On April 23, TSMC officially introduced the latest progress on its next-generation advanced process technology, the A14 (14 angstrom) node, with mass production planned for 2028.
The A14 process represents a significant leap forward from TSMC's industry-leading N2 (2nm) node. Designed to deliver higher performance and improved energy efficiency, A14 is positioned to accelerate the advancement of artificial intelligence (AI) and enhance on-device AI capabilities across applications such as smartphones and edge computing.
According to TSMC, development is proceeding smoothly, with yields exceeding expectations. Compared to the upcoming N2 node set for mass production later this year, the A14 node offers a 15% performance boost at the same power level or a 30% reduction in power consumption at the same speed. It also achieves over 20% improvement in logic density.
A key innovation in the A14 process is the integration of TSMC's NanoFlex Pro standard cell architecture, which builds upon the company's experience in nanosheet transistor optimization. This advancement is expected to deliver superior performance, energy efficiency, and design flexibility.
TSMC Chairman and CEO C.C. Wei emphasized that the company's commitment to advanced manufacturing and technological leadership continues to shape the future of AI. "As our customers look to the next frontier, TSMC delivers a trusted roadmap of innovation," Wei said. "Our cutting-edge platforms like A14 are key to bridging the physical and digital worlds."