Axelera AI raises €61m for RISC-V HPC chiplet
Dutch chip developer Axelera AI has raised over €61m to develop a RISC-V AI chiplet for high performance computing (HPC) applications.
The Titania chiplet will buils on Axelera AI’s digital in-memory computing architecture, which the company says provides near-linear scalability from the edge to the cloud.
The €61.6m grant from the EuroHPC Joint Undertaking (JU) Digital is part of the Autonomy of RISC-V for Europe (DARE) Project and follows the oversubscribed $68 million Series B round for this datacentre development, bringing the total amount raised to more than €200m
The company is expanding its research and development teams in the Netherlands, Italy and Belgium to produce the Titania chiplet by 2028. Using the RISC-V open instruction set architecture with vector extensions enables Axelera AI to rapidly innovate in response to evolving customer needs and multiple Titania chiplets will be packaged in a System-in-Package (SiP).
“Our Digital In-Memory Computing (D-IMC) technology leverages a future-proof, scalable multi-AI-core architecture, ensuring unparalleled adaptability and efficiency. Enhanced with proprietary RISC-V vector extensions, this versatile mixed-precision platform is engineered to excel across diverse AI workloads,” said Evangelos Eleftheriou, CTO and co-founder of Axelera AI. “Uniquely, our architecture facilitates scaling from the edge to the cloud, streamlining expansion and optimizing performance in ways that traditional cloud-to-edge approaches cannot. We are setting a new standard for AI infrastructure, making true scalability a tangible reality”
In-memory computing reduces the power consumption of AI by eliminating energy losses from moving off-chip. Reasoning models such as OpenAI-o1 and DeepSeek R1 require significantly more inference computing than earlier transformer models.
The chiplet will also be available to add into chips used for enterprise data centres, robotics, automotive and others.
“This is an important milestone and validation of our technology. Since Axelera AI was founded in July 2021, we have continuously delivered technologies to help customers tackle the AI industry’s biggest challenges and efficiently implement AI capabilities into their products,” said Fabrizio Del Maffeo, Co-Founder and CEO at Axelera AI. “Today, we deliver a cutting-edge hardware and software platform for accelerating computer vision on edge devices at a fraction of the cost and energy consumption of current solutions. Titania builds upon this unique product suite. We are grateful to the EuroHPC DARE Project and the countries involved for helping accelerate the development of this groundbreaking AI inference technology for HPC data centres.”
Italian equipment maker Seco is launching a range of edge AI systems using the Axerla Metis chip at the Embedded World 2025 exhibition in Nuremberg next week. Seco is integrating the technology into both its hardware and software products for a complete AI/IoT market offering.
The SOM-COMe-BT6-RK3588 COM Express Type 6 module combines a Rockchip RK3588 processor with Axelera AI’s Metis AIPU for industrial AI workloads such as computer vision and predictive maintenance. This has 32 GB LPDDR5-3200 memory for the CPU and a separate 2 GB LPDDRx-2133 for the AIPU, 1x Gigabit Ethernet, 2x USB Type-C with DP Alt mode, 4x USB 5 Gbps, 4x PCIe lanes, and AI performance of up to 214 TOPS at INT8 precision with 15 TOPS/W energy efficiency.
The system runs Seco’s Yocto-based Linux distribution, Cleo OS, that facilitates AI and IoT deployments integrating Axelera’s Voyager software development kit (SDK) to optimize AI performance. A demo will features a real-time object detection model, utilizing a camera feed for instant object recognition using an AI model from Axelera’s Model Zoo highlights the system’s ability to handle high-performance edge AI applications with low latency and maximum efficiency.
An M.2 Key B+M plug-in module with four Metis chips enables slot-equipped edge computing systems. The M.2 2280 size integrates into a wide range of systems. Example uses include multicamera AI processing in surveillance and drones/UAVs, gesture recognition in robotics, and improving real-time diagnostics in medical applications.
“Our collaboration with Axelera AI is a testament to our commitment to pushing the boundaries of AI-driven edge computing,” stated Vincenzo Difronzo, Chief Sales Officer of Seco. “By integrating Axelera’s Metis AIPU into SECO’s portfolio, we are delivering high-performance, scalable solutions that unlock new opportunities for our clients, enabling them to deploy powerful AI applications with efficiency and confidence.”
“AI has the capacity to solve real-world problems and Axelera’s goal is to empower everyone with high-performance, cost-effective solutions. By combining our multi-core, user friendly Metis platform with the robust portfolio from SECO, users globally can benefit from real-time insights and better outcomes,” said Alexis Crowell, Chief Marketing Officer for Axelera AI.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
