Nikolaos Bellas is Professor at the ECE Department of the University of Thessaly in Volos, Greece. He received the diploma in computer engineering and informatics from the University of Patras,Greece, in 1992, the MSc and PhD degrees in electrical and computer engineering from the University of Illinois, Urbana-Champaign, in 1995 and 1998, respectively. His research interests include approximate computing, reconfigurable computing, low power design, CAD tools for architectural synthesis . From 1999 to 2007, he was a principal member of Technical Staff at Motorola Labs in the US. He was one of the architects of Falcon, an MPEG4 video decoding chip used by the first Motorola camera phone, and has worked extensively on architecting systems on chip for multimedia and imaging applications. He holds 10 issued US patents.
- US Patent 8,855,441 Sek M. Chai, Malcolm Dwyer, Dan Linzmeier, Ruei-Sung Lin, Nikos Bellas. “Method and apparatus for transforming a non-linear lens-distorted image”, October 2014, Motorola Corp.
- US Patent 8,326,077 Sek M. Chai, Malcolm Dwyer, Dan Linzmeier, Ruei-Sung Lin, Nikos Bellas. “Method and apparatus for transforming a non-linear lens-distorted image”, December 2012, Motorola Corp.
- US Patent 7,802,005 Sek M. Chai, Nikos Bellas, Dan Linzmeier. “Method and Apparatus for Configuring Buffers for Streaming Data Transfer”, September 2010, Motorola Corp.
- US Patent 7,683,948 Arnold Yanof, Nikos Bellas. "System and method for bad pixel replacement in image processing", March 2010, Freescale Corp.
- US Patent 7,603,492 Sek M. Chai, Nikos Bellas, Malcolm Dwyer, Erica Lau, Zhiyuan Li, Dan Linzmeier. "Automatic generation of streaming data interface circuit", October 2009, Motorola Corp.
- US Patent 7,580,070 Arnold Yanof, Nikos Bellas. "System and method for roll-off correction in image processing", August 2009, Freescale Corp.
- US Patent 7,441,224 Nikolaos Bellas, Sek M. Chai, Dan Linzmeier. “Streaming kernel selection for reconfigurable processor”, October 2008, Motorola Corp.
- US Patent 7,305,649 Nikolaos Bellas, Sek Chai, Erica Lau, Zhiyuan Li, Dan Linzmeier. "Automatic generation of streaming processor circuit", December 2007, Motorola Corp.
- US Patent 7,073,041 Malcolm Dwyer, Nikolaos Bellas. "Virtual Memory Translation Unit for Media Acceleration", July 2006, Motorola Corp.
- US Patent 6,868,123 Nikolaos Bellas, Malcolm Dwyer. "A programmable, high performance Vector array unit used for Real-time Motion Estimation", March 2005, Motorola Corp.
- August 1995-December 1998: PhD Student, Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA.
- PhD Dissertation Title: "Architectural and Compiler Techniques for Energy Reduction in High-Performance Microprocessors. Advisors: Professors Ibrahim Hajj and Constantine Polychronopoulos.
- August 1993-August 1995: MSc Student, Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA.
- MSc thesis title: "A Novel Design for Testability Approach using State-Space information". Advisor: Professor Daniel Saab.
- September 1987-1992: Undergraduate Student, Computer Engineering and Informatics Department, University of Patras, Greece
- Diploma thesis title: Design and Simulation of a Linear Equation Solver Architecture
- Significance-based computing is a new computing paradigm that exploits uncertainty to design systems that are energy-efficient and scale gracefully under hardware errors by operating below the nominal operating point in a controlled way. We have been working on system software and architectures that realize the significance-based computing vision in the context of SCoRPiO and Uniserver projects.
- I am also actively working on mapping and optimization of interesting and emerging applications on reconfigurable platforms (FPGAs). We are currently working on improving the performance and energy efficiency of Simultaneous Localization and Mapping (SLAM) Algorithms used for real-time navigation of robots, drones, etc.
In the past, we have investigated programming models, runtime systems, and compilation tools to automate the generation of new platform architectures. Starting from many-core programming models (e.g. OpenCL), we automatically detect the SW/HW boundary, generate multiple hardware accelerators based on user requirements and system constraints, and create the appropriate run-time system to dynamically allocate resources and orchestrate data movement.
- My earlier research activity involved the study of minimizing power dissipation in processors using compiler and architectural techniques. It was one of the first efforts to investigate power minimization at such a high level of abstraction.
Current PhD students
- Alexandros Patras, PhD (since 2019)
- Maria-Rafaela Gkeka, PhD (since 2018)
PhD and MSc Alumni
- Panos Koutsovasilis, PhD 2020 (Research Scientist at IBM Ireland. Primary advisor Prof. Antonopoulos)
- Konstantinos Parasiris, PhD 2018 (Postdoctoral Researcher at Lawrence Livermore National Labs, USA)
- Vassilios Vasileiadis, PhD 2017 (Research Scientist at IBM Ireland. Primary advisor Prof. Antonopoulos)
- Mohsen Ewaida, PhD 2012 (Team Leader and Founder at SnowBell AI, Switzerland)
- Aggeliki Delakoura, MSc 2016 (STMicroelectronics, Edinburgh, UK)
- Konstantis Daloukas, MSc 2010 (ANSYS, Greece)
Department of Electrical and Computer Engineering,
37 Gklavani Street,
Telephone - Fax
Tel. No.: +30 24210 74704
Inverse: gr dot uth dot inf at nbellas
Tuesdays 14:00 - 16:00