If it’s not too late to take stock of 2025 in HPC-AI, then holding up the Supercomputing Conference as a trends test site might be a good approach. I’m no perennial* but I’ve been to about half of the 37 SCs , including all 11 since 2015. Looking ….
HPE to Offer AMD Helios AI Rack-Scale Architecture with Ethernet
December 2, 2025 by
At HPE’s Discover Barcelona 2025 event today, the company said it is offering the AMD “Helios”AI rack-scale architecture with Ethernet, intended to speed up deployment of at-scale artificial intelligence training and inferencing for cloud service providers.
OpenAI and Broadcom to Deploy 10 GW of OpenAI-Designed AI Accelerators
October 14, 2025 by
When it comes to AI compute, the big cloud platform providers are chip-agnostic, adopting processors from the big chip companies (mostly NVIDIA) along with their own custom-designed GPUs ….
Broadcom Ships Jericho4 for Distributed AI Computing across Data Center
August 4, 2025 by
PALO ALTO, Calif., Aug. 4, 2025 — Broadcom Inc. (NASDAQ: AVGO), a semiconductor and infrastructure software company, today announced it is now shipping the Jericho4 ethernet fabric router — a platform for distributed AI infrastructure. Designed to interconnect over 1 million XPUs across multiple data centers, Jericho4 breaks through traditional scaling limits with unmatched bandwidth, […]
Broadcom Ships Tomahawk Ultra Ethernet Switch for HPC and AI
July 15, 2025 by
PALO ALTO, Calif., July 15, 2025 — Broadcom Inc. (NASDAQ:AVGO), a global leader in semiconductor and infrastructure software solutions, today 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 industry-leading ultra-low latency, massive throughput, and lossless networking. “Tomahawk Ultra is […]
Broadcom Ships Tomahawk 6 102.4 Tbps Switch
June 4, 2025 by
PALO ALTO, Calif., June 03, 2025 — Broadcom Inc. (NASDAQ:AVGO) announced today that it is now shipping the Tomahawk 6 switch series, delivering what the company said is the first 102.4 Terabits/sec of switching capacity in a single chip – double the bandwidth of any Ethernet switch currently available on the market, according to Broadcom. […]
Report: TSMC to Operate Intel Fabs under Tentative Joint Venture
April 3, 2025 by
The online technology publication The Information reported today that Intel and Taiwan Semiconductor Manufacturing Company have reached a tentative agreement to form a joint venture in which TSMC would operate Intel’s chipmaking facilities.
News Bytes Podcast 20250303: GPUs vs. ASICs for AI Compute, DOGE and Fears at U.S. Science Agencies, Cat Qubits for AWS Quantum
March 3, 2025 by
A happy start to March to you! We offer a quick (8:28) run through recent news from the world of HPC-AI, including: GPUs versus ASICs for AI accelerated compute, DOGE-led government layoffs ….
Broadcom Delivers Industry Leading 200G/lane DSP for Gen AI Infrastructure
September 23, 2024 by
Broadcom Inc. (NASDAQ: AVGO) today announced the general availability of SianTM2, 200 Gbps per lane (200G/lane) PAM-4 DSP PHY. Sian2 features 200G/lane electrical and optical interfaces to augment the Sian DSP that supports 100 Gbps electrical and 200Gbps optical interfaces. Sian and Sian2 DSPs enable pluggable modules with 200G/lane interfaces that are foundational to connect next generation AI clusters.
Ultra Accelerator Link Group for Data Center AI Connectivity Formed: AMD, Broadcom, Cisco, Google, HPE, Intel, Meta and Microsoft
May 30, 2024 by
BEAVERTON, Ore.– AMD, Broadcom, Cisco, Google, Hewlett Packard Enterprise (HPE), Intel, Meta and Microsoft today announced they have aligned to develop a new industry standard dedicated to advancing high-speed and low latency communication for scale-up AI systems linking in data centers. Called the Ultra Accelerator Link (UALink), this initial group will define and establish an […]
