Andrés Goens, a former member of the CC Chair (2014-2021), has been awarded the “Cloud & Heat Dissertationspreis” for his thesis “Improving Model-based Software Synthesis”. Andrés’ thesis encompasses much of his work at the CC Chair, including 25 different co-authored publications during his PhD research time at the chair. As the title suggests, it deals with model-based software synthesis, one of the main areas of research at our chair. The Cloud & Heat prize is awarded to outstanding doctoral dissertation work at TU Dresden. Andrés is now at the University of Edinbugh, in Scotland, where he works on verification and interactive theorem proving, focusing on the Lean theorem prover, hardware description languages and weak memory models. He couldn't join us during this year's OUTPUT.DD science event in person, so we had to improvise a picture. We are happy for Andrés, congratulations!
The design automation conference (DAC) is a premier event for academics and industry working on the design and automation of electronic chips to systems. DAC 2022 was organized in San Francisco, California, from 10-14 July with over 5500 participants and over 200 emerging and leading companies exhibiting their solutions. Asif Ali Khan represented the chair for compiler construction and talked to like-minded researchers and industry experts working in emerging memory technologies and architectures, and their optimizations for various application domains. Asif also visited Prof. Alex K. Jones's group at the University of Pittsburgh to discuss our ongoing collaboration on accelerating genomics applications using racetrack memories.
We are happy to welcome João Cardoso to the CC chair! João obtained his bachelors (2016) and masters (2019) degrees in computer engineering and computer science from the Federal University of Santa Catarina (UFSC) and the Federal University of Rio Grande do Sul (UFRGS), in Brasil. Since then, he has been working with Prof. Luigi Carro at UFRGS as a PhD student on low-precision training of neural networks with emerging computing platforms. We are looking forward to working with João and on possible collaboration with Prof. Luigi Carro! In our group, João will be joining the large-scaleSCADS.AI project. In this context, he will investigate software optimization methodologies for emerging architectures and novel algorithms in machine learning and artificial intelligence. Welcome to the team!
This year’s HiPEAC conference was moved from winter to June 20 to improve in-person participation. This worked and it was great to see 200+ HiPEAC members in Budapest! The CC chair co-organized a workshop around the topics of the EVEREST project and contributed two talks to the conference. The first one opened the PARMA-DITAM workshop, where Prof. Castrillon talked about tool flows for high-performance reconfigurable computing, reporting on latest results from the EVEREST project and proving an research outlook on emerging in- and near-memory computing paradigms. In the second talk, within EVEREST workshop, Prof. Castrillon talked about domain specific languages and compilation flows in the EVEREST project. Both talks were visited and discussions were plentiful. Looking forward to other HiPEAC events!
We are happy to host Francesco Ratto at the CC Chair. He is a PhD student enrolled in the Electronics engineering and Computer science program (DRIEI) at the University of Cagliari. He received the Masters degree in Electrical engineering from the same university in 2020. He is co-supervised by Prof. Luigi Raffo (University of Cagliari) and Prof. Francesca Palumbo (University of Sassari). He works on adaptive deployment of CNNs and on the design of multithread accelerators for FPGAs for signal processing applications. At the CC Chair, he will be working on hybrid mapping of 5G baseband processing on heterogenous platforms under the supervision of Robert Khasanov and Julian Robledo. Big thanks go to the funding instruments for this exchange, provided by Ph.D. mobility scholarship of the the University of Cagliar and the Erasmus+ Traineeship PLACEDOC program.
Four members of the CC Chair participated in the 2022 Rewe Team Challenge Dresden (4x5km), after three years of our last participation. Conny Okuma, Robert Khasanov, Julian Robledo and Jeronimo Castrillon made a mixed team that got place 289 out of 1602 teams. The total time of 1:45:06 was only slightly better than the time from 2019 of 1:45:44. More training is needed for next time!
We congratulate Asif Khan for having successfully defended his PhD on April 25th, 2022. Asif joined our team a bit less than five years ago in May 2017. Together with Fazal, Asif helped shape most of the work on emerging technologies at the CC Chair. He worked on several memory and in-memory architectures and developed pioneering compiler optimizations for systems with emerging memory technologies. His work has been published in several renown conferences and journals, including DAC, DATE, LCTES, CASES, ACM TECS, ACM TACO, IEEE TCAD and IEEE TC. Today he defended his thesis on "Design and code optimization for systems with next-generation racetrack memories” in a hybrid setup, with family and friends connecting remotely. Special thanks go to Prof. Yiran Chen from Duke University for acting as external reviewer. We are more than happy that Asif will stay with us as PostDoc for the near future!
The CC Chair, together with Prof. Christian Pilato and Dr. Christoph Hagleitner, organised a workshop at the DATE Conference 2022 entitled "Data-driven applications for industrial and societal challenges: Problems, methods, and computing platforms" (DATA-DREAM'22). The workshop provided an international forum for researchers in the field of large-scale data analysis technologies to discuss challenges and ideas for the future of big data analytics. Participants shared their insights into current political, economic and technological developments, and placed special focus on their approaches to overcoming the hurdles towards wide adoption of reconfigurable computing platforms. This event is an initiative of the EVEREST project, which we hope will trigger collaborations and awareness in the community.