ESWEEK 2025 hosts fine education lectures online through Zoom, which will be given free of charge on September 26, 2025.
Please subscribe through the following link: https://forms.gle/
Timeslot A
08:00-10:00 (PDT, GMT-7), 11:00-13:00 (EDT, GMT-4), 17:00-19:00 (CEST, GMT+2), 23:00-01:00 (Taipei, GMT+8)
Education class 1 “Revisiting approximate computing – new possibilities on the horizon”
Instructor: Nima TaheriNejad (Heidelberg University, GE)
Summary: In this talk, we throw a glance at the basics of approximate computing before concentrating on approximate hardware. We present a few fundamental examples and take two new positions; From the first one, we challenge the mainstream view that approximate computing must necessarily come at the cost of system accuracy. We show that there are interesting exceptions beneficial for widely used application. Next, we discuss democratization of approximate computing hardware. That is, bringing hardware-level gains of approximate computing to the fingertips of software engineers.
Bio: Nima Taherinejad received his Ph.D. degree in electrical and computer engineering from The University of British Columbia (UBC), Vancouver, Canada, in 2015. He is currently a full professor at Heidelberg University, Heidelberg, Germany. His areas of work include computer architecture and emerging computing paradigms (especially memory-centric and approximate computing), cyber-physical and embedded systems, smart health-care, and artificial intelligence. He has published three books, five patents, and more than 100 articles.
Prof. Taherinejad has served as an editor of many journals, an organizer and a chair of various conferences and workshops. He has received several awards and scholarships from universities, conferences, and competitions he has attended. This includes the Best University Booth award at DATE 2021, First prize in the 15th Digilent Design Contest (2019) and in the Open-Source Hardware Competition at Eurolab4HPC (2019) as well as Best Teacher and Best Course awards at TU Wien (2020). Since 2023, he has been listed among the world’s top 2% scientists in the Stanford-Elsevier report.
Education Class 2 “Getting Started with the Quest RTOS and Quest-V Partitioning Hypervisor”
Instructors: Richard West, Shriram Raja, Zhiyuan Ruan (Boston University, USA), Rafiuddin Syed (Drako Motors)
Summary: Quest is a relatively small real-time operating system (RTOS), developed at Boston University. It works on both uni- and multicore processors, and supports various operating modes depending on the underlying hardware features. It can be configured as either a lightweight SMP system, having a single memory image running on multiple cores, or as a secure separation kernel, known as Quest-V (as in “V for Virtualization”).
The Quest RTOS features a novel real-time scheduling framework, where all control flows (including those triggered by interrupts) are associated with threads mapped to priority-aware and resource accountable virtual CPUs (VCPUs). This enables Quest to provide resource reservations to tasks and interrupt handlers, which are scheduled together.
When configured as a secure separation kernel, Quest-V uses hardware virtualization features to sandbox guest OSes into separate domains, each having direct access to dedicated CPU cores, physical memory, and a subset of I/O devices. The Quest-V partitioning hypervisor is used to establish separate sandboxes for guest OS domains such as Quest, which can co-exist and work in unison with other OSes such as Linux. Secure shared memory channels link multiple guest domains together to form a tightly-coupled separation kernel.
Bio:
Richard West (Boston University) richwest@bu.edu | Personal Website
Rich West joined the BU Department of Computer Science in 2000 after completing his PhD at Georgia Tech. Rich is a tinkerer of systems, notably, but not limited to, those in embedded and real-time computing. He likes to take a principled approach to system design, having dabbled in the development of standalone kernels and resource management policies where safety and predictability are paramount. He has studied real-time scheduling and resource management, cache-aware performance of multicore processors, and machine virtualization, amongst other topics. He is currently leading the development of the Quest real-time operating system for multicore processors. Its sister system, Quest-V is a secure and predictable separation kernel that forms a distributed system on a chip, providing efficient, predictable and safe execution of sandboxed guest systems including Linux. Rich is also the Chief Software Architect at Drako Motors where he leads the kernel development for DriveOS, which consolidates mixed-criticality functions on a centralized platform using Quest-V.
Zhiyuan Ruan (Boston University) zruan@bu.edu | Personal Website
Zhiyuan Ruan is a Computer Science PhD student, working with Professor Rich West.
Shriram Raja (Boston University) shriramr@bu.edu | Personal Website
Shriram Raja is a Computer Science PhD student, working with Professor Rich West.
Rafiuddin Syed (Drako Motors) rafiuddin.syed@drakomotors.com
Rafiuddin Syed is a Kernel Engineer at Drako Motors, working on the development of DriveOS.
Timeslot B
10:30-12:30 (PDT, GMT-7), 13:30-15:30 (EDT, GMT-4), 19:30-21:30 (CEST, GMT+2), 01:30-03:30 (Taipei, GMT+8).
Education class 3: “Reliability of Object Detection for Automotive and Aerospace Applications”
Instructor: Paolo Rech (University of Trento, Italy)
Summary: The main goal of this course is to provide students with an overview of the challenges associated with the hardware and software necessary for an application, such as object detection, that represents one of the major advances in the technology for computing devices. All the major cars builder and chip designers are targeting self-driven vehicles. Moreover, autonomous vehicles are extremely useful for space exploration. The NASA’s JPL Perseverance mission lunched at the end of July 2020, for instance, includes the first autonomous vehicle used for space exploration. The next ESA/NASA Mars samples return mission will be composed of fully autonomous rovers and drones. The course proposes a revision of basic concepts of real-time systems, parallel or programmable architectures, safety-critical systems, and approximate computing. These concepts are used and applied to deeply understand the object detection frameworks based on neural networks and their application in automotive and aerospace markets. A study of the limitations in terms of reliability and of the problems that can affect the correct execution of software and hardware will be presented. The focus will be on the study of both the hardware and the software necessary to detect object in a scene in real time. The problems and the constraints related to the security and reliability that can influence a safety-critical system will be considered.
The main topics covered during the course are:
– Introduction. Safety-critical applications concepts
– Automotive and aerospace applications
– Parallel and Programmable processors
– Approximate computing and energy consumption
– Object detection: state of the art
– Convolution and Activation function
– Neural networks based object detection
– CNNs in GPUs and FPGAs
– GPUs, FPGAs, what else? Automotive vs Aerospace
– Standard ISO 26262.
– Faults in hardware, errors in software.
– Hardening techniques for object detection.
– Energy consumption, execution time, precision, fault tolerance: can we have it all?
Bio: Paolo Rech received his master and Ph.D. degrees from Padova University, Padova, Italy, in 2006 and 2009, respectively. He was then a Post Doc at LIRMM in Montpellier, France. Since 2022 Paolo is an associate professor at Università di Trento, in Italy and since 2012 he is an associate professor at UFRGS in Brazil. He is the 2019 Rosen Scholar Fellow at the Los Alamos National Laboratory, he received the 2024 Italy-Canada innovation award, the 2020 impact in society award from the Rutherford Appleton Laboratory, UK and the Marie Curie Fellowship at Politecnico di Torino, in Italy. His main research interests include the evaluation and mitigation of radiation-induced effects in autonomous vehicles for automotive applications and space exploration, in large-scale HPC centers, and quantum computers.
Education class 4 “Neuromorphic computing for extremely constrained embedded applications”
Instructor: Stefano Di Carlo (Politecnico di Torino, Italy)
Summary: This lecture serves as an introductory survey of the emerging field of neuromorphic computing. While mainstream artificial intelligence is moving towards extremely large, computation-hungry models, neuromorphic computing takes a different approach, aiming to replicate the remarkable computational efficiency of the human brain. This lecture will introduce students to this promising and fascinating area, with a focus on spiking neural network models and the hardware architectures used for their efficient implementation in embedded devices.
Bio: Prof. Stefano Di Carlo is a Full Professor at the Politecnico di Torino, where he teaches and conducts research in the areas of computer architecture, dependable systems, and emerging computing paradigms. His current research focuses particularly on neuromorphic computing, exploring innovative hardware and software co-design strategies inspired by the computational efficiency of the human brain.
Prof. Di Carlo’s contributions in this field span the design and evaluation of spiking neural network models, the development of energy-efficient hardware accelerators, and the integration of neuromorphic approaches into embedded and edge computing platforms. He has coordinated national and international projects investigating the reliability, security, and performance of neuromorphic architectures, with applications ranging from autonomous systems to low-power AI for IoT devices. He has published extensively in leading journals and conferences, actively collaborates with industrial partners on transferring neuromorphic solutions to real-world use cases, and supervises doctoral students working on novel brain-inspired computing technologies.
Education class 5 “Hardware-software co-design for printed and flexible electronics for emerging on-sensor processing applications ”
Instructor: Mehdi B. Tahoori (Karlsruhe Institute of Technology, GE)
Summary: Printed and flexible electronics is an emerging and fast-growing field which can be used in many demanding and emerging application domains such as wearables, smart sensors, and Internet of Things (IoT). Unlike traditional computing and electronics domain which is mostly driven by performance characteristics, printed and flexible electronics based on additive manufacturing processes or special lithography processes are mainly associated with low fabrication costs and low energy. Printed and flexible electronics offer certain technological advantages over their silicon-based counterparts, such as mechanical flexibility, low process temperatures, maskless and additive manufacturing possibilities. Neverteless, due to low device count, large feature sizes and high variabilities, originated in low-cost additive manufacturing, existing design automation and computing paradigms of digital VLSI are not applicable to printed electronics. This tutorial covers the technology, process, modeling, fabrication, design automation, and computing paradigms for circuits and systems based on printed and flexible technologies.
Bio: Mehdi Tahoori is Professor and Chair of Dependable Nano-Computing at Karlsruhe Institute of Technology (KIT), Germany, and the Scientific Director at imec, where he focuses on system reliability, CMOS 2.0 and the future of chip design and manufacturing technologies. He received his PhD degree from Stanford university in 2003. He is a fellow of IEEE and recipient of European Research Council Advanced Grant.
