Axelera AI Unveils Titania Chiplet with €61.6 Million Funding to Transform AI Inference
Axelera AI, a leader in AI hardware acceleration, has unveiled its latest innovation, Titania, a scalable, high-performance, and energy-efficient AI inference chiplet designed to meet the growing demands of AI and computer vision applications. This launch builds upon Axelera AI’s Digital In-Memory Computing (D-IMC) architecture, offering near-linear scalability from the edge to the cloud.
Axelera AI secured €61.6 million in funding through the DARE Project, led by EuroHPC JU, to develop Titania. The company raised over $200 million in three years, including $68 million from an oversubscribed Series B round.
Axelera AI is part of the DARE consortium, advancing European supercomputing and developing processors and technologies for extreme-scale applications.
Innovative Technology for Scalability
Titania's chiplet design integrates Axelera AI's D-IMC technology with RISC-V capabilities to address the growing needs of AI computing. The system delivers exceptional performance and energy efficiency, supporting scalability in HPC, robotics, automotive, and enterprise data centers.
Axelera’s D-IMC technology allows for near-linear scalability in performance without the power and cooling overhead typical of other solutions. RISC-V integration with vector extensions lets Titania quickly adapt to customer needs while providing efficient, optimized AI acceleration.
Revolutionizing AI Inference for Data-Intensive Applications
Titania will address the challenges facing the AI industry, particularly the increasing demands for inference computing driven by advanced models such as OpenAI's reasoning models and DeepSeek R1. Axelera AI is targeting a 2028 deployment date for Titania, offering exceptional throughput and efficiency for data-intensive AI applications and future zetta-scale HPC centers, all at a competitive price.
AI technologies are accelerating, with their applications forecast to grow at a 28%+ rate (CAGR). Issues around cloud performance, price, and environmental sustainability are emerging, making advances such as Titania essential in solving these pervasive issues.
Accelerating Research and Development in Europe
Through the DARE initiative, Axelera AI will grow its R&D teams in the Netherlands, Italy, and Belgium, supporting Europe's digital autonomy. The collaboration with EuroHPC JU aligns with Axelera AI’s mission to help build a world-class supercomputing ecosystem in Europe.
Fabrizio Del Maffeo, Co-Founder and CEO of Axelera AI, said, "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."
Axelera AI's Titania sets a new AI infrastructure standard, providing scalability and efficiency for both cloud and edge applications. Axelera AI’s focus on advancing hardware drives its mission to democratize AI, with Titania enabling scalable, energy-efficient solutions.
Additionally, Titania builds on Axelera AI's Metis AI Platform, boosting inference performance by 3-5x, helping businesses deploy AI efficiently.
