"SC25 Power is becoming a major headache for datacenter operators as they grapple with how to support ever larger deployments of GPU servers - so much so that the AI boom is now driving the adoption of a technology once thought too immature and failure-prone to merit the risk. We're talking, of course, about co-packaged optical (CPO) switching. At the SC25 supercomputing conference in St. Louis this week, Nvidia revealed that GPU-bit barn operators Lambda and CoreWeave would be adopting its Quantum-X Photonics CPO switches."
"Nvidia has some competition: Broadcom showed off its own Tomahawk 5- and 6-based CPO switches. But while CPO switching is poised to take off in 2026, getting to this point has been a journey - and it's far from over. So what's driving the CPO transition? In the words of former Top Gear host Jeremy Clarkson, "speed and power." AI networks require exceptionally fast port speeds, up to 800 Gbps, with Nvidia already charting a course toward 1.6 Tbps ports with its next-gen ConnectX-9 NICs."
Co-packaged optical (CPO) switching is being adopted to address power, cabling, and scaling limits in large GPU datacenter networks. Vendors like Nvidia and Broadcom are deploying or demoing CPO switches to support very high port speeds required by AI networks, with paths toward 800 Gbps and 1.6 Tbps. CPO moves optical components from pluggable transceivers into photonic chiplets packaged alongside switch ASICs, attaching fiber directly to the switch front panel. This reduces the hundreds of watts consumed by many pluggables and overcomes copper cable reach and retimer constraints for dense, non-blocking GPU fabrics.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]