Mathieu Louvat

About

Mathieu Louvat is a leading figure in ultra-low-power artificial intelligence hardware, specializing in AI-enabled Internet-of-Things (AI-IoT) system-on-chip (SoC) design. His most impactful contribution is the development of a groundbreaking SoC that integrates 16 RISC-V cores with precision-scalable deep neural network (DNN) acceleration, supporting 2-to-8-bit operations. This chip achieves an impressive 12.4 TOPS/W at 136 GOPS, enabled by a 30%-boost adaptive body-biasing technique—a key innovation for energy-constrained edge devices. His work directly addresses the challenge of running compute-intensive DNNs for applications like augmented reality and personalized healthcare within a power envelope of just tens of milliwatts. With his 2023 paper already garnering 34 citations, Louvat’s research is rapidly shaping the future of efficient on-device intelligence. His achievements highlight a rare ability to bridge architectural innovation with practical silicon implementation, making him a pivotal voice in the push toward truly autonomous, energy-sustainable AI-IoT 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

Key Collaborators

Contact & Links