CEA-Leti is pleased to host Subhasish Mitra, Professor of Electrical Engineering and Computer Science at Stanford University, as Chair of Excellence on Novel Technologies and Architectures for Big Data, funded by Leti’s Carnot Program. According to Prof. Mitra, the future demands of data-intensive applications cannot be met by simple improvement of the capabilities of current electronics. Isolated refinements of transistors, data storage technologies or integrated circuit architectures alone will not be sufficient. Transformative nanosystems, holistically implementing new computing paradigms will be essential for future high-performance and highly energy-efficient electronic systems.

Prof. Mitra’s research interests include robust computing, VLSI design, electronic design automation, disruptive 3D integrated circuits and their application in fields going from high performance computing to neuroscience. Leti collaborates with Prof. Mitra to identify the best suited novel architecture and emerging nanotechnologies that will allow the future disruptive applications of the day-aftertomorrow. The on-going work involves exploring and designing a Processing-in-Memory architecture, targeting Abundant-Data and dense interconnections applications. For data intensive tasks, Leti envisions a new architecture paradigm that will bring computation close to the data using advanced 3D integration. The concept will be designed and validated on silicon. In this partnership, Leti also expects to demonstrate the efficacy of Resistive Memories as basic building blocks for emerging computing paradigms as brain-inspired hyper dimensional computing. Subhasish Mitra directs the Stanford Robust Systems Group at Stanford University and co-leads the Computation focus area of the Stanford SystemX Alliance. He is also a faculty member of the Stanford Neurosciences Institute. More information about Prof. Mitra can be found at web.stanford.edu/~subh/