The Byrne-Wheeler Report Episode 4 discusses the RISC-V Summit NA, BlueField-4, SambaNova, and AWS Rainier. You can skip to 12:12 if you're uninterested in RISC-V.

October was a busy month, between the OCP Global Summit and being the lead author on the LightCounting switch report. The new report adds another level of granularity to the scale-up switch forecast, which incorporates NVLink, UALink, Scale-Up Ethernet (SUE), and non-Nvidia proprietary interconnects. There are many other changes to the report, including revisions to the methodology for the co-packaged optics (CPO) forecast. The newsletter summary is freely available: Co-packaged Optics Grow the Scale-out Switch Pie Source: Wheeler's Network

In Episode 3, Joe and Bob discuss OCP-related announcements and the AMD-OpenAI deal. 00:00:26 OCP recap 00:01 AMD Helios rack 00:06:46 Broadcom Thor Ultra 00:12:32 Intel Crescent Island 00:19:11 AMD-OpenAI deal 00:26:33 Signing off

 In case you missed it, Episode 2 of The Byrne-Wheeler Report is available. In this episode, Joe and I discuss the Intel-Nvidia deal, the Nvidia-Enfabrica combination, and Upscale AI's launch.

My colleague Joe Byrne and I launched a video podcast covering the latest news in the chip world. Episode 1 covers Hot Interconnects and Hot Chips news from August as well as Arm's Lumex announcement and Nvidia's Rubin CPX. We hope you enjoy this new format, which will complement our respective blogs.  

Source: Hot Chips The accelerated life cycles that AI is driving woke up a normally sleepy August. Held virtually, Hot Interconnects (HotI 2025) spanned three days with a mix of invited talks, sponsor talks, and tutorials. Some of the brief sponsor talks merely previewed larger disclosures at Hot Chips, which was held at Stanford University the following week. This year, Hot Chips’ agenda included an Optical session that featured three startups plus Nvidia. It also included Networking and Machine Learning (ML) sessions with talks from leading vendors. Although Nvidia was the marquee name in Hot Chips' Optical session, Gilad Shainer's talk on co-packaged silicon photonics lacked any new technical details on the company's CPO switches. Instead, the company used the event to announce Spectrum-XGS, which extends its Spectrum-X Ethernet solution across data centers. Nvidia calls this "scale-across" networking because it primarily targets data center clusters, but it is...

Source: Broadcom Tomahawk Ultra is a misnomer. Although the name leverages Tomahawk's brand equity, Tomahawk Ultra represents a new architecture. In fact, when it began development, Broadcom's competitive target was InfiniBand. During development, however, AI scale-up interconnects emerged as a critical component of performance scaling, particularly for large language models (LLMs). Through luck or foresight, Tomahawk Ultra suddenly had a new and fast-growing target market. Now, the leading competitor was NVIDIA's NVLink. Also happening in parallel, Broadcom built a multi-billion-dollar business in custom AI accelerators for hyperscalers, most notably Google. At the end of April, Broadcom announced its Scale-Up Ethernet (SUE) framework, which it published and contributed to the Open Compute Project (OCP). Appendix A of the framework includes a latency budget, which allocates less than 250ns to the switch. At the time, we saw this as an impossibly low target for existing Eth...