NVIDIA accuses AMD of Catalyst driver "questionable optimizations" to improve benchmark results

NVIDIA is accusing AMD of carrying out "questionable optimizations" to its Catalyst drivers in order to gain an unfair advantage over GeForce hardware in benchmark testing.

NVIDIA is accusing AMD of carrying out "questionable optimizations" to its Catalyst drivers in order to gain an unfair advantage over GeForce hardware in benchmark testing.

NVIDIA's Technical Marketing Director Nick Stam explains in a blog post:

Important Benchmarking Issues and Questionable Optimizations We are writing this blog post to bring broader attention to some very important image quality findings uncovered recently by top technology Web sites including ComputerBase, PC Games Hardware, Tweak PC, and 3DCenter.org. They all found that changes introduced in AMD’s Catalyst 10.10 default driver settings caused an increase in performance and a decrease in image quality. These changes in AMD’s default settings do not permit a fair apples-to-apples comparison to NVIDIA default driver settings. NVIDIA GPUs provide higher image quality at default driver settings, which means comparative AMD vs. NVIDIA testing methods need to be adjusted to compensate for the image quality differences.

So what's going on here? Well, the accusation is that AMD has lowered the image quality of the "Quality" setting to the point that users have to select the "High" setting in the Catalyst AI texture filtering options in order to get an image quality close to that offered by the default setting for NVIDIA's drivers.

The affect on performance of this change seems to add up to seems to mean a 10% advantage to AMD, which is far from insignificant.

This issue affects Catalyst drivers 10.10 and 10.11 (the last two releases) and the 5800- and 6000-series GPUs.

TweakPC has posted some videos (it helps if you translate the page or can read German ...) showing the difference between the two setting and on AMD and NVIDIA hardware, and the difference is noticeable. Initial testing that I've carried out also supports the findings.

Currently awaiting response from AMD. Will update you as soon as I have more.

Newsletters

You have been successfully signed up. To sign up for more newsletters or to manage your account, visit the Newsletter Subscription Center.
See All
See All