Alfio Di Mauro

About

Alfio Di Mauro is a leading researcher in energy-efficient artificial intelligence hardware, specializing in AI-enabled Internet-of-Things (AI-IoT) System-on-Chips (SoCs). His work focuses on designing heterogeneous computing platforms that combine RISC-V processors with precision-scalable Deep Neural Network (DNN) accelerators, enabling complex AI tasks—such as augmented reality, personalized healthcare, and nano-robotics—within ultra-low power envelopes of just tens of milliwatts. Di Mauro’s major contributions include the development of the AI-IoT SoC achieving 12.4 TOPS/W at 136 GOPS, integrating 16 RISC-V cores with 2-to-8-bit precision-scalable DNN acceleration and 30%-boost adaptive body biasing (34 citations). He also co-developed Marsellus, a heterogeneous RISC-V AI-IoT end-node SoC with similar adaptive body biasing and DNN acceleration capabilities. His work demonstrates how to balance compute-intensive DNN workloads with stringent power constraints across diverse operating conditions. Di Mauro’s innovations are pivotal for next-generation edge AI devices, pushing the boundaries of performance-per-watt in intelligent, low-power systems.

Research Focus

Key Achievements

Top Papers

1. 1
   22.1 A 12.4TOPS/W @ 136GOPS AI-IoT System-on-Chip with 16 RISC-V, 2-to-8b Precision-Scalable DNN Acceleration and 30%-Boost Adaptive Body Biasing

   34 citations · 2023
2. 2
   Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30%-Boost Adaptive Body Biasing

   2 citations · 2023

Key Collaborators

Contact & Links