TSMC announced on Wednesday (April 24th) that a new chip manufacturing technology called "A16", which the company is currently developing, will be put into production in the second half of 2026. At that time, TSMC will engage in a "big battle" with its long-term competitor Intel for cutting-edge chips.
TSMC is the world's largest advanced chip foundry manufacturer and a major partner of Nvidia and Apple.
The company announced the news of "A16" at a meeting held in Santa Clara, California. TSMC executives stated at the meeting that artificial intelligence chip companies may become the first adopters of this technology, rather than smartphone manufacturers. However, artificial intelligence chip companies need to optimize their designs to fully utilize the performance of TSMC processes.
It is reported that A16 will combine TSMC's super rail architecture with nanosheet transistors. Super rail technology can move the power supply network to the back of the wafer, freeing up more space on the front of the wafer, thereby improving logic density and performance, making A16 suitable for high-performance computing (HPC) products with complex signal wiring and dense power supply networks.
According to media reports, compared to the N2P process, the A16 chip density has increased by up to 1.10 times, and under the same operating voltage, the speed has increased by 8-10%; At the same speed, power consumption is reduced by 15-20%.
In addition to A16, TSMC has also announced the launch of N4C technology, which continues N4P technology and reduces grain costs by up to 8.5% with a low adoption threshold. It is expected to be mass-produced in 2025.
Regarding this latest announcement, analysts pointed out that TSMC's new technology may bring considerable pressure to Intel, which announced in February that it will replace TSMC with a new technology called "14A" to manufacture the world's fastest computing chip.
The Big Duel with Intel
Kevin Zhang, Senior Vice President of TSMC's Business Development, stated that due to the demand of artificial intelligence chip companies, the company's newly developed A16 chip manufacturing process is faster than expected.
Zhang Xiaoqiang pointed out, "Artificial intelligence chip companies urgently hope to optimize their designs to fully utilize the performance of our processes."
TSMC has sufficient confidence in A16. Zhang Xiaoqiang believes that it is not necessary to use the new "high numerical aperture EUV" lithography machine from Dutch chip equipment manufacturer ASML to produce A16 chips. In contrast, Intel revealed last week that it plans to become the first company to use the Asma machine to develop its 14A chip.
It is reported that the cost of each high numerical aperture EUV in Asma is $373 million.
Dan Hutcheson, Vice Chairman of TechInsights, an analysis company, said of Intel; Quota; From certain indicators, I don't think they are leading& Amp; Quota;
Kevin Krewell, the head of TIRIAS Research, believes that the technology being developed by Intel and TSMC is still several years away from mass production, and they need to prove that the final chip matches the technological capabilities they promote.