Channels
The AI Channel
The Networking Channel
The Cybersecurity Channel
The Distributed Infrastructure Channel
The Telecom Channel
The Silicon & Supercomputing Channel
The Cloud & Storage Channel
Media
News
Analysis
Editors' Views
Industry Views
Supplements & Magazines
Video Interviews
Broadcasts
On Demand Broadcasts
Explainers
MarketWatch
Press Releases
Resources
Live Events
Xcelerated Compute Series
The Xcelerated Compute Show | LDN 2026
The Xcelerated Compute Show | MEX 2026
The Xcelerated Compute Show | NYC 2027
Digital Infrastructure Series
Yotta 2026
Search
Show Menu
Channels
Back
The AI Channel
The Networking Channel
The Cybersecurity Channel
The Distributed Infrastructure Channel
The Telecom Channel
The Silicon & Supercomputing Channel
The Cloud & Storage Channel
Media
Back
News
Analysis
Editors' Views
Industry Views
Supplements & Magazines
Video Interviews
Broadcasts
On Demand Broadcasts
Explainers
MarketWatch
Press Releases
Resources
Live Events
Back
Xcelerated Compute Series
The Xcelerated Compute Show | LDN 2026
The Xcelerated Compute Show | MEX 2026
The Xcelerated Compute Show | NYC 2027
Digital Infrastructure Series
Yotta 2026
Close modal
Search Suggestions
READ: How OpenAI made the network 'dumb' for AI
Home
xPU
News
More
28 Aug 2026
Meta bakes networking on-chip in custom silicon designed to cut CPU hops
27 Aug 2026
Nvidia expands NVLink Fusion strategy to supercharge custom silicon memory
25 Jun 2026
OpenAI gets spicy with Broadcom via AI data movement-optimized ‘Jalapeño’ chip
02 Apr 2026
NTT DoCoMo and SK Telecom propose XPU-led approach to AI-RAN
31 Mar 2026
Nvidia marks Marvell for AI-RAN, silicon photonics work ... with a $2B kicker
30 Mar 2026
Upscale AI bets on pure‑play, open‑standards switches for AI fabrics
27 Feb 2026
Broadcom just fired the starting gun in the race to 2nm AI chips
12 Dec 2025
Broadcom bulges with Anthropic, AI orders