After the course the participants should be able to write simple parallel programs and parallelize existing programs with the basic features of MPI. No prior knowledge on parallel programming is required, but the participants are assumed to have working knowledge of either Fortran 90 or C programming languages.

Registration and more information: please see the course website

The purpose of the workshop is to provide application teams with an opportunity to scale their code across the full Blue Gene/P system JUGENE which now provides a total of 294,912 cores.

Further information can be found at: http://www.fz-juelich.de/jsc/bg-ws09/

More information: read the press release.

Academic Computer Centre CYFRONET AGH, in Cracow, Poland organises a PRACE code porting workshop. The workshop will be held on 14–16 October in Cracow, Poland, at the same time with the Cracow Grid Workshop 2009.

The workshop will focus on specific aspects of NEC and BlueGene HPC (High Performance Computing) solutions by renowned experts in the area. The workshop is addressed to researchers and students from Europe who are interested in the state of the art HPC infrastructures and practical introduction into porting applications to them.

Registration is open until October 4th, 2009 on the below mentioned website. The workshop attendance is free of charge, however the attendees have to cover their travel and lodging in Cracow. The maximum number of participants in the event is limited to 50 people.

The workshop attendees will have a chance to have a hands-on experience with programming on HPC systems including BlueGene/P at FZJ (Juelich) and NEC at HRLS (Stuttgart) and will receive user accounts on these machines which will be valid during the workshop’s hands-on sessions. The particpants will have a chance to get experience with code porting on real machines during the workshop’s sessions.

The first day of the workshop will provide introductory presentations into the subject and the next two days will hold the actual workshop. First half of each day will be dedicated to one machine and the second to other so that on the second day the attendees have a chance to discover differences between these systems.

Workshop speakers are Ph. D. Lukas Arnold, FZJ, Germany; Ph. D. Kamil Iskra, Argonne National Laboratory, US and Harald Klimach, University of Stuttgart.

Registration and agenda:  http://fivo.cyf-kr.edu.pl/prace

Contact information: Lukasz Dutka, e-mail: dutka@agh.edu.pl

The workshop will be held from the 13th – 15th July, 2009 at CSCS, Manno and will consist of a series of lectures and “hands-ons” sessions covering fundamental through advanced code optimization and porting techniques. The workshop is open to participants from all PRACE Member countries.

To registrater and receive more information visit CSCS's website.

Message Passing Interface (MPI) for beginners

On clusters and distributed memory architectures, parallel programming with the Message Passing Interface (MPI) is the dominating programming model. The course gives an full introduction into MPI-1. Further aspects are domain decomposition, load balancing, and debugging.  An MPI-2 overview and the MPI-2 one-sided communication is also taught.  Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of the Message Passing Interface (MPI).

https://fs.hlrs.de/projects/par/events/2009/parallel_prog_spring2009/G-a.html

Shared memory parallelization with OpenMP

The focus is on shared memory parallelization with OpenMP, the key concept on hyper-threading, dual-core, multi-core, shared memory, and ccNUMA platforms.  This course teaches shared memory OpenMP parallelization.  Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the directives and other interfaces of OpenMP.  Tools for performance tuning and debugging are presented.

https://fs.hlrs.de/projects/par/events/2009/parallel_prog_spring2009/G-b.html

Advanced topics in parallel programming

Topics are MPI-2 parallel file I/O, hybrid mixed model MPI+OpenMP parallelization, OpenMP on clusters, parallelization of explicit and implicit solvers and of particle based applications, parallel numerics and libraries, and parallelization with PETSc. Hands-on sessions are included.

https://fs.hlrs.de/projects/par/events/2009/parallel_prog_spring2009/G-c.html

Lectures will be given by:
Katharina Benkert, Shiqing Fan, Uwe Kuester, Uwe Woessner, and Dr. Rolf Rabenseifner (member of MPI-3 Forum).

The course language is English. All slides and handouts are in English.

Further courses can be found at
https://fs.hlrs.de/projects/par/events/2009/parallel_prog_fall2009/

Registration and additional information: please see the course website

Programming GPUs to accelerate algorithms and heavy computations has over the last years gained a lot of interest.

This course will offer two days of CUDA training and hands-on exercises. It will also briefly cover the new OpenCL language. This course is intended for people who want to take advantage of this new technology and that has ordinary programming skills, but are new to CUDA.

Learn CUDA and write your fastest program ever!

More information and registration: http://www.csc.fi/csc/kurssit/arkisto/cuda09

The European PVM/MPI Users’ Group conference is a forum for the users and developers of PVM, MPI, and other message-passing programming environments. They will have the opportunity to meet each other, share ideas and experiences, and meet members of the PVM and MPI teams.

2009 conference is organized by CSC- IT center for science. The call for papers has begun.

More information: see the conference website.

During two intensive summer weeks at the KTH campus students will be able to learn and improve their skills in writing efficient programs for serial and parallel scientific applications.  The course will carry four or five academic credits.

The student receives two credits for completing the labs during the course.  The student receives two or three additional credits only on completing a post-course project.  Participants are strongly encouraged to bring their own problems or programs for discussion and to possibly use as the basis of the post-course project.  Participants are provided with remote access to the PDC Linux clusters such as Ferlin (Dell Harpertown), Lenngren (Dell Xeon), Hebb (IBM Blue Gene), and Key (HP Itanium SMP).  Industrial participation is welcome.  The number of seats for all participants is limited.

Registration is open on a first-come basis until June 1, 2009, at the below mentioned web page.

Outline

A number of topics will be covered in overview lectures given by international experts and in-depth technical lectures followed by hands-on computer lab sessions.  The course will consist of about 35 hours of lectures and 35 hours of computer lab sessions.  Among the topics:

• Programming Environments at PDC

• Parallel Programming

• Modern Computer Architectures

• Parallel Algorithms

• Efficient Programming

• Case Studies

For more information and registration visit: http://www.pdc.kth.se/education/summer-school/

The focus is on programming models, MPI and OpenMP, and PETSc.
Presented tools are the Intel Thread Checker, Totalview, DDT,
Kojak, and Vampir.  Language support is given for Fortran and C.
The course was developed by HLRS, EPCC, JSC and ZIH.
Hands-on sessions will allow users to test and understand the basic
constructs of MPI, OpenMP, and PETSc.

Message Passing with MPI is the major programming model on
large distributed-memory systems in high-performance computing.
OpenMP is dedicated to shared memory systems.
PETSc is a high-level progamming interface for parallel solver. 

Registration and further information:

  http://fs.hlrs.de/projects/par/events/2009/parallel_prog_fall2009/
  (course H)

More information: http://www.nsc.liu.se/nsc09/

Speakers:
Representatives of IBM, Intel and ParTec, JSC staff members

Topics covered are:
* Overview of the supercomputer systems
* Usage
* Grid access via UNICORE
* Blue Gene/P architecture
* JUROPA architecture
* Programming (compilers, MPI, OpenMP, debuggers, tools)
* Performance tuning
* Libraries and application software
* I/O and data management

Time:
10 - 11 August 2009,
starting at 13:00 on 10 August 2009

Application:
Application is necessary!
Please send your application to :
Mr. Marc-André Hermanns, Phone: +49 2461 61 2054,
M.A.Hermanns@fz-juelich.de

For more information visit
http://www.fz-juelich.de/jsc/neues/termine/supercomputer
======================================================================

We would also like to draw your attention on a TotalView Debugging Workshop at JSC on August 12 open to everyone. An expert from Totalview technlogies will introduce the parallel debugger totalview, available on all JSC production machines, and will explain basic and advanced features of this debugger. A more detailed workshop announcement is available at

http://www.fz-juelich.de/jsc/neues/termine/totalview-2009

======================================================================

Objectives:

Through lectures from different stakeholders, hands-on sessions on the Grid5000, EGEE and DEISA infrastructures using various middleware, and a selection of focused conferences, this school will give attendees the opportunity to:

• understand the basics of grid computing,

• get acquainted with the different mechanisms of grids,

• be aware of challenges and scientific perspectives of grid usage

• be able to use grid environments and/or to port their own application on a grid infrastructure

Audiences:

This school is designed for computational scientists and end users from any application discipline as well as for computer scientists in the field of distributed systems and will be built on this diversity. Some background in programming and computer science is the only prerequisite.
Grid newcomers and beginners are welcome, but people already involved in grid projects should also benefit from this school.

Registration:

More information about the Summer School can be found on the Summer School website.

See also the Summer School poster (pdf)

The lectures will cover new programming models suited for future petaflops supercomputers, issues involved in selecting and using numerical libraries and best-practices learned from tuning and porting three scientific applications.  Finally an introduction to two important performance measurement tools, Scalaca and Paraver, will be given.

Registration and more information: http://www.csc.fi/csc/kurssit/arkisto/praceworkshop

On clusters and distributed memory architectures, parallel programming with the Message Passing Interface (MPI) is the dominating programming model. The course gives an full introduction into MPI-1. Further aspects are domain decomposition, load balancing, and debugging. An MPI-2 overview and the MPI-2 one-sided communication is also taught. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of the Message Passing Interface (MPI). Course language is ENGLISH.

More information: HLRS

The focus is on shared memory parallelization with OpenMP, the key concept on hyper-threading, dual-core, multi-core, shared memory, and ccNUMA platforms. This course teaches shared memory OpenMP parallelization. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the directives and other interfaces of OpenMP. Tools for performance tuning and debugging are presented. Course language is ENGLISH (if required).

More information: HLRS.

Topics are MPI-2 parallel file I/O, hybrid mixed model MPI+OpenMP parallelization, OpenMP on clusters, parallelization of explicit and implicit solvers and of particle based applications, parallel numerics and libraries, and parallelization with PETSc. Hands-on sessions are included. Course language is ENGLISH (if required)

More details: HLRS

Partitioned Global Address Space (PGAS) is a new model for parallel programming. Unified Parallel C (UPC) and Co-array Fortran (CAF) are PGAS extensions to C and Fortran. Because UPC and CAF are language extensions, parallelism is part of the language and not dependent upon library function calls as is MPI. Also, since a PGAS language allows any processor to directly address memory/data on any other processors, complex algorithms can be implemented more quickly and easily, and this increases developer productivity. This course gives an introduction to this novel approach of expressing parallelism. Hands-on sessions (in UPC and/or CAF) will allow users to immediately test and understand the basic constructs of PGAS languages.

More details: HLRS

This course is dedicated for scientists and students to learn (sequential) programming with Fortran of scientific applications. The course teaches newest Fortran standards. The beginners part is based on the RRZN handbook "Fortran 95". Hands-on sessions will allow users to immediately test and understand the language constructs. This workshop provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves.

More details: HLRS

For the old users of Louhi there will be a lot of new information on the quad-core architecture and the new XT5 cabinets.

This course takes place at CSC's premises in Espoo, Finland.

More information: CSC.

The focus is on programming models MPI, OpenMP, and PETSc. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of the Message Passing Interface (MPI) and the shared memory directives of OpenMP. This course is organized by NIC/ZAM in collaboration with HLRS.

More details: HLRS

To improve the quality and accelerate the development process of parallel simulation codes using MPI and OpenMP, we develop integrated state-of-the-art programming tools for high-performance computing that assist in optimising application performance and diagnosing programming errors.
As a service for application developers, we also offer training in using our tools.

The 3rd VI-HPS Tuning Workshop will:

• give an overview of our programming tool suite

• explain the functionality of individual tools

• offer hands-on experience in using the tools

Attendees are invited to bring their own applications and analyze them using the tools available with guidance from our tool experts.

The course itself is free of charge, however, attendees must cover their own travel and accommodation expenses.

For workshop details and registration, please visit:

http://www.fz-juelich.de/jsc/vi-hps-tw3

The focus is on programming models MPI, OpenMP, and PETSc. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of the Message Passing Interface (MPI) and the shared memory directives of OpenMP. This course is organized by NIC/ZAM in collaboration with HLRS.

More details: HLRS

The following items are covered, together with an estimate of the level of difficulty:

• Days 1-2 (beginner to intermediate)
  Introduction to the important features of Fortran 95: Type system, arrays, pointers, memory management, expressions and assignment, control constructs, modules and procedures, specification statements, intrinsics
• Days 3-4 (intermediate)
  Tools and Compilers: Make, SVN; usage of compilers, especially those from Intel and IBM; handling of libraries; the intrinsic modules of Fortran 2003: C interoperability and exception handling; Fortran I/O facilities and their optimal use
• Days 5-7 (advanced)
  Introduction to Fortran 2003: Object orientation and its efficient use; some aspects of software design based on object orientation; parallel programming with Coarrays, a new concept scheduled for inclusion in the next Fortran standard.

The participants of the course have the opportunity to experiment with the lecture materials in hands-on sessions.

Further details: LRZ

The event is hosted by the Greek Research and Technology Network with the contribution of the Aristotle University of Thessaloniki (AUTH), and addresses potential users of future Petascale systems in Europe. Researchers and students from Europe and beyond will receive advanced training in programming models and optimization techniques, MPI/OpenMP hybrid programming and profiling. The first three days of the Winter School will focus on the in-depth presentation for thorough understanding of these HPC (High Performance Computing) topics during morning lectures followed by hands-on training in the afternoon. The last day will be dedicated to a novel multiprocessor architecture, with all-day parallel lectures and hands-on training.

To enable students to solve problems in scalable scientific computing, access will be provided to two PRACE prototype systems: The Power 6 system at the SARA Computing and Networking Services in Amsterdam, The Netherlands, and the Cell system at the Barcelona Supercomputing Center (BSC) in Spain.

The full program and how to register for the PRACE Winter School can be found at: http://pracewinterschool.grnet.gr/

More information: Contact prace-winter-pc (at) fz-juelich.de

See also the press release about the event.

The focus is on programming models MPI, OpenMP, and PETSc. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of the Message Passing Interface (MPI) and the shared memory directives of OpenMP. The last day is dedicated to tools. This course is organized by ZIH in collaboration with HLRS.

Further Info: HLRS

Its contents include more advanced features of the message passing interface (MPI) paradigm, shared memory parallelization model, as well as parallel numerical libraries and writing efficient parallel I/O.

Basic knowledge of parallel programming with MPI is required, and the participants are assumed to have working knowledge of either Fortran 90 or C programming languages.

For more information and registration visit CSC's website.

The focus is on iterative and parallel solvers, the parallel programming models MPI and OpenMP, and the parallel middleware PETSc. Thereby, 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 HLRS, IAG, and Uni. Kassel.

For workshop details and registration, please visit the HLRS course webpage.

The Winter School 2009 continues a series of Schools that was devoted over the years to several well-defined and mature areas like "Quantum Chemistry" (2000), "Quantum Many-Body Systems" (2002), "Soft Matter" (2004), or "Nanoscience" (2006). This School will cover three main strings of themes focusing on how to deal with hard matter, soft matter, and bio matter when it is necessary to cope with disparate length and time scales. Therein aspects like coarse graining of molecular systems and solids, quantum/classical hybrid methods, embedding and multiple time step techniques, creating reactive potentials, multiscale magnetism, adaptive resolution ideas or hydrodynamic interactions will be discussed in detail.

In addition, another string of lectures will be devoted to the genuine mathematical and the generic algorithmic aspects of multiscale approaches and their parallel implementation on large, multiprocessor systems including techniques such as multigrid and wavelet transformations. Although this is beyond what can be achieved in a very systematic fashion given the breadth of the topic, introductions into fundamental techniques such as molecular dynamics, Monte Carlo simulation, and electronic structure (total
energy) calculations in the flavor of both wavefunction-based and density-based methods will be provided.

The School about "Multiscale Simulation Methods in Molecular Sciences" is tailored for PhD students and early Postdocs with a solid background in basic quantum mechanics coming from physics, chemistry, material science and related disciplines.

More information: Forschungszentrum Jülich

The goal of using this toolset is to identify bottlenecks in parallel programs such as communication and synchronization overheads, computational imbalance, etc., allowing users to easily understand the execution behavior of their applications and thereby guide tuning and optimization.

This training workshop is targeted at users of high performance computers and advance parallel systems with knowledge of parallel programming with MPI and/or OpenMP.

The registration is first come, first served. We have space for 32 participants in a PC lab for the practical sessions. Early registration is highly recommended.

For workshop details and registration, please visit:

http://www.lrz-muenchen.de/services/compute/courses/#scalasca

The course deals with current numerical methods for Computational Fluid Dynamics. The emphasis is placed on explicit finite volume methods for the compressible Euler equations. Moreover outlooks on implicit methods, the extension to the Navier-Stokes equations and turbulence modelling are given. Additional topics are classical numerical methods for the solution of the incompressible Navier-Stokes equations, Aeracoustics and high order numerical methods for the solution of systems of partial differential equations. The last day is dedicated to parallelization of explicit and implicit solvers.

Hands-on sessions will manifest the contents of the lectures. The emphasis of these session is put on the application of CFD codes, especially on grid generation, visualization and the interpretation of results. Furthermore the implementation of algorithms presented in the lectures points up the general structure of CFD codes.
The course is organized by the HLRS, the IAG and the University of Kassel. It is based on the course "Numerical Gasdynamics" held at the IAG which has been awarded the "Landeslehrpreis (prize for excellence in teaching) Baden-Württemberg 2003" (held at Uni. Stuttgart, under auspices of the BMBF project NUSS, contract 08NM227).

For workshop details and registration, please visit the HLRS course webpage.

The objective of the workshop is to present and demonstrate interesting results of UNICORE usage in Supercomputing to major stakeholders in Supercomputing from Germany and Europe as well as to members of the UNICORE Forum.

For more information see the event website.

The topics of the course include all the essential considerations for improving the performance and parallel scalability of scientific software. A significant part is reserved for optimizing participants' own applications with the help of CSC's high-performance computing experts.

For more information and registration, please visit the workshop's website:
http://www.csc.fi/english/csc/courses/archive/optimization09

The workshop will offer an introduction to OpenCL and stream/GPU programming. It will consist of lectures and hands-on experiences in using OpenCL on state-of-the-art stream processors.

The workshop will also cover lectures on stream processor architectures and programming tools for stream processors and multi-core systems. Lectures reporting on successful use of stream processors in scientific applications will also be presented.

The workshop is addressed to scientist and graduate students with interest in exploiting stream processing for applications. Good programming experience is a prerequisite.

Contributions to the workshop have been confirmed from AMD, NVIDIA, Stockholm University and Synective.

The event is part of PRACE’s training and education programme, which aims to prepare and initiate a sustainable and comprehensive European HPC education and training programme encompassing summer schools, winter schools, training workshops and training material.

For more information on the event and registration please see the following website:
http://agenda.albanova.se/conferenceDisplay.py?confId=1621

About the Stockholm Stream Computing Center: The Stockholm Stream Computing Center was formed in 2008 by scientists at KTH’s High Performance Computing Center, PDC, and the Center for Biomembrane Research (CBR) at Stockholm University.  Within the past year, the center has had two educational events. In the summer of 2008, a seminar course on writing scientific codes in CUDA (for nVidia hardware) was held.  In the winter, the center housed a workshop where AMD presented their hardware and software stack for general purpose GPU computing, and gave hands-on computer labs and one-on-one tutoring.  Further training events that help spread the understanding and efficient use of stream/GPU proramming are likely in the coming year.  More detailed information on the Stockholm Stream Computing Center can be found at: http://www.pdc.kth.se/sscc

About PRACE: The Partnership for Advanced Computing in Europe (PRACE) prepares the creation of a persistent pan-European HPC service, consisting of several tier-0 centres providing European researchers with access to capability computers and forming the top level of the European HPC ecosystem. PRACE is a project funded in part by the EU’s 7th Framework Programme (FP7/2007-2013) under grant agreement n° RI-211528.

This course is a sequel to the CSC course "Introduction to parallel programming". Its contents include more advanced features of the message passing interface (MPI) paradigm, shared memory parallelization model, as well as parallel numerical libraries and writing efficient parallel I/O.

More information: http://www.csc.fi/english/csc/courses/archive/app10

Register by January 13.

Two days of CUDA and OpenCL training and hands-on exercises - this course is intended for people who want harness the extreme number-crunching power of GPGPU technology but are new to CUDA.

To get yourself convinced, visit the CudaZone at www.nvidia.com/cuda

http://www.csc.fi/english/csc/courses/archive/cuda10

Register by January 26

The HPC Advisory Council will hold the Switzerland HPC Workshop in March 2010 together with the Swiss National Supercomputing Centre (www.cscs.ch).

The workshop will be dedicated to HPC training (interconnect architecture and advanced features, network management, HPC storage, CPU technologies, High performance visualization, accelerators and more). This is an excellent training and education opportunity for HPC IT professionals. The 3-day conference is free for attendees and we already have registrants from both Swiss National Supercomputing Centre and several universities in Switzerland, Italy and more.
Registration is required. For registration information please go to http://www.hpcadvisorycouncil.com/events/switzerland_workshop/attendee_reg.php.
The workshop includes coffee breaks and lunch courtesy of the HPC Advisory Council.
 
Call for speakers and presentations are now open. Please go to
http://www.hpcadvisorycouncil.com/events/switzerland_workshop/speakers_reg.php
to sign-up. Please use this link if you intend to propose HPC training sessions.

An intermediate and advanced level treatment of all the essential ingredients for achieving high performance in scientific computing on modern supercomputers.

More information: http://www.csc.fi/english/csc/courses/archive/code-opt-10

Register by March 17.

Python is modern, object-oriented programming language which has become popular in several areas of software development. This course introduces the basic concepts of the Python programming language and how Python can be used in the context of scientific computing. Several useful Python packages such as numpy, scipy, mpi4py are introduced. Examples include prototyping numerical problems with Python, steering simulations with Python scripts and analysing results with the help of Python.

Participants are assumed to know basic programming concepts (variables, statements, control structures), but previous knowledge of Python is not required. Course consists of lectures and of hands-on exercises.

Please visit the course homepage for more information and registration:
http://www.csc.fi/english/csc/courses/archive/python_2010

The morning will be devoted to a presentation of Chapel by Steve Deitz, from Cray Inc. USA, and the afternoon to a tutorial about both Chapel and X10 by Steve Deitz and Marc Tajchman, from CEA, France.

Participation is free of charge.

More information about the seminar and how to register is available on the seminar website.

The Virtual Institute - High Productivity Supercomputing (VI-HPS) is a joint initiative of Forschungszentrum Juelich, RWTH Aachen, TU Dresden, University of Tennessee, and Universitaet Stuttgart. To improve the quality and accelerate the development process of parallel simulation codes using MPI and OpenMP, VI-HPS develops integrated state-of-the-art programming tools for high-performance computing that assist in optimising application performance and diagnosing programming errors. As a service for application developers, VI-HPS offers trainings in using their tools.

The 6th VI-HPS Tuning Workshop will:

• give an overview of the VI-HPS programming tool suite

• explain the functionality of individual tools, and how to use them effectively

• offer hands-on experience and expert assistance using the tools

For workshop details please visit: http://www.vi-hps.org/vi-hps-tw6/

For registration and organizational details please visit:
https://subtrac.sara.nl/userdoc/wiki/vi-hps

Several sites will present their specific LUSTRE installations, their requirements and their ideas for the future of parallel file systems.

The goal is to define a common position concerning the future of LUSTRE for Linux in Europe and its relation to activities for the promotion of LUSTRE overseas.

Emphasis is put on the organization of the future development of LUSTRE for Linux in Europe and the creation of suitable support structures.

More information and how to register: http://www.fz-juelich.de/jsc/events/olfl

The first CSC Summer School takes place on 12-20 June 2010. It is aimed for graduate students working with computational sciences, e.g. computational chemistry, physics, biosciences, or engineering; also undergraduates as well as post-docs will find the school very useful.

The contents consist of lectures and hands-on training on parallel programming, code optimization and advanced usage of popular scientific programs. The venue is Solvalla Sports Institute in Nuuksio National Park in Espoo, Finland.

Visit www.csc.fi/hpc/summerschool for more information!

Scalasca is an open-source toolset that can be used to analyze the performance behavior of parallel applications and to identify opportunities for optimization. It has been specifically designed for use on large-scale systems including IBM Blue Gene and Cray XT, but is also well-suited for small- and medium-scale HPC platforms. Scalasca integrates runtime summaries with in-depth studies of concurrent behavior via event tracing. A distinctive feature is the ability to identify wait states that occur, for example, as a result of unevenly distributed workloads.

More information and how to register: 

http://www.cscs.ch/378.0.html?&tx_seminars_pi1[showUid]=20

The students will work together with scientists from JSC on topics of current interest in research and development. Depending on their previous experience and interests, they will be involved in various fields of work, for example:

 Computational Science, Applied Mathematics

• Modelling and simulation in physics, chemistry and biophysics

• Techniques of parallel molecular dynamics simulation

• Efficient methods for long-range interactions

• Parallel computational procedures in quantum chemistry and structural mechanics

• Performance evaluation of parallel algorithms in linear algebra

• Mathematical modelling and statistics, data mining

High-Performance Computing, Visualisation

• Performance analysis and optimization of parallel programs

• Programming of hierarchical parallel computer systems

• Distributed applications, interactive control and visualisation

• Virtual reality techniques for visualising scientific data

Computer Architectures, Grid Computing

• Grid computing, uniform and secure access to IT resources

• Cluster operating systems

• Interconnection networks in clusters

• Data management

• High-speed data networks

• Network management

The programme will run for ten weeks from 2 August to 8 October 2010. The students will be able to use the supercomputers at JSC, including JUGENE - currently the fastest computer in Europe. They should naturally be familiar with computer-oriented areas of their subjects. In addition, they should also have practical computer experience including at least a good knowledge of programming with C, C++ or Fortran on Unix systems.

More information and how to apply on JSC's website for Guest Student Programme on Scientific Computing.

During two intensive summer weeks at the KTH campus students will be able to learn and improve their skills in writing efficient programs for serial and parallel scientific applications.

The course carries 7.5 ECTS (European Credit Transfer and Accumulation System), where 1.5 ECTS credits are equivalent to one week's workload of 40 hours.  The student receives these credits on successful completion of the post-course project.  Participants are strongly encouraged to bring their own problems or programs for discussion and to possibly use as the basis of the post-course project.  Participants are provided with remote access to the PDC Linux clusters such as Ferlin (Dell Harpertown), Hebb (IBM Blue Gene), and Key (HP Itanium SMP).  Industrial participation is welcome.  The number of seats for all participants is limited.

Registration opened March 15; registration closes on June 1, 2010.

Outline

A number of topics will be covered in overview lectures given by international experts and in-depth technical lectures followed by hands-on computer lab sessions.  The course will consist of about 35 hours of lectures and 35 hours of computer lab sessions.  Among the
topics:

• Programming Environments at PDC

• Parallel Programming

• Modern Computer Architectures

• Parallel Algorithms

• Efficient Programming

• Case Studies

These topics will be covered both in lectures and labs by the following
teachers:

• Lilit Axner (PDC)

• David Black-Schaffer (Uppsala University)

• Iris Christadler (LRZ - Leibniz-Rechenzentrum)

• Björn Engquist (KTH and the University of Austin)

• Thomas Ericsson (Chalmers)

• Erik Hagersten (Uppsala University)

• Michael Hammill (PDC)

• Sverker Holmgren (Uppsala University and SNIC)

• Niclas Jansson (CSC - KTH School of Computer Science and

Communication)

• Lennart Johnsson (PDC and University of Houston)

• Erwin Laure (PDC)

• Michaela Lechner (PDC)

• Dag Lindbo (CSC - KTH School of Computer Science and Communication)

• Elisabet Molin (PDC)

• Jesper Oppelstrup (CSC - KTH School of Computer Science and Communication

• Michael Schliephake (PDC)

• Olav Vahtras (PDC)

• Anders Ynnerman (Linköpings Universitet)

Computer Laboratories

Roughly half of the class time will be spent hands-on in the lab.  The lecturers and the PDC staff will assist in the computer labs.
Students who do not already have an account at PDC will receive one.
These accounts will stay active after the course so students may work on the post-course project.

PDC

Visiting address:  Teknikringen 14, Plan 4, KTH, Stockholm
Mail: PDC, KTH, SE-100 44 Stockholm
Summer School Email: summer-2010-info(at)pdc.kth.se
URL: http://www.pdc.kth.se/
Phone: +46 8 790 78 00
Fax: +46 8 24 77 84

More information and registration

To register, and find out more about the class, visit the course Web page at http://www.pdc.kth.se/education/summer-school/

Program, additional information and registration on:

http://www.csc.fi/english/csc/courses/archive/complexflow