1. Welcome
|
As of 31st May 2022, the first funding phase of EXCELLERAT has come to an end. Over the past three and a half years, our 13-partner European consortium provided expertise on how data management, data analytics, visualisation, simulation-driven design and co-design could benefit engineering, in particular in the aerospace, automotive, energy and manufacturing sectors. Overall, our work strongly focused on improving computational efficiency, dynamic mesh adaptation, load balancing, scalable data handling, usability (visualisation and workflow tools), as well as investigating novel architectures and opportunities for co-design and developing more efficient numerical methods. We will continue this newsletter on a regular basis until the end of this year and hope that we can initiate a second project phase starting in January 2023.
|
In this issue of our newsletter, you can find out how we integrated our core code Nek5000 into the visualisation tool Vistle, learn more about uncertainty quantification and our data exchange platform, and discover the reason why to use FPGAs as an accelerator in our latest white papers.
|
I hope you enjoy reading our newsletter and have a great summer!
|
|
EXCELLERAT Project Coordinator
|
|
|
|
2. Success Story: In situ VR visualisation of Nek5000 simulations with Vistle
|
|
|
Nek5000 cases that use Exascale level performance compute data on very large grids. Writing this data to disk frequently becomes a major run time bottleneck, while handling all the data on disk comes with its own challenges. With increasing data sizes and complexity analysing the usually 3D data with conventional 2D methods becomes even harder. Running large simulations is also costly, therefore errors should be identified sooner rather than later. Learn how our partner HLRS used the SENSAI in situ interface to couple Nek5000 simulations with our core code Vistle in this new success story.
|
|
|
|
3 a) White paper: Enabling High-Performance Collaboration: A Data exchange platform for HPC
|
|
|
We know that starting to use HPC can entail a steep learning curve, especially for small and medium-sized enterprises with no prior experience or access. So what can we do about it? We're enabling high-performance collaboration and increasing industrial access to HPC with our data transfer platform. Check out the details and results so far in the white paper by our partner SSC-Services.
|
|
3 b) White paper: Empowering Large-Scale Turbulent Flow Simulations With UQ Techniques
|
|
An effective, robust simulation must account for potential sources of uncertainty. Computational Fluid Dynamics (CFD) has to deal with many uncertainties from various sources. The real world forces many kinds of uncertainties upon engineering components – everything from changes in numerical and computational parameters to uncertainty in initial and boundary conditions and geometry. But how do you know which uncertainties to expect and quantify without using an enormous amount of computing power? Find out in a recent EXCELLERAT white paper why UQit – an open-source Python package – is the answer.
|
|
3 c) White paper: FPGAs for accelerating HPC engineering workloads – the why and the how
|
|
Running high performance workloads on Field Programmable Gate Arrays (FPGAs) has been explored but is yet to demonstrate widespread success. Software developers have traditionally felt a significant disconnect from the knowledge required to effectively exploit FPGAs, which included the esoteric programming technologies, long build times, and lack of familiar software tooling. Why would one ever choose to accelerate their HPC application on an FPGA compared to other hardware? How can we best design our high performance FPGA codes algorithmically so that they are fast by construction? A new white paper explores these two questions based on lessons learnt during the EXCELLERAT CoE's runtime.
|
|
|
|
4. Further news & events
|
|
EXCELLERAT Conference: Impressions, Takeaways, and How to Watch
|
The two-day online conference "EXCELLERAT: Enabling Exascale potentials for engineering applications" in May 2022 showcased the impact, innovations and tools resulting from the project. If you missed the conference, you can read a summary in our blog article and get access to the recordings via YouTube.
|
|
Self-paced course: Approaches to analysing time-series data
|
Tourist destination managers, service providers, and researchers want to better understand traffic flows: what impact traffic flows have, when do traffic peaks occur, what are the seasonal effects, which areas are more / less congested with tourists, how do weather, holidays and other events affect this behaviour. With the help of data analysis and forecasts, they can prepare for periods of increased visits, as well as adjust marketing activities, service offerings, or resources allocation. In this tutorial we look at a real-world dataset consisting of traffic counters on Slovenian roads, provided by the Slovenian Road Network (DARS), and its application to the questions above. Get access to the tutorial through our Service Portal.
|
|
Training course: Scientific Visualization with COVISE and Vistle
|
(29-30 September 2022, Stuttgart, Germany)
|
|
This two-day workshop gives a short overview of scientific visualization in general, followed by a hands-on introduction to 3D desktop visualization with VISTLE and COVISE. Participants will further learn how to build interactive 3D models for virtual environments, and how to set up an augmented reality visualization. Register now
|
|
|
|
|
|
