The generative AI boom is driving the demand for AI chips, that are purpose-built to coach and run generative AI models. And major players, from VCs to startups, are scrambling to get in on the bottom floor.
SoftBank’s Masayoshi Son is reportedly seeking to raise $100 billion for a chip initiative that may compete with tech giant Nvidia. OpenAI, meanwhile, is said to be in talks with investment firms to launch an AI chip-making enterprise.
AI chip startup Axelera has kept a relatively low profile. Nevertheless, it has managed to win over backers including Samsung partly by specializing in a distinct segment inside the burgeoning AI chip market: chips that run AI on edge devices.
“There’s no denying that the AI industry has the potential to rework a large number of sectors,” Fabrizio Del Maffeo, certainly one of the co-founders of Axelera and its CEO, told TechCrunch in an interview. “Nevertheless, to really harness the worth of AI, organizations need an answer that delivers high-performance and efficiency while balancing cost.”
Axelera — headquartered within the Netherlands, with a roughly 180-person workforce spread across offices in Belgium, Switzerland, Italy and the U.K. — designs AI-running chips and systems for applications like security, retail, automotive and robotics that it supplies to partners manufacturing B2B edge computing and web of things products.
Axelera was born out of an effort led by Del Maffeo and a bunch at Imec, the Belgium-based technology lab, together with Evangelos Eleftheriou and a bunch of Zurich-based IBM researchers to construct a highly efficient AI chip architecture. The founding team incubated much of Axelera inside Bitfury Group, a blockchain company specializing in Bitcoin hardware.
The defining characteristics of Axelera’s AI hardware stack are the instruction set architecture (ISA) RISC-V and in-memory computing.
ISAs are a technical spec at the inspiration of chips that describe how software controls the chip’s hardware. Chip designers typically license an existing ISA from a big chipmaker similar to Arm or Intel, but RISC-V presents an open, no-royalties-attached alternative. As for in-memory computing, it refers to running calculations in a system’s RAM to scale back the latency introduced by storage devices.
Axelera isn’t the primary to try its hand at an in-memory and/or RISC-V-based architecture for AI chips.
NeuroBlade is developing chips that mix each compute and memory right into a single hardware block for data processing. MemVerge, GigaSpaces, Hazelcast and H20.ai also offer in-memory hardware solutions for AI and data analytics applications. Elsewhere, Tenstorrent, backed by Hyundai Motor Group and Samsung, sells AI processors and other related IP built around RISC-V.
Axelera has attempted to distinguish itself by delivering each chip hardware and software to administer and deploy AI models to that hardware. And from all appearances, the strategy appears to be working for it.
Axelera on Thursday announced that it closed a $68 million Series B funding round that brings its total raised to $120 million. Contributors to the round include the European Innovation Council Fund, Innovation Industries Strategic Partnership Fund, Invest-NL and Samsung Catalyst Fund.
The brand new money will probably be put toward expanding to recent markets ahead of full production of Axelera’s flagship Metis AI platform in H2 2024, in line with Del Maffeo. Axelera also has an eye fixed on the info center chip market, with preliminary plans to fund R&D of chips aimed toward high-performance compute use cases.
“Metis entered in full production in Q2 and will probably be delivered in volume in Q3,” Del Maffeo said. “Axelera AI is now developing a brand new generation of products for computer vision, large language models and enormous multimodal models. This recent product family will probably be unveiled later this yr and enter in full production in 2025.”
The challenge will probably be shipping its AI chips at scale — and competing against countless others within the AI chip race. Many rivals have formidable backing; a Crunchbase report from June finds that VC-backed chip startups have raised nearly $5.3 billion in only 175 deals up to now this yr.
The reward may very well be substantial, nonetheless. In accordance with Statista and Market.us data, the AI chip market might gross as much as $67 billion in revenue by 2027. Axelera has little likelihood of unseating entrenched vendors like Nvidia anytime soon, if ever. (Nvidia has an estimated 70% to 95% share of the AI chip market, per Mizuho Securities.) But nabbing even a fraction of the market can be a meaningful win.
“The funding supports our mission to democratize access to AI, from the sting to the cloud,” Del Maffeo said, adding that Axelera has “tens” of enterprise customers. “By expanding our product lines beyond the sting computing market, we’re in a position to address industry challenges in AI inference and support current and future AI processing needs.”
