Axelera AI Secures €61.6 Million for Scalable AI Chiplet Development

Axelera AI has secured up to €61.6 million in funding from the EuroHPC Joint Undertaking (JU) and member states to develop its Titania AI chiplet, announced in a press release. This funding is part of the Digital Autonomy with RISC-V for Europe (DARE) Project, which aims to foster the development of European processors and accelerators for high-performance computing (HPC) and emerging applications.

The Titania chiplet is designed to be a high-performance, energy-efficient, and scalable AI inference solution. It leverages Axelera AI's Digital In-Memory Computing (D-IMC) architecture, which allows for near-linear scalability from the edge to the cloud. This architecture is enhanced with proprietary RISC-V vector extensions, enabling the chiplet to excel across diverse AI workloads.

Axelera AI plans to expand its research and development teams in the Netherlands, Italy, and Belgium to support the development of Titania. The chiplet is expected to address the increasing demands for AI inference computing, particularly in data-intensive applications and future zetta-scale HPC centers, with a target deployment date of 2028.