Intel signs its first external customer for the 18A-P chip process
Intel has signed its first external customer for its 18A family of chip manufacturing processes, chief executive Lip-Bu Tan told the TomorrowX Summit in Austin, Texas. Chief technology officer Pushkar Ranade later confirmed on X that the customer has signed up for 18A-P, a version of the node that went into risk production in June. Intel has not named the customer.
On Intel's third quarter earnings call, Tan said the company was engaged with "a couple of highly strategic customers" about its 18A chips, and that yields on both Intel 3 and Intel 18A had increased again, with 18A improving at a double-digit rate. He said 18A-P remained on track for launch by the end of the year across Intel's own products.
Intel 18A is one of the final nodes in the company's "5 Nodes in 4 Years" roadmap and the first to include its RibbonFET gate-all-around transistors and PowerVia power delivery. 18A-P is designed to improve performance and is fully compatible with 18A designs. Earlier this year, The Wall Street Journal reported that Intel and Apple were looking to close a deal for Intel to make some chips for Apple devices, according to DatacenterDynamics.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.
Also, consider following us on social media:
More from Data Centers
Nov 19 $480 million AI chip loan for ByteDance-linked Malaysian data centre frozen Nov 19 Nscale brings its first Nvidia Vera Rubin rack online Nov 19 Tesla unveils Powercore, a solid-state transformer platform for data centres Nov 19 Nvidia delays its quarterly SEC filing as the Huang investigation continues Nov 18 Cloudflare releases open-weight Clairic models for extracting data from documentsSilicon Brief
Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Intel Shares Plunge on Weak Q4 Forecast Despite 78% Data Center Growth
PowerLattice Raises $86 Million for AI Power Chiplets
Intel and Oracle plan Xeon expansion on OCI
ASM Lifts 2027 Outlook Above €5.7 Billion on AI Chip Demand
DeepX tapes out 2nm DX-M2 edge AI chip built for 100B-parameter models at 5W
Daily AI Brief: the AI news that matters, in your inbox.