Intel showcases Arm-based reference SoC built on 18A node

Intel presented a ´Deer Creek Falls´ Arm-based reference SoC on its 18A node, illustrating heterogeneous core mixes and third-party IP integration for foundry customers.

Intel foundry surfaced a reference ´Deer Creek Falls´ system on chip described as a ´non-x86´ design and built on the company’s 18A process node. The reference chip is Arm-based and uses a seven core layout: one performance core, two efficiency cores, and four low-power efficiency cores. It also integrates embedded PCIe and memory controller intellectual property and PHYs supplied by ecosystem partners, signaling a heterogeneous assembly of hybrid cores and third-party blocks rather than a monolithic in-house design.

The firm did not overtly label the design as Arm in the initial overlays, but a later section of the demonstration on performance tuning referenced AArch64, confirming the 64-bit Arm instruction set. Alongside the hardware, Intel highlighted a suite of performance optimization tools that support Arm-based processors, positioning its foundry services as able to assist customers with software tuning across different instruction set architectures, not only x86. That software toolset is aimed at helping customers extract better performance from their chosen core configurations and partner IP.

Observers noted that the showcased SoC is modest in scope, and not a flagship design, but it performs an important marketing and technical role for Intel foundry. It illustrates that Intel can manufacture heterogeneous designs that mix core types and third-party controllers on advanced process nodes. The video evidence was later delisted from Intel’s YouTube channel, though screenshots remain available. The timing matters because interest from external foundry customers could be critical as Intel seeks to scale its foundry business amid increased oversight and strategic interest from the U.S. government.

66

Impact Score

Artificial Intelligence LLM confessions and geothermal hot spots

OpenAI is testing a method that prompts large language models to produce confessions explaining how they completed tasks and acknowledging misconduct, part of efforts to make multitrillion-dollar Artificial Intelligence systems more trustworthy. Separately, startups are using Artificial Intelligence to locate blind geothermal systems and energy observers note seasonal patterns in nuclear reactor operations.

Saudi Artificial Intelligence startup launches Arabic LLM

Misraj Artificial Intelligence unveiled Kawn, an Arabic large language model, at AWS re:Invent and launched Workforces, a platform for creating and managing Artificial Intelligence agents for enterprises and public institutions.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.