As Intel prepares to manufacture chips with its 18A process, the company is previewing its next chip node, 14A, which will feature a mysterious “turbo cell” technology meant to boost CPU and even GPU speeds.
First disclosed a year ago, Intel’s 14A process promises to pack even more transistors on the silicon, improving the CPU density. On Tuesday, the company confirmed the 14A process will offer a 15% to 20% performance-per-watt increase over the 18A process.
(Credit: PCMag/Michael Kan)
The 14A process will introduce a new “turbo cell” technology designed to further increase the chip’s speeds, “including CPU maximum frequency and GPU critical paths,” Intel says.
“Turbo Cells allows designers to optimize a mix of more performant cells and more power-efficient cells within a design block, enabling a tailored balance between power, performance, and area for target applications,” Intel said in a statement, which was first reported by PCWorld.
(Credit: PCMag/Michael Kan)
The company discussed the 14A process at an Intel foundry event in San Jose as it tries to take on rival TSMC, the major chip maker for AMD, Apple, and Nvidia. Intel’s 18A process is its most considerable effort yet to become a major semiconductor manufacturer after investing $90 billion over the last four years to build its foundry business.
(Credit: PCMag/Michael Kan)
Get Our Best Stories!
Your Daily Dose of Our Top Tech News
By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy Policy.
Thanks for signing up!
Your subscription has been confirmed. Keep an eye on your inbox!
In addition to 18A, Intel says it’s already talking with customers about using the 14A process. This includes distributing a Process Design Kit, or blueprint files, to help customers develop their chip designs for a specific process node. “Multiple customers have expressed their intent to build test chips” on 14A, according to Intel.
During Tuesday’s event, Intel SVP for foundry services, Kevin O’Buckley, went out of his way to say that Intel is focused on becoming an “AI services company” at a time when AI chip demand has skyrocketed. He then showed a 3D image of what appeared to be an Nvidia-like enterprise-grade GPU packed with high-speed memory. Executives also emphasized that Intel has been listening to customer feedback to make the company’s chip technology follow a “predictable 2-year cycle,” and easy to plan around.
Recommended by Our Editors
Intel’s roadmap adds that the 14A process will arrive in 2027, alongside a “14A-E” node developed to contain some additional “feature extensions.” Along with the turbo cell technology, 14A chips will feature Intel’s second-generation “RibbonFET” and backside power delivery system to further boost performance.
(Credit: PCMag/Michael Kan)
In the meantime, Intel plans to use its 18A chip node to develop semiconductors not only for third-party customers but also for its own business. This includes Intel’s upcoming “Panther Lake” laptop-focused CPUs, which are scheduled to arrive in the second half of this year.
The company is also developing another node, called 18A-P, which will arrive next year. Intel says it’s been “designed to deliver enhanced performance to a broader set of foundry customers,” suggesting it can be used for chips outside general CPU computing.
About Michael Kan
Senior Reporter
