Running Research and Development Projects

DFG: German Research Foundation

Research Software Sustainability

preDOM – Domestication of the Coupling Library preCICE

Funded by	DFG
Begin	2018
End	2021
Leader	Dr. rer. nat. Benjamin Uekermann, Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff
Contact person	Dr. rer. nat. Benjamin Uekermann

Brief description

The purpose of the proposed project is to domesticate preCICE – to make preCICE usable without support by the developer team. To achieve this goal, usability and documentation of preCICE have to be improved significantly. Marketing and sustainability strategies are required to build-up awareness of and trust in the software in the community. In addition, best practices on how to make a scientific software prototype usable for a wide academic range, can be derived and shall be applied to similar software projects.

Reference: preCICE Webpage, preCICE Source Code

SeisSol-CoCoReCS – SeisSol as a Community Code for Reproducible Computational Seismology

Funded by	DFG
Begin	2018
End	2021
Leader	Univ.-Prof. Dr. Michael Bader, Dr. Anton Frank, (LRZ), Dr. Alice-Agnes Gabriel (LMU)
Staff	Ravil Dorozhinskii, M.Sc., Lukas Krenz, M.Sc., Carsten Uphoff
Contact person	Univ.-Prof. Dr. Michael Bader

Brief description

The project is funded as part of DFG's initiative to support sustainable research software. In the CoCoReCS project, we will improve several issues that impede a wider adoption of the earthquake simulation software SeisSol. This includes improvements to the workflows for CAD and meshing, establishing better training and introductory material and the setup of an infrastructure to reproduce test cases, benchmarks and user-provided simulation scenarios.

Priority Program 1648 SPPEXA - Software for Exascale Computing

Coordination Project

Funded by	DFG
Begin	2012
End	2020
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Severin Reiz
Contact person	Univ.-Prof. Dr. Hans-Joachim Bungartz

Brief description

The Priority Programme (SPP) SPPEXA is different from other SPP with respect to its genesis, its volume, its funding via DFG's Strategy Fund, with respect to the range of disciplines involved, and to a clear strategic orientation towards a set of time-critical objectives. Therefore, despite its distributed structure, SPPEXA also resembles a Collaborative Research Centre to a large extent. Its successful implementation and evolution will require both more and more intense structural measures. The Coordination Project comprises all intended SPPEXAwide activities, including steering and coordination, internal and international collaboration and networking, and educational activities.

Reference: Priority Program 1648 SPPEXA - Software for Exascale Computing

ExaFSA - Exascale Simulation of Fluid-Structure-Acoustics Interaction

Funded by	DFG
Begin	2012
End	2019
Leader	Prof. Dr. Miriam Mehl
Staff	Dr. rer. nat. Benjamin Uekermann, Benjamin Rüth
Contact person	Prof. Dr. Miriam Mehl

Brief description

In scientific computing, an increasing need for ever more detailed insights and optimization leads to improved models often including several physical effects described by different types of equations. The complexity of the corresponding solver algorithms and implementations typically leads to coupled simulations reusing existing software codes for different physical phenomena (multiphysics simulations) or for different parts of the simulation pipeline such as grid handling, matrix assembly, system solvers, and visualization. Accuracy requirements can only be met with a high spatial and temporal resolution making exascale computing a necessary technology to address runtime constraints for realistic scenarios. However, running a multicomponent simulation efficiently on massively parallel architectures is far more challenging than the parallelization of a single simulation code. Open questions range from suitable load balancing strategies over bottleneck-avoiding communication, interactive visualization for online analysis of results, synchronization of several components to parallel numerical coupling schemes. We intend to tackle these challenges for fluid-structure-acoustics interactions, which are extremely costly due to the large range of scales. Specifically, this requires innovative surface and volume coupling numerics between the different solvers as well as sophisticated dynamical load balancing and in-situ coupling and visualization methods.

Reference: ExaFSA Webpage, preCICE Webpage, preCICE Source Code

EXAHD - An Exa-Scalable Two-Level Sparse Grid Approach for Higher-Dimensional Problems in Plasma Physics and Beyond

Funded by	DFG
Begin	2012
End	2020
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Michael Obersteiner
Contact person	Univ.-Prof. Dr. Hans-Joachim Bungartz

Brief description

Higher-dimensional problems (i.e., beyond four dimensions) appear in medicine, finance, and plasma physics, posing a challenge for tomorrow's HPC. As an example application, we consider turbulence simulations for plasma fusion with one of the leading codes, GENE, which promises to advance science on the way to carbon-free energy production. While higher-dimensional applications involve a huge number of degrees of freedom such that exascale computing gets necessary, mere domainde composition approaches for their parallelization are infeasible since the communication explodes with increasing dimensionality. Thus, to ensure high scalability beyond domain decomposition, a second major level of parallelism has to be provided. To this end, we propose to employ the sparse grid combination scheme, a model reduction approach for higher-dimensional problems. It computes the desired solution via a combination of smaller, anisotropic and independent simulations, and thus provides this extra level of parallelization. In its randomized asynchronous and iterative version, it will break the communication bottleneck in exascale computing, achieving full scalability. Our two-level methodology enables novel approaches to scalability (ultra-scalable due to numerically decoupled subtasks), resilience (fault and outlier detection and even compensation without the need of recomputing), and load balancing (high-level compensation for insufficiencies on the application level).

Reference: Priority Program 1648 SPPEXA - Software for Exascale Computing

SFB-TRR 89: Invasive Computing

Funded by	DFG
Begin	Mid 2010
End	3rd phase in mid 2022
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz (D3), Univ.-Prof. Dr. Michael Bader (A4)
Staff	Santiago Narvaez, M.Sc., Emily Mo-Hellenbrand, M.Sc., Alexander Pöppl, M.Sc., Dr. rer. nat. Tobias Neckel, Dr. rer. nat. Philipp Neumann; former staff: Dr. rer. nat. Martin Schreiber
Contact person	Univ.-Prof. Dr. Hans-Joachim Bungartz (D3), Univ.-Prof. Dr. Michael Bader (A4)

Brief description

In the CRC/Transregio "Invasive Computing", we investigate a novel paradigm for designing and programming future parallel computing systems - called invasive computing. The main idea and novelty of invasive computing is to introduce resource-aware programming support in the sense that a given program gets the ability to explore and dynamically spread its computations to neighbour processors similar to a phase of invasion, then to execute portions of code of high parallelism degree in parallel based on the available (invasible) region on a given multi-processor architecture. Afterwards, once the program terminates or if the degree of parallelism should be lower again, the program may enter a retreat phase, deallocate resources and resume execution again, for example, sequentially on a single processor. In order to support this idea of self-adaptive and resource-aware programming, not only new programming concepts, languages, compilers and operating systems are necessary but also revolutionary architectural changes in the design of MPSoCs (Multi-Processor Systems-on-a-Chip) must be provided so to efficiently support invasion, infection and retreat operations involving concepts for dynamic processor, interconnect and memory reconfiguration.

Reference: Transregional Collaborative Research Centre 89 - Invasive Computing

A4: Design-Time Characterisation and Analysis of Invasive Algorithmic Patterns

• Phase 2 and 3 (2014-2022): see description of project A4 on the Invasic website

D3: Invasion for High Performance Computing

• Phases 1,2 and 3 (2010-2022): see description of project D3 on the Invasic website

EU Horizon 2020

An Exascale Hyperbolic PDE Engine (ExaHyPE)

Project type	EU Horizon 2020, FET-PROACTIVE call Towards Exascale High Performance Computing (FETHPC)
Funded by	European Union’s Horizon 2020 research and innovation programme
Begin	October 2015
End	September 2019
Leader	Univ.-Prof. Dr. Michael Bader
Staff	Dr. Anne Reinarz, Jean-Matthieu Gallard, Leonhard Rannabauer, Philipp Samfass, M.Sc.; former staff: Dr. rer. nat. Vasco Varduhn, Angelika Schwarz, M.Sc.
Contact person	Univ.-Prof. Dr. Michael Bader
Co-operation partner	Prof. Michael Dumbser (Univ. Trento), Dr. Tobias Weinzierl (Durham University), Prof. Dr. Luciano Rezzolla (Fra nkfurt Institute for Advanced Studies), Prof. Dr. Heiner Igel and Dr. Alice Gabriel (LMU München), Robert Iberl (BayFor), Dr. Alexander Moskovsky (RSC Group); Prof. Dr. Arndt Bode (LRZ)

Brief description

The Horizon 2020 project ExaHyPE is an international collaborative project to develop an exascale-ready engine to solve hyperbolic partial differential equations. The engine will rely on high-order ADER-DG discretization (Arbitrary high-order DERivative Discontinuous Galerkin) on dynamically adaptive Cartesian meshes (building on the Peano framework for adaptive mesh refinement).

ExaHyPE focuses on grand challenges from computational seismology (earthquake simulation) and computational astrophysics (simulation of binary neutron star systems), but at the same time aims at developing a flexible engine to solve a wide range of hyperbolic PDE systems.

See the ExaHyPE website for further information!

Centre of Excellence for Exascale Supercomputing in the area of ​​the Solid Earth (ChEESE)

Project type	EU Horizon 2020, INFRAEDI-02-2018 call Centres of Excellence on HPC
Funded by	European Union’s Horizon 2020 research and innovation programme
Begin	November 2018
End	October 2021
Leader	Barcelona Supercomputing Centre
Staff	Ravil Dorozhinskii, M.Sc., Lukas Krenz, M.Sc., Leonhard Rannabauer, M.Sc., Jean-Matthieu Gallard, M.Sc.
Contact person	Univ.-Prof. Dr. Michael Bader
Co-operation partner	14 participating institutes, see the ChEESE website for details.

Brief description

The ChEESE Center of Excellence will prepare flagship codes and enable services for Exascale supercomputing in the area of Solid Earth (SE). ChEESE will harness European institutions in charge of operational monitoring networks, tier-0 supercomputing centers, academia, hardware developers and third-parties from SMEs, Industry and public-governance. The scientific ambition is to prepare 10 flagship codes to address Exascale Computing Challenging (ECC) problems on computational seismology, magnetohydrodynamics, physical volcanology, tsunamis, and data analysis and predictive techniques for earthquake and volcano monitoring.

SCCS contributes SeisSol and ExaHyPE as flagship in ChEESE. See the ChEESE website for further information!

ENERXICO - Supercomputing and Energy for Mexico

Project type	EU Horizon 2020, call FETHPC-01-2018 International Cooperation on HPC
Funded by	European Union’s Horizon 2020 research and innovation programme
Begin	June 2019
End	June 2021
Leader	Barcelona Supercomputing Centre
Staff	Dr. Anne Reinarz, Sebastian Wolf, M.Sc.
Contact person	Univ.-Prof. Dr. Michael Bader
Co-operation partner	16 participating institutes, see the ENERXICO website for details.

Brief description

ENERXICO is a collaborative research and innovation action that shall foster the collaboration between Europe and Mexico in supercomputing. ENERXICO will develop performance simulation tools that require exascale HPC and data intensive algorithms for different energy sources: wind energy production, efficient combustion systems for biomass-derived fuels (biogas) and exploration geophysics for hydrocarbon reservoirs.

SCCS is mainly concerned with large-scale seismic simulations based on SeisSol and ExaHyPE. See the ENERXICO website for further information!

BMBF: Federal Ministry of Education and Research

ELPA-AEO - Eigenwert-Löser für PetaFlop-Anwendungen: Algorithmische Erweiterungen und Optimierungen

Project type	Fördermassnahme IKT 2020 - Höchstleistungsrechnen im Förderbereich: HPC
Funded by	BMBF
Begin	2016
End	2018
Leader	Dr. Hermann Lederer, Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Univ.-Prof. Dr. Thomas Huckle, Michael Rippl, M.Sc.
Contact person	Univ.-Prof. Dr. Thomas Huckle
Co-operation partner	Dr. Hermann Lederer (Rechenzentrum MPG Garching), Prof. Dr. Bruno Lang (Universität Wuppertal), Prof. Dr. Karsten Reuter (Chemie, TUM), Dr. Christoph Scheuerer (TUM-Chemie), Fritz-Haber-Institut Berlin

Brief description

Übergeordnetes Ziel ist es, die Effizienz von Supercomputer-Simulationen zu steigern, für die die Lösung des Eigenwertproblems für dichte und Band-strukturierte symmetrische Matrizen zu einem entscheidenden Beitrag wird. Dies ist insbesondere bei Fragestellungen aus der Materialforschung, der biomolekularen Forschung und der Strukturdynamik der Fall. Aufbauend auf den Ergebnissen des ELPA-Vorhabens sollen im Rahmen dieses Vorhabens noch größere Probleme als bisher adressiert werden können, der mit der Simulation verbundene Rechenaufwand verringert und bei vorgegebener Genauigkeit und weiterhin hoher Software-Skalierbarkeit Ressourceneinsatz und Energieverbrauch reduziert werden.

TaLPas: Task-basierte Lastverteilung und Auto-Tuning in der Partikelsimulation

Project type	BMBF Programm: Grundlagenorientierte Forschung für HPC-Software im Hoch- und Höchstleistungsrechnen
Funded by	BMBF
Begin	January 2017
End	June 2020
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz, TUM, Philipp Neumann, Universität Hamburg
Staff	Univ.-Prof. Dr. Hans-Joachim Bungartz, Nikola Tchipev, M.Sc., Steffen Seckler, M.Sc. (hons)
Contact person	Nikola Tchipev, M.Sc.
Co-operation partner	Philipp Neumann, Universität Hamburg, Colin W. Glass, HLRS/Universität Stuttgart, Guido Reina, VISUS/Universität Stuttgart, Felix Wolf, TU Darmstadt, Martin Horsch, TU Kaiserslautern, Jadran Vrabec, Universität Paderborn

Brief description

The main goal of TaLPas is to provide a solution to fast and robust simulation of many, potentially dependent particle systems in a distributed environment. This is required in many applications, including, but not limited to,

• sampling in molecular dynamics: so-called “rare events”, e.g. droplet formation, require a multitude of molecular dynamics simulations to investigate the actual conditions of phase transition,
• uncertainty quantification: various simulations are performed using different parametrisations to investigate the sensitivity of the parameters on the actual solution,
• parameter identification: given, e.g., a set of experimental data and a molecular model, an optimal set of model parameters needs to be found to fit the model to the experiment.

For this purpose, TaLPas targets

• the development of innovative auto-tuning based particle simulation software in form of an open-source library to leverage optimal node-level performance. This will guarantee an optimal time-to-solution for small- to mid-sized particle simulations,
• the development of a scalable task scheduler to yield an optimal distribution of potentially dependent simulation tasks on available HPC compute resources,
• the combination of both auto-tuning based particle simulation and scalable task scheduler, augmented by an approach to resilience. This will guarantee robust, that is fault-tolerant, sampling evaluations on peta- and future exascale platforms.

For more details, see the project website.

Chameleon: Eine Taskbasierte Programmierumgebung zur Entwicklung reaktiver HPC Anwendungen

Project type	BMBF Programm: Grundlagenorientierte Forschung für HPC-Software im Hoch- und Höchstleistungsrechnen
Funded by	BMBF
Begin	April 2017
End	March 2020
Leader	Dr. Karl Fürlinger, LMU, Prof. Dr. Dieter Kranzlmüller, LMU
Staff	Univ.-Prof. Dr. Michael Bader, Philipp Samfass, Carsten Uphoff
Contact person	Univ.-Prof. Dr. Michael Bader
Co-operation partner	Dr. Christian Terboven, RWTH Aachen University

Brief description

The project Chameleon develops a task-based programming environment for reactive applications. "Reactive" means that programmers can let application react to changing hardware conditions. Chameleon envisages three components that together with MPI and OpenMP facilitate reaktive applications: (1) A task-based environment that allows applications to better tolerate idle times and load imbalances across nodes. This environment will be implemented by extending the established programming models MPI and OpenMP. (2) A component for "performance introspection", which allows applications and runtime environment to gain information on the current, dynamic performance properties (using techniques and tools from performance analysis), to improve performance at runtime. (3) An analysis component that will bring together and further process measured data and runtime information. Based on its analysis, the component will provide applications with methods and services to improve decisions on repartitioning, task migration, etc.

See the Chameleon project website for further information.

BMWi: Federal Ministry for Economics Affairs and Energy

ATHLET-preCICE - Erweiterung von ATHLET durch die allgemeine Kopplungsschnittstelle preCICE für die Simulation von Multiphysikproblemen in der Reaktorsicherheit

Project type	PT-GRS Reaktorsicherheitsforschung im Förderbereich Transienten und Unfallabläufe
Funded by	BMWi
Begin	2019
End	2022
Leader	Dr. rer. nat. Benjamin Uekermann , Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Gerasimos Chourdakis, M.Sc.
Contact person	Dr. rer. nat. Benjamin Uekermann
Co-operation partner	Dr.-Ing. Fabian Weyermann, Gesellschaft für Anlagen- und Reaktorsicherheit (GRS) gGmbH

Brief description

Durch den Einsatz passiver Sicherheitssysteme bei Reaktoren der Generation 3+ können der Kühlkreislauf und das Containment nicht mehr getrennt voneinander betrachtet werden. So sind zum Beispiel bei Gebäudekondensatoren physikalische Effekte beider Systeme stark gekoppelt: Thermohydraulik in den Rohrleitungen, Wärmeleitung in komplizierten dreidimensionalen Strukturen (Kühlrippen) und eine konvektive Gas- oder Dampfströmung auf der Kondensatoraußenseite. Die Simulation des Gesamtsystems ist daher ein Multiphysikproblem, und damit ist eine Kopplung mehrerer Simulationsprogramme notwendig. Eine allgemeine Code-unabhängige Kopplung kann mittels der Open-Source Kopplungsbibliothek preCICE, sehr effizient realisiert werden. Im Rahmen dieses Projektes wollen wir eine preCICE-Schnittstelle für AC2 entwickeln. Diese soll zuerst für das Modul ATHLET implementiert werden. Da schon eine große Anzahl verschiedenster Simulationsprogramme wie ANSYS Fluent, COMSOL, OpenFOAM, CalculiX, oder Code_Aster über eine preCICE-Schnittstelle verfügen, würden dadurch alle diese Programme unmittelbar für gekoppelte Analysen mit ATHLET nutzbar. Ein weiterer Vorteil dieser Schnittstelle ist, dass dadurch nicht nur die gleichzeitige Kopplung von zwei Rechenprogrammen, sondern drei oder auch mehr, möglich ist. Die detaillierte Simulation des genannten Beispiels des Gebäudekondensators wird hierdurch erst möglich. Da ähnliche multiphysikalische Probleme auch bei den modularen Reaktoren, die in vielen Ländern als die Zukunft der Nukleartechnik gesehen, auftreten, ist die angestrebte Implementierung einer preCICE- Schnittstelle in ATHLET ein notwendiger Schritt für die Zukunftsfähigkeit von ATHLET.

HydroBITS: Code Optimisation and Simulation for Bavarian Water Supply and Distribution

Project type	Research Project
Funded by	Bavarian State Ministry of the Environment and Consumer Protection / LfU
Begin	January 2018
End	December 2021
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Dr. rer. nat. Tobias Neckel, Ivana Jovanovic, M.Sc. (hons)
Contact person	Dr. rer. nat. Tobias Neckel
Co-operation partner	Dr. Jens Weismüller, Dr. Wolfgang Kurtz, LRZ

Brief description

In HydroBITS, existing IT structures at different institutions related to water supply and distribution in Bavaria are going to be analysed. Basics for modernising the corresponding IT infrastructure are going to be created which are necessary due to various technological developmentss in the recent years. In cooperation with the LRZ, workflows as well as simulation models and data of the Bavarian Landesamts für Umwelt are analysed. A demonstrator platform with a prototype for a modern IT structure are going to be created.

Helmholtz Gemeinschaft: MUnich School of Data Science (MUDS): Integrated Data Analysis 2.0

Project type	Research Project
Funded by	Helmholtz Gemeinschaft
Begin	September 2019
End	August 2023
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz, Prof. Frank Jenko (MPP)
Staff	Dr. rer. nat. Tobias Neckel, Ravi Kislaya, M.Sc.
Contact person	Dr. rer. nat. Tobias Neckel
Co-operation partner	Michael Bergmann (MPP)

Brief description

In this project of MUDS, the existing approaches for Bayesian Inversion in the context of fusion plasma simulations (the so-called Integrated Data Analysis) will be generalized and extended to incorporate a) stochastic information for forward propagation of uncertainties and b) simulation results of plasma microturbulence back into the Inversion process. In particular, the code GENE will be used.

KONWIHR: The Bavarian Competence Network for Technical and Scientific High Performance Computing

ProPE-AL: Process-oriented Performance Engineering Service Infrastructure for Scientific Software at German HPC Centers - Algorithms

Project type	KONWIHR
Funded by	KONWIHR
Begin	Obtober 2017
End	September 2020
Leader	Univ.-Prof. Dr. Michael Bader, Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Hayden Liu Weng, M.Sc. (hons)
Contact person	Univ.-Prof. Dr. Michael Bader, Univ.-Prof. Dr. Hans-Joachim Bungartz
Co-operation partner	Univ.-Prof. Dr. Gerhard Wellein, FAU Erlangen-Nürnberg, Univ.-Prof. Dr. Matthias Müller, RWTH Aachen, Univ.-Prof. Dr. Wolfgang Nagel, TU Dresden

Brief description

As part of the DFG call "Performance Engineering for Scientific Software", the Project partners G. Wellein (FAU Erlangen-Nuremberg), M. Müller (RWTH Aachen) and W. Nagel (TU Dresden) initiated the project "Process-oriented Performance Engineering Service Infrastructure for Scientific Software at German HPC Centers" (acronym ProPE). The project aims at implementing performance engineering (PE) as a well-defined, structured process to improve the resource efficiency of programs. This structured PE process should allow for target-oriented optimization and parallelization of application codes guided by performance patterns and performance models. The associated KONWIHR project ProPE-Algorithms (ProPE-AL) adds a further algorithmic optimization step to this well-defined, structured process. This extension takes into account that the best possible sustainable use of HPC resources through application codes is not only a question of the efficiency of the implementation, but also a question of the efficiency of the (numerical) algorithms that application codes are based on.

Volkswagen Stiftung: ASCETE, ASCETE-II (Advanced Simulation of Coupled Earthquake-Tsunami Events)

Project type	Call "Extreme Events: Modelling, Analysis and Prediction"
Funded by	Volkswagen Stiftung
Begin	February 2012
End	December 2019
Leader	Univ.-Prof. Dr. Jörn Behrens (KlimaCampus, Univ. Hamburg)
Staff	Leonhard Rannabauer, M.Sc., Carsten Uphoff; former staff: Alexander Breuer, Kaveh Rahnema
Contact person	Univ.-Prof. Dr. Michael Bader
Co-operation partner	Univ.-Prof. Dr. Jörn Behrens (KlimaCampus, Univ. Hamburg), Univ.-Prof. Dr. Heiner Igel, Dr. Martin Käser, Dr. Christian Pelties, Dr. Alice-Agnes Gabriel (all: GeoPhysics, Univ. München), Dr. Luis Angel Dalguer, Dr. Ylona van Dinther (ETH Zürich, Swiss Seismological Service). see official ASCETE webpage

Brief description

Earthquakes and tsunamis represent the most dangerous natural catastrophes and can cause large numbers of fatalities and severe economic loss in a single and unexpected extreme event as shown in Sumatra in 2004, Samoa in 2009, Haiti in 2010, or Japan in 2011. Both phenomena are consequences of the complex system of interactions of tectonic stress, fracture mechanics, rock friction, rupture dynamics, fault geometry, ocean bathymetry, and coast line geometry. The ASCETE project forms an interdisciplinary research consortium that – for the first time – will couple the most advanced simulation technologies for earthquake rupture dynamics and tsunami propagation to understand the fundamental conditions of tsunami generation. To our knowledge, tsunami models that consider the fully dynamic rupture process coupled to hydrodynamic models have not been investigated yet. Therefore, the proposed project is original and unique in its character, and has the potential to gain insight into the underlying physics of earthquakes capable to generate devastating tsunamis.

See the ASCETE website for further information.

Intel Parallel Computing Center: Extreme Scaling on x86/MIC/KNL (ExScaMIC)

Project type	Intel Parallel Computing Center
Funded by	Intel
Begin	July 2014
End	October 2018
Leader	Univ.-Prof. Dr. Michael Bader, Univ.-Prof. Dr. Hans-Joachim Bungartz, Univ.-Prof. Dr. Arndt Bode
Staff	Nikola Tchipev, Steffen Seckler, Carsten Uphoff, Sebastian Rettenberger; former staff: Alexander Breuer
Contact person	Univ.-Prof. Dr. Michael Bader
Co-operation partner	Leibniz Supercomputing Centre

Brief description

The project is optimizing four different established or upcoming CSE community codes for Intel-based supercomputers. We assume a target platform that will offer several hundred PetaFlop/s based on Intel's x86 (including Intel® Xeon Phi™) architecture. To prepare simulation software for such platforms, we tackle two expected major challenges: achieving a high fraction of the available node-level performance on (shared-memory) compute nodes and scaling this performance up to the range of 10,000 to 100,000 compute nodes.

We examine four applications from different areas of science and engineering: earthquake simulation and seismic wave propagation with the ADER-DG code SeisSol, simulation of cosmological structure formation using GADGET, the molecular dynamics code ls1 mardyn developed for applications in chemical engineering, and the software framework SG++ to tackle high-dimensional problems in data mining or financial mathematics (using sparse grids). While addressing the Xeon Phi™ (co-)processor architectures, in particular, the project tackles fundamental challenges that are relevant for most supercomputing architectures – such as parallelism on multiple levels (nodes, cores, hardware threads per core, data parallelism) or compute cores that offer strong SIMD capabilities with increasing vector width.

While the first project phase (2014-2016) addressed the Intel Xeon Phi coprocessor (Knights Corner), the second project phase (2016-2018) will specifically focuses on the Xeon Phi as stand-alone processor (Knights Landing architecture).

Elite Network of Bavaria (ENB):

Bavarian Graduate School of Computational Engineering (BGCE)

Website of the BGCE

Project type	Elite Study Program
Funded by	Elite Network of Bavaria, TUM, FAU
Begin	April 2005
End	April 2025
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Dr. rer. nat. Tobias Neckel, Michael Rippl, M.Sc. (hons), Benjamin Rüth, M.Sc. (hons)
Contact person	Dr. rer. nat. Tobias Neckel
Co-operation partner	International Master's Program Computational Science and Engineering (TUM) International Master's Program Computational Mechanics (TUM) International Master's Program Computational Engineering (U Erlangen)

Brief description

The Bavarian Graduate School of Computational Engineering is an association of the three Master programs: Computational Engineering (CE) at the University of Erlangen-Nürnberg, Computational Mechanics (COME), and Computational Science and Engineering (CSE), both at TUM. Funded by the Elitenetzwerk Bayern, the Bavarian Graduate School offers an Honours program for gifted and highly motivated students. The Honours program extends the regular Master's programs by several academic offers:

• additional courses in the area of computational engineering, in particular block courses, and summer academies.
• Courses and seminars on "soft skills" - like communication skills, management, leadership, etc.
• an additional semester project closely connected to current research

Students who master the regular program with an above-average grade, and successfully finish the Honours program, as well, earn the academic degree "Master of Science with Honours".

International Graduate School of Science and Engineering (IGSSE):

An Exascale Library for Numerically Inspired Machine Learning (ExaNIML)

Project type	International IGGSE project
Funded by	International Graduate School of Science and Engineering
Begin	June 2018
End	December 2020
Leader	Univ.-Prof. Dr. Hans-Joachim Bungartz
Staff	Dr. rer. nat. Tobias Neckel, Severin Reiz
Contact person	Severin Reiz
Co-operation partner	The University of Texas at Austin Institute for Computational Engineering and Sciences

Brief description

There is a significant gap between algorithms and software in Data Analytics and those in Computational Science and Engineering (CSE) concerning their maturity on High-Performance Computing (HPC) systems. Given the fact that Data Analytics tasks show a rapidly growing share of supercomputer usage, this gap is a serious issue. This proposal aims to bridge this gap for a number of important tasks arising, e.g., in a Machine Learning (ML) context: density estimation, and high-dimensional approximation (for example (semi-supervised) classification). To this end, we aim to (1) design and analyze novel algorithms that combine two powerful numerical methods: sparse grids and kernel methods; and to (2) design and implement an HPC library that provides an open-source implementation of these algorithms and supports heterogeneous distributed-memory architectures. The attractiveness of sparse grids is mainly due to their high-quality accuracy guarantees and their foundation on rigorous approximation theory. But their shortcoming is that they require (regular) Cartesian grids. Kernel methods do not require Cartesian grids but, first, their approximation properties can be suboptimal in a practice, and second, they require regularization whose parameters can be expensive to determine. Our main idea is to use kernel methods for manifold learning and to combine them with the sparse grids to define approximations on the manifold. Such high-dimensional approximation problems find applications in model reduction, uncertainty quantification (UQ), and ML.