Broadcom Pitches Ethernet for AI Scale Up

Tomahawk 6 is First to 102.4T

Through relentless execution, Broadcom has been first to market generation after generation in data-center switching. The company just announced sampling of Tomahawk 6 (TH6), its 102.4T Ethernet switch ASIC. This generation actually consists of two switch chips, TH6-200G with 512x200G SerDes, and TH6-100G with 1,024x100G SerDes, both of which are sampling now. A version with fully co-packaged optics, TH6-Davisson, will follow on a to-be-announced schedule.  Whereas Tomahawk 5 (TH5) is a monolithic 5nm chip, TH6 comprises a core die and separate chiplets for the two SerDes options, all of which use 3nm technology.


Source: Broadcom

For AI scale-out networks, TH6 enables a 128K-XPU network using only two switch tiers. Fewer tiers mean lower latency, simpler load balancing and congestion control, and fewer optics. The new chip is first to handle 1.6T Ethernet ports, but it also handles up to 512x200GbE ports for maximum radix. Beyond sheer port density, TH6 makes incremental improvements over TH5 for scale-out networks. Global Load Balancing 2.0 selects links on a per-packet basis using network-wide congestion information, delivering 50% greater throughput than traditional hash-based ECMP.


The unexpected aspect of Broadcom's announcement is its focus on Ethernet for AI-cluster scale-up interconnects. A single TH6 can connect 512 XPUs, providing single-hop all-to-all connectivity. More realistically, one chip can connect 128 XPUs at 800Gbps each, and multiple switch planes can multiply the per-XPU bandwidth further. In his keynote at the OCP EMEA Summit in April, Broadcom's Ram Velaga previewed this application by announcing the Scale-Up Ethernet (SUE) Framework. SUE builds a new transport protocol on top of standard Ethernet, and Broadcom's custom-ASIC customers can integrate SUE intellectual property into their AI accelerators.


TH6 comes at a crucial time, as Broadcom faces surging, yet indirect, competition from Nvidia. The leader in AI infrastructure exceeded $2 billion in Spectrum-X platform sales in its most-recent quarter, citing adoption at Google Cloud, Meta, Microsoft Azure, and Oracle Cloud as well as so-called neoclouds CoreWeave and xAI. For context, $2 billion is also Arista Networks' total sales in its most-recent quarter. Broadcom sells chips, not systems, but Nvidia is clearly gaining Ethernet market share using its in-house Spectrum ASICs.


What's clear is that the market for scale-up and scale-out networking will be dynamic in 2026, presenting opportunities for competing technologies and vendors. Broadcom is attempting to establish a beachhead for scale-up Ethernet before alternatives such as UALink can mature. For the networking ecosystem, anything that loosens Nvidia's grip on AI-platform architecture will be welcome.

LightCounting subscribers can access additional details, figures, and analysis in a full-length research note: www.lightcounting.com/login

Comments

Post a Comment

Popular posts from this blog

AMD Looks to Infinity for AI Interconnects

Image
With the formal launch of the MI300 GPU, AMD revealed new plans for scaling the multi-GPU interconnects vital to AI-training performance. The company's approach relies on a partner ecosystem, which stands in stark contrast with NVIDIA's end-to-end solutions. The plans revolve around AMD's proprietary Infinity Fabric and its underlying XGMI interconnect. Infinity Fabric Adopts Switching As with its prior generation, AMD uses XGMI to connect multiple MI300 GPUs in what it calls a hive. The hive shares a homogeneous memory space formed by the HBM attached to each GPU. In current designs, the GPUs connect directly using XGMI in a mesh or ring topology. Each MI300X GPU has up to seven Infinity Fabric links, each with 16 lanes. The 4th-gen Infinity Fabric supports up to 32Gbps per lane, yielding 128GB/s of bidirectional bandwidth per link. At the MI300 launch, Broadcom announced that its next-generation PCI Express (PCIe) switch chip will add support for XGMI. At last October...
Read more

NVIDIA Pivots as Networking Stalls

Image
Yes, $11B in Blackwell revenue is impressive. Yes, Nvidia's data-center revenue grew 93% year over year. Under the surface, however, there's trouble in networking. In the January quarter (Q4 FY25), networking revenue declined 9% year over year and 3% sequentially. In its earnings call, CFO Collette Kress said that Nvidia's networking attach rate was "robust" at more than 75%. Her very next sentence, however, hinted at what's happening underneath that supposed robustness. "We are transitioning from small NVLink8 with InfiniBand to large NVLink72 with Spectrum-X," said Kress. About one year ago, Nvidia positioned InfiniBand for "AI factories" and Spectrum-X for multi-tenant clouds. That positioning collapsed when the company revealed xAI selected Spectrum-X for what is clearly an AI factory. InfiniBand appears to be retreating to its legacy HPC market while Ethernet comes to the fore. Nvidia Data-Center Revenue So how do we square 93% DC grow...
Read more

PAM4 DSPs Battle LPO for OFC Mindshare

Image
Last year, module vendors demonstrated the first 1.6T optical modules, and this year DSP vendors looked ahead to second-generation 1.6T module designs. Whereas the first 1.6T modules connect a 16x100G host interface to 8x200G optics (16:8), next-generation designs will work with forthcoming 200G/lane switch ASICs, as shown in the top row of the figure. Broadcom disclosed its Sian2 1.6T 8:8 DSP at a March investor event, and Marvell followed by announcing its similar Nova 2 at OFC. Not wanting to be left out of the 1.6T landscape, MaxLinear pre-announced Rushmore, which similarly targets 8:8 designs. Although the company withheld product details, it disclosed Samsung Foundry as its manufacturing partner for Rushmore, setting it apart from competitors using TSMC. Source: Broadcom Progress on linear pluggable optics (LPO) and other less-than-full-DSP variants was evident at 100G/lane, but vendors also set the stage for 200G/lane. Last November, Credo Semiconductor was first to announc...
Read more