LPO vs NPO vs CPO: The Evolution of Optical
Today, 800G optical transceivers are widely deployed in modern AI data centers to support high-performance GPU networking. As AI clusters continue to scale, the industry is moving
Related Topics:
Optical Module Interconnection
Font Test
NVIDIA P100 Tesla GPU (2016) Tesla P100 tightly integrates compute and data on the same package by adding chip-on-wafer-on-substrate (CoWoS) with HBM2 technology.
GlobalFoundries accelerates adoption of co-packaged optics for
MALTA, N.Y., May 4, 2026 – GlobalFoundries (Nasdaq: GFS) (GF) today announced the introduction of its SCALE™ optical module solution for co-packaged optics (CPO). GF''s SCALE solution, or Silicon
BEAM: A Multi-Channel Optical Interconnect for Multi-GPU Systems
High-performance computing and AI applications necessitate high-bandwidth communication between GPUs. Traditional electrical interconnects for GPU-to-GPU commun.
Optical Interconnects For AI Data Centers | Syntec Optics
Startups are stepping up to address this bottleneck by developing innovative optical interconnects that can be integrated directly onto standard GPU and memory chiplets, promising a
All AI Data Center Interconnects Will Be Optical Within 5 Years
OFC and GTC are entangled because data center AI needs optical interconnect to keep compute fed. Optical interconnect enabled the internet with transoceanic and transcontinental high
NVIDIA LinkX Ethernet Optical Transceivers
Discover the next generation of transceivers for GPU-accelerated computing. NVIDIA ® LinkX ® Optics Ethernet transceivers are used to create high-speed, 100G–400G links supporting every
Optical Interconnect Technology Analysis: LPO, NPO, CPO
NPO, or Near-Packaged Optics, is a highly integrated optical interconnect solution that falls between traditional pluggable optical modules and CPO.
Optical Modules for GPU Clusters | AI Training Network Infrastructure
This article explores how optical modules enable GPU cluster architectures, the specific requirements of GPU interconnects, and best practices for designing high-performance AI training
Nvidia outlines plans for using light for
Earlier this year, Nvidia outlined that its next-generation rack-scale AI platforms will use silicon photonics interconnects with co-packaged optics (CPO) for higher transfer rates at lower...