HLRS Virtual Booth at SC20

Due to restrictions caused by the global COVID-19 pandemic, the SC20 conference – the world’s leading HPC event – will take place online this year from November 9-19. HLRS is pleased to be participating and invites you to join us. The following schedule details HLRS-related presentations that will be given at SC.

To register for any of the presentations with your email address, click here.
Registration is optional, but ensures that you will receive updates on schedule changes and an invitation to the WebEx meetings by email. The following timetable will also indicate any schedule updates and links to the WebEx meetings when they take place.

Strengthening HPC Competences in Europe in the Exa-Era

Strengthening HPC Competences in Europe in the Exa-Era

16.11.2020: 11:45 - 12:15 (ET)

This talk will provide an overview about the EuroHPC activities and different activities to realize the European HPC strategy. The main emphasis will be put on the activity of implementing National Competence Centres in HPC in 33 nations and their strategic alignment on the European level. Furthermore, a quick insight into the FF4EuroHPC activity will be given, which will support European Small and Medium-Sized Enterprises in evaluating the applicability of HPC and associated technologies to improve their business.

Speaker: Dr. Bastian Koller

Virtual Twins, Smart Cities and Smart Citizens

Copyright: HLRS
Copyright: HLRS
Virtual Twins, Smart Cities and Smart Citizens

16.11.2020: 12:30 - 13:30 (ET)

Digital twins of cities and regions can help us understand and solve today’s complex problems and assess risks and scenarios for the future. However, today's process of the digital transformation in urban planning marks a new revolutionary era that poses highly complex, socially relevant, spatial and temporal challenges to cities, planners and society. The Smart City approach must become more accessible to all stakeholders. Digital twins, visualised in VR and AR ("Virtual Twins") can help to tackle these challenges and support participatory and collaborative processes for a more democratic urban development.

Speakers: Leyla Kern, Dr. Fabian Dembski, Dr. Uwe Wössner

HiDALGO: Addressing Global Challenges with HPC and Big Data Technologies

Copyright: Brunel University London
Copyright: Brunel University London
HiDALGO: Addressing Global Challenges with HPC and Big Data Technologies

17.11.2020: 10:00 - 10:30 (ET)

As a society, we are facing several global challenges in fields such as economy, sociology, or ecology; challenges range from predicting and analysing migration flows over urban air quality assessments to social network analytics. These challenges require massive amounts of data to be collected, aggregated, (pre-)processed, and coupled to yield reasonable results for prediction and to discover hidden insights. HiDALGO, a European research project, leverages supercomputing to address these challenges. In this talk, we will highlight the advancements made by HiDALGO, as well as introduce a case study conducted by the Brunel University London to mitigate the effects of COVID-19 and pandemics in general; the computer simulation predicted an inevitable second wave of the COVID-19 pandemic. Further Information

Speakers: Dennis Hoppe, Dr. Derek Groen

SODALITE: Software-Defined Execution and Optimization of In-Silico Clinical Trials in HPC with SODALITE Platform

Copyright: Atos
Copyright: Atos
SODALITE: Software-defined Execution and Optimization of In-silico Clinical Trials in HPC with SODALITE Platform

17.11.2020: 10:45 - 11:15 (ET)

The methodology of in-silico clinical trials in biomechanical simulations stands at the border of being productively used in medical device development. Therefore, it has become especially important to increase the effectiveness of deployment, management and adaption to different IT-infrastructures. This will ease the use of the methodology for end users like medical device manufacturers or medical research institutes, and it will additionally significantly reduce the support effort of the developers.
Such compute-intensive applications can be deployed across a wide range of diverse computing platforms, including supercomputers and cloud infrastructures with heterogeneous architectures and hardware. In order to deal with this diversity, software-defined infrastructures, modelled with Infrastructure-as-Code (IaC), provide a deployment abstraction to hide the complexity of underlying platforms and promise both deployment flexibility and portability. However, there is still a need for applications to optimally use and benefit from these diverse resources.
These deployment and optimization challenges are addressed in an EU-funded project - SODALITE. It provides tools to enable simpler and faster development of IaC, and optimized deployment and execution of heterogeneous applications in HPC, Cloud & SW defined computing environments. In this presentation, we will introduce the simulation chain of in-silico clinical trials, developed by HLRS, for assessment of bone-implant-systems, and then demonstrate how this chain was modelled, optimized and executed using the SODALITE platform.

Speakers: Dr. Ralf Schneider, Kamil Tokmakov

CATALYST: Leveraging HPC to Drive Innovation in AI

Copyright: Johannes Stelzer, Lunar Ring
Copyright: Johannes Stelzer, Lunar Ring
CATALYST: Leveraging HPC to drive innovation in AI

17.11.2020: 11:30 - 11:45 (ET)

The growth of artificial intelligence (AI) is accelerating. AI has left research and innovation labs, and nowadays plays a significant role in everyday lives. The impact on society is graspable: autonomous driving cars produced by Tesla, voice assistants such as Siri, and AI systems that beat renowned champions in board games like Go. All these advancements are facilitated by powerful computing infrastructures based on HPC and advanced AI-specific hardware, as well as highly-optimized AI codes. For the past several years, HLRS has been engaged in big data and AI-specific activities around HPC. In this talk, Dennis will give a brief overview about our research project CATALYST to engage with researchers and SMEs, as well as present exciting case studies from our customers.

Speaker: Dennis Hoppe

FF4EuroHPC: First Open Call

Copyirght: Arctur
Copyirght: Arctur
FF4EuroHPC: First Open Call

17.11.2020: 12:00 - 12:30 (ET)

FF4EuroHPC is a European R&D project funded by the European Commission as part of the EuroHPC Joint Undertaking programme. The key concept behind FF4EuroHPC is to demonstrate to European SMEs ways to optimize their performance with the use of advanced HPC services (e.g., modelling & simulation, data analytics, machine-learning and AI, and possibly combinations thereof) and thereby take advantage of these innovative ICT solutions for business benefit. It follows on from the prior Fortissimo and Fortissimo 2 projects. Two open calls will be organized by the project, with the aim to create two tranches of application experiments addressing the business challenges of SMEs from diverse industry sectors. The presentation will give an introduction to the project and the Fortissimo approach and then explain the opportunities and expectations for participants in the first open call.

Speaker: Guy Lonsdale

EXCELLERAT (part 1): Paving the Way towards Exascale

Copyright: HLRS
Copyright: HLRS
EXCELLERAT (part 1): paving the way towards Exascale

18.11.2020: 10:00 - 10:15 (ET)

Engineering applications will be among the first to reach the Exascale level, not only in academia but also in industry. The industrial engineering field is the area with the highest Exascale potential. For this reason, the EU-funded EXCELLERAT project brings together European experts to establish a Centre of Excellence (CoE) in Engineering Applications on HPC with a broad service portfolio, paving the way for the evolution towards Exascale. The aim is to solve highly complex and costly engineering problems and create enhanced technological solutions. EXCELLERAT focusses on developing six reference applications: Nek5000, Alya, AVBP, TPLS, FeniCS, and Coda. They were analysed for their potential to achieve Exascale performance in HPC for engineering and thus are promising candidates to act as showcases for the evolution of applications towards execution on high scale Demonstrators, Pre-Exascale Systems and Exascale Machines.

Speaker: Amgad Dessoky

EXCELLERAT (part 2): Why is UQ Essential for Large-Scale Flow Simulations?

Copyright: KTH Stockholm
Copyright: KTH Stockholm
EXCELLERAT (part 2): Why is UQ Essential for Large-Scale Flow Simulations?

18.11.2020: 10:15 - 10:30 (ET)

We will present the recent progress in the development and application of uncertainty quantification (UQ) techniques to the high-fidelity scale-resolving simulations of wall-bounded turbulent flows. These simulations are highly computationally expensive but have a vital role in understanding the flow physics and engineering design.
The topics to discuss are the application of a UQ framework for assessing different validation and verification metrics in these simulations as well as estimation of uncertainties due to the lack of samples when computing time-averaged quantities of interest. It is also discussed how to perform different UQ analyses when numerical and sampling uncertainties are simultaneously present.

Speaker: Saleh Rezaeiravesh

EXCELLERAT (part 3): Airplane Simulations on Heterogeneous Pre-Exascale Architectures

(Left): Comparison of (balanced) co-execution vs pure GPU execution – elapsed time per MPI Rank. (Right): Snapshot of Q iso-surfaces of the turbulent flow around an airplane.
Copyright: Barcelona Supercomputing Centre
(Left): Comparison of (balanced) co-execution vs pure GPU execution – elapsed time per MPI Rank. (Right): Snapshot of Q iso-surfaces of the turbulent flow around an airplane. Copyright: Barcelona Supercomputing Centre
EXCELLERAT (part 3): Airplane Simulations on Heterogeneous Pre-Exascale Architectures

18.11.2020: 10:30 - 10:45 (ET)

We can affirm with quite a certainty that some of the future Exascale systems will be heterogeneous including GPUs. We can also expect higher variability on the performance of the computing devices engaged in a simulation. In this context, dynamic load balancing (DLB) becomes a must for parallel efficiency. In EXCELLERAT, Alya has been provisioned with a distributed memory DLB mechanism, complementary to node-level mechanisms. The kernel parts of the method are an SFC-based mesh practitioner and an online redistribution module. Those are used to correct the partition according to runtime measurements. We have used this technology to perform simulations on an heterogeneous POWER9 + NVIDIA cluster. Well-balanced co-executions of airplane simulations outperformed by 23% the GPU-only executions.

Speaker: Ricard Borrell

HPCWE: High-Performance Computing Applied in Wind Energy

Copyright: HLRS
Copyright: HLRS
HPCWE: High-performance computing applied in wind energy

18.11.2020: 11:00 - 11:45 (ET)

Wind energy has become increasingly important as a clean and renewable alternative in the energy portfolios of both Europe and Brazil. At every stage in wind energy exploitation, ranging from wind turbine design, to wind resource assessment, to wind farm layout and operations, the application of HPC is a must. The goal of HPCWE is to address key open challenges in applying HPC on wind energy, such as the efficient use of HPC resources in wind turbine simulations and the accurate integration of mesoscale atmosphere dynamics and microscale wind turbine flow simulations. This leads to the development of methods for verification, validation, uncertainty quantification (VVUQ), in-situ scientific data interpretation, and solutions for large I/O consumption and storage on large-scale file systems.

Speaker: Flavio Cesar Cunha Galeazzo