TSMC reportedly targeting 2025 and 2027 for next-generation 2nm and 1.4nm processes

Now that TSMC is shifting into high gear with its 3nm process, the discussion turns to the company’s next-generation processes, which will be 2nm followed by 1.4nm. Now a new report states TSMC has set its schedule for the highly-anticipated nodes, with 2nm arriving in 2025 and 1.4nm starting to appear somewhere around 2027. Apple will likely be the first customer for both nodes, just like it was with the company’s 5nm and 3nm processes.

The new information on TSMC’s roadmap comes from Digitimes, so it should be taken with a grain of salt. The article is paywalled, but Macrumors has a summary, stating 2nm trial production will begin later this year, but go into high-volume in 2025. The company will eventually begin 1.4nm production around 2027, but given the timelines involved, that number could change. There was also an earthquake in Taiwan last week that disrupted TSMC’s operations for a bit, highlighting how unpredictable life can be on the island. There’s also the potential for geopolitical destabilization as well, and TSMC is planning for it by allegedly moving some of its advanced nodes to its US operations.

Speaking of which, the report states TSMC will be making some of its 2nm chips at its Arizona facility. This sounds like it’ll be sharing the burden for these chips between Arizona and its Taiwan HQ, which is a reversal for the company as its most advanced nodes have always been located in Taiwan. It was previously reported that TSMC would keep 2nm production in Taiwan, but perhaps it’s changed its mind about that strategy. The company will reportedly offer its first 2nm wafers—called just N2—to customers in 2025, and then offer an enhanced version in 2026 named N2P.

The move to 2nm is a huge step for TSMC, as it will finally ditch FinFET and move to gate-all-around (GAA) nanosheet transistors. It previously stated it would not be adding backside power delivery until N2P comes out, which would put it at least two years behind Intel, which is expected to introduce that feature in this year’s Intel 20A process for Arrow Lake. TSMC will add a third variant of 2nm after N2P named N2X, which will be for high-performance computing applications.

Given the timelines involved, and the increased pressure Intel may be exerting on TSMC starting later this year, it’ll be interesting to see it if can hit these targets. It was previously reported TSMC was pushing 2nm production back to 2026, which would be a one-year delay. However, Intel will theoretically already have a 2nm process in 2024, which might motivate TSMC to pick up the pace a bit. Intel is also already firing up the world’s first High-NA lithography machine, which it will use for its 1.4nm process around 2026. Meanwhile, TSMC is sticking to EUV for now, so the battle between these two companies is about to get spicy come late 2024 and into 2025.