Technology

Chiplet Standards Aim For Plug-n-Play

Source

SemiEngineering

Published

Apr 16, 2026

TL;DR

AI Generated

Chiplet standards are crucial for creating a marketplace where chiplets can be easily interchanged like LEGOs. Various standards are being developed to ensure interoperability and physical composability of chiplets, including die-to-die interconnect standards like Bunch of Wires (BoW) and Universal Chiplet Interconnect Express (UCIe). These standards cover system architecture, security, power delivery, data semantics, physical placement, testing, and more. Organizations like the Open Compute Project (OCP) are leading efforts to standardize chiplet-related aspects, such as packaging descriptions and system architectures. The goal is to pave the way for a plug-and-play chiplet marketplace, although challenges related to practical and economic factors still exist.

Read Full Article

Silicon Photonics Lights The Way To More Efficient Data Centers

Silicon photonics is paving the way for more efficient data centers by potentially increasing bandwidth density and reducing power consumption, particularly driven by AI workloads. However, challenges such as process compatibility, thermal issues, and mechanical stress arise due to the use of various materials in photonic interconnects. Integrated electro-optical I/O modules are the desired outcome, but design and process complexities need to be addressed. The article delves into the technical aspects of silicon photonics, including the components involved, such as light sources, modulators, waveguides, and photodetectors, as well as the challenges of integrating optical and electronic components for efficient data transmission.

SemiEngineering•

5 days ago

11 Myths About Automotive Ethernet

The article "11 Myths About Automotive Ethernet" debunks misconceptions about the technology, highlighting its benefits for modern vehicles. It clarifies that Automotive Ethernet is not just for the future but is already benefiting OEMs by addressing connectivity requirements. The article explains the differences between regular Ethernet and automotive Ethernet, emphasizing cost-effectiveness and reduced complexity. It also addresses concerns about reliability, security, energy efficiency, and suitability for various vehicle types. Additionally, it emphasizes the standardization of Automotive Ethernet for improved interoperability and support for high-bandwidth applications in vehicles.

ElectronicDesign•

4 weeks ago

Tech titans team up to form optical interconnect alliance to solve the AI buildout's big data bottleneck — Nvidia, AMD, Broadcom & more set sights on building PHY to break through the limitations of copper

Tech giants like Nvidia, AMD, Broadcom, Microsoft, and others have formed the Optical Compute Interconnect Multi-Source Agreement (OCI MSA) group to develop an open connectivity specification for optical interconnections in AI data centers. The goal is to overcome the limitations of copper by enabling higher data transfer speeds and reducing power consumption through optical interconnections. The group aims to create a physical layer (PHY) capable of delivering speeds up to 3.2Tb/s to support large-scale AI workloads. The standardization of optical interconnects would allow for multi-vendor supply chains and alleviate supply chain constraints faced by copper. The alliance seeks to establish a platform-agnostic approach to optical interconnections to drive innovation in AI data center infrastructure.

Tom's Hardware•

1 month ago

AMD, Broadcom, and Nvidia join hyperscalers to define optical scale-up interconnect of the future for AI clusters — Meta, Microsoft, and OpenAI to benefit as speeds eventually scale to 3.2 Tb/s

Hyperscalers like Microsoft, Meta, and OpenAI are collaborating with AMD, Broadcom, and Nvidia to develop an open optical interconnect technology for future AI clusters, aiming for speeds up to 3.2 Tb/s. The consortium established the Optical Compute Interconnect (OCI) Multi-Source Agreement (MSA) group to define a common optical physical layer for AI systems. This technology will support various protocols and enable the use of optical cables instead of copper for high-speed connections between accelerators. The OCI MSA group, led by AMD, Broadcom, and Microsoft, aims to simplify system integration and accelerate the deployment of new AI hardware.