Gianmarco Ottavi
Papers
1
Total Citations
2
H-Index
1
About
Gianmarco Ottavi is a leading researcher in energy-efficient digital systems, with a primary focus on RISC-V-based heterogeneous architectures for Artificial Intelligence-enabled Internet-of-Things (AI-IoT) applications. His work addresses the critical challenge of enabling complex tasks—such as augmented reality, personalized healthcare, and nano-robotics—within stringent power envelopes of just tens of milliwatts. Ottavi’s major contribution is the design and demonstration of Marsellus, a heterogeneous RISC-V AI-IoT end-node System-on-a-Chip (SoC) that integrates 2-to-8-bit deep neural network (DNN) acceleration with adaptive body biasing, achieving a 30% boost in energy efficiency. This work, published in 2023, has already garnered significant attention for its practical approach to balancing compute-intensive workloads with ultra-low-power constraints. Ottavi’s research is pivotal for advancing edge AI, where real-time intelligence must operate under extreme energy limitations. His innovations in adaptive body biasing and mixed-precision DNN acceleration represent a notable step forward in making sophisticated AI capabilities viable for battery-powered, always-on devices, positioning him as a key contributor to the next generation of intelligent, autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1