Prof. Dr. Erika Covi , TU München
Friday Get-together: “Emerging Memory Integration for Energy-Efficient Edge Computing”
05.06.2026 (Friday)
, 14:00 - 15:00
- Dresden: Barkhausenbau Room BAR E64A
- Aachen: new Walter Schottky Haus Room B101/B102
- Halle/RUB: at your institutions
- Online: https://tu-dresden.zoomx.de/j/87264138030?pwd=WG41dkN6L0NOaXFaaVRORzM3QmdFQT09
Abstract:
The shift from cloud-based data classification toward edge computing has enabled real-time data processing closer to the source of data collection, cutting latency and improving overall efficiency. Yet this shift brings with it strict demands around power consumption, physical footprint, and computational performance. Meeting these demands calls for novel hardware approaches that can operate within such tight constraints.
Incorporating emerging memory technologies at the back-end-of-line (BEOL) of CMOS circuits, or within 3D array configurations, opens up exciting possibilities for advancing neuromorphic hardware.
This presentation highlights the importance of design-technology co-optimization (DTCO) as a means of seamlessly combining emerging memory devices with CMOS circuits, laying a design foundation for next-generation memory systems built on BEOL and 3D integration. It will explore the challenges and opportunities that arise when co-designing devices, circuits, and architectures together, making the case for a co-development approach to enabling the full potential of computing at the edge.