Strenghtening the leadership in High Performance Computing and Data Analytics
The HPE HPC/AI EMEA Research Lab (ERL) performs research and development in strategic areas that strengthen HPE leadership in high-performance computing and data analytics, and which deepen HPE’s involvement in the scientific and technical communities of EMEA.
The ERL is focused on collaborative R&D and codesign efforts, including:
- Software codesign
- Experimental hardware codesign
- In-house innovation projects
- Publicly funded R&D projects
- Collaborations with partners/customers and Advanced Collaboration Centres
- Internships and student hosting
Current focus areas
The HPE HPC/AI EMEA Research Lab is currently focused on workflow and component optimization for HPC and analytics frameworks, machine learning and the role of new technologies such as non-volatile memory. The HPE HPC/AI EMEA Research Lab can bring deep expertise in the more traditional HPC ecosystem along with expertise in machine learning, asynchronous tasking, data analytics and mathematical optimization.
Advanced collaboration centers
ERL staff provides expertise in Advanced Collaboration Centres ARCHER2 in Edinburgh, LUMI in Finland, KAUST in Saudi Arabia, and GW4 in Bristol. These ACCs are forums for bespoke deep technical engagements where, for example, advanced software is designed specifically for the needs of the customer’s application base.
Key areas / Current projects
Destination Earth Climate Digital Twin (DE 340)
The Climate Adaptation Digital Twin (“Climate DT”) will design and implement a pre-exascale climate information system to support climate adaptation efforts. The climate DT system harnesses two-kilometre scale Earth-system models (ESMs) to Europe’s most performant computing systems to provide the light (information) source for adaptation use cases drawn from five climate impact sectors: forestry, urban environments, hydrology, hydro-meteorology, and energy.
The climate DT system will be developed around two of Europe’s leading ESMs, ICON and IFS-FESOM/NEMO. Climate DT introduces the idea of a generic state vector (GSV), which is evolved by the ESMs and “streamed” to applications. The GSV enforces a separation of concerns that enables the climate DT ESM's to work at an unprecedented scale (multi-decadal simulations on 5km or finer global meshes), something which is required to improve both their fidelity and the relevance of the information they provide. Within climate DT the models will be adapted to two of Europe’s largest computing infrastructures: MareNostrum 5 at the Barcelona Supercomputing Centre in Barcelona, Spain, and LUMI operated in Kajaani, Finland by the CSC–IT Center for Science.
For more information visit
OPENCUBE
Opencube develops a full-stack solution of a validated European Cloud computing blueprint to be deployed on European hardware infrastructure. OpenCUBE will develop a custom cloud installation with the guarantee that an entirely European solution like SiPearl processors and Semidynamics RISC-V accelerators can be deployed reproducibly. OpenCUBE will be built on industry-standard open APIs using Open-Source components and will provide a unified software stack that captures the different best practices and open-source tooling on the operating system, middleware, and system management level. It will thus provide a solid basis for the European cloud services, research, and commercial deployments envisioned to be core for federated digital services via Gaia-X. To remain competitive for the European Green Deal, OpenCUBE is designed to make energy awareness a core feature at all levels of the stack, exploiting the advanced features of the SiPearl Rhea processor family at the hardware level and exposing the necessary API at the site level, up to and including interfaces to the electricity grid. This project will leverage representative workloads like those of ECMWF characteristics for production and Digital Twin workflows as drivers for the design and deployment of the cluster infrastructure.
- Partners: KTH, TUM, ECMWF, SiPearl, SemiDynamics, HPE
For more information visit
EE-HPC
EE-HPC (BMBF German GreenHPC) is a project studying the automated optimization of the energy efficiency of HPC systems. By means of job-specific control and optimization of the hardware configuration and the runtime environments (OpenMP and MPI), HPC systems are to achieve more efficient energy utilization by means of reduced power consumption while simultaneously maximizing throughput. The starting point is a system-wide job-specific framework for performance and energy monitoring. The existing ClusterCockpit environment will be adapted and extended. The LIKWID library is used to collect hardware metrics and implement the hardware configuration. Analytical modelling, machine learning, and empirical methods will be combined to determine the parameters.
- Partners: FAU, RWTH, HLRS, DKRZ, HPE
For more information visit
Partner projects
AQTIVATE
AQTIVATE is a Marie Curie Action delivering an interdisciplinary training program for 15 PhD fellows who will use high-performance computing, develop scalable algorithms and machine learning approaches, and explore quantum computing for research projects from physics, engineering, and biology.
- Partners: U Cyprus, The Cyprus Institute, Institut Mines-Telecom, U Roma Tor Vergata, KTH, U Padova, JSC, U Wuppertal, TU Berlin, DESY, CINECA, Fondazione Istituto Italiano Di Tecnologia, SIDACT, QRUISE, Aignostics, Retail Zoom Cyprus, Institut Polytechnique de Paris, RTWH, HPE
For more information visit
EUROPLEX
With the support of the Marie Skłodowska-Curie Actions programme, the EuroPLEx project will create an innovative training network to enhance theoretical understanding of strongly interacting matter beyond its current limits–and potentially beyond the Standard Model–with numerical simulations of theories including QCD.
- Academic Partners: Università di Parma, HUMBOLDT-UNIVERSITAET ZU BERLIN, Universitaet Bielefeld, Trinty College, University of Edinburgh, Universidad de Madrid, Universitaet Regensburg, Swansea University, Syddansk Universitet
For more information visit
Completed projects
Plan4Res
The objective of the project was to fill the gaps between the increasing complexity of the energy system planning and operational problems, and the available system analysis tools. The project has developed:
- An end-to-end planning and operation tool, composed of a set of optimization models based on an integrated modelling of the pan-European Energy System.
- An IT platform for providing seamless access to data and high-performance computing resources, catering for flexible models (easily replacing submodels and the corresponding efficient solution algorithm) and workflows.
- A database of public data and 3 case studies highlighting the tool’s adequacy and relevance.
For more information visit
EXPERTISE
EXPERTISE was a European Training Network (ETN) that has trained 15 early-stage researchers on the challenges, paradigms, technologies, and methodologies in the field of nonlinear structural dynamics of turbomachinery and high-performance computing. The research objective of the network was to develop advanced tools for the dynamics analysis of large-scale models of turbine components to pave the way towards the virtual testing of the entire machine.
For more information visit
MAESTRO
Maestro has developed a data-aware and memory-aware middleware framework that addresses ubiquitous problems of data movement in complex memory hierarchies and at many levels of the HPC software stack. Moving data through memory was not always the bottleneck. Software rightfully insulates users from hardware details.
For more information visit
EPIGRAM-HS
EPiGRAM-HS has developed and validated a new programming environment for large-scale heterogeneous computing systems, including accelerators, reconfigurable hardware, and low-power microprocessor together with non-volatile and high-bandwidth memories. The aim is to enable applications to run on large-scale heterogeneous systems at maximum performance.
For more information visit
SODALITE
SODALITE vision was to support the digital transformation of the European industry through increasing design and runtime effectiveness of software-defined infrastructures, to ensure high-performance execution over dynamic heterogeneous execution environments; increasing simplicity of modelling applications and infrastructures, to improve manageability, collaboration, and time to market. SODALITE provided application developers and infrastructure operators with tools that abstract their application and infrastructure requirements. The aim was to enable simpler and faster development, deployment, operation, and execution of heterogeneous applications reflecting diverse circumstances over heterogeneous, software-defined, high-performance, cloud infrastructures, with a particular focus on performance, quality, manageability, and reliability.
For more information visit
Internships and placements
The ERL offers internships and placements from time to time, usually these are part of a programme (such as a UK Centre for Doctoral Training) or engagement with an educational institution we are partnered with. Bespoke one-off internships are sometimes available. Previous internships/placements have worked on such topics as: large-scale cosmological visualization, study of tasking frameworks, data analytics and modelling of supercomputing job data, FPGA dataflow and interfacing with Fortran.
ERL staff and research interest
Utz-Uwe Haus, Distinguished Technologist
David Brayford, Senior Research Engineer
David joined ERL as a Research Engineer in 2023, where he currently leads HPE efforts in the EE-HPC project. He holds a Ph.D. in Computer Science from the University of Manchester, U.K. Before joining ERL, David worked for PixelFusion/ClearSpeed, Scientific Computing and Imaging Institute (University of Utah), BioFire Diagnostics, General Electric, LRZ and Intel. He has extensive experience in high performance computing, scientific and numerical computing, software development, and 3D computer graphics including device driver development, physics based photorealistic rendering, scientific and medical visualization.
Sebastien Cabaniols, Principal Research Engineer
Sebastien has been working in the HPC team for twenty years in HPE. He joined ERL in 2020 following the CRAY acquisition. His area of expertise is large scale system provisioning, monitoring, linux kernel tuning for performance but also container computing and devops. Sebastien worked hands in hands with hundreds of HPE HPC customers spanning a wide range of application fields.
Tim Dykes, Senior Research Engineer
Tim joined ERL as a Research Engineer in 2018. He holds a Ph.D. from the University of Portsmouth, U.K., focusing on high performance scientific visualisation in Astronomy. His research interests include heterogeneous high-performance architectures, performance portability, complex memory hierarchies, software and compiler optimisation, and scientific visualisation.
Aniello Esposito, Principal Research Engineer
Aniello Esposito is responsible for the centre of excellence collaboration with KAUST (Saudi Arabia) among other research activities in the area of supercomputing. He is also involved in pre-sales as an expert application analyst for European procurements as well as site acceptances and he is part of the algorithms track technical committee of the Supercomputing conference. Before joining the research lab, Aniello worked as an application analyst, focusing on the optimization of large-scale scientific codes and general user support as well as trainings on Cray systems which took place on-site at HLRS, DWD, HLRN, and KAUST. Aniello studied physics at the Swiss Federal Institute of Technology in Zurich (ETHZ) with a focus on theory and computational methods and earned a Ph.D. from ETHZ in applied physics. After a postdoc he joined Cray in January 2012. His main interests lie in the implementation and optimization of large-scale scientific codes in the area of traditional high-performance computing as well as machine learning.
Gallig Renaud, Distinguished Technologist
Gallig became part of HPE in 2001, assuming diverse roles—from EMEA Pre-sales architect in the field to WW Hybrid HPC architect and Innovations Lead within the Office of the CTO. His expertise spans hardware technologies like FPGA, Persistent Memory, and CXL/GenZ, as well as software platforms involving containers for the HPC ecosystem, hybrid deployments, and confidential computing,
Christopher Haine, Research Engineer
Christopher Haine joined ERL in October 2018 as a research engineer, working in particular on the Maestro EU project. He earned a bachelor's degree in computer science at the Université de Reims Champagne-Ardenne, and a master's degree at the Université de Versailles, specializing in high-performance computing and simulation. Christopher earned a Ph.D. from the Université de Bordeaux, focused on loop kernel optimization by data layout restructuring. Christopher's main interests are data movement in complex memory hierarchies and optimization of scientific applications.
Alfio Lazzaro, Senior Research Engineer
Alfio Lazzaro joined ERL in October 2018 as a research engineer. He earned his Ph.D. in experimental particle physics at the University of Milan in 2007. In 2010 he joined CERN openlab with a COFUND-CERN and Marie Curie fellowship. From 2012 to 2014 he was an application analyst at Cray, based at the Swiss National Supercomputing Centre. From 2015 to 2018, he was a postdoctoral research associate at ETH Zurich and University of Zurich, working on the CP2K team under the Swiss PASC project. His main interests are optimization and parallelization of scientific applications.
Ali Mohammed, Research engineer
Ali joined ERL as a research engineer in April 2021. Before joining HPE, he was a postdoctoral researcher at the High-Performance Computing Group at the Department of Mathematics and Computer Science at the University of Basel, Switzerland. He received his doctoral degree in robust scheduling for high-performance computing from the University of Basel in 2020. His interests include data orchestration in scientific workflows, enhancing the performance of computationally-intensive scientific applications on HPC systems with various dynamic loop scheduling techniques in the presence of perturbations and failures. Also, he is interested in simulating scientific applications' execution and experimentally verifying the accuracy of the simulative of scientific applications' performance.
Nina Mujkanovic, Research Engineer
Nina Mujkanovic joined ERL in 2017. She performs system administration duties and contributes to various research projects as a research engineer with additional input as a system administrator. Prior to joining ERL, she was part of the HPC system administration team at the University of Bern in Switzerland, where she also earned an M.Sc. in computer science. During her studies, she specialized in advanced information processing, with a special focus on machine learning. Her thesis focused on creating a deep neural network for the detection of pathologies in the retina. Nina’s interests include deep learning, high-performance computing, and open source.
Tiziano Müller, Research Engineer
Tiziano Müller joined ERL in August 2021 as a research engineer. He studied Physics and Computational Science at the University of Zurich and worked at the University of Zurich in the field of electronic structure methods. In parallel to his studies, he worked as a software and system engineer in robotics and IT. Tiziano’s interests are in high-performance computing, human-machine interaction, open source and discovering simple solutions for complex problems.
Harvey Richardson, Principal Research Engineer
Harvey Richardson began his career with research roles after being awarded a Ph.D. in physics. As a researcher, he gained an interest in parallel computing through use and management of AMD DAP and Meiko systems. In 1992 Harvey joined Thinking Machines Corporation providing on-site support of the national Connection Machine CM-200 service at EPCC in Edinburgh. Harvey was responsible for user training, hardware, software, and application support. In 1998 Harvey joined the HPC benchmarking group of Sun Microsystems where he ran customer benchmarks to determine suitability of product and performance for customers’ applications. Harvey joined Cray in 2010 to work on research projects, both directly with customers and in larger research collaborations such as the EU CRESTA, EPIGRAM and EPIGRAM-HS projects looking at technologies that can help take real applications to exascale. Harvey has developed and taught many training courses and workshops. He has also developed various profiling and benchmarking tools. Harvey has particular interests in computer architecture and performance, programming models, and language standards.
Emilien TELLIER, Apprentice
Emilien joined ERL in 2022. He is currently an apprentice, working for HPE half time as an HPC Engineer and studying Computer Science and Applied Mathematics at the Ensimag engineering school in Grenoble, France the rest of the time aiming for the obtention of an engineering degree. Still currently discovering the computer science field, his interests are focused on high performance computing, systems programming but also working with containerized workloads, development and DevOps.
Irene Ferrario, Project Manager
Irene Ferrario joined ERL in 2018 to support the coordination and project management of ERL’s R&D projects. Irene has an expertise in project management, communication and legal and financial frameworks of projectized organizations. Before joining ERL, Irene worked in different advisory roles in EU Affairs in the UK and in Italy. Irene holds a PMP Qualification from the Project Management Institute and an M.A. in public policy. In her professional path, she has developed a keen interest in the communication and impact of new technologies on society.
See all current HPE job openings
You are an innovator at heart. Your curiosity sparks ideas. Every day at HPE is a new opportunity to make your mark.
Interested in engaging with the ERL?
Are you interested in engaging with ERL and take advantage of its pool of resources and expertise?