Broadcom Inc. Ships Tomahawk Ultra: Reimagining the Ethernet Switch for HPC and AI Scale-Up

Published: 2025-07-15 10:05:59 ET AVGO

Published on 07/15/2025 at 10:05

Broadcom Inc. announced the shipment of its breakthrough Ethernet switch -- the Tomahawk Ultra. Engineered to transform the Ethernet switch for high-performance computing (HPC) and AI workloads, Tomahawk Ultra delivers ultra-low latency, massive throughput, and lossless networking. Built from the ground up to meet the extreme demands of HPC environments and tightly coupled AI clusters, Tomahawk Ultra redefines what an Ethernet switch can deliver.

Long perceived as higher-latency and lossy, Ethernet takes on a new role: Ultra-low latency: Achieves 250ns switch latency at full 51.2 Tbps throughput. High performance: Delivers line-rate switching performance even at minimum packet sizes of 64 bytes, supporting up to 77 billion packets per second. Adaptable, optimized Ethernet headers: Reduces header overhead from 46 bytes down to as low as 10 bytes, while maintaining full Ethernet compliance --boosting network efficiency and enabling flexible, application-specific optimizations.

Lossless fabric: Implements Link Layer Retry (LLR) and Credit-Based Flow Control (CBFC) to eliminate packet loss and ensure reliability. With 250ns latency, 51.2 Tbps switching, and advanced features like Link Layer Retry, In-Network Collectives, and the AI Fabric header, it delivers the performance, reliability, and efficiency its customers need for AI at scale. Thanks to pin compatibility with Tomahawk 5, Micas can rapidly bring Tomahawk Ultra-based systems to market, enabling seamless upgrades to meet the demands of next-generation AI infrastructure.