Professor Dimitrios S. Nikolopoulos (Director of Research)
Dimitrios is Director of Research in HPDC. His research interests include the architecture, programming, characterisation and optimisation of scalable computing systems. His current research activity explores systems for real-time data analytics, energy-efficient many-core distributed and embedded systems, data centre monitoring and new computing paradigms at the limits of power and reliability. He has been awarded the NSF CAREER Award, the US DoE Early Career Principal Investigator Award, an IBM Faculty Award, a Marie Curie Fellowship, and a Fellowship from HiPEAC. His research has been supported with over £18 million of highly competitive, external research funding (out of over £6.5 million funded projects where Dimitrios is or was Principal Investigator). Dimitrios and his research group have earned seven best paper awards including the SC'2000 Best Technical Paper Award, ACM SIGPLAN PPoPP'2007 Best Paper Award, the IPDPS'2002 Best Paper Award and the CCGrid'2002 Best Paper Award. Dimitrios has taught undergraduate and postgraduate courses in parallel computing, parallel programming, computer organisation, computer architecture, operating systems, and embedded systems. He is a Senior Member of the IEEE and a Senior Member of the ACM. He earned a BEng (1996), MEng (1997) and PhD (2000) in Computer Engineering and Informatics from the University of Patras, working under the late Theodore S. Papatheodorou.
Professor Stan Scott (Head of School)
Stan is Professor of Computational Science at Queen’s, a Fellow of the British Computer Society, a Fellow of the Institute of Engineering and Technology and a senior member of the IEEE. He is Head of the School of Electronics, Electrical Engineering and Computer Science, having previously held the positions of Director of Research for High Performance and Distributed Computing and Director of Education. He is Editor-in-Chief of the Elsevier journal Computer Physics Communications and is Director of its associated International Software Library. For over thirty years he has been involved in the design and implementation of major software packages in computational science that can exploit high performance computing architectures. In 1994 he was awarded an Alexander von Humboldt Fellowship which was held at the Max-Planck Institute for Astrophysics. From 2005-07 he held a visiting professorship at the Laboratoire d’Informatique de Paris 6, Pierre and Marie Curie University in Paris, where he worked with the CADNA team to produce computational science software that is demonstrably numerically accurate. More recently he has been a visiting professor at Shanghai University. In 2006 he was awarded the HPC Prize for Machine Utilization by the UK Research Council's High End Computing Strategy Committee.
Peter has a long-held interest in the pragmatic use of formal specification notations to model and reason about systems, most recently distributed/grid-based systems and, in particular, autonomic aspects of such systems. He is involved in two EU-funded projects: ParaPhrase and CACTOS. Other current interests include variability management, particularly in the context of software product lines and feature modelling, and model-driven engineering. Peter has worked in the areas of program transformation, formal methods, and language design for parallel systems. Lists of his publications can be found on ResearchGate and on PURE. He is co-chair of PDP 2014. Peter teaches two final-year courses: "Algorithms: Analysis and Applications", which explores the complexity of a range of classical algorithms including sorting, searching, pattern matching, etc., and "High Performance Computing: Principles Of Parallel Programming" which explores fundamentals of parallel programming and emphasises practical aspects via MPI, OpenMP and CUDA. Previously he has taught courses on Introductory Programming, Concurrency Theory and Practice, Formal Methods (VDM), Computation Theory, Language Semantics, and Human-Computer Interaction.
Ivor's research interests include software for telecommunications (ECIT institute); software product lines (PFERG research group); solvers for propositional satisfiability (the Ternary Tree Solver); benchmarks for propositional satisfiability (sgen); formal methods for specifying and testing software systems; languages for parallel processing and their implementation; and image processing on parallel processors. He teaches on algorithms and software design techniques.
Georgios works on energy-efficient and reliable circuits and architectures. He is among the first to explore the error-resilience of various applications and how to utilise their properties for building energy-efficient and low-cost variation-tolerant systems. In 2012, he was awarded a 4-year Marie-Curie Career Integration Grant by the European Commission for pursuing his novel ideas as stated in the awarded project DARE. The proposed ideas have also gained the support of the highly competitive Future and Emerging Technologies scheme of the E.U. with the project SCoRPiO, as well as support from the Swiss National Science Foundation. Prior to joining Queen’s Georgios worked as a research scientist at the Swiss Federal Institute of Technology in Lausanne (EPFL), leading research efforts related to the design of energy-efficient and resilient wireless and embedded systems. He received his PhD. from the Electrical and Computer Engineering Department of Purdue University, USA, in 2010. In the summer of 2008, he was with the Advanced Technology Group, Qualcomm Inc., San Diego, while in 2003 he worked in the VLSI lab of Intracom, Athens, Greece. He has authored over 40 papers in refereed journals and conferences, a patent and a book chapter. In 2010, his work on a quality adaptive and energy efficient camera was recognised at the International Altera Innovate Design Contest. In 2015 Giorgios was the programme chair of the 1st workshop on Approximate Computing. He is serving as a member of the programme committee and referee of several top-tier conferences and journals. His research interests include approximate computing and storage architectures for nanometer technologies, and energy-efficient and variation-tolerant circuits and systems.
Amitabh's research interests are in CS theory and algorithms, especially those arising from or applicable to real world and human engineered systems; primarily distributed algorithms, networks, graph theory, and game theory. He is well-known for his work on designing efficient distributed algorithms for self-healing in systems under attack from a computationally unbounded adversary. Current research includes Self-healing/Resilient network algorithms, Leader Election, Game theoretic coalition formation and Software Defined Networks. His interests centre around multi-agent systems in dynamic scenarios which includes designing efficient distributed algorithms for robustness/self-healing/self-* properties in systems under attack, classic questions in distributed computing and distributed verification, and studying game theoretic and other mechanisms for evolving networks, such as social networks or distributed systems. He was awarded a PhD with Distinction in Computer Science by the University of New Mexico, USA. Before coming to QUB he held an Israeli-Centre for Research Excellence Postdoctoral Fellowship at Hebrew University of Jerusalem and postdocs at the Technion and University of Victoria, Canada. He was also awarded the Newton Incoming Fellowship of the Royal Society (which he had to decline). He is a member of ACM, IEEE, AAAI and has published in major ACM/IEEE/AAAI conferences and journals.
Hans's research interests are in compilers, runtime systems and architectures for parallel systems with special attention to the programmability of such systems. Hans also has a vested interest in computer architecture and particularly in cache architecture, prediction and performance evaluation. Hans received the IBM Belgium Prize for Computer Science in 2000 for his graduation thesis on "Bank prediction in multi-bank caches" and in 2004 for his PhD dissertation on "Avoiding mapping conflicts in microprocessors". His graduation thesis also received the Jozef Plateau prize from the Alumni Engineers Ghent in 2000. Hans was finalist in the 2004 Championship Branch Prediction competition. Prior to joining Queen's, Hans was Fellow with the Research Foundation Flanders and placed at Ghent University. He was visiting researcher at the Foundation for Research and Technology - Hellas in the Computer Architecture and VLSI Systems Laboratory in 2010-2011. He was visiting researcher in the Amdahl's Law is Forever team at INRIA Rennes in 2005 and he was visiting researcher at the Departament d'Arquitectura de Computadors at the Universitat Polytècnica de Catalunya in 2001.
Professor Bronis de Supinski (Centre for Applied Scientific Computing, Lawrence Livermore National Laboratory)
Bronis holds a World Leading Research Professorship in Exascale Computing in the School of Electronics, Electrical Engineering and Computer Science at Queen’s University Belfast. He is known worldwide for his seminal research in large-scale architectures, programming models (he is the chair of the OpenMP Language Committee) and tools. Throughout his career he has won several awards, including the prestigious Gordon Bell Prize in 2005 and 2006. He has also received a R&D 100 Award for STAT, a novel large-scale correctness tool. He has published over 140 papers, including eight that received Best Paper Awards, and has served on numerous program committees. He is the Co-Editor-in-Chief of the International Journal of High Performance Computing Applications and an Associate Editor of the IEEE Transactions on Parallel and Distributed Systems. He is the Technical Papers Committee Co-chair for SC14. He was the Program Committee Co-Chair of PACT (2009) and ICS (2011).
Cheol-Ho is working on the RAPID project. The main purpose of the project is to build an efficient heterogeneous CPU-GPU cloud computing infrastructure. In this infrastructure, CPU- and GPU-based tasks on low-power devices such as smartphones can be offloaded to more powerful devices on cloud platforms in order to reduce the execution time and the energy cost. In this project, he is developing a holistic task scheduler that considers both the CPU and GPU usage of virtual machines on the cloud platform. Cheol-Ho received his BS, MS and PhD degrees in Computer Science from Korea University, Seoul. He was a Research Professor in the Department of Computer Science, Korea University.
Lev's research interests are in optimizing compilers, thread-level automatic parallelization, EPIC/VLIW architectures, secure computing and energy efficient computing. Lev is involved in the EPSRC ALEA project. He is investigating energy profiling techniques at the instruction level, effects of compiler optimizations on energy consumption, and abstract level energy accounting models. He held the position of Senior Compiler Engineer/Head of Sector at Elbrus MCST. He obtained his MEng (2005) and PhD (2009) in Computer Science from the National Research Nuclear University MEPhI (Moscow Engineering Physics Institute).
Mahwish is working on an EPSRC-funded project: Hybrid Static/Dynamic Scheduling for Task Dataflow Parallel Programs. The idea is to investigate the benefits of hybrid scheduling for parallel programming models based on task dataflow. She will be working on developing compilation techniques and extending runtime system to embed static scheduling for such programs. The outcome of the project is expected to be performance improvement by reducing the overhead of dynamic scheduling and allowing more fine-grain parallelism in task dataflow programs. Mahwish has obtained her MSc in Computer Science from the University of Edinburgh.
Giorgis is in the final year of his PhD in affiliation with the University of Thessaly, Greece. His research interests revolve around performance and power optimisation by building resource-awareness in the system software stack. More specifically, his research interests include adaptive scheduling in heterogeneous and asymmetric multicore architectures, context-aware dynamic binary rewriting, and cross-layer optimisation. He is involved in the GEMSCLAIM project which aims to provide a novel, cross-layer power optimisation framework spanning from the hardware architecture to the application level. Giorgis has worked as a research assistant in the Institute of Research Technology in Thessaly and was an external collaborating researcher with the Foundation for Research and Technology in Crete.
Niaz is working on an EPSRC-funded project: Heterogeneous Parallel and Distributed Computing with Java (HPDCJ). The main aim of the project is to enable parallel computing within Java with minimal change to the specifics of the language. The project will develop Java library tools and programming models for scalable parallel computing on heterogeneous systems.Niaz will be working on the low level optimization which will involve: JVM runtime offloading for heterogeneous many-core nodes which will involve porting JVM to heterogeneous nodes with accelerators as GPUs and MIC, Scalable memory management and locality management where the focus will be on the garbage collection and Scalable task-based execution for heterogeneous nodes. Niaz's research interests are in High Performance Computing, GPGPU and Visual Computing. He obtained his MSc by research in Computer Science from Swansea University. His MSc thesis was on improving radix sort bandwidth requirements where he implemented a high performance parallel Radix Sort for CPUs.
Karen works in HPDC on the ASAP project, which proposes a unified, open-source execution framework for scalable data analytics processing utilising heterogeneous execution engines and heterogeneous data stores. She is seeking to abstract the best from existing novel programming languages and runtime systems in graph analytics. The result should lead to the creation of an adaptive optimisation model which will satisfy a wide range of query types targeting diverse data stores. Karen aims to exploit optimisation potential to maximise parallel exploitation of both multi-core and distributed systems.
Chhaya's interests include theoretical computer science and algorithmic aspects of networked systems. She is specifically interested in distributed algorithms for systems with unreliable components. Her MSc thesis was on designing and analysing distributed algorithms that efficiently self-stabilize in the presence of transient faults. In addition, she has also done some interesting projects during her MSc in Machine Learning, NLP and Logic and its application to Graph Theory and Combinatorics. Prior to her MSc, she worked as a software consultant for 7 years on various assignments with Microsoft and eBay. She is currently involved in the SCoRPIo project and is investigating the use of Distributed Optimization techniques to achieve energy efficiency on a significance driven computing platform.