LRZ-Newsletter Nr. 04/2019 vom 04.04.2019

Unsere Themen:


Neuigkeiten


Bundestagsabgeordneter Florian Hahn besucht das LRZ

Am 28. März 2019 besuchte der Abgeordnete des Deutschen Bundestages Florian Hahn das Leibniz-Rechenzentrum und informierte sich dabei u.a. über den neuen Höchstleistungsrechner am LRZ SuperMUC-NG.

„Der SuperMUC-NG ist nicht nur der schnellste Computer Deutschlands, sondern auch einer der schnellsten der Welt“, so der örtliche Bundestagsabgeordnete Florian Hahn bei einem Rundgang mit Prof. Dr. Dieter Kranzlmüller, Vorsitzender des Direktoriums des LRZ. „Damit eröffnen sich völlig neue Möglichkeiten für die Wissenschaft sowie die Entwicklung eines revolutionären Quantencomputers. Kurzum: Beste Bedingungen für Spitzenforschung made in Bavaria“, so der Putzbrunner Politiker beeindruckt.

Zurück zum Inhaltsverzeichnis


LRZ joins the OpenMP effort

The Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities in Germany (LRZ) has joined the OpenMP Architecture Review Board (ARB), a group of leading hardware and software vendors and research organizations creating the standard for the most popular shared-memory parallel programming model in use today.

The Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities in Germany provides comprehensive services to scientific and academic communities in Germany and Europe. LRZ has a long history of offering high-performance computing resources and parallel computing support since its foundation in 1962. Among other leading systems, it has hosted an SGI Altix 4700 around a decade ago, at that time the largest shared memory system in the world, which permitted large-scale programming with OpenMP. This year LRZ has started operation of SuperMUC-NG, the fastest system in the European Union with a peak performance of 26.9 PetaFlop/s, which targets hybrid parallel programming with OpenMP and MPI.

“With the rise of core counts and the expected future deployment of accelerated systems, optimizing node-level performance is getting more and more important. As a member of the OpenMP ARB, we want to contribute to the future of OpenMP to meet the challenges of new architectures“, says Prof. Dieter Kranzlmüller, Chairman of the Board of Directors of LRZ.

“The LRZ will bring the European OpenMP community closer to the OpenMP ARB. Having three members (BSC, EPCC and LRZ of the Gauss Centre for Supercomputing) of the European PRACE initiative in the ARB underlines the importance of OpenMP as a parallel programming API", says Michael Klemm, OpenMP ARB CEO.

The OpenMP ARB now has 33 members, see https://www.openmp.org/about/members/.

About OpenMP

The OpenMP Architecture Review Board (ARB) has as mission to standardize directive-based multi-language high-level parallelism that is performant, productive and portable. Jointly defined by a group of major computer hardware and software vendors, the OpenMP API is a portable, scalable model that gives parallel programmers a simple and flexible interface for developing parallel applications for platforms ranging from embedded systems and accelerator devices to multicore systems and shared-memory systems. The OpenMP ARB owns the OpenMP brand, oversees the OpenMP specification and produces and approves new versions of the specification.

Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


GCSnews des Gauss Centre for Supercomputing (GCS)

Die aktuelle Ausgabe der GCSnews des Gauss Centre for Supercomputing (GCS) finden Sie hier . Alle Ausgaben sind über die Webseite des GCS verfügbar.

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. To receive PRACE' newsletter, please go to http://www.prace-ri.eu/subscribe-to-prace-gdpr-compliance/

Zurück zum Inhaltsverzeichnis


Termine, Kurse und Veranstaltungen


PRACE Workshop: HPC code optimisation workshop

Date: Monday, May 20 - Wednesday, May  22, 2019, 9:00-17:00
Lecturers: Dr. Fabio Baruffa (Intel), Dr. Mathias Gerald (LRZ), Dr. Luigi Iapichino (LRZ)
Further Details and Registration: https://events.prace-ri.eu/event/872/
Registration deadline: 6 May 2019
Location: LRZ Building, University campus Garching, near Munich, Germany

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, experts from LRZ and Intel will answer these questions and provide a unique 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.

NEW: this year the workshop will consist of three days. We will dedicate most of the third day to the Intel Math Kernel Library (MKL), in order to show how to gain performance through the use of libraries.

We provide also an N-body code, to support the described optimization solutions with practical hands-on.

The course is a PRACE training event.

Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


Introduction to Intel FPGA Programming Models

Date: Tuesday, May 21, 2019, 09:00-17:00
Lecturers: Bill Jenkins (Intel)
Further Details and Registration: https://www.lrz.de/services/compute/courses/2019-05-21_hfpg1s19/
Registration deadline: 6 May 2019
Location: LRZ Building, University campus Garching, near Munich, Germany

FPGAs can help accelerate many of the core data center workloads that process the growing volume of data that our hyper-connected world creates. They can be reprogrammed in a fraction of a second with a datapath that exactly matches your workload’s key algorithms. This versatility results in a higher performing, more power efficient, and well utilized data center – lowering your total cost of ownership. FPGAS can be connected directly to processors, memories, networks, and numerous other interfaces. Traditionally, FPGAs require deep domain expertise to program for, but Intel is investing in significantly simplifying the development flow and enable rapid deployment across the data center.

This full day course offered by Intel in cooperation with LRZ is a high-level overview of FPGAs with the intention of level setting people on what they are, why they are so important as accelerators, what their programming models are and how easily they can be adopted into compute clusters through the use of the Acceleration Stack for Intel® Xeon® CPU with FPGAs.  This course contains both lecture and lab exercises to help gain familiarity with these concepts using the tools available for FPGA developers such as Quartus, Platform Designer, High Level Synthesis, OpenCL, and DSP Builder.

At completion you will have learned:

  • Why FPGA accelerators are so important in solving tomorrows problems
  • Identify the various programming models for the FPGA
  • Understand the components of the Acceleration Stack and where to get them and how to use them
  • Explain the software development model for writing software applications using the OPAE layer to run acceleration workloads on an FPGA accelerator
  • Where to get or how to create accelerator workloads for Programmable Accelerator Cards (PAC) using the Acceleration Stack for Intel® Xeon® CPU with FPGAs
Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


NEW PRACE Course: Deep Learning and GPU programming workshop @ LRZ

Date: Monday, June 3 - Thursday, June 6, 2019, 9:00-17:00
Location: LRZ
Lecturer:Dr. Momme Allalen, Dr. Juan Durillo Barrionuevo, Dr. Yu Wang, Dr. Volker Weinberg (LRZ)

Summary: This new 4-days PRACE workshop offered for the first time at LRZ combines lectures about fundamentals of Deep Learning for Multiple Data Types and Multi-GPUs with lectures about Accelerated Computing with CUDA C/C++ and OpenACC.

Further information: https://events.prace-ri.eu/event/860/

Zurück zum Inhaltsverzeichnis


NEW: Deep Learning and GPU programming using OpenACC @ HLRS Stuttgart

Date: Monday, July 15 - Wednesday, July 17, 2019, 9:00-17:00
Location: HLRS, University of Stuttgart, Nobelstr. 19, D-70569 Stuttgart, Germany
Lecturer:Yu Wang (LRZ), Volker Weinberg (LRZ), Momme Allalen (LRZ)

Summary: The workshop combines lectures about fundamentals of Deep Learning for Computer Vision and Multiple Data Types with a lecture about Accelerated Computing with OpenACC.

Further information: http://www.hlrs.de/training/2019/DL1

All lectures are interleaved with many hands-on sessions using Jupyter Notebooks. The exercises will be done on a fully configured GPU-accelerated workstation in the cloud.

All involved instructors are NVIDIA certified University Ambassadors.

Please also pass this course announcement to other interested colleagues.

Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


Training on data analytics, big data and machine learning workflows at LRZ

In addition to supporting traditional HPC applications, the Leibniz Supercomputing Centre (LRZ) is offering systems and services to address the increasing demand of data analytics, big data and machine learning workflows. In a series of trainings, we will provide introductory courses for researchers and students who want to utilize LRZ resources for tasks of this nature.

The "opening session" on Tuesday, April 9th will provide an "Introduction to the LRZ Supercomputing & Machine Learning Infrastructure". Attending this full day course will give you an overview of the high performance computing hardware and software services available at LRZ and you will learn how to utilize these systems, focusing on different machine learning tools and applications.

For further details and registration, please see https://www.lrz.de/services/compute/courses/2019-04-09_hsmi1s19/

A follow-up training on Wednesday, April 10th will take a deep-dive into "Using R at LRZ". This full day workshop will illustrate the different possibilities of utilizing R for data analytics and machine learning tasks on various LRZ systems by providing guidelines and best practice examples.

For further details and registration, please see https://www.lrz.de/services/compute/courses/2019-04-10_hurl1s19/

On Thursday, April 11th an Intel Artificial Intelligence Workshop will highlight the usage of Intel's optimized performance libraries underneath popular machine learning frameworks. The workshop includes hands-on sessions around classical machine learning as well as deep learning on HPC systems. Besides introducing the transparent usage of performance libraries, the focus will be to empower participants to scale their deep learning (TensorFlow) application training on distributed HPC systems.

For further details and registration, please see https://www.lrz.de/services/compute/courses/2019-04-11_hiai1s19/

Finally, on Friday, April 12th we will offer a "Using Python at LRZ" workshop. In this refresher course, different Python topics of interest to data analytics/machine learning practitioners and distinctive use cases of high performance computing environments will be covered.

For further details and registration, please see https://www.lrz.de/services/compute/courses/2019-04-12_hupl1s19/

If you have any questions regarding these trainings prior to registration, feel free to contact Dr. Johannes Albert-von der Gönna (johannes.albert-vondergoenna@lrz.de).

Autor: Volker Weinberg

Zurück zum Inhaltsverzeichnis


Next HPC Courses and Workshops at LRZ

Following, please, find a list of the next HPC courses at LRZ
Introduction to ANSYS Fluid Dynamics (CFX, Fluent) on LRZ HPC Systems
Monday, April 8 - Friday, April 12, 2019, 09:00-17:00
Introduction to the LRZ Supercomputing & Machine Learning Infrastructure
Tuesday, April 9, 2019, 9:00-17:00
Using R at LRZ
Wednesday, April 10, 2019, 9:00-17:00
Intel Artificial Intelligence Workshop
Thursday, April 11, 2019, 9:00-17:00
Using Python at LRZ
Friday, April 12, 2019, 10:00-15:00
PRACE Workshop: HPC code optimisation workshop
Monday, May 20 - Wednesday, May 22, 2019, 9:00-17:00
Introduction to Intel FPGA Programming Models
Tuesday, May 21, 2019, 09:00-17:00
PRACE Course: Deep Learning and GPU programming workshop
Monday, June 3 - Thursday, June 6, 2019, 9:00-17:00
Advanced C++ with Focus on Software Engineering
Wednesday, June 12 - Friday, June 14, 2019, 9:00 - 17:00
Deep Learning and GPU programming using OpenACC @ HLRS Stuttgart
Monday, July 15 - Wednesday, July 17, 2019, 9:00-17:00
Introduction to ANSYS Fluid Dynamics (CFX, Fluent) on LRZ HPC Systems
Monday, September 2 - Friday, September 6, 2019, 09:00-17:00
Advanced C++ with Focus on Software Engineering
Wednesday, November 20 - Friday, November 22, 2019, 9:00 - 17:00
C++ Language for Beginners
Monday, November 25 - Friday, November 29, 2019, 9:00 - 17:00
Past Courses
Archive of previous courses
Other Courses
Courses at other GCS and PRACE locations
Resources
Lecture Notes of Courses & Workshops

Information on further HPC courses:

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.