Nvidia has responded to accusations of misleading consumers with an apology over the credentials of the GeForce GTX 970.
The company’s president and CEO, Jen-Hsun Huang, has published a blog post on the company’s website, admitting that its actions were disingenuous.
“Some of you are disappointed that we didn’t clearly describe the segmented memory of GeForce GTX 970 when we launched it,” the post reads. “I can see why, so let me address it.
“We invented a new memory architecture in Maxwell. This new capability was created so that reduced-configurations of Maxwell can have a larger framebuffer – i.e., so that GTX 970 is not limited to 3GB, and can have an additional 1GB.”
“GTX 970 is a 4GB card. 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.”
Simply put, Nvidia claimed that the GeForce GTX 970 4GB of GDDR5 VRAM, but didn’t explain that this is split into two separate segments, rather than one big lump. The topmost 512MB runs significantly slower than the rest, and can result in performance issues with some games.
As a result, the company is now facing a class-action lawsuit.
Huang also admitted that these details weren’t communicated to either Nvidia’s marketing team or to reviewers when the GTX 970 launched.
He described the backlash Nvidia has faced as “understandable”, but claimed that the company had our best intentions at heart.
“But, let me be clear: Our only intention was to create the best GPU for you,” he continued. “We wanted GTX 970 to have 4GB of memory, as games are using more memory than ever.
“The 4GB of memory on GTX 970 is used and useful to achieve the performance you are enjoying. This new feature of Maxwell should have been clearly detailed from the beginning. We won’t let this happen again. We’ll do a better job next time.”