MENU

Ayar Labs Secures Additional $150M, Totaling $650M for 2026, to Scale Co-Packaged Optics (CPO) for AI Infrastructure

Converge Digest USA
Overview
Ayar Labs has raised an additional $150 million, bringing its total 2026 funding to $650 million, to expand manufacturing capacity for co-packaged optics (CPO) targeting AI scale-up infrastructure. The company’s CPO approach, based on its TeraPHY optical engine, integrates optical connectivity close to compute silicon, addressing bandwidth, reach, and power constraints of electrical I/O. Ayar Labs is collaborating with Wiwynn on rack-scale AI systems and establishing a new design center in Bengaluru, India, to support high-volume production.
In Depth

Key Findings

Ayar Labs has secured an additional $150 million in funding, raising its total capital for 2026 to $650 million, to significantly expand its manufacturing capacity for co-packaged optics (CPO) destined for AI scale-up infrastructure. This substantial investment aims to accelerate the mass production of its CPO technology, addressing critical data transfer bottlenecks in AI computing.

Technical / Clinical Details

Ayar Labs’ CPO technology is built upon its TeraPHY optical engine and external optical sources. This approach involves placing optical connectivity in extremely close proximity to compute silicon (e.g., GPUs and CPUs), thereby overcoming the severe limitations of bandwidth, reach, and power consumption inherent in existing electrical I/O. This enables a dramatic increase in data transfer speed and efficiency within AI clusters, both chip-to-chip and rack-to-rack. The company is actively collaborating with cloud infrastructure provider Wiwynn on the development of rack-scale AI systems, demonstrating concrete progress towards practical implementation. Furthermore, by establishing a new design center in Bengaluru, India, Ayar Labs is bolstering its product development capabilities and high-volume production support, strengthening its global manufacturing and supply chain.

Background & Context

The explosive growth of AI workloads, particularly large language models (LLMs), has imposed unprecedented demands on both computational and data transfer capabilities within data centers. Traditional electrical interconnections for chip-to-chip and server-to-server communication have become a primary bottleneck in scaling AI cluster performance due to power consumption, signal degradation, and physical wiring length limitations. In this context, optical interconnects, especially CPO technology that integrates compute chips with optical modules, are widely recognized as the next frontier for AI infrastructure. The substantial investment in Ayar Labs reflects a strong industry-wide consensus that this technology is indispensable for AI-era data centers.

Strategic Significance & Outlook

Ayar Labs’ CPO technology holds the potential to fundamentally transform AI data center architectures. With expanded manufacturing capabilities and strategic partnerships, the company is poised to accelerate the mass production and market penetration of its CPO solutions. As CPO becomes more prevalent, AI clusters can be built on a larger scale, with greater speed and improved power efficiency, providing robust support for the development of next-generation AI applications. Ayar Labs’ efforts are expected to play a critical role in shaping the future of AI computing.

Source: https://convergedigest.com/ayar-labs-150m-cpo-ai-scale-up/

Get our weekly technology intelligence — free

Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.

Subscribe Free — Weekly Tech Intelligence

By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.

  • Your email and selected fields are used only to deliver the newsletter.
  • We never share your information with third parties.
  • You can unsubscribe anytime via the link in each email.

See our Privacy Policy for details.

Takes about a minute · Unsubscribe anytime

Let's share this post !

Author of this article

Comments

To comment

TOC