Date: 06/12/2023

Lattice Collaborates with NVIDIA to Accelerate Edge AI

Announces integrated solution combining low-power, low-latency Lattice FPGAs with the NVIDIA Orin platform to efficiently bridge sensors to AI applications –





Lattice Semiconductor introduced a new reference sensor-bridging design to accelerate the development of edge AI applications using the NVIDIA Jetson Orin and IGX Orin platforms.

Based on power-efficient Lattice FPGAs and NVIDIA Orin, the open-source reference board is designed to address developers’ needs for connectivity to a diverse variety of sensors and interfaces, design scalability, and low latency when designing high-performance edge AI applications for healthcare, robotics, and embedded vision. Lattice’s collaboration with NVIDIA is set to expand the open-source developer community by improving the efficiency of connecting sensors to edge AI compute applications.

“With AI technology at the forefront of transforming various markets, including manufacturing, transportation, communications, and medical instruments, this collaboration will accelerate this fundamental shift,” said Esam Elashmawi, Chief Strategy and Marketing Officer, Lattice Semiconductor. “We are excited to work with NVIDIA to extend the reach of our reference solutions, bringing more innovation to our customers and ecosystem to help simplify and speed the implementation of edge AI applications.”

“As companies increasingly demand real-time insights and autonomous decision-making powered by AI, more developers are connecting their various sensors to NVIDIA edge computing platforms,” said Amit Goel, Director of Embedded AI Product Management, NVIDIA. “This collaboration with Lattice will accelerate innovations in sensor processing and help simplify the deployment of edge-to-cloud AI applications.”

The Lattice FPGA-based reference board is available today for early-access customers. Lattice plans to make the board and application examples more broadly available in the first half of 2024.

Source: Lattice Semiconductor

Tweet Follow @ecewire