BROADCOM INTRODUCES INDUSTRY’S FIRST SWITCH WITH ON-CHIP NEURAL NETWORK

In a world’s first for switching silicon, Broadcom Inc announced a novel on-chip, neural-network inference engine called NetGNT (Networking General-purpose Neural-network Traffic-analyzer) in its new, software-programmable Trident 5-X12 chip.

NetGNT works in parallel to augment the standard packet-processing pipeline. The standard pipeline is one-packet/one-path, meaning that it looks at one packet as it takes a specific path through the chip’s ports and buffers. NetGNT, in contrast, is an ML inference engine and can be trained to look for different types of traffic patterns that span the entire chip.

For example, NetGNT can look for a traffic pattern common in AI/ML workloads called “incast” in which many packet flows all converge on the same port and buffer at roughly the same time causing congestion. NetGNT can recognize this pattern in real-time as it begins and invoke congestion-control techniques to avoid degraded network performance. And since NetGNT runs in hardware at full line rate— there is no impact to throughput or latency.

Trident 5-X12 is software-programmable, field-upgradable and provides 16.0 Terabits/second of bandwidth, which is double that of the market-leading Trident 4-X9. It also adds support for 800G ports, allowing direct connection to Broadcom’s leading-edge Tomahawk 5, which is used as the spine/fabric in the newest compute and AI/ML data centres. This chip is uniquely positioned to enable a 1RU data centre ToR supporting 48x200G downlink ports and 8x800G uplink ports.

Additional Trident 5-X12 Key Benefits

Availability
Broadcom is now shipping Trident 5-X12 devices to qualified customers. For more information on the Broadcom Trident 5-X12 Ethernet switch please click here.