@misc{HernandezMahmoodBrandaleroetal., author = {Hernandez, Hector Gerardo Mu{\~n}oz and Mahmood, Safdar and Brandalero, Marcelo and H{\"u}bner, Michael}, title = {A Modular Software Library for Effective High-Level Synthesis of Convolutional Neural Networks}, series = {Applied Reconfigurable Computing. Architectures, Tools, and Applications, 16th International Symposium, ARC 2020, Toledo, Spain, April 1-3, 2020, Proceedings}, journal = {Applied Reconfigurable Computing. Architectures, Tools, and Applications, 16th International Symposium, ARC 2020, Toledo, Spain, April 1-3, 2020, Proceedings}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-44533-1}, issn = {0302-9743}, doi = {10.1007/978-3-030-44534-8_16}, pages = {211 -- 220}, language = {en} } @misc{BrandaleroHernandezVeleskietal., author = {Brandalero, Marcelo and Hernandez, Hector Gerardo Mu{\~n}oz and Veleski, Mitko and Al Kadi, Muhammed and Rech, Paolo and H{\"u}bner, Michael}, title = {Enabling Domain-Specific Architectures with an Open-Source Soft-Core GPGPU}, series = {2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), New Orleans, LA, 18-22 May 2020}, journal = {2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), New Orleans, LA, 18-22 May 2020}, isbn = {978-1-7281-7445-7}, doi = {10.1109/IPDPSW50202.2020.00015}, language = {en} } @misc{NavarroYudiHoffmannetal., author = {Navarro, Osvaldo and Yudi, Jones and Hoffmann, Javier Eduardo and Hernandez, Hector Gerardo Mu{\~n}oz and H{\"u}bner, Michael}, title = {A Machine Learning Methodology for Cache Memory Design Based on Dynamic Instructions}, series = {ACM Transactions on Embedded Computing Systems}, volume = {19}, journal = {ACM Transactions on Embedded Computing Systems}, number = {2}, issn = {1539-9087}, doi = {10.1145/3376920}, pages = {20}, 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{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{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{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{SchwengerHolzingerFeyetal., author = {Schwenger, Lars and Holzinger, Philipp and Fey, Dietmar and Munoz-Hernandez, Hector Gerardo and Reichenbach, Marc}, title = {EasyHBM: Simple and Fast HBM Access for FPGAs Using High-Level-Synthesis}, series = {Embedded computer systems : architectures, modeling, and simulation : 22nd International Conference, SAMOS 2022, Samos, Greece, July 3-7, 2022, proceedings}, journal = {Embedded computer systems : architectures, modeling, and simulation : 22nd International Conference, SAMOS 2022, Samos, Greece, July 3-7, 2022, proceedings}, editor = {Orailoglu, Alex and Reichenbach, Marc and Jung, Matthias}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-15073-9}, pages = {43 -- 60}, language = {en} } @misc{KnoedtelMunozHernandezLehnertetal., author = {Kn{\"o}dtel, Johannes and Munoz-Hernandez, Hector Gerardo and Lehnert, Alexander and Thieu, Gia Bao and Gesper, Sven and Pay{\´a}-Vay{\´a}, Guillermo and Reichenbach, Marc}, title = {TAPRE-HBM: Trace-Based Processor Rapid Emulation Using HBM on FPGAs}, series = {Applied Reconfigurable Computing. Architectures, Tools, and Applications, 19th International Symposium, ARC 2023, Cottbus, Germany, September 27-29, 2023, Proceedings}, journal = {Applied Reconfigurable Computing. Architectures, Tools, and Applications, 19th International Symposium, ARC 2023, Cottbus, Germany, September 27-29, 2023, Proceedings}, editor = {Palumbo, Francesca and Keramidas, Georgios and Voros, Nikolaos and Diniz, Pedro C.}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-42920-0}, doi = {10.1007/978-3-031-42921-7_21}, pages = {307 -- 321}, 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} }