This Article Changed My Opinion of FPS Measuring

[Ocean]

http://techreport.com/articles.x/21516

FRAPS-based testing didn't seem to square with our seat-of-the-pants experience. The fundamental problem is that, in terms of both computer time and human visual perception, one second is a very long time. Averaging results over a single second can obscure some big and important performance differences between systems.

This article ultimately explains why many people do still see a difference between 120Hz and 60Hz, and the origin of micro-stuttering, especially when it comes to multi GPU solutions.

Instead of averaging all the frames in a whole second, it postulates that we should focus on how often an individual frame takes too long to render, which ruins the perception of fluidity, regardless of how imperceptibly excessively fast every other frame might render in that same second.

this article is almost a year old, but they've recently done an update for cpu and gaming.
this is an absolutely awesome read from a site ive never heard of before today.

 

[450]

Its a great article. I hope more reviewers consider including tests like this in their reviews. Perhaps [H] should consider doing this...

 

[Red Falcon]

Great article, I get what they are going for, but for an average FPS counter, FRAPS works well for 99% of us.

 

[Mechasheeba]

Pretty interesting, although when you consider the best case scenario input latency for any current gen console is 67ms, source, and on a number of games over 100ms, I don't think scrutinizing frame rendering latency on a 1-2 frame basis holds any value outside of maybe a good marketing campaign for Intel.

Most PC gamers would be quick to complain about console analog controls, but not many would complain about the minimum 4 frames of input latency (not including added display lag) on even a 60fps game. The truth of the matter is we're too human to notice, most people probably would have had no idea there was at least a 67ms delay between their button presses and an action happening on screen until they read an article like the one above.

I'll admit it's definitely a better testing methodology than what was previously being used as far as a direct head-to-head comparison of different hardware, but unfortunately many people will probably misinterpret the data as "I need a 3770K to smoothly play PC games" and that's really not the case.

 

[OmegaDL50]

Pretty interesting, although when you consider the best case scenario input latency for any current gen console is 67ms, source, and on a number of games over 100ms, I don't think scrutinizing frame rendering latency on a 1-2 frame basis holds any value outside of maybe a good marketing campaign for Intel.

Most PC gamers would be quick to complain about console analog controls, but not many would complain about the minimum 4 frames of input latency (not including added display lag) on even a 60fps game. The truth of the matter is we're too human to notice, most people probably would have had no idea there was at least a 67ms delay between their button presses and an action happening on screen until they read an article like the one above.

I'll admit it's definitely a better testing methodology than what was previously being used as far as a direct head-to-head comparison of different hardware, but unfortunately many people will probably misinterpret the data as "I need a 3770K to smoothly play PC games" and that's really not the case.

It may matter to some people. Some fighting game enthusiasts and tournament players generally can execute moves that require frame input of 1/60th of a frame. Heck even some Arcade Bullet Hell Shooters like (Games like Gradius or R-Type) also have an extreme emphasis of being able to react to whats going on the screen upon a mere seconds notice.

People generally won't notice such input delays on the more slower or methodically paced games but again I suppose the above examples are beyond normal and tend to fall in line with the more practice until perfect crowd.

Which brings up an interesting point for Racing games too, because I've seen things with people using a Wheel / Pedal setup that generally seem impossible compared to people using a gamepad or keyboard controls. I mean reaction timing such as breaking and optimum corners at the absolute last possible second they can be done and not losing any sort of control.

It gives credibility to people being able to tell the difference between 60hz and 120hz.

EDIT: I am saying this from the perspective of human reaction being able to keep up and pace with the action they see on screen with crucial timing. A matter of perception so to speak.