FCAT: The Evolution of Frame Interval Benchmarking, Part 1
by Ryan Smith on March 27, 2013 9:00 AM ESTMore To Come
While we were unable to complete our work with FCAT ahead of NVIDIA’s embargo, we wanted to provide an article that at least gives a brief overview of FCAT, as FCAT is in many ways itself part two of a process we started yesterday with our article and analysis of stuttering on AMD cards.
FCAT, we believe, is the next evolution of frame interval benchmarking. Where FRAPS' coarse nature does not suffice, FCAT provides a clear picture of what’s happening at the end of the rendering pipeline, giving us for the first time an automated, quantitative look at frame intervals, stuttering, and more. To be clear it is by no means a perfect tool, but as we have taken the time to lay out yesterday and today, compared to the beginning of the rendering pipeline, it is the end of the rendering pipeline that is more meaningful both for quantitative analysis, and ultimately for the users.
Speaking more directly however, FCAT is quite simply the frame interval analysis tool we have long wanted. It is the tool that will enable us to analyze stuttering, micro-stuttering, and more, in a manner consistent with our benchmarking methods and core beliefs in the scientific method. It’s exceedingly rare that we say this, but we haven’t been this excited by a new benchmarking tool in a very long time.
Wrapping things up, we will be following up this article next week with part 2 in our look at FCAT. In part 2 we will go into further detail about how to analyze the results FCAT generates, and what we’re finding across a range of video cards and games, both in single-GPU and multi-GPU configurations. So until then, stay tuned.
Facebook
Twitter
RSS
88 Comments
View All Comments
arbiter9605 - Wednesday, April 17, 2013 - link
As Ryan shrout has talked about, Frame issues with AMD cards happen in games were GPU is the limiting factor in fps. In games that use cpu more then gpu power for issue doesn't show up. So in case why AMD cpu's have problem less compared to intel cpu most likely is a case where amd cpu is maxing out well before gpu gets to its max. Its pretty common that per core per watt intel is faster.Unoquepasaba - Tuesday, April 9, 2013 - link
This is fucking tool unnecessary.Engaged in fixing the bugs that have disgusting play some games like Darksiders 2 or Bioshock Infinite.
We see that AMD is doing a lot of damage, the best proof is that the new consoles carry their hardware, while Nvidia says not interested in that market but also throw them a console lol.
Sorry for my English, it is google :)
ARealAnand - Tuesday, April 9, 2013 - link
I do not believe your statement on patents is completely accurate. Patents do cover a specific implementation of an idea, although they also cover independent discoveries of that same implementation and clean room reverse engineering of said implementation. What I mean by a specific implementation is that taking for example the RSA cryptosystem, the patent did not cover all possible implementations of a public key cryptosystem although it might have been the only way to implement a public key system at the time. I'm reasonably certain that if diffie-hellman had been known of at the time people could have used that at the time just as it was used once it was discovered without infringing any patents. Similarly, LZW patents didn't cover generic data compression but instead a compression system that used less processing then LZ-77/78. People working on making patent free audio and visual codecs have been finding different ways to avoid various algorithms for some time now. I am not a lawyer or a trained solicitor. I have not taken any formal classes in practicing law and this post should not be taken as offering professional legal advice. I appreciate your comment and just felt it could use some clarification.ARealAnand - Tuesday, April 9, 2013 - link
I apologize. I meant this comment to be a reply to zanon's comment above.529th - Tuesday, April 9, 2013 - link
Where can this tool be downloaded from?marraco - Sunday, April 14, 2013 - link
I wonder how 3Dmark will react to this evolution, because it gives scores based on FPS, but this kind of analysis requires an add on card to capture video.Will 3Dmark ignore frame by frame analysis?
Will require more hardware (capture card)?
Will resort to a software solution (questionable)?
Will give the user a choice on methodology (giving different, non comparable results)?
I hope that AMD also give a similar tool. Nvidia and AMD already tried to cheat with his software, and if nVIDIA is the only one providing tools…
I’m happy with this evolution. I ranted for long time about noticeable freezes on benchmarks and games reporting great FPS (on single cards, not SLI/stuttering), but I felt frustrated by benchmarks review sites.
Now I’m worried by not having the same hardware than reviewers, and not being able to verify websites claims/results.
FbF analysis (Frame by Frame) is a step in the right direction, but makes us consumers vulnerable to companies corrupting websites to get better, non reader-verifiable, results.
arbiter9605 - Wednesday, April 17, 2013 - link
Um not sure there is anything AMD can add to this. the DX overlay add's colors to each frame before it gets to sub systems, and colors are analyzed to be in a certain order. If a color is missing then a frame was dropped. i wouldn't say AMD is trying to cheat but they surely have an issue with frame's being dropped or being so small they don't improve gaming experience. When you remove those tiny and dropped frames from fps numbers. It paints a different picture on which card is faster in SLI/CF setup's. Single card setup, which card is better is a toss up.dreamer77dd - Wednesday, April 24, 2013 - link
The first time I read about this was on PC Perspective.http://www.pcper.com/reviews/Graphics-Cards/Frame-...
This article you have written a good read. It all a new direction :)