TSMC’s 2nm chips are coming to a device near you in 2026

Taiwan Semiconductor Manufacturing Co. (TSMC) has officially announced its 2nm class process node. It is expected to ship to customers in 2025. The company also revealed more details about its 3nm technology, which is expected to start production later this year.

TSMC has performed North America Technology Symposium (opens in new tab) on June 16th. He spoke about its advanced technologies, including updates to its various processes and packaging technology. He also outlined his future expansion plans. The highlight for PC enthusiasts was undoubtedly the reveal of its 2nm node – known as N2 – which includes a shift from well-established FinFET technology to a nano-leaf transistor architecture. We can expect to see this technology on our computers for years to come.

TSMC’s nanosheet technology uses what are known as GAAFETs (General Gate Field Effect Transistors). The goal is to reduce quantum tunneling effects and leakage, which is a major barrier to further scaling of FinFETs. With GAAFETs, these effects are greatly reduced, and Moore’s Law may have some dying breaths.

The N2 offers the gains you would expect to see from a process reduction, including 10-15% higher performance at the same power or 25-30% lower power consumption at the same frequency and transistor count when compared to TSMC’s N3 node. .

(Image credit: TSMC)

It is important to note that node naming schemes are becoming less and less relevant. The move to a smaller node implies smaller transistors and higher density, but TSMC’s N2 node won’t be too impressive when measured in those terms, providing a relatively smaller 1.1x density increase compared to the N3E node.

While devices built with N2 products are still a few years away, N3 products are much closer. TSMC has detailed five different N3 levels. TSMC will start with its first generation N3 before fine-tuning the process with N3E (Enhanced), N3P (Enhanced in Performance), N3S (Enhanced in Density) and the ultra-high performance N3X. The first 3nm chips are expected to ship to manufacturers later this year.

That would mean the N3 won’t be used in Apple’s upcoming iPhone 14, although in 2023 devices with M3 processors are likely. There are some speculations that Intel may use N3 blocks (opens in new tab) on its 15th generation of Arrow Lake processors in 2024. AMD’s Zen 5 processors can also use it. As for graphics cards, given that Nvidia and AMD are extending their release schedules, the RDNA 4 and RTX 50 series cards are certainly at least two years away from launch.

It’s too early to speculate on which devices might include N2 products. Companies with large bank balances are sure to be first in line. The usual suspects including Apple, Qualcomm, AMD and Nvidia will be sniffing around. But a lot can change in four years.

Leave a Comment