STOCK TITAN

Credo Introduces Cardinal: A Low‑Power 1.6T Optical DSP Family Engineered for Massive‑Scale AI Fabrics

Rhea-AI Impact
(Neutral)
Rhea-AI Sentiment
(Positive)
Tags
AI

Key Terms

optical dsps technical
Optical DSPs are specialized chips that clean up and interpret light-based data sent over fiber-optic cables, converting noisy, distorted optical signals into accurate digital information. For investors, they matter because these chips determine how fast and reliably networks, data centers, and telecom systems can transmit information—so improvements or supply changes can affect equipment performance, costs, and the competitive landscape in high-speed communications.
silicon photonics technical
Silicon photonics is the technology that uses tiny structures etched into silicon chips to generate, control and detect light for moving data and sensing, essentially putting optical fiber functions onto a computer chip. For investors, it matters because it can dramatically increase data speed and energy efficiency in data centers, telecom networks and advanced sensors, potentially lowering costs and enabling new products much like replacing many metal wires with faster, low-power optical highways.
linear receive optics (lro) technical
Linear receive optics (LRO) are hardware components that convert incoming light signals on a fiber or optical cable into electrical signals with a consistent, proportional response across a wide range of signal strengths. Think of it like a camera sensor that faithfully captures both bright and dim parts of a scene without distortion; for investors, LRO matters because it enables higher-speed, lower-error data links in data centers and telecom networks, influencing product performance, cost, and market competitiveness.
bit error rates technical
Bit error rate is the fraction of digital bits that are received incorrectly when data moves over a network or through a device. Think of it as the number of typos in a long page of text: higher rates mean more mistakes, which can reduce product reliability, slow services, increase costs for error correction and refunds, and ultimately affect customer trust and a company’s financial performance.
dsp architecture technical
A DSP architecture is the internal design and organization of a digital signal processor—the specialized chip or software layout that turns raw data (like sound, video, or sensor signals) into useful information. Think of it as the blueprint for a factory line: it determines how quickly and efficiently signals get processed, how much battery or power is used, and what kinds of tasks the device can handle. Investors care because a more efficient DSP architecture can lower costs, improve product performance, enable new features, and create competitive advantage in markets like communications, consumer electronics, and industrial sensors.
predictive monitoring technical
Predictive monitoring is a continuous system that watches real-time data from equipment, patients, or business operations to spot patterns that suggest a future problem or opportunity before it happens. For investors, it matters because early warnings can cut costs, prevent downtime or safety issues, and make revenue and risk more predictable—similar to how a car’s dashboard alerts you to a developing mechanical issue so you can fix it before it becomes expensive.

Features World-Class Energy Efficiency in a Highly Integrated Design

SAN JOSE, Calif.--(BUSINESS WIRE)-- Credo Technology Group Holding Ltd (Credo) (NASDAQ: CRDO), an innovator in providing connectivity at scale through fast, reliable, and energy-efficient system solutions, today announced Cardinal, a groundbreaking family of 3nm low‑power, highly integrated 224G/lane optical DSPs designed specifically to meet the explosive bandwidth, latency, and reliability demands of modern AI compute fabrics.

Credo's Cardinal 1.6T optical DSP family addresses the bandwidth, scale, and power requirements of massive AI clusters with a proven low‑power architecture, superior latency with the flexibility to support both retimed 1.6T optics, and ultra‑efficient linear‑receive implementations.

Credo's Cardinal 1.6T optical DSP family addresses the bandwidth, scale, and power requirements of massive AI clusters with a proven low‑power architecture, superior latency with the flexibility to support both retimed 1.6T optics, and ultra‑efficient linear‑receive implementations.

News Highlights:

  • Credo has announced its second generation of 1.6T optical DSP family for addressing the bandwidth, scale, and power requirements of massive AI clusters.
  • The Cardinal family of devices includes low-power, high-swing integrated EML and silicon photonics drivers.
  • The Cardinal family consists of dedicated DSPs for full-retimed and linear receive optics (LRO) applications.

AI compute clusters are pushing the limits of network infrastructure, with high‑radix switches, dense GPU topologies, and massive east‑west traffic patterns. These environments demand optics that deliver maximum bandwidth per watt, extremely low bit error rates, and robust monitoring for uptime and serviceability. Cardinal delivers on each of these fronts enabling 1.6T transceivers with a comprehensive link monitoring toolkit while consuming less than 15W in LRO implementations.

“AI fabrics have shifted the center of gravity for optical design, and Cardinal was developed from day one with those unique requirements in mind,” said Chris Collins, AVP of Sales & Optical Product Marketing at Credo. “By combining a proven low‑power architecture, superior latency with the flexibility to support both retimed 1.6T optics, and ultra‑efficient linear‑receive implementations, Cardinal gives our customers the exact tools they need to scale their AI infrastructure.”

“Credo’s LRO solution in the Cardinal family will be a critical enabler for our teams to deliver ultra-low power optical solutions designed for rack-scale AI infrastructure,” said Jason Wildt, VP/GM, Photonics at Jabil, a global engineering, supply chain, and manufacturing solutions provider. “The power savings and associated thermal benefits are exactly what is needed for high‑density GPU clusters. Cardinal’s LRO option will provide our customers a solution that allows them to pack more performance into their power footprint.”

Key Features of the Cardinal DSP Family for AI Fabrics

  • Proven seventh generation DSP architecture
  • Dedicated 224G/lane solutions for full retimed and linear receive optics (LRO) applications
  • Integrated high‑swing laser drivers for both EML and silicon photonics
  • Advanced diagnostics and predictive monitoring for high‑uptime AI fabrics
  • Ultra-low latency below 40 ns per direction

To learn more about the Credo products in this release, go to the product pages linked here.

Product Availability

Credo is now sampling the Cardinal DSP family to lead customers.

About Credo

Credo’s mission is to transform connectivity at scale through fast, reliable, and energy-efficient system solutions. Our high-speed copper and optical interconnect products deliver industry-leading power and performance at up to 1.6T to meet the ever-expanding data infrastructure demands of AI.

Our product portfolio includes ZeroFlap (ZF) Active Electrical Cables (AECs) and ZF optical transceivers, OmniConnect memory solutions, and a suite of retimers and DSPs for optical and copper Ethernet and PCIe, all leveraging the PILOT diagnostic and analytics software platform. Credo innovations enable our customers to connect the systems that connect the world.

For more information, please visit https://www.credosemi.com. Follow Credo on LinkedIn.

Credo and the Credo logo are registered trademarks of Credo Technology Group Limited in the United States and other jurisdictions. All other trademarks referenced herein are the property of their respective owners.

Media Contact:

Kristin Hehir

kristin.hehir@credosemi.com

Investor Contact:

Dan O’Neil

dan.oneil@credosemi.com

Source: Credo

CREDO TECHNOLOGY GROUP HOLDING

NASDAQ:CRDO

View CRDO Stock Overview

CRDO Rankings

CRDO Latest News

CRDO Latest SEC Filings

CRDO Stock Data

21.56B
164.28M
Semiconductors
Semiconductors & Related Devices
Link
Cayman Islands
GRAND CAYMAN