@misc{HoffmannKuschnerusJonesetal., author = {Hoffmann, Javier Eduardo and Kuschnerus, Dirk and Jones, Trevor and H{\"u}bner, Michael}, title = {Towards a Safety and Energy Aware protocol for Wireless Communication}, series = {13th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), Lille}, journal = {13th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), Lille}, publisher = {Piscataway, NJ}, address = {IEEE}, isbn = {978-1-5386-7957-9}, doi = {10.1109/ReCoSoC.2018.8449380}, pages = {6}, language = {en} } @misc{KaestnerGuzmanJan­ssenetal., author = {K{\"a}stner, Florian and Guzman, Osvaldo Navarro and Jan­ßen, Be­ne­dikt and Hoffmann, Javier Eduardo and H{\"u}bner, Michael}, title = {Analysis of Hardware Implementations to Accelerate Convolutional and Recurrent Neuronal Net­works}, series = {In­ter­na­tio­nal Jour­nal on Ad­van­ces in Soft­ware}, volume = {10}, journal = {In­ter­na­tio­nal Jour­nal on Ad­van­ces in Soft­ware}, number = {3/4}, publisher = {IARIA}, issn = {1942-2628}, pages = {308 -- 323}, language = {en} } @misc{HoffmannGuzmanKaestneretal., author = {Hoffmann, Javier Eduardo and Guzman, Osvaldo Navarro and K{\"a}stner, Florian and Jan­ßen, Be­ne­dikt and H{\"u}bner, Michael}, title = {A survey on CNN and RNN implementations}, series = {PE­SA­RO 2017, The Seventh In­ter­na­tio­nal Con­fe­rence on Per­for­mance, Sa­fe­ty and Ro­bust­ness in Com­plex Sys­tems and Ap­p­li­ca­ti­ons}, journal = {PE­SA­RO 2017, The Seventh In­ter­na­tio­nal Con­fe­rence on Per­for­mance, Sa­fe­ty and Ro­bust­ness in Com­plex Sys­tems and Ap­p­li­ca­ti­ons}, publisher = {IARIA}, address = {Wilmington, DE, USA}, isbn = {978-1-61208-549-4}, pages = {33 -- 39}, language = {en} } @misc{AntonopoulosKeramidasVorosetal., author = {Antonopoulos, Christos and Keramidas, Georgios and Voros, Nikolaos and H{\"u}bner, Michael and Schwiegelshohn, Fynn and G{\"o}hringer, Diana and Dagioglou, Maria and Stavrinos, Georgios and Konstantopoulos, Stasinos and Karkaletsis, Vangelis}, title = {Toward an ICT-Based Service Oriented Health Care Paradigm}, series = {IEEE Consumer Electronics Magazine}, volume = {9}, journal = {IEEE Consumer Electronics Magazine}, number = {4}, publisher = {IEEE}, issn = {2162-2248}, doi = {10.1109/MCE.2020.2969202}, pages = {77 -- 82}, language = {en} } @misc{HuebnerGuntzel, author = {H{\"u}bner, Michael and Guntzel, Jose Luis}, title = {Guest Editors' Introduction: SBCCI 2018}, series = {IEEE Design \& Test}, volume = {37}, journal = {IEEE Design \& Test}, number = {3}, issn = {2168-2364}, doi = {10.1109/MDAT.2020.2989094}, pages = {5 -- 6}, language = {en} } @misc{FouadMetwallySchmitzetal., author = {Fouad, Mariam and Metwally, Yousef and Schmitz, Georg and H{\"u}bner, Michael and Abd El Ghany, Mohamed A.}, title = {Deep Learning Utilization In Beamforming Enhancement for Medical Ultrasound}, series = {2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), 13-17 July 2020, Madrid, Spain}, journal = {2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), 13-17 July 2020, Madrid, Spain}, publisher = {IEEE}, isbn = {978-1-7281-7303-0}, doi = {10.1109/COMPSAC48688.2020.0-175}, pages = {717 -- 722}, language = {en} } @misc{HoffmannMahmoodSuawaFogouetal., author = {Hoffmann, Javier Eduardo and Mahmood, Safdar and Suawa Fogou, Priscile and George, Nevin and Raha, Solaiman and Safi, Sabur and Schmailzl, Kurt JG and Brandalero, Marcelo and H{\"u}bner, Michael}, title = {A Survey on Machine Learning Approaches to ECG Processing}, series = {2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 23-25 Sept. 2020 , Poznan, Poland}, journal = {2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 23-25 Sept. 2020 , Poznan, Poland}, isbn = {978-83-62065-39-4}, language = {en} } @misc{HoffmannBrandaleroHuebner, author = {Hoffmann, Javier Eduardo and Brandalero, Marcelo and H{\"u}bner, Michael}, title = {TIRUB: A Safety and Energy-Aware Scheduling Algorithm}, series = {Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 23-25 Sept. 2020, Poznan, Poland}, journal = {Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 23-25 Sept. 2020, Poznan, Poland}, isbn = {978-83-62065-39-4}, doi = {10.23919/SPA50552.2020.9241280}, pages = {6}, language = {en} } @misc{VeleskiHuebnerKrsticetal., author = {Veleski, Mitko and H{\"u}bner, Michael and Krstic, Milos and Kraemer, Rolf}, title = {Highly Configurable Framework for Adaptive Low Power and Error-Resilient System-On-Chip}, series = {23rd EUROMICRO Conference on Digital System Design (DSD 2020), Portoroz, Slovenia, 26 - 28 August 2020}, journal = {23rd EUROMICRO Conference on Digital System Design (DSD 2020), Portoroz, Slovenia, 26 - 28 August 2020}, publisher = {IEEE}, isbn = {978-1-7281-9535-3}, doi = {10.1109/DSD51259.2020.00015}, pages = {24 -- 28}, language = {en} } @misc{MedeirosBernedNavarroetal., author = {Medeiros, Thiarles S. and Berned, Gustavo P. and Navarro, Antoni and Rossi, F{\´a}bio D. and Luizelli, Marcelo C. and Brandalero, Marcelo and H{\"u}bner, Michael and Beck, Antonio Carlos Schneider and Lorenzon, Arthur F.}, title = {Aging-Aware Parallel Execution}, series = {IEEE Embedded System Letters}, volume = {13 (2021)}, journal = {IEEE Embedded System Letters}, number = {3}, issn = {1943-0663}, doi = {10.1109/LES.2020.3021854}, pages = {122 -- 125}, language = {en} } @misc{FouadSchmitzHuebneretal., author = {Fouad, Mariam and Schmitz, Georg and H{\"u}bner, Michael and Abdelghany, Mohamed}, title = {Deep Learning in Signal Linearization for Harmonic Imaging Application}, series = {IEEE 18th International Symposium on Biomedical Imaging (ISBI)}, journal = {IEEE 18th International Symposium on Biomedical Imaging (ISBI)}, isbn = {978-1-6654-1246-9}, issn = {1945-8452}, doi = {10.1109/ISBI48211.2021.9434134}, pages = {4}, language = {en} } @misc{SchmailzlHuebner, author = {Schmailzl, Georg J. G. and H{\"u}bner, Michael}, title = {From the Internet of Things to an Internet of Services in Healthcare}, series = {Enhanced Telemedicine and e-Health}, journal = {Enhanced Telemedicine and e-Health}, isbn = {978-3-030-70110-9}, issn = {1860-0808}, doi = {10.1007/978-3-030-70111-6_7}, pages = {141 -- 153}, language = {en} } @misc{HernandezVeleskiBrandaleroetal., author = {Hernandez, Hector Gerardo Mu{\~n}oz and Veleski, Mitko and Brandalero, Marcelo and H{\"u}bner, Michael}, title = {Accelerating Convolutional Neural Networks in FPGA-based SoCs using a Soft-Core GPU}, series = {Applied Reconfigurable Computing. Architectures, Tools, and Applications : 17th International Symposium, ARC 2021, Virtual Event, June 29-30, 2021, Proceedings}, journal = {Applied Reconfigurable Computing. Architectures, Tools, and Applications : 17th International Symposium, ARC 2021, Virtual Event, June 29-30, 2021, Proceedings}, editor = {Derrien, Steven and Hannig, Frank and Diniz, Pedro C. and Chillet, Daniel}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-79024-0}, issn = {0302-9743}, doi = {10.1007/978-3-030-79025-7_20}, pages = {275 -- 284}, language = {en} } @misc{DaSilvaLimaGarciaetal., author = {Da Silva, Bruno A. and Lima, Arthur M. and Garcia, Janier Arias and H{\"u}bner, Michael and Yudi, Jones}, title = {A Manycore Vision Processor for Real-Time Smart Cameras}, series = {Sensors}, volume = {21}, journal = {Sensors}, number = {21}, issn = {1424-8220}, doi = {10.3390/s21217137}, language = {en} } @misc{RettkowskiHaasePrimusetal., author = {Rettkowski, Jens and Haase, Julian and Primus, Sven and H{\"u}bner, Michael and G{\"o}hringer, Diana}, title = {Performance analysis of application-specific instruction-set routers in networks-on-chip}, series = {NoCArc '21: Performance analysis of application-specific instruction-set routers in networks-on-chip}, journal = {NoCArc '21: Performance analysis of application-specific instruction-set routers in networks-on-chip}, publisher = {ACM Digital Library}, address = {New York}, doi = {10.1145/3477231.3490426}, pages = {16 -- 21}, language = {en} } @misc{SuawaFogouMeiselJongmannsetal., author = {Suawa Fogou, Priscile and Meisel, Tenia and Jongmanns, Marcel and H{\"u}bner, Michael and Reichenbach, Marc}, title = {Modeling and Fault Detection of Brushless Direct Current Motor by Deep Learning Sensor Data Fusion}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {9}, issn = {1424-8220}, doi = {10.3390/s22093516}, pages = {17}, language = {en} } @misc{HernandezFrickeAlKadietal., author = {Hernandez, Hector Gerardo Mu{\~n}oz and Fricke, Florian and Al Kadi, Muhammed and Reichenbach, Marc and H{\"u}bner, Michael}, title = {Edge GPU based on an FPGA Overlay Architecture using PYNQ}, series = {35th SBC/SBMicro/IEEE/ACM Symposium on Integrated Circuits and Systems Design (SBCCI). 2022}, journal = {35th SBC/SBMicro/IEEE/ACM Symposium on Integrated Circuits and Systems Design (SBCCI). 2022}, isbn = {978-1-6654-8128-1}, doi = {10.1109/SBCCI55532.2022.9893229}, pages = {6}, language = {en} } @misc{SteuerSchwarzOehmeetal., author = {Steuer, Oliver and Schwarz, Daniel and Oehme, Michael and Schulze, J. and Maczko, H. and Kudrawiec, Robert and Fischer, Inga Anita and Heller, R. and H{\"u}bner, R. and Khan, M. M. and Georgiev, Yordan M. and Zhou, Shengqiang and Helm, M. and Prucnal, Slawomir}, title = {Band-gap and strain engineering in GeSn alloys using post-growth pulsed laser melting}, series = {Journal of Physics: Condensed Matter}, volume = {35}, journal = {Journal of Physics: Condensed Matter}, number = {5}, issn = {1361-648X}, doi = {10.1088/1361-648X/aca3ea}, language = {en} } @misc{NannipieriGiuffridaLorenzoetal., author = {Nannipieri, Pietro and Giuffrida, Gianluca and Lorenzo, Diana and Panicacci, Silvia and Zulberti, Luca and Fanucci, Luca and Munoz-Hernandez, Hector Gerardo and H{\"u}bner, Michael}, title = {ICU4SAT: A General-Purpose Reconfigurable Instrument Control Unit Based on Open Source Components}, series = {IEEE Aerospace Conference (AERO), 5-12 March 2022}, journal = {IEEE Aerospace Conference (AERO), 5-12 March 2022}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-16654-3760-8}, doi = {10.1109/AERO53065.2022.9843414}, pages = {1 -- 9}, language = {en} } @misc{BrandaleroVeleskiMunozHernandezetal., author = {Brandalero, Marcelo and Veleski, Mitko and Mu{\~n}oz-Hernandez, Hector Gerardo and Ali, Muhammad and Le Jeune, Laurens and Goedem{\´e}, Toon and Mentens, Nele and Vandendriessche, Jurgen and Lhoest, Lancelot and Da Silva, Bruno A. and Touhafi, Abdellah and Goehringer, Diana and H{\"u}bner, Michael}, title = {Embedded AI Techniques for Industrial Applications}, series = {31st International Conference on Field-Programmable Logic and Applications (FPL), Dresden, Germany, 30 August-3 September 2021}, journal = {31st International Conference on Field-Programmable Logic and Applications (FPL), Dresden, Germany, 30 August-3 September 2021}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-6654-3759-2}, doi = {10.1109/FPL53798.2021.00071}, pages = {374 -- 375}, language = {en} } @misc{GianiBenevenutiGoncalvesetal., author = {Giani, Braga and Benevenuti, Fabio and Gon{\c{c}}alves, Marcio M. and H{\"u}bner, Michael and Brandalero, Marcelo and Kastensmidt, Fernanda and Azambuja, Jose Rodrigo}, title = {Evaluating softcore GPU in SRAM-based FPGA under radiation-induced effects}, series = {Microelectronics Reliability}, volume = {126}, journal = {Microelectronics Reliability}, issn = {0026-2714}, doi = {10.1016/j.microrel.2021.114348}, language = {en} } @misc{GoncalvesBenevenutiMunozHernandezetal., author = {Gon{\c{c}}alves, Marcio M. and Benevenuti, Fabio and Munoz-Hernandez, Hector Gerardo and Brandalero, Marcelo and H{\"u}bner, Michael and Kastensmidt, Fernanda and Azambuja, Jose Rodrigo}, title = {Investigating Floating-Point Implementations in a Softcore GPU under Radiation-Induced Faults}, series = {27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), virtual conference, November 23-25, 2020}, journal = {27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), virtual conference, November 23-25, 2020}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-7281-6044-3}, doi = {10.1109/ICECS49266.2020.9294939}, pages = {1 -- 4}, language = {en} } @misc{BrandaleroAliLeJeuneetal., author = {Brandalero, Marcelo and Ali, Muhammad and Le Jeune, Laurens and Munoz-Hernandez, Hector Gerardo and Veleski, Mitko and Silva, Bruno da and Lemeire, Jan and Van Beeck, Kristof and Touhafi, Abdellah and Goedem{\´e}, Toon and Mentens, Nele and G{\"o}hringer, Diana and H{\"u}bner, Michael}, title = {AITIA: Embedded AI Techniques for Industrial Applications}, series = {International Conference on Omni-Layer Intelligent Systems (COINS), 31 August-2 September 2020, Barcelona, Spain}, journal = {International Conference on Omni-Layer Intelligent Systems (COINS), 31 August-2 September 2020, Barcelona, Spain}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-7281-6371-0}, doi = {10.1109/COINS49042.2020.9191672}, pages = {1 -- 7}, language = {en} } @misc{AssafoLautschSuawaetal., author = {Assafo, Maryam and Lautsch, Martin and Suawa, Priscile Fogou and Jongmanns, Marcel and H{\"u}bner, Michael and Reichenbach, Marc and Brockmann, Carsten and Reinhardt, Denis and Langend{\"o}rfer, Peter}, title = {The ForTune Toolbox: Building Solutions for Condition-Based and Predictive Maintenance Focusing on Retrofitting}, publisher = {VDE Verlag}, address = {Berlin}, isbn = {978-3-8007-6204-0}, pages = {S. 541}, language = {en} } @misc{VeleskiHuebnerKrsticetal., author = {Veleski, Mitko and H{\"u}bner, Michael and Krstic, Milos and Kraemer, Rolf}, title = {Design and implementation strategy of adaptive processor-based systems for error resilient and power-efficient operation}, series = {24th International Symposium on Design and Diagnostics of Electronic Circuits \& Systems, DDECS, April 7-9 2021}, journal = {24th International Symposium on Design and Diagnostics of Electronic Circuits \& Systems, DDECS, April 7-9 2021}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-6654-3595-6}, doi = {10.1109/DDECS52668.2021.9417023}, pages = {57 -- 62}, language = {en} } @misc{VeleskiHuebnerKrsticetal., author = {Veleski, Mitko and H{\"u}bner, Michael and Krstic, Milos and Kraemer, Rolf}, title = {Towards Error Resilient and Power-Efficient Adaptive Multiprocessor System using Highly Configurable and Flexible Cross-Layer Framework}, series = {IEEE 27th International Symposium on On-Line Testing and Robust System Design (IOLTS), IOLTS 2021, June 28-30, 2021}, journal = {IEEE 27th International Symposium on On-Line Testing and Robust System Design (IOLTS), IOLTS 2021, June 28-30, 2021}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-6654-3370-9}, doi = {10.1109/IOLTS52814.2021.9486695}, pages = {1 -- 7}, language = {en} } @misc{BielefeldtBasenerKhanetal., author = {Bielefeldt, Jens and Basener, Kai-Uwe and Khan, Siddique R. and Massah, Mozhdeh and Wiesbrock, Hans-Werner and Scharoba, Stefan and H{\"u}bner, Michael}, title = {DeepTest: How Machine Learning Can Improve the Test of Embedded Systems }, series = {10th Mediterranean Conference on Embedded Computing (MECO), 7-10 June 2021}, journal = {10th Mediterranean Conference on Embedded Computing (MECO), 7-10 June 2021}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-6654-3912-1}, doi = {10.1109/meco52532.2021.9460182}, pages = {1 -- 6}, language = {en} } @misc{ScharobaBasenerBielefeldtetal., author = {Scharoba, Stefan and Basener, Kai-Uwe and Bielefeldt, Jens and Wiesbrock, Hans-Werner and H{\"u}bner, Michael}, title = {Towards Machine Learning Support for Embedded System Tests}, series = {24th Euromicro Conference on Digital System Design, DSD 2021, virtual conference, 1-3 September 2021}, journal = {24th Euromicro Conference on Digital System Design, DSD 2021, virtual conference, 1-3 September 2021}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-6654-2703-6}, doi = {10.1109/dsd53832.2021.00034}, pages = {166 -- 173}, language = {en} } @misc{MahmoodScharobaSchorlemeretal., author = {Mahmood, Safdar and Scharoba, Stefan and Schorlemer, Jonas and Schulz, Christian and H{\"u}bner, Michael and Reichenbach, Marc}, title = {Detecting Improvised Land-mines using Deep Neural Networks on GPR Image Dataset targeting FPGAs }, series = {IEEE Nordic Circuits and Systems Conference (NORCAS), 25-26 October 2022, Oslo, Norway}, journal = {IEEE Nordic Circuits and Systems Conference (NORCAS), 25-26 October 2022, Oslo, Norway}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {979-8-3503-4550-6}, doi = {10.1109/norcas57515.2022.9934735}, pages = {1 -- 7}, language = {en} } @misc{MahmoodHuebnerReichenbach, author = {Mahmood, Safdar and H{\"u}bner, Michael and Reichenbach, Marc}, title = {A Design-Space Exploration Framework for Application-Specific Machine Learning Targeting Reconfigurable Computing}, series = {Applied Reconfigurable Computing. Architectures, Tools, and Applications, 19th International Symposium, ARC 2023, Cottbus, Germany, September 27-29, 2023}, journal = {Applied Reconfigurable Computing. Architectures, Tools, and Applications, 19th International Symposium, ARC 2023, Cottbus, Germany, September 27-29, 2023}, editor = {Palumbo, Francesca and Keramidas, Georgios and Voros, Nikolaos and Diniz, Pedro C.}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-42921-7}, doi = {10.1007/978-3-031-42921-7_27}, pages = {371 -- 374}, language = {en} } @misc{DaSilvaCardosoNardoetal., author = {Da Silva, Samuel Souza and Cardoso, Matheus and Nardo, Lucas and Nepomuceno, Erivelton and H{\"u}bner, Michael and Arias-Garcia, Janier}, title = {A New Chaos-Based PRNG Hardware Architecture Using The HUB Fixed-Point Format}, series = {IEEE Transactions on Instrumentation and Measurement}, volume = {Vol. 72}, journal = {IEEE Transactions on Instrumentation and Measurement}, issn = {1557-9662}, doi = {10.1109/TIM.2023.3235457}, pages = {1 -- 8}, language = {en} } @misc{ShahinHuebnerHerglotz, author = {Shahin, Keyvan and H{\"u}bner, Michael and Herglotz, Christian}, title = {A width-configurable hardware approach for accelerating fixed-point simulation}, series = {IEEE Computer Society Annual Symposium on VLSI (ISVLSI)}, journal = {IEEE Computer Society Annual Symposium on VLSI (ISVLSI)}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {979-8-3315-3477-6}, issn = {2159-3477}, doi = {10.1109/ISVLSI65124.2025.11130205}, pages = {6}, abstract = {Fixed-point simulation is a critical step in the design flow of Digital Signal Processing (DSP) systems and consumes a significant portion of the overall development time. This work proposes a novel hardware-based approach to improve the performance of fixed-point simulation through a widthconfigurable architecture implemented on Field-Programmable Gate Arrays (FPGAs). To our knowledge, this is the first reported hardware-based solution for fixed-point simulation reported in the literature, which provides substantial speedup compared to traditional software-based approaches. The presented approach utilizes High-Level Synthesis (HLS) tools to create modular, reusable components that enhance the design reusability. This approach accelerates fixed-point simulation for various applications, requiring only minor modifications to the application code to utilize it. By incorporating simulation capabilities within reusable functions, this work improves the efficiency and adaptability of the fixed-point simulation process. Implementation results for two FIR filter applications show that the proposed methodology is superior to traditional software-based approaches in reducing simulation time by two orders of magnitude and thus has the potential to improve the productivity of the DSP system design flow.}, language = {en} } @misc{ShahinHuebner, author = {Shahin, Keyvan and H{\"u}bner, Michael}, title = {Accelerating fixed-point simulations using width reconfigurable hardware architectures}, series = {31st International Conference on Field-Programmable Logic and Applications (FPL), Dresden, Germany, 30 August-3 September 2021}, journal = {31st International Conference on Field-Programmable Logic and Applications (FPL), Dresden, Germany, 30 August-3 September 2021}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-6654-3759-2}, issn = {1946-1488}, doi = {10.1109/FPL53798.2021.00055}, pages = {275 -- 276}, abstract = {Digital Signal Processing (DSP) systems can be described using either fixed-point or floating-point for their numeric representations. As the general computers use floating-point representation, software-based simulation tools used for modeling and simulation of the arithmetic operations in DSP systems, use floating-point representation as well. However, synthesizing customized hardware for fixed-point arithmetic operations for FPGAs or ASICs is more efficient compared to their floating-point counterparts. Thus it is necessary to convert the representation of a floating-point simulated algorithm on MATLAB for example, to a fixed-point representation which is more suitable for hardware implementation. While former approaches for this conversion step have always been software-based, like on MATLAB itself, this paper presents a new approach to show the possibility of accelerating it by using hardware width reconfigurable designs.}, language = {en} } @misc{MunozHernandezAliShahinetal., author = {Mu{\~n}oz-Hernandez, Hector Gerardo and Ali, Muhammad and Shahin, Keyvan and Siyavashi, Alireza and G{\"o}hringer, Diana and Reichenbach, Marc and Herglotz, Christian and H{\"u}bner, Michael}, title = {Towards complete open-source environments : FPGA-based GPU overlay controlled by RISC-V}, series = {Architecture of computing systems : 38th International Conference, ARCS 2025 Kiel, Germany, April 22-24, 2025, proceedings}, journal = {Architecture of computing systems : 38th International Conference, ARCS 2025 Kiel, Germany, April 22-24, 2025, proceedings}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-032-03280-5}, issn = {0302-9743}, doi = {https://doi.org/10.1007/978-3-032-03281-2_7}, pages = {94 -- 108}, abstract = {Image and signal processing applications have been widely implemented in Field Programmable Gate Arrays (FPGAs) and Graphical Processing Units (GPUs) due to their energy efficiency and performance, respectively. GPUs provide high data processing parallelism and are usually chosen to accelerate applications where low energy consumption is not a high priority. On the other hand, FPGAs are more tailored to hardware solutions due to their reconfigurability, but they struggle to outperform GPUs in data throughput. Soft IP cores implemented on reconfigurable hardware, are an alternative offering advantages from both worlds. Some of these soft-core solutions offer an entire environment that includes scripts to automate their implementation, custom compilers, and other diverse tools. Unfortunately, some of these soft-cores are dependent on proprietary Intellectual Property (IP) or require hardware expertise to use properly. In this work, we propose an extended version of a popular open-source soft GPU, which can now run alongside a soft RISC-V core, and with High-Bandwidth memory (HBM2) compatibility. Previously, this soft GPU was only ready to be deployed in boards with a hard ARM core, but now it can be easily used in FPGAs without this requirement. We also provide an evaluation of how the soft GPU performs with respect to the pure RISC-V core, and a hard ARM core achieving geometric mean speed-ups of 114.60x and 19.72x respectively when performing some image and signal processing applications. Finally, we demonstrate how our soft GPU benefits from the HBM integration.}, language = {en} }