Nvidia Maxwell in 20 nanometers is delayed until 2015

In mid-February, Nvidia launched the first graphics processors with Maxwell architecture. The new generation begins with the mid-range Geforce GTX 750 and 750 Ti, which means that the Kepler architecture still reigns in the higher performance classes.

Despite the new architecture, 28 nanometer technologies are still used. Although the semiconductor manufacturer TSMC is in the process of production in 20 nanometers, it does not seem to apply to the type of high-performance circuits used for graphics processors. This affects Nvidia’s future plans.

Taiwanese partner manufacturers now tell SweClockers that it will be a while before Nvidia can introduce graphics processors with the Maxwell architecture at 20 nanometers. At best, a single model may appear towards the end of the year, but it is more likely that it will be some time into 2015.

A transition from 28 to 20 nanometers is considered necessary for Nvidia to be able to use Maxwell in the higher performance classes. This is especially true of the successor to the monster circuit GK110, which is the basis for the Geforce GTX 780, GTX 780 Ti, Titan and Titan Black.

The delay of 20 nanometers may also explain why the first graphics cards with the Maxwell architecture do not constitute a new model series but now have to be associated with the Kepler generation in the existing 700 series.