Newsletter

Announcements of HPC events for users in Frankfurt

The HKHLR regularly organizes High Performance Computing (HPC) events aimed at researchers and students in the region of Hessen.

If you are interested in receiving information about HPC events, like courses, tutorials or workshops, please subscribe to the HPC-frankfurt-events newsletter.

Events 2020

Course: Cython in Depth is Cancelled due to Covid-19

When

30, 31 March 2020, from 9:00 to 17:00

Location

Goethe Universität, Campus Riedberg (Frankfurt am Main) – Physics building, Room: 01.120 

Max-von-Laue Straße 1

60438, Frankfurt am Main

Trainer

Dr. Stefan Behnel, core developer of Cython

Description

The goal of the course is to get to know the Cython language and to learn to use it to speed up Python code. The participants will learn also how to wrap external C libraries to efficiently and comfortably use them from Python.

The course targets medium level to experienced Python programmers who want to break through the limits of Python performance. A basic understanding of the C language is helpful but not required.

Topics covered in the course
  • building a Python extension module with Cython & distutils
  • speeding up Python code with Cython
  • interfacing with external C code
  • interfacing with C++ and using C++ features in Cython
  • processing NumPy data with memory views
  • parallel data processing with OpenMP
Exercises

The course will include exercises. A desktop computer will be available for each participant, but each participant can use her/his own laptop if wished.

Tune your own code

Attendees who have a piece of their own code that they would like to adapt and speed up using Cython, can send it to the organisers to include it in the course as a case study. Please make sure that it is easily runnable and self-contained (except for common processing libraries like NumPy) and includes all necessary input, e.g. in a script or Jupyter Notebook. Please also include a benchmark command that evaluates its performance within less than one minute of runtime. If multiple participants submit their examples, a suitable choice will be made based on time constraints. If you are interested in tuning your code, please send us the code at least one week before the course (to david.palao@hpc-hessen.de).

Registration

To register, please use this webpage.

For more information, please write to david.palao@hpc-hessen.de.

Events 2019

Intel AI Workshop: October 2019

Tuesday, Oct 15th 2019

Location:

Goethe Universität, Campus Westend (Frankfurt am Main) – PEG-Gebäude, Room: HRZ Poolraum PEG 1.G078 

Theodor-W.-Adorno-Platz 6

60323 Frankfurt am Main

Trainer: Fabio Baruffa from Intel

Program
Enhance Machine Learning and Deep Learning Performance with Intel® Software tools

The use of data analytics techniques, such as Machine Learning and Deep Learning, has become the key for gaining insight into the incredible amount of data generated by scientific investigations (simulations and observations). Therefore, it is crucial for the scientific community to incorporate these new tools in their workflows, in order to make full use of modern and upcoming data sets. In this tutorial we will provide an overview on the most known machine learning algorithms for supervised and unsupervised learning. With small example codes we show how to implement such algorithms using the Intel® Distribution for Python*, and which performance benefit can be obtained with minimal effort from the developer perspective. Furthermore, the demand of using Deep Learning techniques in many scientific domains is rapidly emerging and the requirements for large compute and memory resources is increasing. One of the consequences is the need of the high-performance computing capability for processing and inferring the valuable information inherent in the data. We cover also how to accelerate the training of deep neural networks with Tensorflow, thanks to the highly optimized Intel® Math Kernel Library (Intel® MKL). We also demonstrate techniques on how to leverage deep neural network training on multiple nodes on an HPC system.

Agenda

9:00 - 10:30 : Artificial Intelligence on Intel Hardware Platforms

  • Intel’s Hardware and Software directions for Artificial Intelligence (AI)
    • Machine Learning (ML) and Deep Learning (DL)
  • Hardware Accelerated Deep Learning instructions and implementations
    • DL Boost, VNNI instructions

10:30 – 11:00 Break

11:00 – 12:30 : Performance optimized Python

  • Hands-on Labs with Python focus on Classical Machine Learning examples and algorithms

12:30 – 14:00 Lunch Break

14:00 - 15:30 : Optimized Deep Learning Frameworks

  • Performance optimized Frameworks solutions from Intel
    • Tensorflow, Keras, Caffe, Pytorch, BigDL and others
  • Performance acceleration with Intel MKL and Intel MKL-DNN for Deep Neural Network

15:30 - 16:00 Break

16:00 - 17:00 : Distributed Deep Learning Solutions on HPC systems

  • Accelerate Training and Inference of Distributed solutions on HPC (MPI) environments using Xeon (x86)
    • Distributed Tensorflow with Horovod
    • Distributed Machine Learning with Daal4py
Biography

Fabio Baruffa is a senior software technical consulting engineer at Intel. He provides customer support in the high performance computing (HPC) area and artificial intelligence software solutions at large scale.

Prior at Intel, he has been working as HPC application specialist and developer in the largest supercomputing centers in Europe, mainly the Leibniz Supercomputing Center and the Max-Plank Computing and Data Facility in Munich, as well as Cineca in Italy. He has been involved in software development, analysis of scientific code and optimization for HPC systems. He holds a PhD in Physics from University of Regensburg for his research in the area of spintronics devices and quantum computing.

Registration

Registration is now open! Participation is free.

Please register via Indico conference management system in order to join the course, therefore you have to create a new account on Indico to register to the course “Intel AI Workshop”.

The registration is open until Monday, October 07th.

Please take into account, that the number of participants is limited. You will get a notification about the status of your registration.

Detailed information at Indico website: https://events.fias.science/.


Contact

Anja Gerbes, +49 (0)69 798-47356, gerbes[at]csc.uni-frankfurt.de

This course is organized by CSC, Goethe University Frankfurt in cooperation with &

HKHLR-Tutorials

Node-Level Performance Engineering: September 2019

Monday/Tuesday, Sep 02nd/Sep 03rd 2019

Location:

Goethe Universität Frankfurt am Main, Uni Campus Riedberg,

Biozentrum, Beilstein Computer Center, Building N100, EG, Room 0.12 A+B

Max-von-Laue-Straße 9

60438 Frankfurt am Main

Trainer: Dr.-Ing. Jan Eitzinger & Thomas Gruber from Erlangen Regional Computing Center at the University of Erlangen-Nuremberg

Program

This course covers performance engineering approaches on the compute node level. Even application developers who are fluent in OpenMP and MPI often lack a good grasp of how much performance could at best be achieved by their code. This is because parallelism takes us only half the way to good performance. Even worse, slow serial code tends to scale very well, hiding the fact that resources are wasted. This course conveys the required knowledge to develop a thorough understanding of the interactions between software and hardware. This process must start at the core, socket, and node level, where the code gets executed that does the actual computational work. We introduce the basic architectural features and bottlenecks of modern processors and compute nodes. Pipelining, SIMD, superscalarity, caches, memory interfaces, ccNUMA, etc., are covered. A cornerstone of node-level performance analysis is the Roofline model, which is introduced in due detail and applied to various examples from computational science. We also show how simple software tools can be used to acquire knowledge about the system, run code in a reproducible way, and validate hypotheses about resource consumption. Finally, once the architectural requirements of a code are understood and correlated with performance measurements, the potential benefit of code changes can often be predicted, replacing hope-for-the-best optimizations by a scientific process.

Registration

Registration is now open! Participation is free.

Please register via Indico conference management system in order to join the course, therefore you have to create a new account on Indico to register to the course “Node-Level Performance Engineering”.

Please take into account, that the number of participants is limited. You will get a notification about the status of your registration.

Detailed information at Indico website: https://events.fias.science/.

Social Events:

On the first evening, we plan a dinner (self-paying) at “Zum Storch am Dom” (https://www.zumstorch.com/).

Cluster Computing Course

The Cluster Computing Course is for participants of Node-Level Performance Engineering

Friday, August 30 2019, 10-14 o'clock

Location: Room 0|101, FIAS, Ruth-Moufang-Straße 1, 60438 Frankfurt am Main

Goethe Universität, Campus Riedberg (Frankfurt am Main)

Cluster facts of the GOETHE-HLR & FUCHS cluster:

  • Hardware resources
  • File system
  • Environments modules
  • Partitions on the cluster
  • Architecture of the partitions

Batch Usage:

SLURM is the job scheduler installed on GOETHE-HLR & FUCHS cluster. The session teaches attendees

  • how to prepare a submission script
  • how to submit, monitor, and manage jobs on the clusters
  • theory about resource and CPU management
Travel Information and Accommodation

See our directions, the campus map, and the entrance and room 114 of building N100

Public transportation:

From main railway Station “Hauptbahnhof” with S-Bahn S1 - S9 to “Hauptwache”, then with U-Bahn U8 (direction Riedberg) to “Uni Campus Riedberg”.

Hotel Recommendation:


Contact

Anja Gerbes, +49 (0)69 798-47356, gerbes[at]csc.uni-frankfurt.de

This course is organized by HKHLR and CSC, Goethe University Frankfurt in cooperation with RRZE &

C++ Beginners Course: July/Aug 2019

Wednesday/Thursday, July 31st/Aug 01st 2019, 09:00 - 17:00

Location:

Goethe Universität Frankfurt am Main, Uni Campus Riedberg,

Biozentrum, Beilstein Computer Center, Building N100, EG, Room 0.12 A+B

Max-von-Laue-Straße 9

60438 Frankfurt am Main

Registration

If you wish to participate, please send an email to frankfurt@hpc-hessen.de.

Program

Introduction to Cpp with Philipp Sitzmann. He is IoT Solutions Engineer at System Vertrieb Alexander GmbH, SVA.

We offer an introductory course on Cpp. This course aims to provide you with the basic concepts of Cpp, how to write and read programs written in Cpp. At the end of this course you should also be able to understand the basic concept of any program written in a c-like language.

Content: In this session we will discuss the following subjects:

  • Introduction: C to Cpp
  • How to write a Cpp program
  • Cpp Syntax, Variables and Types
  • Pointer and Memory management
  • Object Oriented Programming with Cpp
    • classes
    • objects
    • members
    • inheritance
    • polymorphism
  • The Cpp standard library

HPC Day: June 2019

Invitation-Flyer

Thursday June 13 2019, 8:00-19:00

Location:

Goethe Universität, Campus Westend (Frankfurt am Main) – PEG-Gebäude, Room: HRZ Poolraum PEG 1.G078 

Theodor-W.-Adorno-Platz 6

60323 Frankfurt am Main

Program

Contents:

  • Slurm: Goethe-HLR Cluster and Batch Usage
  • Spack: Managing HPC Software Complexity with Spack
  • Clacc: OpenACC Support for Clang and LLVM
  • TAU: Performance Evaluation using the TAU Performance System.
Goethe-HLR Cluster and Batch Usage

- Anja Gerbes

The Goethe-HLR is a general purpose HPC cluster based on Intel Xeon Skylake CPU architecture. The system was installed in “Industriepark Höchst” in 2019. At the 484 compute server are more than 19 000 cores provided. The nodes are connected via EDR-Infiniband. At each compute node are at least 192 GB RAM available. The measured HPL performance is 958.67 TFlop/s. Slurm is the chosen Batch System (Workload Manager) that is used on Goethe-HLR. The talk will give you an introduction how to write batch script to run them later on a cluster.

Managing HPC Software Complexity with Spack

- Gregory Becker

Spack is an open-source tool for HPC package management, used on some of the fastest supercomputers in the world. It allows developers to write simple recipes in Python to automate builds with arbitrary combinations of compilers, MPI versions, build options, and dependency libraries. With Spack, users can install over 3000 community-maintained packages without knowing how to build them, developers can automate builds of tens or hundreds of dependency libraries, and staff at HPC centers can deploy many versions of software for thousands of users. We provide a thorough introduction to Spack’s capabilities: basic software installation, creating new packages, and development workflows using Spack. Attendees are encouraged to bring a laptop with Docker installed if they wish to follow along with the live demonstrations.

Gregory Becker is a computer scientist at Lawrence Livermore National Laboratory. His focus is on bridging the gap between research code and production use. He is one of the lead developers of the Spack project.

OpenACC Support for Clang and LLVM

- Joel E. Denny

This talk will present the Clacc project, which is developing OpenACC support for Clang and LLVM. It will address the following questions. What is OpenACC? Why is it important for HPC? How does it compare to OpenMP? What is the current state of OpenACC support? What is Clacc? How is it designed? What is the current state of Clacc development? How do I use it?

Joel E. Denny is a Computer Scientist in the Future Technologies Group at Oak Ridge National Laboratory. His research currently focuses on LLVM-based compiler projects. He received his Ph.D. in Computer Science from Clemson University in 2010.

Performance Evaluation using the TAU Performance System

- Sameer Shende

The TAU Performance System provides HPC and AI researchers a powerful profiling and tracing toolkit. This tutorial will focus on performance data collection, analysis, and performance optimization of parallel applications. The tutorial will introduce profiling and debugging support in TAU, cover performance evaluation of parallel programs written in Python, Fortran, C++, and/or C. The tutorial will also cover parallel performance analysis of applications using MPI, OpenMP, and other parallel runtime environments. We will demonstrate different techniques for program instrumentation including compiler-based instrumentation for LLVM and highlight TAU's support for memory debugging and I/O evaluation. The tutorial will guide the developers through the instrumentation, measurement, and analysis process steps in TAU. Performance data will include MPI timings, I/O and memory, and hardware performance counters from PAPI.

Sameer Shende serves as the Director of the Performance Research Laboratory at the University of Oregon. His research interests include performance evaluation tools, runtime systems, instrumentation, measurement, and analysis tools, and optimizing compilers.

Registration

Registration is now open!

Please create a new account on the Indico conference management system to register to the course “HPC Day”.

Detailed information at Indico website: https://events.fias.science/.

Registration Fee: 40 Euro

Fee includes coffee breaks, but not lunch & dinner.

Contact

Anja Gerbes, +49 (0)69 798-47356, gerbes[at]csc.uni-frankfurt.de

This course is organized by HKHLR and CSC, Goethe University Frankfurt in cooperation with

International Events

ISC High Performance at Night of Science

The ISC High Performance conference organizers is contributing two great speakers to Night of Science 2019, which starts at 5 pm on June 14 and ends at 6 am on June 15 2019 in Frankfurt am Main.

Night of Science is a student initiative that started in 2006 as a peaceful protest against the then introduced tuition fees. From the beginning it has been organized by students from every science faculty, such as chemistry, math, physics, computer science, biology, geosciences, biochemistry, pharmacy, psychology and medicine.

As a Night of Science attendee, you can visit more than 60 talks during the course of the night. Everyone is welcome to visit the university's laboratories, which are normally closed to the public.

You will find further information about this event on the NoS website.

This year, the ISC Conference Keynote speaker Prof. Dr. Ivo Sbalzarini will open Night of Science 2019, with a talk titled „Informatik und Biologie: eine Verbindung für die Zukunft“. The opening session will take place in OSZ B, H1 Hörsaal at 17:00 - 18:00 p.m.

Prof. Dr. Ivo Sbalzarini is the TU-Dresden Chair of Scientific Computing for Systems Biology in the joint Max-Planck/TU-Dresden Center for Systems Biology Dresden (CSBD) and is also a full professor of computer science at the faculty at TU Dresden.

In cooperation with ISC, Dr. Georg Hager from Erlangen Regional Computing Center at the University of Erlangen-Nuremberg, will give a talk titled „Von der Wettervorhersage zur Kernwaffe: Supercomputer - was sie sind und was sie können“. His talk will be in Bio B1 Hörsaal at 19:45 - 20:30 p.m.

Dr. Georg Hager is a research scientist in the high performance computing group of the Erlangen Regional Computing Center, and has captured the audience of NoS with his talks in 2017 and 2018.

ISC High Performance

ISC High Performance, the global event for High Performance Computing, Networking, Storage and AI takes place from June 16 to June 20, 2019 in Frankfurt am Main.

The conference website offers you more details on the 2019 program. You can register online for the conference.

There is a special discount for the ISC Tutorials. Please contact Anja Gerbes, gerbes[at]fias.uni-frankfurt.de, for your discount code.

ISC STEM STUDENT DAY & STEM GALA

ISC High Performance is once again hosting the free of admission ISC STEM Student Day & Gala on June 19, 2019.

Wednesday, June 19; 9:30 am – 9:30 pm

PURPOSE:

ISC High Performance has created this program to welcome STEM students into the world of HPC with the hope that an early exposure to the community will encourage them to acquire the necessary HPC skills to propel their future careers. This event will also present the current HPC job landscape and training opportunities for students interested in HPC.

TARGET AUDIENCE:

Undergraduate and graduate students pursuing STEM degrees

ATTENDEE PROFILE:

200 students from regional and international universities

FEE:

Free admission for STEM Students

Sign up is now open. You can sign up via http://www.isc-hpc.com/stem-student-day-sign-up-form.html

The tutorial can only accommodate 100 attendees, and these will be allocated to the earliest signups.

PROGRAM

Day Program at Messe Frankfurt

9:30 am - 11:00 am HPC Tutorial: Applications, Systems & Programming Models (Part 1), Dr. Bernd Mohr
11:00 am - 11:30 am Coffee Break
11:30 am - 12:30 am HPC Tutorial: Applications, Systems & Programming Models (Part 2), Dr. Bernd Mohr
12:30 am - 13:45 am Lunch Break
2:35 pm – 5:00 pm Guided Tour of the ISC 2019 Exhibition
5:15 pm – 5:30 pm Watch the Student Cluster Competition Winners Awarding
5:30 pm – 6:15 pm Attend HPC Expert Thomas Sterling Keynote on HPC Achievements & Impacts in 2019

Evening Program at Messe Frankfurt

6:45 pm - 7:00 pm Welcome & Drinks
7:00 pm - 7:20 pm Big Hair, Big Data & Beyond - A Career in Enterprise Computing, Arno Kolster
7:20 pm - 9:30 pm Dinner, Networking & Career Fair

public/events.txt · Last modified: 2020/03/11 13:42 by gerbes
CC Attribution-Noncommercial-Share Alike 4.0 International
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0