AMD Radeon HD 7990 Review > Testing Methodology

Testing Methodology

As usual we tested each card with Fraps, which lets u.s.a. record the average frame charge per unit in seconds over a set amount of time. Typically, we run our tests for sixty seconds. Reporting the average fps (frames per 2d) is how things have been done for... well, forever. It'due south a fantastic metric in the sense that it's like shooting fish in a barrel to record and easy to understand. Merely it doesn't tell the whole story, every bit The Tech Study and others have shown.

To go a fuller picture, it's increasingly apparent that you need to factor in a card's frame latency, which looks at how speedily each frame is delivered. Regardless of how many frames a graphics menu produces on boilerplate in 60 seconds, if it can't deliver them all at roughly the same speed, you lot might see more than brief jittery points with one GPU over another -- something we've witnessed merely didn't fully empathise.

Bold two cards deliver equal average frame rates, the one with everyman stable frame latency is going to offer the smoothest picture, and that's a pretty important particular to consider if you're near to driblet a wad of cash. As such, nosotros'll be including this data from now on by measuring how long in milliseconds information technology takes cards to render each frame individually and then graphing that in a digestible manner.

We'll be using the latency-focused 99th percentile metric, which looks at 99% of results recorded within X milliseconds, and the lower that number is, the faster and smoother the performance is overall. By removing one% of the most extreme results, information technology's possible to filter anomalies that might have been acquired by other components. Once again, kudos to The Tech Report and other sites like PC Per for shining a lite on this issue.