Work package leaders

Stefano Markidis - Coordinator

Stefano Markidis is Associate Professor in High Performance Computing and Docent in Computer Science at KTH Royal Institute of Technology. He holds a MS degree from Politecnico di Torino and a PhD degree in Nuclear Engineering from the University of Illinois at Urbana-Champaign. Before joining KTH, he was graduate research assistant at Los Alamos National Laboratory and Lawrence Berkeley National Laboratory and postdoc at KU Leuven. Stefano won two R&D100 awards in 2005 and 2017 as part of the CartaBlanca and SHIELDS projects. He is author of more than one hundred peer-reviewed publications.

Daniel Holmes - Network Lead
Programming high-performance communication networks and fabrics in heterogeneous systems

Applications consultant in HPC Research at EPCC in The University of Edinburgh. His research interests focus on programming models for extreme scale supercomputers. He regularly contributes to the MPI Forum, the internal standards body for the message-passing interface, most recently driving the inclusion of persistent collective operations into MPI. Previous research for EU projects includes CRESTA (operating systems), EPiGRAM (programming models), and INTERTWinE (interoperability). He also has extensive experience of applying HPC expertise to create or improve parallel code for numerous commercial clients.

Tim Dykes - Memory Lead
Efficient and simplified usage of diverse memory

Tim Dykes is a Research Engineer in Cray’s EMEA Research Lab – a team dedicated to technical collaborations with customers on future software topics. His research interests are in heterogeneous high performance computing, data transport and memory hierarchies, compiler optimisation, and visualisation. He holds a PhD degree in High Performance Scientific Visualisation from the University of Portsmouth.

Valeria Bartsch - Compute Lead
Productive computing with FPGAs, GPUs and low-power microprocessors

Senior scientist of the HPC department of Fraunhofer ITWM and leads work package 4 “Productive computing with FPGAs, GPUs and low-power microprocessors” of the EPiGRAM-HS project. She has a background in experimental particle physics. Since 2013 she is working at Fraunhofer ITWM with an interest in the programming model GPI.

Olivier Marsden - Applications Lead
Pilot applications and integration

Olivier Marsden is a research scientist at ECMWF in the Integrated Forecast Systems section. Before joining, he lectured in the fields of acoustics and fluid dynamics at the Ecole Centrale de Lyon, France. His current activities focus on code optimisation and adaptation to future architectures. He has played an active part in four EU projects, and co-led a successful PRACE project which received computational resources on the NEC vector machines at HLRS.

Apostolos Vasileiadis - Dissemination Lead
Dissemination and standardization 

Apostolos Vasileiadis has a background in theoretical physics, marketing and entrepreneurship. He has worked as dissemination officer with European projects such as SAGE, EPiGRAM and Bioexcel.

Advisory Board

The Scientific Advisory Board's (SAB) role is providing objective, external feedback on the strategic direction of the EPiGRAM-HS project. The SAB will include international scientists working on programming environment and applications software development for large scale heterogeneous systems.

Antonio Peña
Barcelona Supercomputing Center, Spain

Antonio Peña is an expert of heterogeneous memory and accelerator computing within the programming models and runtime systems area.

Dirk Pleiter
Juelich Supercomputing Center, Germany

Dirk Pleiter is leading the work on application oriented technology development. He is principal investigator of the POWER Acceleration and Design Center and the NVIDIA application Lab at JSC. He is acting as work package leader in H2020 FETHPC projects, namely SAGE and ExaNoDe.

Sai Narasimhamurthy
Seagate, UK

Sai Narasimhamurthy is the coordinator of the SAGE project investigating the use of NVRAM for I/O systems.

Bernardino Romera Paredes
Google Deepmind, UK

Bernardino Romera Paredes brings to the SAB a valuable and informed feedback on the future of deep-learning and also a perspective from programming interfaces for deep- learning applications.

Jeffrey Vetter
Oakridge National Laboratory, US

Jeffrey Vetter is the founding group leader of the Future Technologies Group in the Computer Science and Mathematics Division of Oak Ridge National Laboratory. He has been investigating the effectiveness of next-generation architectures, such as graphics processors, massively multithreaded processors, non-volatile memory systems, heterogeneous multicore processors, and FPGAs, for key applications.

Anthony Skjellum
UTC - Director of SimCenter

Anthony Skjellum is the director of the SimCenter at the University of Tennessee at Chattanooga. His current research is a split between cyber/Internet of Things, and High Performance Computing and Exascale Storage. In the past he has also focused on: cyber, applications of high performance computing to intrusion detection, message passing systems, embedded high performance computing, scientific computing and parallel computing.