aiqbench takeChips & Infra

Cisco's new silicon and optical innovations directly address the critical networking bottlenecks hindering the scaling of large AI clusters, enabling faster chip-to-chip data transfer for frontier models. By introducing programmable architectures and open infrastructure stacks, these developments aim to reduce power consumption and hardware costs while maintaining flexibility for hyperscalers and enterprises. This represents a significant shift in the underlying compute fabric required to support next-generation artificial intelligence workloads.

Source coveringSiliconANGLE

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Cisco scales programmable AI network capacity with new silicon and repluggable optics innovations

SiliconANGLEOctober 12, 20265 min read

Cisco Systems Inc. took to the stage at the annual Open Compute Project Global Summit today, unveiling a new suite of open silicon and optical networking systems as it delivered one of the event’s most eagerly anticipated keynotes. The new innovations are designed to meet the growing demands of power- and data-hungry artificial intelligence workloads. […] The post Cisco scales programmable AI network capacity with new silicon and repluggable optics innovations appeared first on SiliconANGLE.

Cisco Systems Inc. took to the stage at the annual Open Compute Project Global Summit today, unveiling a new suite of open silicon and optical networking systems as it delivered one of the event’s most eagerly anticipated keynotes. The new innovations are designed to meet the growing demands of power- and data-hungry artificial intelligence workloads. They underscore Cisco’s longstanding commitment to fulfilling these needs with an open infrastructure stack that can be deployed by hyperscalers, neoclouds and enterprises alike. Networking has become a major bottleneck in AI data centers. As frontier models…

Excerpt shown under the publisher's RSS terms · 92 words · full text and figures are on the publisher's site

Read at SiliconANGLE ↗Ask about this article