Events and Workshops
The following events and workshops are organized by SPPEXA or by one of its projects.
- 21st IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC 2020)
This workshop will be held in Hilton New Orleans Riverside, New Orleans, Louisiana, USA on May 22, 2020 in conjunction with the 34th IEEE Internatipnal Parallel and Distributed Processing Symposium (IPDPS 2020).
It will bring together computer scientists, applied mathematicians and researchers to present, discuss and exchange ideas, results, work in progress and experiences in the area of parallel and distributed computing for problems in science and engineering applications and inter-disciplinary applications. -
Workshop on Programming and Performance Visualization Tools (ProTools 19)
The Workshop on Programming and Performance Visualization Tools (ProTools) on November 17, 2019 in Denver, Colorado, USA intends to bring together HPC application developers, tool developers, and researchers from the visualization, performance, and program analysis fields for an exchange of new approaches to assist developers in analyzing, understanding, and optimizing programs for extreme-scale platforms. -
Argonne Training Program on Extreme Scale Computing
The Argonne Training Program on Extreme-Scale Computing (ATPESC) provides intensive, two-week training on the key skills, approaches, and tools to design, implement, and execute computational science and engineering applications on current high-end computing systems and the leadership-class computing systems of the future.
The core of the program will focus on programming methodologies that are effective across a variety of supercomputers and that are expected to be applicable to exascale systems. Additional topics to be covered include computer architectures, mathematical models and numerical algorithms, approaches to building community codes for HPC systems, and methodologies and tools relevant for Big Data applications.
Doctoral students, postdocs, and computational scientists interested in attending ATPESC can review eligibility and application details on the application instructions web page.
Markus Huber (TERRA-NEO) joined this workshop (28.7.2019 – 9.8.2019) and was cofinanced by SPPEXA. He would recommend this workshop to future generations of PhD students/post-docs from SPPEXA since it is a great opportunity to learn more about PRACE's offers.
-
ISC High Performance 2019
The ISC High Performance conference will bring together over 3,500 researchers and commercial users, and 160 exhibitors, ready to share their experiences with the latest technology and products of interest to the high performance computing (HPC) community.
Together with our 2019 program chair, Prof. Yutong Lu, we present you 13 topics that we believe are vital to shaping the HPC industry.
One of the expanded topic areas this year is machine learning, a set of technologies that has been adopted by high performance computing users to advance scientific research and commercial applications in novel ways and by HPC vendors to extend their reach into additional markets.
-
Call for contributions: PhD Forum at ISC High Performance 2019
PhD Forum at ISC High Performance 2019, Frankfurt, Germany, Monday, June 17, 2019.
Submission deadline: Wednesday, February 13, 2019, 11:59 pm AoE
The ISC High Performance conference is Europe’s largest international conference and exhibition for high performance computing (HPC), networking and storage. The ISC 2019 PhD Forum provides an opportunity for PhD students to present research results in a setting that sparks scientific exchange and lively discussions.The PhD Forum will be held on Monday, June 17, 2019 and consists of two parts: a set of back-to-back short lightning talks followed by a poster presentation session.
Springer, the international publisher will again sponsor the call for PhD Forum with the ISC 2019 PhD Forum Award.
AREAS OF INTEREST
The topics of research should be related to HPC and may range from performance analysis to optimization, from tools to applications, and from software engineering to hardware architectures, with a cross-cut on reproducible and open-science research. Essentially, all areas covered in the call for research papers are also accepted for the PhD Forum submissions. We strongly encourage submissions by students in an early phase of their PhD track
-
SPPEXA Women’s Workshop 2019
The first SPPEXA workshop for women in HPC will take place in the vicinity of Munich (Starnberger See) from January 23rd until January 25th 2019. The workshop will bring together researchers at all career stages, with an emphasis on supporting younger researchers in their developing career paths. Women in SPPEXA, and the larger HPC community, will be supported through the exchange of experiences, inspiration from sessions with invited senior researchers, and relevant soft-skills education. More information. -
Multi-Physics Simulations with the Coupling Library preCICE
preCICE is an open-source coupling library for partitioned multi-physics simulations. It enables the efficient, robust, and parallel coupling of seperate single-physics solvers. This includes, but is not restricted to fluid-structure interaction. preCICE treats these solvers as black-boxes and, thus, only minimally-invasive changes are necessary to prepare a solver for coupling. Thereby, existing sophisticated solvers can be used for each of the physics in a multi-physics simulation. Ready-to-use adapters for well known commercial and open-source solvers, including OpenFOAM, SU2, Calculix, ANSYS Fluent, and COMSOL, are available. The software offers methods for equation coupling, fully parallel communication, and data mapping schemes.
This minisymposium at the ECCOMAS Coupled Problems, in Sitges (Spain) from June 3rd until June 5th, brings together users and developers of the software. It enables the exchange of academic and industrial users among themselves, which otherwise would not know much of each other. Furthermore, the developer team can get direct feedback from the users, who they sometimes only know from mailing list conversations. Last, the software and its capabilities can be presented to others in a full and broad sense as not only the developers talk about their software, but also users report on experiences. -
Efficient Computational Methods for MD
In the minisymposium "Efficient Computational Methods for Molecular Dynamics" at the SIAM CSE conference in Spokane, Washington, USA February 25 – March 01 2019, challenges for large-scale molecular dynamics applications at exascale are pointed out and potential solutions in terms of simulation methodology are discussed. The focus is put on strategies to exploit current supercomputing systems in terms of efficient algorithms, programming, and self-adaption of code (auto-tuning). This picture is complemented by discussions on the integration of new methodological approaches into community software, such as GROMACS (being the essential software for the GROMEX project), ESPREsSo, and ls1 mardyn, which will eventually enable end users to leverage today's and tomorrow's supercomputing systems for their applications. -
Multiphysics Simulations with Time Resolved Turbulence
This minisymposium at the ECCOMAS Coupled Problems, in Sitges (Spain) from June 3rd until June 5th, invites experts in the field of coupled simulations to talk about coupled multi-physics problems related to turbulent flow. This includes mainly fluid-structure interaction and aeroacoustics. Simulation of turbulent flow is still one of the most challenging tasks in Computational Fluid Dynamics (CFD), due to the multiscale nature of the problem. While considering additional physical fields in CFD is a well-established research topic, coupling turbulent flow provides additional difficulties that are rarely addressed specifically. This includes computational efficiency/scalability, model/algorithm selection or development, and even appropriate visual representation. Additional difficulties occur when more than one field is coupled to the flow. This workshop aims to address comparisons of different approaches to these coupling scenarios, and validation methods.
-
Performance and Software Engineering in Scientific Computing
The workshop is a special track at the PDSEC workshop at IPDPS 2019 (Brazil) and focuses on performance engineering and software maintenance for codes in the scientific research area, in particular in the field of engineering. We bring together code developers from the engineering field with HPC- and software experts. It is held on 24.05.2019. -
HPC Methods in the Geosciences (SIAM Geosiences Conference)
Many phenomena in geophysics, such as mantle convection, seismic wave propagation, oceanic circulation, and the motion of land and sea ice are characterized by complex multiscale physical processes. Accurate computer simulations of these phenomena require suitable mathematical models, high spatial and temporal resolution and, thus, efficient parallel algorithms and implementations. The immense compute power on current and future supercomputers is indispensable for this research, but it brings along challenges for software development, mathematical modeling and the construction of efficient and scalable algorithms.
This minisymposium at the SIAM Geoscience Conference, in Houston, USA from March 11, 2019 to March 14, 2019, addresses researchers working in the interdisciplinary field of complex modeling, mathematical algorithms and their implementation for grand-challenge applications in geophysics on state-of-the-art supercomputers. A special focus is on the reusability and the high-performance awareness of the presented approaches in different software packages. -
Advances in High-Performance Computational Earth Sciences: Applications & Frameworks (IHPCES)
The IHPCES workshop in Faro, Algarve, Portugal June 12 – June 14 2019 provides a forum for presentation and discussion of state-of-the-art research in high performance computational Earth sciences. The emphasis of this seventh workshop continues to be on advanced numerical algorithms, large-scale simulations, architecture-aware and power-aware applications, computational environments and infrastructure, and data analytics methodologies in geosciences. With the imminent arrival of the exascale era, strong multidisciplinary collaborations between these diverse scientific groups are critical for the successful development of Earth science HPC applications.
The workshop facilitates communication between Earth scientists, applied mathematicians, computational and computer scientists. This workshop therefore presents a unique opportunity to exchange advanced knowledge, computational methods, and science discoveries in computational geosciences. Work focusing emerging data and computational technologies that benefit the broader geoscience community is especially welcome.
At the SC 18 - the International Conference for High Performance Computing, Networking, Storage, and Analysis - in Dallas, November 11-16, SPPEXA is represented, among many other things, through the following two contributions:
A SPPEXA team from the FAU Erlangen joins the student cluster competition. The Student Cluster Competition (SCC) was developed in 2007 to provide an immersive high performance computing experience to undergraduate and high school students. With sponsorship from hardware and software vendor partners, student teams design and build small clusters, learn designated scientific applications, apply optimization techniques for their chosen architectures, and compete in a non-stop, 48-hour challenge at the SC conference to complete a real-world scientific workload, showing off their HPC knowledge for conference attendees and judges.
Workshop on Extreme-Scale Programming Tools, November 16
The workshop is the seventh in a series of SC conference workshops organized by the Virtual Institute - High Productivity Supercomputing (VI-HPS), an international initiative of HPC researchers and developers focused on programming and performance tools for parallel systems.
The objectives of this HPC symposium are to bring together the projects of SPPEXA that are focused on large-scale numerical simulation with applications in science and engineering and to be a forum for the exchange of results and ideas in the area of HPC. Another goal is to help increase the visibility of SPPEXA within the international research community. The program will consist of high-level invited talks and a poster session including a Poster Blitz. We will also provide a Best Poster Award with a monetary prize and a certificate.
Parallel and Distributed Computing (PDC) is nowadays omnipresent. It is in all the computational environments, from mobile devices, laptops and desktops to clusters, large-scale data centers and supercomputers, often comprising CPUs and/or coprocessors of different types (GPU, MIC, FPGA). It becomes now vital to train new generations of scientists and engineers in the use of these computational systems: parallelism-related topics must be incorporated in Computer Science (CS) and Computer Engineering (CE) programs.
In this context, the 4th European Workshop on Parallel and Distributed Computing Education for Undergraduate Students (Euro-EDUPAR) invites unpublished manuscripts from individuals or teams from academia, industry, and other educational and research institutes on topics pertaining to the teaching of PDC topics in the Computer Science and Engineering curriculum as well as in Computational Science with PDC and/or High Performance Computing (HPC) concepts, with emphasis on European undergraduate teaching.
-
GROMACS: From Blackbox to Scalable Simulation Toolkit
The focus of this workshop, held from 04.09 - 06.09.2018 at the Max Planck Institute for Biophysical Chemistry, is how to make GROMASC more versatile with respect to the development and incorporation of new and enhanced simulation protocols. Examples would be simulations at constant pH, and the incorporation of experimental data to guide simulations. Questions to be discussed include: How can a highly optimized, parallel simulation code provide a general enough infrastructure that allows the incorporation of new methods in a straightforward way? Can it do so without sacrificing (parallel) performance? Can the software be made less monolithic and black-box like, but more modular and extensible so that providing an own method becomes less of a challenge for the average scientist that is not at the same time a GROMACS coding expert?
-
SPPEXA COLOC Poster Session on Data Locality at Euro-Par 2018
The topic of the Poster Sessions is Data Locality in all its forms.
Specifically this forum asks for submission on topics including, but
not limited to, those listed below:- Programming abstractions for data locality
Submit your Poster using EasyChair:
- Approaches for multi-level locality
- Support for data locality in task-based programming models
- Global address space approaches and data locality
- Language extensions and domain-specific libraries for locality
- On-chip networks and data locality
- Hardware mechanisms for exploiting locality
- Locality in large-scale HPC interconnect networks (inter-node locality)
- Advances in cache coherence protocols and modern shared memory systems
- Data locality and communication avoidance
- Data locality and multi-tier memory systems
- Approaches for processing in memory
- Dataflow approaches
https://easychair.org/conferences/?conf=sppexacolocposter18
Last date for submission: July 31, 2018
Travel support is available
For more information: http://sppexa-coloc-postersession.org/
-
High performance Computing Introductory course
A High Performance Computing introductory course will take place at the summer university "Informatica Feminale", at Bremen, from August 9 to 10, 2018. More details can be found at https://www.informatica-feminale.de/re/en/registration.php course IF SOF 01.
SPPEXA offer grants for travel and accommodation to support students who want to join the course. For more information, please contact Dörte Sternel doerte.sternel@ hpc-hessen.de
- Software workshops @ ESCO, June 3 - 8, 2018, Pilsen, Czech Republic
preCICE - A Coupling Library for Partitioned Multi-Physics Simulations
preCICE (Precise Code Interaction Coupling Environment) is a coupling library for partitioned multi-physics simulations, including, but not restricted to fluid-structure interaction and conjugate heat transfer simulations. Partitioned means that preCICE couples existing programs (solvers) capable of simulating a subpart of the complete physics involved in a simulation. This allows for the high flexibility that is needed to keep a decent time-to-solution for complex multi-physics scenarios. The software offers methods for transient equation coupling, communication means, and data mapping schemes. Ready-to-use adapters for well-known commercial and open-source solvers, such as OpenFOAM, SU2, or CalculiX, are available. Adapters for in-house codes can be implemented and validated in only a few weeks. preCICE is an open-source software under the LGPL3 license.
pyMOR - Model Order Reduction with Python
Reduced basis methods are projection-based model order reduction techniques for reducing the computational complexity of solving parametrized partial differential equation problems. Written in Python, pyMOR is a freely available, open source software (BSD-2 licensed), library of model order reduction algorithms. As its main design feature, all reduction algorithms in pyMOR are implemented generically via operations on well-defined vector array, operator and discretization interface classes. This allows for an easy integration with existing open-source high-performance partial differential equation solvers without adding any model reduction specific code to these solvers. Currently, there are bindings available for FEniCS, NGSolve,deal.II, and dune-gdt.
Please check pymor.org/esco18/ for details about this hands-on session. - 4th European Workshop on Parallel and Distributed Computing Education for Undergraduate Students (Euro-EDUPAR)
The 4th European Workshop on Parallel and Distributed Computing Education for Undergraduate Students (Euro-EDUPAR) will be held on 27th of August 2018 and invites unpublished manuscripts from individuals or teams from academia, industry, and other educational and research institutes on topics pertaining to the teaching of PDC topics in the Computer Science and Engineering curriculum as well as in Computational Science with PDC and/or High Performance Computing (HPC) concepts, with emphasis on European undergraduate teaching. Paper submission deadline is May 4, 2018.
- Project Poster Session@ISC 2018
The project poster session is an excellent opportunity to present information about your research ideas and projects at ISC 2018. With more than 3,000 participants, ISC has established itself as the HPC event in Europe to disseminate ongoing and future research work, as well as foster discussion within the community, and engage in international cooperation. The Project Posters will be on Display from Monday, June 25th until Wednesday, June 27th 2018. - PhD Forum@ISC 2018
The ISC 2018 PhD Forum will be held on Monday, June 25, 2018 and consists of two parts: a set of back-to-back short lightning talks followed by a poster presentation session. Topics will be related to HPC and range from performance analysis to optimization, from tools to applications, and from software engineering to hardware architectures, with a cross-cut on reproducible and open-science research.
- Solving Complex Partial Differential Equations on Massively Parallel Machines
Todays simulation models for technical and biological applications are mostly highly complex, multi-scale and multi-physics. They require very high resolution to achieve the desired accuracy. This calls for their efficient implementation on supercomputers. From the German priority program SPP 1648 -- Software for Exascale Computing this minisymposium, held in Tokyo from Mar 07-10 2018, presents three groups. ExaMAG targets the structure formation of the universe, ExaFSA fluid-structure-acoustic interactions, and ExaStencils pursues a domain-specific design approach for stencil codes, a fundamental building block of most solvers. We present methods and software advancing the state-of-the-art towards modular, portable, efficient and scalable simulation frameworks. - 5th Workshop on Sparse Grids and Applications
Sparse grids have gained increasing interest in recent years for the numerical treatment of high-dimensional problems. Where classical numerical discretization schemes fail in more than three or four dimensions, sparse grids allow to overcome the curse of dimensionality to some extent - extending the number of dimensions that can be dealt with.
The aim of this workshop is to bring together researchers and practitioners using sparse grids and their variants. Both theoretical and practical aspects are highly welcome.
It will be held from 23.07.2018-27.07.2018 at the Institute for Advanced Study in Garching. - 3rd Workshop on Parallel Programming Models – Productivity and Applications
The goal of this workshop is to continue the successful workshop series and foster collaboration after previous workshops in Tokyo and Versailles regarding the three fields parallel programming models, HPC tools to foster productivity, and applications in numerical computing form the common interests of the SPPEXA projects MYX, ESSEX-II and DASH.
This time it is held in Aachen at the IT Center from the RWTH Aachen University on the 15th of March.
The opportunities for young researchers to participate in the workshop and to present their work will support the exchange of ideas concerning how research within the projects can influence the high performance computing community on the way to Exascale, and provide an overview about the international state-of-the-art. Given the attendance from Japan, France and Germany, a wide range of approaches and ideas will be represented. The agenda and the social interactions are expected to make new contacts among the participants to build upon in the future.
- Multi-Physics Simulations with the Coupling Library preCICE
This minisymposium will be held at the ECCOMAS ECCM-ECFD in Glasgow from 11.06.-15-06.2018.
It brings together users and developers of the Software preCICE. preCICE is an open-source coupling library for partitioned multi-physics simulations. It enables the efficient, robust, and parallel coupling of seperate single-physics solvers. This includes, but is not restricted to fluid-structure interaction. preCICE treats these solvers as black-boxes and, thus, only minimally-invasive changes are necessary to prepare a solver for coupling. Thereby, existing sophisticated solvers can be used for each of the physics in a multi-physics simulation. Ready-to-use adapters for well known commercial and open-source solvers, including OpenFOAM, SU2, Calculix, ANSYS Fluent, and COMSOL, are available. The software offers methods for equation coupling, fully parallel communication, and data mapping schemes. It enables the exchange of academic and industrial users among themselves, which otherwise would not know much of each other. Furthermore, the developer team can get direct feedback from the users, who they sometimes only know from mailing list conversations. Last, the software and its capabilities can be presented to others in a full and broad sense as not only the developers talk about their software, but also users report on experiences. - 6th Workshop on Parallel-in-Time Integration
This workshop will be held in Monte Verità, CH from 23.10.-27.10.2017. Even though the scalability needed for the use of high performance computers is provided by pure spatial parallelization, there are still many unanswered questions. This includes mathematical questions as well as questions from the computer science perspective, like how to implement parallel-in-time algorithms in the most efficient way. The workshop brings together experts from computer science, mathematics, and application fields. It is the 6th workshop in a row, previous workshops were held in Banff, Toulouse, Dresden, Jülich, Manchester, and Lugano.
- Parallel Programming Models -- Productivity and Applications (2nd Edition)
After the first edition of this workshop, held in Tokyo, which allowed to identify opportunities for interaction between the three SPPEXA-projects MYX, ESSEX-II and Dash, it was decided to try to organize another join workshop in Europe with these 3 projects.
The goal of this second edition of Workshop (held on the 18th of October at the University of Versaille, France) is to foster collaborations between these three Projects and attract attendance from Europe and Japan beyond the SPPEXA projects.
The opportunities for young researchers to participate in the workshop and to present their work will support the exchange of ideas concerning how research within the projects can influence the high performance computing community on the way to Exascale, and provide an overview about the international state-of-the-art. Given the attendance from Japan, France and Germany, a wide range of approaches and ideas will be represented. The agenda and the social interactions are expected to make new contacts among the participants to build upon in the future.
- GAMM Applied Numerical Linear Algebra 2017 (HPC)
This is the annual workshop of the GAMM Special Interest Group Applied Numerical Linear Algebral, it will be held at the University of Cologne from 07.09-08.09.2017.
Each year there is a special topic with invited speakers and additional contributed talks. This year's special topic is High Performance Computing. The invited speakers Pierre Gosselet, Oliver Rheinbach, and Wim Vanroose are all specialists in this field. With respect to the special topic HPC it is one goal of the workshop to bring together specialists from the Applied Numerical Linear Algebra Community working on HPC algorithms with a relation to numerical linear algebra, e.g., communication avoiding Krylov solvers, domain decomposition methods, algebraic multigrid methods, new nonlinear solvers avoiding communication and localizing work, etc.
-
Project Poster Session@ISC 2017
The project poster session is an excellent opportunity to present information about your research ideas and projects at ISC 2017. For attendees it is an opportunity to gain an overview of new developments, HPC research and engineering activities. Many projects from SPPEXA are displayed from Monday, June 19 through Wednesday, June 21, 2017 in the exhibition hall. During the two coffee breaks on Tuesday and Wednesday afternoon, ISC attendees will have the opportunity to meet the authors at their posters to discuss their projects. -
PhD Forum@ISC 2017
The ISC 2017 PhD Forum provides an opportunity for PhD students to present research results in a setting that sparks scientific exchange and lively discussions. The PhD Forum will be held on Monday, June 19, 2017 and consists of two parts: a set of back-to-back four-minute lightning talks followed by a one-hour poster session. The lightning talk gives a quick, to-the-point presentation of research objectives and early results, while the poster provides more in-depth information as a starting point for intense discussions. - SPPEXA@PASC 2017
SPPEXA participates in the Platform for Advanced Scientific Computing, in Lugano, June 26-28 2017, amongst others in terms of three minisymposia;
1) Computing bulks of inner Eigenpairs of large sparse matrices: from applications and algorithms to performance and software engineering, organized by the project ESSEX,
2) Exa-scale solver for application-driven science, organized by the project TERRA-NEO and EXA-Dune,
3) Recent Advances in Fault-Tolerant, Asynchronous and Communication-Avoiding Algorithms, organized by the project EXA-DUNE,
and an exhibition booth.
-
Exascale I/O for Unstructured Grids
Held at “Deutsches Klimarechenzentrum” in Hamburg from Sept. 26th-27th 2017, this workshop will bring together experts from application development, middleware and storage design to discuss the issues of storing and accessing large datasets, especially data on unstructured grids. The goal is the identi?cation of future proof strategies for the e?cient access large data sets with respect to an optimal utilizsation of modern storage subsystems and memory hierarchies.
-
Exascale data generation and analysis for MD simulation
The workshop will be held at the Max Planck Institute for Biophysical Chemistry in Göttingen, from May 25th-28th 2017. The workshop will address how to communicate and access data generated by massively parallel biomolecular simulations, and harmonize software interfaces for inter and intra software data communication. Beyond pure performance gains, these data interfaces will add increased ?exibility and usability for the scienti?c community.
- Parallel Programming Models - Productivity and Applications
The goal of this workshop, held in Tokyo at the University of Tsukuba on April 6th 2017 is to identify opportunities for interaction between the three SPPEXA projects MYX, ESSEX-II and DASH and to foster collaboration. The workshop will be embedded into the CREST workshop series and consequently attract attendance from Japan beyond the SPPEXA projects. Young researchers are given the opportunity to participate in the workshop and to present their work and this will support the exchange of ideas concerning how research within the projects can influence the high performance computing community on the way to Exascale, and provide an overview about the international state-of-the-art.
- Understanding I/O Performance Behavior (UIOP)
This workshop is held in Hamburg from Mar. 23rd-24th 2017, and its main goal is the discussion of tools to identify (in-)e?cient usage of I/O resources on modern storage subsystems from the perspective of users and data centers. The workshop covers: 1) a discussion of design alternatives of storage architectures and their implications on user work?ows; 2) telemetry and monitoring information necessary to enable e?cient performance optimization of system and applications; 3) the development of representative benchmarks resembling the applications’ needs. It is intended to use the workshop to de?ne a meaningful I/O benchmark for future systems as part of the (currently developed) IO-500 list.
- Fast high order DG methods for future architecture
In this workshop held at the Mathematikon, Uni Heidelberg, from Feb. 20th-22nd, we discuss mathematical and algorithmic problems arising when implementing fast, massively parallel solvers for high-order DG discretizations of PDE problems.
- SPPEXA@PMAA 2016
SPPEXA participates in the 9th International Workshop on Parallel Matrix Algorithms and Applications, July 6-8 2016, Bordeaux, amongst others in terms of the minisymposium "Efficient computation of inner eigenvalues of large sparse matrices". - PhD Forum@ISC 2016
The ISC 2016 PhD Forum provides an opportunity for PhD students to present research results in a setting that sparks scientific exchange and lively discussions. The PhD Forum will be held on Monday, June 20, from 1:00 pm – 3:00 pm, and consists of two parts: a set of back-to-back three-minute lightning talks followed by a one-hour poster session. Travel grants and support by SPPEXA. - SPPEXA@PASC 2016
SPPEXA participates in the Platform for Advanced Scientific Computing, June 8-10 2016, Lausanne, amongst others in terms of the minisymposium "Development, Adaption, and Implementation of Numerical Methods for Exascale" and an exhibition booth. - SPPEXA@ESCO 2016
SPPEXA participates in the European Seminar on Computing, June 5-10 2016, Pilsen, amongst others in terms of the minisymposium "HPC-FEA: High-Performance Computing in Finite Element Applications". - SPPEXA@SIAM PP 2016
SPPEXA participates in the SIAM Conference on Parallel Processing for Scientific Computing, April 12-15 2016, Paris, with various activities, including (but not limited to) the minisymposia Extreme Scale Solvers for Coupled Problems, Parallel Programming Frameworks, and Nonlinear Preconditioning, as well as with an exhibition stand. - SPPEXA Symposium
The SPPEXA Symposium takes place Jan 25-27, 2016 at the LRZ, Garching. It comprises three invited talks and 14 minisymposia in two parallel sessions. More information is provided here. - Tutorials Insightful Automatic Performance Modeling
The Catwalk Project offers two conference tutorials with the title "Insightful Automatic Performance Modeling". The first will take place at EuroMPI'15 in Bordeaux, France, and the second at SC15 in Austin, Texas. The two tutorials teach the usage of a performance modelling tool developed in Catwalk. Please check the details here. - ESPT 2015: Workshop on Extreme-Scale Programming Tools at SC15.
A workshop on Extreme-Scale Programming Tools will be held with the SC15 conference in Austin on 16 November 2015. Original contributions may be submitted as short paper (up to 6 pages) or regular contributions (up to 10 pages) via EasyChair. More information available here. - Workshop on Software Frameworks for Scalable Scientific Simulations.
The aim of this workshop is to address performance throughout entire simulation
frameworks, to highlight existing or potential bottlenecks, and to investigate how
these might be overcome in real use cases. The workshop seeks to discuss challenges, methods and best-practice examples. For session details look here.
The workshop will be presentation and discussion based.
Specifically we call for talk proposals to these topics:
* scalable data organization: storage, conversion and reduction
* scalable mesh generation
* scalable interaction between framework components
* scalable analysis frameworks
* scalable visualization
If you would like to present your work in a ~15 minute talk, please submit an
extended abstract to: isc.ws-sts@ by May 24th. uni-siegen.de
- Workshop on Parallel-in-Time Integration, Dresden, Germany, May 2015. With the ever increasing availability of distributed processing power new ways to exploit parallelism have to be found, with one emerging trend being the parallelization in the time domain. In this workshop, we want to bring together scientists working on parallel time integration methods (like Parareal, PFASST, etc.) with scientists from the areas of atmospheric and multibody dynamics. We aim at exploring similarities and mutual benefits between the more traditional multiscale/multirate/cosimulation time integration methods and the relatively new parallel-in-time algorithms. For registration and more information visit next page.
- DUNE/PDELab Course (February 23-27, 2015). This one week course will provide an introduction to the most important DUNE modules and especially to DUNE-PDELab. At the end the attendees will have a solid knowledge of the simulation workflow from mesh generation and implementation of finite element and finite volume methods to visualization of the results. Topics covered are the solution of stationary and time-dependent problems, as well as local adaptivity, the use of parallel computers and the solution of non-linear PDE's and systems of PDE's. For registration and further information see link.
- The SC14 Panels. Funding strategies for HPC software beyond borders. Info.
- The Dagstuhl-Seminar "Advanced Stencil-Code Engineering" takes place April 12 – 17 , 2015. The seminar will investigate and further the state of the art of stencil-code engineering. The goal of the seminar is to raise the level of abstraction for application programmers significantly and to support this raise with an automated software technology that generates highly efficient massively parallel implementations which are tuned to the specific problem at hand and the execution platform used. Further information you can find here.
- International Workshop "Sparse Solvers for Exascale: From Building Blocks to Applications." Scalable algorithms - Solver efficiency - Performance engineering - Energy efficiency - Fault tolerance. The International Workshop is funded by the Alfried Krupp von Bohlen und Halbach-Stiftung, Essen, the German Research Foundation, Bonn, and Intel. It will be held on the 23-25th March 2015. Additional information can be found here.
- A minisymposium "Towards Exascale Simulations and Applications" will be held at the Third International Workshop on Computational Engineering (ICCE), Oct 6-10 2014, in Stuttgart. In this minisymposium, speakers from various SPPEXA projects (GROMEX, EXASTEEL, ExaFSA, EXA-DUNE, EXAHD) present their latest work with particular regard to numerical simulation software for application on peta- and exascale supercomputers. Common issues arising for each particular application are discussed and strategies to resolve them are pointed out. For more information, see here or contact: Philipp Neumann and Alfredo Parra Hinojosa.
- Workshop on "Numerical Methods for High-Performance Computers".
The aim of this workshop is to bring together computer scientists and mathematicians to provide an overview of the state-of-the-art in numerical methods for the solution of partial differential equations and related fields in order to discuss the mutual implications of expected exascale hardware and these numerical algorithms. There will be 10 invited presentations as well as contributed talks. More information regarding contribution and registration can be obtained from here.
The workshop is part of DFG's Priority Programme 1648 "Software for Exascale Computing" and will be held at the Interdisciplinary Center for Scientific Computing of the University of Heidelberg, Heidelberg, Germany, December 1-3, 2014.
The Workshop organizers:
Peter Bastian, Hester Bijl, Barbara Wohlmuth and Christian Klingenberg.
- SPPEXA@Euro-Par 2014.
A workshop SPPEXA is held at Euro-Par on 25.8.2014. The workshop's goal is to serve as a platform for international guests to learn about the activities in the priority programme SPPEXA, and for SPPEXA members to learn about the progress in SPPEXA. Presentations are by invitation only and, except for an opening keynote, only by SPPEXA members. Six or seven SPPEXA projects of particular interest to the Euro-Par community will be presented. The papers (in the usual Euro-Par format of 12 pages 11pt LNCS style) will go into the Euro-Par 2014 workshop postproceedings. Each submission will be reviewed by three of the six committee members. More information can be found here.
- 3rd Extreme-Scale Programming Tools workshop at SC14.
The 3rd workshop on Extreme-Scale Programming Tools will be held with the SC14 conference in New Orleans on 17 November 2014. One-page abstracts for proposed presentations can be submitted until 30 June 2014. More information available here.
- A workshop on HPC for Life-Science Researchers will be held on September 5, 2014 at the KIT Karlsruhe. The workshop will provide the participants with an introduction to high performance computing, covering computing platforms and parallel programming. Registration deadline: August 8, 2014. See details here.
- The 3rd Workshop on Parallel-in-Time Integration will be held at research center Jülich on May 26-28, 2014. More information available here.
- The Annual Plenary Meeting 2014 will be held at TU Dresden on April 02, 2014, together with a gender training on April 01, 2014 in the afternoon (following up the workshop EXASTENCILS 2014).
- A workshop ExaStencils 2014 will be held at TU Dresden from March 31 to April 01, 2014. More information available here.
- The project EXA-DUNE will provide an intensive course on the DUNE software from March 24 to 28, 2014 at the University of Heidelberg.
See details and registration deadlines here.
- The GAMM Annual Meeting 2014 at the University of Erlangen will be hosting a Young Researchers' Minisymposium on Time-parallel Methods. The talks will be held on March 11, 2014. More information available here.
- The two-part minisymposium Toward Multilevel Solvers for Exascale with several speakers out of different SPPEXA projects will take place at the SIAM PP14 conference on February 20, 2014 in Portland, Oregon, USA. See more details on part I and on part II.
- On February 19, 2014 the EXASOLVERS project will be represented at the SIAM PP14 conference by a minisymposium on Implementation Aspects of Parallel-in-time Methods on HPC Systems. More details here.
- The first international workshop on high-performance stencil computations will take place on January 21, 2014 in Vienna, Austria. Read more.
- The SPPEXA project FFMK will mount an informal, invitation-only Workshop on System Software for Exascale Computing. It will take place on December 11 - 13, 2013 at Hebrew University of Jerusalem. More details available here.
- A SPPEXA workshop on new algorithms for exascale computing will be held at the University of Cologne on December 04 - 06, 2013. Read more.
- The LRZ in Garching near Munich offers a PRACE PATC Course on Node-Level Performance Engineering on December 03 - 04, 2013. More information and registration here.
- On November 18, 2013 SPPEXA co-organizes a workshop on Extreme-Scale Programming Tools at Supercomputing 2013. More details can be found here.
- The first Doctoral Retreat & Coding Week is held on September 16 - 20, 2013. More information is available here.
- The EXAHD minisymposium High-Dimensional Meets Parallel is being hosted by ParCo 2013 on September 13, 2013 at the TU Munich. Read more.
- On June 19, 2013 SPPEXA hosts a satellite event at ISC 2013. See SPPEXA @ ISC 2013.
- The first Annual Plenary Meeting is held on March 22, 2013 in Munich.
- The SPPEXA ESSEX project presents a two-day short course on “Node-Level Performance Engineering” on March 13 - 14, 2013. More information is available here.
- The DUNE PDELab Spring Course is held on March 11-15, 2013. It is organized by the SPPEXA EXADUNE project. More information is available here.