Nvidia CEO Jen-Hsun Huang has spoken out in response to the recent GTX 970 memory configuration controversy, an issue over which the company is now facing a class-action lawsuit.
For those unfamiliar, the controversy surrounds the GTX 970, which breaks its 4GB VRAM into a 3.5GB chunk of GDDR5 and a separate 500MB that runs significantly slower.
In a statement, Huang describes the segmentation as intentional, allowing the card to be a step up from a 3GB card.
"GTX 970 is a 4GB card," Huang said. "However, the upper 512MB of the additional 1GB is segmented and has reduced bandwidth. This is a good design because we were able to add an additional 1GB for GTX 970 and our software engineers can keep less frequently used data in the 512MB segment."
However, this was failed to be properly communicated to the company's internal marketing teams (as well as externally to reviewers at launch), leading to confusion and, on many users parts, anger. Rather than viewing the 970's segmented design as a step up from 3GB, it was seen as a failure to deliver on the promise of 4GB.
"We won’t let this happen again," Huang said. "We’ll do a better job next time."
You can read Huang's full (though still brief) statement on the issue here.