Intel has lagged behind its main competitor, TSMC, for many years now when it comes to progress on advanced nodes. To remedy this situation, CEO Pat Gelsinger set in motion an aggressive comeback strategy when he returned to the company in 2021. Its IDM 2.0 strategy involves moving through five nodes in four years, which will theoretically allow the company to leapfrog all of its competitors and land at the apex of semiconductor manufacturing once again. Now, it appears the company might just be on track to deliver on that promise.
In a recent interview, one of its VPs stated the company is set to begin production on its "2nm" node next year, which it calls Intel 20A. If it pulls this off—always uncertain in the semiconductor business—it would put Intel years ahead of TSMC in the race to 2nm. Sanjay Natarajan, the company's chief vice president of technology development at Intel, commented in a paywalled article flagged by Wccftech. Natarajan stated, "We will enter mass production [of its 2nm process] in 2024, and Intel will lead miniaturization again." It's a bold claim from the company but also means it's still adhering to its roadmap.
If it does begin cranking out 2nm chips in 2024, it would theoretically put the company at the forefront of the industry, as TSMC will have just begun to hit its stride with its latest 3nm process next year. Also, TSMC isn't expected to start 2nm production until 2025, though there have also been rumors suggesting that it might get pushed back to 2026 as well. Samsung is also in this race, and it's already stated it expects to begin 2nm production in 2025, meaning Intel might also beat the Korean chipmaker to the punch. Samsung has said it's targeting TSMC in the 2nm race, indicating it wasn't considering Intel's stated goals to be a credible threat.
If Intel hits its target and begins 20A production next year, it will allow it to deliver its first desktop-class process on the 2nm node in the latter half of 2024. That is expected to be Arrow Lake, which will be the company's first tile-based desktop chip. Unlike its all-new Meteor Lake architecture, which was made on Intel 4 (formerly 7nm), Arrow Lake will be made with RibbonFET gate-all-around (GAA) transistors instead of FinFET. In addition, Intel will also begin using backside power delivery (top of article), which it calls PowerVia, for Intel 20A.
We'll soon find out what Intel has in store, as it will theoretically have begun cranking out 20A chips in the next six months. If that occurs, it will put it at least one year ahead of TSMC in getting to 2nm first, which would indeed be a feather in Gelsinger's cap. Intel has hit its roadmap target for Meteor Lake by delivering it this week after years of delays, so it seems like the company is back on track in moving from node to node. We shall soon see if it can keep this momentum up as it advances to ever-smaller nodes.
