Neurophos has secured $110m in a Series A funding round to support the launch of its exaflop-scale photonic AI chips, bringing the Texas-based company’s total funding to $118m.

Gates Frontier led the investment, with participation from Microsoft’s venture fund M12, Carbon Direct Capital, Bosch Ventures, Aramco Ventures, Space Capital, Tectonic Ventures, and other backers.

DNX Ventures, Geometry, Alumni Ventures, Wonderstone Ventures, MetaVC Partners, Silicon Catalyst Ventures, Morgan Creek Capital, Mana Ventures, and Gaingels also joined the round. Cooley acted as legal counsel.

The new capital will enable Neurophos to accelerate delivery of its first integrated photonic computing system. This includes datacentre-ready optical processing unit (OPU) modules, a complete software stack and early-access developer hardware.

The company is also expanding its headquarters in Austin and establishing an engineering site in San Francisco to address initial customer requirements.

Neurophos develops proprietary OPU technology that contains over one million micron-scale optical processing elements on a single chip.

According to the company, these chips can be implemented directly in data centres as alternatives to current graphics processing units (GPUs).

Neurophos stated that its approach results in higher computational performance and improved energy efficiency when compared to traditional silicon-based GPUs.

The firm attributes its design advancements to micron-scale metamaterial optical modulators.

This component constitutes a significant size reduction compared with previous photonic elements and allows for scalable production of photonic computing hardware.

Neurophos CEO and co-founder Dr. Patrick Bowen said: “Our breakthrough in photonics unlocks an entirely new dimension of scaling, by packing massive optical parallelism on a single chip. This physics-level shift means both efficiency and raw speed improve as we scale up, breaking free from the power walls that constrain traditional GPUs.” 

As AI adoption continues across sectors, data centres are experiencing increased demand for power and scalability.

Industry reports indicate that traditional silicon-based architectures are unable to keep pace with growing computational requirements due to rising costs and energy needs.

Neurophos aims to address these issues by enabling lower power consumption to support future AI infrastructure expansion.

M12 managing partner Michael Stewart said: “As the AI industry grapples with a surge in demand that tests our ability to satisfy with compute and power, disruptive approaches to compute may open routes to sustained or accelerated systems scaling that will be needed before the end of the decade.

“With their approach to hyper-efficient optical computation, the Neurophos team have advanced swiftly from a working proof of concept towards a realistic plan to deliver products on a timeline we can underwrite and believe in.”