Broadcom Ships Jericho4 for Distributed AI Data Centers
Broadcom Inc. has launched its next-generation Jericho4 ethernet fabric router, designed to enhance distributed AI computing across data centers. According to Reuters, the Jericho4 chip is engineered to connect data centers over distances exceeding 60 miles (96.5 km), facilitating faster AI computations.
The Jericho4 platform is capable of interconnecting over 1 million XPUs across multiple data centers, breaking traditional scaling limits with its high bandwidth, security, and lossless performance. A single system can scale to 36,000 HyperPorts, each operating at 3.2 Tb/s, ensuring efficient data movement across large networks.
Broadcom's Jericho4 also incorporates deep buffering and intelligent congestion control, ensuring lossless RoCE across distances over 100 km. The chip supports MACsec encryption on every port, providing robust security without compromising performance, even under high traffic loads.
Manufactured on a 3nm process, Jericho4 features advanced 200G PAM4 SerDes, eliminating the need for additional components like retimers, which reduces power usage and costs while enhancing system reliability. This innovation aligns with Broadcom's commitment to supporting large-scale distributed computing systems in an open and interoperable manner.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.
Also, consider following us on social media:
More from Data Centers
Sep 30 Sophia Space and Redwire Explore Orbital Data Centers Sep 30 SKF Recreates Greta Garbo With AI for Magnetic Bearing Campaign Sep 30 LG Innotek Targets $5.94 Billion in Semiconductor and Physical AI Businesses Sep 29 Efficient Computer Raises $97 Million to Scale Its Processors Sep 29 Hikvision Adds HIKO AI Engine to Hik-Connect 7Silicon Brief
Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
Qualcomm and Amazon to Develop Custom Silicon for AI Data Centers
iPronics Raises $125 Million for Optical AI Data Center Networking
ITRI Unveils 3.2 Tbps Silicon Photonics Optical Engine
Acer Introduces Veriton RI110 AI Mini Workstation
Huawei Unveils UnifiedBus Architecture for AI Clusters
Daily AI Brief: the AI news that matters, in your inbox.