturers: Dr. Fabio Baruffa (Intel), Dr. Luigi Iapichino (Intel Parallel Computing Centre @ LRZ)
Further Details and Registration: https://events.prace-ri.eu/event/727/
Registration deadline: 7 June 2018

Abstract: In this workshop we provide the opportunity to learn techniques, methods and solutions on how to improve code, how to enable the new hardware features and how to use the roofline model to visualize the potential benefits of an optimization process.
We will begin with a description of the latest micro-processor architectures and how the developers can efficiently use modern HPC hardware, in particular the vector units via SIMD programming and AVX-512 optimization and the memory hierarchy.
The attendees are then conducted along the optimization process by means of hands-on exercises and learn how to enable vectorization using simple pragmas and more effective techniques, like changing data layout and alignment.
The work is guided by the hints from the Intel compiler reports, and using Intel Advisor.
We provide also an N-body code, to support the described optimization solutions with practical hands-on.

A special focus will be dedicated to scalar and vector optimizations for the latest Intel Xeon Scalable processor, code-named Skylake, which is going to be utilized in the upcoming SuperMUC-NG machine at LRZ.

We will provide to the attendees access to Skylake processors and Intel tools using VM instances provided by Google Cloud Platform.

Please also pass this workshop announcement to other interested colleagues.

Information on further HPC courses:

Autor: Dr. Luigi Iapichino / Dr. Volker Weinberg

Zurück zum Inhaltsverzeichnis


PRACE Summer of HPC 2018

Early-stage postgraduate and late-stage undergraduate students are invited to apply for the PRACE Summer of HPC 2018 programme, to be held in July & August 2018. Consisting of a training week and two months on placement at top HPC centres around Europe, the programme offers participants the opportunity to learn and share more about PRACE and HPC, and includes accommodation, a stipend and travel to their HPC centre.

For details see

https://summerofhpc.prace-ri.eu/prace-summer-of-hpc-2018-opens-applications/

Zurück zum Inhaltsverzeichnis


European HPC Summit Week & PRACEdays18

The European HPC Summit Week 2018, taking place from May 28 to June 1, 2018 in Ljubljana will gather the main HPC stakeholders in Europe. Similar to previous years, this edition will offer a wide variety of workshops covering a number of application areas where supercomputers are key, as well as HPC technologies and infrastructures. As part of the working group on Energy Efficiency of the ETP4HPC, Dr. Michael Ott from LRZ will organise a one day workshop on this topic. For details please see here: http://www.etp4hpc.eu/events/workshop-on-energy-efficiency-in-hpc-organize_449.html.

The European HPC Summit Week also offers a great opportunity to network with all relevant European HPC stakeholders, from technology suppliers and HPC infrastructures to scientific and industrial HPC users in Europe.

PRACEdays18 is the central event of the European HPC Summit Week, and is hosted by PRACE's Slovenian Member ULFME – University of Ljubljana, Faculty of Mechanical Engineering. The conference will bring together experts from academia and industry who will present their advancements in HPC-supported science and engineering.

Registration for the European HPC Summit Week and PRACEdays18 is still open. The deadline to register is 7 May 2018.

Please go here http://www.eiseverywhere.com/europeanhpcsummitweek18
Further information: PRACEdays18: https://events.prace-ri.eu/event/622/
European HPC Summit Week: https://exdci.eu/events/european-hpc-summit-week-2018

Zurück zum Inhaltsverzeichnis


Next HPC Courses and Workshops at LRZ

Following, please, find a list of the next HPC courses at LRZ

Introduction to programming with GASPI in HPC
Tuesday, May 8, 2018 09:00 - Wednesday, May 9, 2018 16:30
Fortran Modernization Workshop
Monday, June 4 - Tuesday, June 5 2018, 9:00-17:00
Deep Learning Workshop
Tuesday, June 12, 2018, 9:00-18:00
PRACE Workshop: HPC code optimisation workshop
Thursday, June 21 - Friday, June 22 2018, 9:00-17:00
SuperMUC Status and Results Workshop 2018
Tuesday July 24 2018 - Wednesday July 25 2018, 09:00 (Tue) -17:00 (Wed)
EnviroInfo 2018 Conference
Wednesday, September 5 - Friday, September 7, 2018
Compact Course: Iterative Linear Solvers and Parallelization
Monday, September 10 - Friday, September 14, 2018, 08:30 (Mo) - 15:30 (Fr)
PRACE Course: Advanced Fortran Topics
Monday, September 17 - Friday, September 21, 2018, 09:00 - 18:00
C Language for Beginners
Tuesday, October 9 - Thursday, October 11, 2018, 9:00 - 17:00
Advanced C++ with Focus on Software Engineering
Tuesday, October 23 - Thursday, October 25, 2018, 9:00 - 17:00
C++ Language for Beginners
Tuesday, November 6 - Friday, November 9, 2018, 9:00 - 17:00

Information on further HPC courses:

Zurück zum Inhaltsverzeichnis


GCSnews des Gauss Centre for Supercomputing (GCS)

Die GCSnews des Gauss Centre for Supercomputing (GCS) März 2018 sind erschienen. Sie finden sie über die Webseite des GCSoder direkt über den Link zur März-Ausgabe.

Das Gauss Centre for Supercomputing(GCS) ist der Zusammenschluss der drei nationalen Höchstleistungsrechenzentren in Deutschland (FZ Jülich, HLRS in Stuttgart und LRZ in Garching bei München). GCS ist der deutsche Partner in der Partnership for Advanced Computing in Europe (PRACE).

Zurück zum Inhaltsverzeichnis


Infobrief der Gauß-Allianz

Die Gauß-Allianz (GA) ist der Zusammenschluss von 18 Rechenzentren und Institutionen in Deutschland zur nachhaltigen und effizienten Nutzung von Supercomputing-Ressourcen der obersten Leistungsklassen. Hier finden Sie die aktuelle Ausgabe des GA-Infobriefs.

Die Gauß-Allianz schreibt den Namen des großen Mathematikers mit "ß", das Gauss Centre schreibt seinen Namen in britischem Englisch mit "ss" statt "ß".

Zurück zum Inhaltsverzeichnis


PRACE Newsletter

PRACE, the Partnership for Advanced Computing in Europe , was established in 2010 to create a persistent pan-European Research Infrastructure (RI) of world-class supercomputers. This infrastructure is currently made up of seven leading edge machines, hosted by five member countries, (France, Germany, Italy, Spain and Switzerland) and is accessible through an open peer-review process, complemented by national resources operated and accessible via High Performance Computing (HPC) centres throughout Europe. Please, take a look at the latest PRACE newsletter.

Zurück zum Inhaltsverzeichnis


Stellenangebote / Job Opportunities


Sie finden alle aktuellen Stellenangebote des LRZ immer auf unser Webseite www.lrz.de/wir/stellen/.

You will find all job opportunities at LRZ, some of them in English, on our web page www.lrz.de/wir/stellen/.


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

Sollten Sie Schwierigkeiten mit der Darstellung unseres Newsletters haben, dann schicken Sie uns bitte eine kurze Beschreibung des Problems an NewsletterRedaktion_AT_lrz.de . Danke!

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.