NECSTLab Seminar and Poster Session
Date: February 17, 2023
CISE Seminar: 2:00PM-3:30PM
Poster Session: 3:30PM-4:30PM
Location: 15 St. Mary’s Street, EMB 105 & Lobby
Please visit here to see Poster Abstracts.
BRIDGES: Boosting Research, Innovation and Personal Development through a Global EcoSystem
ID1 Title: Leonardo: the “multimagineering” project
Speaker: Marco Santambrogio, Politecnico di Milano
Abstract: In the general perception, Research and Education form a dichotomy, for it is hard to couple them into productive and virtuous cycles. At NECSTLab, we embrace such a dichotomy, pushing it further by expanding our view over a third axis: personal well- being/ness.
We call it Leonardo.
Leonardo is our research project to augment students’ awareness of themselves and their abilities. It bloomed from the seed idea that technical competencies are just one of the key components to personal success. Resilience – the ability to define individual goals and plan towards them – is the natural step further. Finally – so far – we add one last term to complete the equation: awareness of personal talents and limits.
The Leonardo project is organized over 4 Levels bundled in 2 Phases of 2 Levels each; more in detail, each Level spans from 1 up to 3 semesters. During each Level, the participants face challenges as part of a series of activities drawn from 3 areas: Learning, Personal Well-being/ness, Research. Nutrition, sleep and psychology counselors, coaches, research and study mentors build our expert team to assemble a holistic teaching experience. For instance, coaches challenge participants in sports activities. This experience drives their motivation to increase their adaptability and self-efficiency in the Personal Well- being/ness area. All of this encourages the participants to realize their true potential towards better knowing and accepting themselves.
Each phase has its exit activity: an experience that encourages the participants to measure themselves over the skills and competencies they have become more aware of. The NECST Group Conference (NGC) is the last of these exit activities. It offers the participant the final exposure to the real world thanks to talks at outstanding companies’ headquarters and first- class universities’ laboratories and research groups.
ID2 Title: Heterogeneous High Performance Computing @ NECSTLab
Speaker: Guido Walter Di Donato, PhD student @ Politecnico di Milano
Abstract: Numerical system solvers, machine/deep learning, dense/sparse linear algebra, genomics, and physics simulation. These are a few examples of highly performance- demanding applications hungry for computational power. Unfortunately, modern general- purpose architectures fail to deliver the ever-increasing required performance in such a context, causing long energy-inefficient runtimes. Consequently, High-Performance Computing (HPC) systems started embracing heterogeneity and leveraging hardware accelerators. In this way, the adoption of devices like Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs) alongside general-purpose processors offers a unique solution to offload workloads, boost performance, and increase energy efficiency. This research line concentrates on Heterogeneous HPC (HHPC) systems, showcasing our efforts towards the acceleration of highly demanding applications on GPUs and FPGAs.
ID3 Title: Domain Specific Computing @ NECSTLab
Speaker: Davide Conficconi, Post Doctoral Researcher @ Politecnico di Milano
Abstract: The end of Moore’s law is heavily limiting CPUs performance scaling at a reasonable energy budget. Therefore, at NECSTLab we explore the architecture research area of narrowing the computational domain to a single one as energy-efficient high- performance solutions. We explore areas of design methodologies and automation of domain specialization. This research line spans from spatial multi-domain architectures to domain-specific architectures and their custom instruction sets, from automatic design flows for dynamically configurable edge accelerators to cross-platform frameworks for context-specific architectures. We mainly exploit FPGAs as prototyping platforms for fixed architectures or as driving devices for unique reconfigurability capabilities. In this regard, we exploit them as adaptable architectures for continuously evolving domains able to keep pace with the latest advancements.
ID4 Title: Information Technologies for Life Science @ NECSTLab
Speaker: Eleonora D’Arnese, Post Doctoral Researcher @ Politecnico di Milano
Abstract: IT for Life Science is a research area of NECSTLab’s Computer Architecture group that focuses on a broad spectrum of applications in the medical, biological, and wellness fields. Within these domains, we explore different computer architectures and computational paradigms to enable novel solutions to complex problems, or to improve the performance of well-known compute-intensive operations. An example is the usage of Knowledge Graphs to represent heterogeneous biological information, and the exploration of Graph Machine Learning techniques to automate predictive tasks on such graphs, in order to solve complex problems like drug repurposing or dementia detection. Another example is the work in the medical imaging domain, where we are exploring various computer architectures and computational approaches to speed up and expand the application of image registration, and to efficiently deploy semantic segmentation and the detection of pathologies such as lung cancer.
Event led by Marco D. Santambrogio, Associate Professor, Politecnico di Milano
Marco Domenico Santambrogio is an Associate Professor at Politecnico di Milano since 2018, and an Adjunct Professor del College of Engineering of the University of Illinois at Chicago (UIC) since 2009. He was Assistant Professor at Politecnico di Milano from 2011 to 2018 and Research Affiliate with the Computer Science and Artificial Intelligence Laboratory (CSAIL) at Massachusetts Institute of Technology (MIT) from 2010 to 2015. He received his laurea (M.Sc. equivalent) degree in Computer Engineering from the Politecnico di Milano (2004), a M.Sc. degree in Computer Science from the University of Illinois at Chicago (UIC) in 2005 and his PhD degree in Computer Engineering from the Politecnico di Milano (2008) and we was a postdoc fellow at CSAIL, MIT (2009-2010).
He has been with the Micro Architectures Laboratory at the Politecnico di Milano, where he founded the Dynamic Reconfigurability in Embedded System Design (DRESD) project in 2004. In 2011, he founded the Novel, Emerging Computing System Technologies Laboratory (NECSTLab), merging together the two previously existing labs: MicroLab and VPLab, and he is, since then, in charge of the laboratory. He conducts research and teaches in the areas of reconfigurable computing, self-aware and autonomic systems, hardware/software co-design, embedded systems, and high performance processors and systems. Marco D. Santambrogio is a senior member of both the IEEE and ACM, he is the Chair of the Italy Chapter of the IEEE Computer Society (CS) and member of the IEEE Circuits and Systems Society (CAS). He is or has been member of different program committees of electronic design automation conferences, among which: DAC, DATE, ICCAD, CODES+ISSS, FCCM, FPL, RAW.
Faculty Host: Ayse Coskun