TSMC begins to risk-produce 16FF+ chips for Nvidia, MediaTek, LG, Xilinx, others

Taiwan Semiconductor Manufacturing Co. on Wednesday said that it has begun producing chips using its 16nm FinFET+ (16FF+) manufacturing technology. The new process technology will be used by a number of TSMC’s partners to make their leading edge chips due next year. Among the first companies to adopt the improved 16nm FinFET process technology from TSMC will be Nvidia, MediaTek, LG Electronics and others.

If TSMC starts risk production of chips using 16nm FinFET+ process technology now, expect commercial products made using 16FF+ fabrication process to arrive in the late third quarter of 2015 at the earliest. TSMC officially anticipates that the 16FF+ volume ramp will begin around July in 2015.

TSMC’s 16nm FinFET (CLN16FF) and 16nm FinFET+ (CLN16FF+) process technologies rely on the back-end-of-line (BEOL) interconnect flow of the company’s 20nm SOC (CLN20SOC) fabrication process, but use FinFET transistors instead of planar transistors. Such hybrid approach to CLN16FF process technologies provides additional performance and/or power savings, but does not allow to significantly shrink the size of chips compared to chips made using the 20nm SOC technology. The proven BEOL interconnect flow means that it gets easier for TSMC to start mass production of chips using its 16FF and 16FF+ manufacturing technologies.

“Our successful ramp-up in 20SoC has blazed a trail for 16FF and 16FF+, allowing us to rapidly offer a highly competitive technology to achieve maximum value for customers’ products,” said Mark Liu, the president and co-CEO of TSMC. “We believe this new process can provide our customers the right balance between performance and cost so they can best meet their design requirements and time-to-market goals.”

According to TSMC, 16nm FinFET+ provides up to 15 per cent performance improvement over the 16nm FinFET at the same level of power consumption. At the same clock-rate, chips produced using 16nm FinFET+ are expected to consume 30 per cent less power compared to the same chips made using 16nm FinFET. Products manufactured using 16nm FinFET+ will offer up to 40 per cent speed improvement over chips made using 20nm technology, or will consume 50 per cent lower amount of power at the same clock-rate.

The 16FF+ process is on track to pass full reliability qualification later in November, and nearly 60 customer designs are currently scheduled to tape out by the end of 2015. Among the early adopters of TSMC’s 16nm FinFET+ fabrication processes are Avago, Freescale, Nvidia, MediaTek, LG Electronics, Renesas, Xilinx,

“Nvidia and TSMC have collaborated for more than 15 years to deliver complex GPU architectures on state-of-the-art process nodes,” said Jeff Fisher, senior vice president of GeForce business unit at Nvidia. “Our partnership has delivered well over a billion GPUs that are deployed in everything from automobiles to supercomputers. Through working together on the next-generation 16nm FinFET process, we look forward to delivering industry-leading performance and power efficiency with future GPUs and SoCs.”

Discuss on our Facebook page, HERE.

KitGuru Says: Keeping in mind that many of 16FF+ adopters are unlikely to make chips using 16FF process technology, it looks like a number of companies, including Nvidia, MediaTek and LG will unlikely offer brand-ne chips made using a next-generation process technology before fall 2015. It is noteworthy that AMD is not among the early adopters of TSMC's 16FF+ process technology.

Become a Patron!