Under the Hood: Scaling AI infrastructure
34:45
Microsoft’s Deepak Bansal and Cisco’s Will Eatherton discuss the shift to AI-first infrastructure. They explore using DPUs and Sonic to improve network efficiency and cost-per-token, while analyzing the competition between hyperscalers and Neoclouds.
Related Videos
In Enterprise Networks
-
Play video Unified Architecture: Single SDK & P4 Programmability Across All Cisco Silicon One Chip Families
Unified Architecture: Single SDK & P4 Programmability Across All Cisco Silicon One Chip Families
Advanced SerDes technology in Cisco Silicon One reduces AI data center power consumption. Discover how integrated retimers enable Linear Pluggable Optics, saving 500W per switch, along with direct copper cables that deliver zero-watt connectivity.
1:44
-
Play video Advanced SerDes Innovation: Cisco Silicon One Reduces AI Data Center Power with LPO & Direct Copper
Advanced SerDes Innovation: Cisco Silicon One Reduces AI Data Center Power with LPO & Direct Copper
Advanced SerDes technology in Cisco Silicon One reduces AI data center power consumption. Discover how integrated retimers enable Linear Pluggable Optics, saving 500W per switch, along with direct copper cables that deliver zero-watt connectivity.
2:05
-
Play video Adaptive Load Balancing: Cisco Silicon One Manages Mixed AI Traffic with Congestion-Aware Routing
Adaptive Load Balancing: Cisco Silicon One Manages Mixed AI Traffic with Congestion-Aware Routing
Cisco Silicon One dynamically manages mixed traffic in distributed AI clusters. Discover microsecond-level congestion detection, intelligent rerouting, and adaptive load balancing that optimizes packet spraying and flowlet-based traffic flows.
1:42
-
Play video Network Programmability: Cisco Silicon One P4-Powered Dynamic ASIC Updates Without Hardware Changes
Network Programmability: Cisco Silicon One P4-Powered Dynamic ASIC Updates Without Hardware Changes
Cisco Silicon One uses P4-powered programmability to enable dynamic ASIC updates without hardware changes. Learn how packet inspection, traffic shaping, advanced routing, and real-time policy enforcement help networks adapt to evolving standards.
1:39
-
Play video Building Scalable AI Infrastructure: Neoclouds, GPU Clusters & Operational Excellence
Building Scalable AI Infrastructure: Neoclouds, GPU Clusters & Operational Excellence
Explore how Neoclouds are scaling AI infrastructure with GMI Cloud and Cisco. Learn about managing GPU clusters, simplifying operations with unified visibility, and deploying NCP-compliant architectures for predictable, high-performance AI services.
30:23
-
Play video Traffic Engineering with Cisco Silicon One: AI-Driven Segment Routing, Policy & Static Pinning
Traffic Engineering with Cisco Silicon One: AI-Driven Segment Routing, Policy & Static Pinning
Explore advanced traffic engineering capabilities enabled by Cisco Silicon One, including AI-driven segment routing, policy-based routing, and static pinning. Optimize data flows and ensure predictable performance.
2:19
