Review Index:
Feedback

Frame Rating Dissected: Full Details on Capture-based Graphics Performance Testing

DiRT 3 – HD 7970 versus GTX 680

View Full Size

Dirt 3 is a game that is already running at very high frame rates at 1920x1080 so it comes as no surprise that the scaling in CrossFire and SLI is minimal.  In terms of single GPU performance though the HD 7970 stays ahead of the GXT 680 consistently.

View Full Size

This is an interesting plot; while the green and black lines both are pretty thin and tight indicating a solid gaming experience with little stutter or frame variance, both the blue and orange lines of the multi-GPU configs have higher than expected variance.  What might be more interesting is that this is the first time thus far that we haven’t found the HD 7970s in CrossFire to be completely abysmal. 

View Full Size

Well look at that!  Both the observed and FRAPS FPS graphs are nearly the same, telling us that while AMD has some definite CrossFire scaling issues with Battlefield 3 and Crysis 3, DiRT 3 doesn’t appear to have suffering from the same ailment. 

View Full Size

The minimum frame rate percentile graph shows us that the HD 7970 is indeed faster than the GTX 680 across the board, though both cards are overpowered for this game at 19x10.  CrossFire and SLI both stay in range of each other the entire time as well with SLI falling a bit behind after the 84th percentile.

View Full Size

Our ISU graph here shows an interesting result and different view of performance than the minimum FPS percentile graph above it.  While the two cards were close in comparison before the HD 7970s in CrossFire actually look much better than SLI in this case, indicating a “tighter” band of frame times. 

 

View Full Size

The results are starting out the same here at 2560x1440 though there is much more scaling occurring on both AMD and NVIDIA setups by adding a second card.

View Full Size

Hmm, that’s interesting.  This was an occurrence we saw nearly every run of Dirt 3 with CrossFire at 25x14 so I wanted to be sure to include it here.  At the times between 25 and 30 seconds (it was different times in each run) we saw runts pop up again, almost as if the CrossFire cards were “getting out of phase” or something like that.  SLI has a few bigger spikes but nothing ever showed up that consistently. 

As a tip to one of my concluding thoughts of this article, I think that this result, and others we’ll show before the end, is indicative of the major problem for CrossFire.  It appears that when the GPU is the primary bottleneck, CrossFire just can’t keep up in some way and produces runts.  That would explain why would see it at 25x14 here but NOT at 19x12.  Just keep that in mind as you keep reading.

View Full Size

As a result of that series of runts, the observed FPS of HD 7970s in CrossFire drops during that time.

View Full Size

The minimum FPS percentiles graph shows the same result in a different way – it is obvious that the runts are causing the frame rates at the back 5% of this chart and the “build up” to and away from that subsection are what causes the decline around the 85% mark.

View Full Size

The frame variance and potential stutter graph here shows the results of that spike of runts as well with a much higher overall variance than SLI or either single card.

 

View Full Size

Dirt 3 was another game case where 5760x1080 results didn’t pan out for the HD 7970 in CrossFire so we are only seeing single GPUs and SLI results.  SLI is scaling very well but the single GTX 680 is getting bested by the HD 7970 the entire time.

View Full Size

All of our results are pretty good here the GTX 680s in SLI produce a fairly tight frame time line and frame rates well above either single card.

View Full Size

Without any runts or drops our observed frame rates are identical to our FRAPS frame rates.

View Full Size

Tight plots of frame times indicate and nearly straight lines here match our real-world game play experiences of smooth frame rates.

View Full Size

While this might look bad for the cards in question – check the scale on the left!  The most frame time variance we see on any option here is 1.6ms so we come away from our testing happy with 5760x1080 results for everything but the HD 7970s in CrossFire.

April 9, 2013 | 08:18 AM - Posted by Anonymous (not verified)

Thanks Dan,

As you mentioned, there is certainly something to this stuttering. It is worthwhile to continue to optimize the test criteria so that it completely removes any Nvidia bias.

Ryan, can you comment about the possibility of raising the size of the scan lines for runts?

Thanks!

April 9, 2013 | 02:52 AM - Posted by Danieldp

Sorry, double post. XD

April 11, 2013 | 03:46 AM - Posted by Cookie (not verified)

Dan,

Just because Toms hardware is longer around does not mean that they do a better job. My vote goes to Pcper, I prefer to read something proper, no offence to Toms hardware.

April 11, 2013 | 08:53 PM - Posted by Danieldp

Hi,

Not really the point I was making, obviously both sites have sufficient expertise. The thing I was pointing at is the vastly different results...

Dan

April 11, 2013 | 05:22 PM - Posted by Dominic (not verified)

Can you do a test with an APU like the A10-5800K in crossfire with like an HD 6670 to see if this frame rate discrepancy occurs in this circumstance as well?

I would assume it would based on your results but nonetheless I'm curious on its results.

April 13, 2013 | 12:34 AM - Posted by JCCIII

Dear Mr. Stroud and friends,

Thank you for a tremendous amount of work, diligence, and integrity...

I thoroughly enjoyed the video with you and Tom Petersem. Although, I have to mention; I have been very disappointed in Nvidia since my purchase of a group of GTX 480s, believing, from day one, I had thrown away more than $1500 for three unmanageable 1500 Watt hairdryers marketed as graphics cards, which were subsequently relabeled GTX 580s, once the bugs were worked out, kind of like Microsoft's Vista to XP, kind of like scamming on people--no, definitely scamming.

I have always been an enthusiast of the Nvidia since the days of 3dfx and had likewise always enjoyed anticipating and buying Nvidia's new products, and the GTX Titan is awesome.

With memories of ATI, Matrox, and Nvidia (I still have my RIVA 128), a home has been found within my memories, and that is why I am excited about what you and the rest of PC Perspective have done and are going to do. With collaboration you-all are moving a beloved industry onward toward a better future for us and for the companies we want to succeed.

Sincerely,
Joseph C. Carbone III; 13 April 2013

April 18, 2013 | 01:57 AM - Posted by Anonymous (not verified)

All you have to do is use RadeonPro and it will fix all these issues...

April 18, 2013 | 08:29 PM - Posted by CoderX71 (not verified)

This

April 22, 2013 | 06:07 PM - Posted by Anonymous (not verified)

I dont see this huge problem i guess i am blind or only run 1 screen but i have played all titles listed and got better FPS in all of them using my GTX680's and My 7970's.

I still prefer my AMD cards for now for these reason:

1)In benchmarks my AMD cards kill my 680's in crossfire overclocked.

2)Graphics just look allot nicer on the AMD cards.

3)Biggest problem is Nvidia cards Cant Mine!!! (That's the big killer there for me)as id rather make $500.00 off my cards a week if i feel like it and be able to game as well.

I am not an Nvidia or AMD Fanboy as i have 680's in one of my builds and 7970's in a couple others plus have bought many of both cards in between.

I think maybe there is a problem for those running triple screens that hopefully AMD fixes as you have to admit they did a hell of allot on drivers recently that gave huge performance boosts.But 1920 x 1080 60 hertz i have no issues and def a big difference when i add a 2nd 7970 as i have swapped a card to other builds and put it back in do to loss of performance. The other thing i use my cards for is overclocking and Benchmarking and they def show huge performance there.I had my 680's over 1300mhz and they couldn't come close to 2 7970's at only 1225mhz.

So id have to say for working computers i will run my 7970's until there is no more money to be made and i will game on the 680's.

Pretty much not many games need more then 1 card anyway unless running multiple screens and high resolutions, Hell an APU can Max most console port games on the Market but the very few true PC games we actually have.

Yes i agree AMD fix the damn problem. But i also don't think Nvidia fan boys should be rooting for this because if they do the 7970 will be a nasty card all around that's capable of allot more then playing just games.

Just my opinion and experience on the to many cards i have owned to count in my life from both brands.

Take Care

May 4, 2013 | 09:13 PM - Posted by Evo (not verified)

If only we had a tool such as radeon pro to tweak the crossfire to make it operate properly. If only it existed...

The crysis 3 results are a bit questionable as in game vsync was causing havoc for nvidia (input lag) and amd (stuttering). Also crossfire was not engaging properly unless you alt-tabbed (this still occurs half the time). Not to mention the weird fix of opening an instance of google chrome to fix some of the problems with frame rate people were having with AMD setups.

My 7970 cf with radeon pro and other fixes works perfectly for me with Crysis 3, but there are some people still having issues. Also depends when the testing was done as when patch 1.3 was first released it caused massive problems for AMD cards that were later fixed.

May 19, 2013 | 11:17 PM - Posted by tigerclaws12894

Might have a typo or grammar error in the paragraph before the last in the Vsync topic. Anywho, have you ever considered triple buffering on AMD solutions as well as that config on 60Hz vs 120Hz as well? Input latency sure will be an issue but it'd be nice to know if it's better with 120Hz monitors.

May 20, 2013 | 04:11 PM - Posted by ServerStation668 (not verified)

This Dell T5600 has good video benchmarks: https://www.youtube.com/watch?v=3uK1J3o1fks

August 13, 2013 | 06:04 PM - Posted by Anonymous (not verified)

I have read this article four or five times and I find it intriguing. I must admit to not understanding most of it though. However, I must say being the owner of THREE 7970's, MSI Lightning BE, MSI Ghz OC Edition & Club3D RoyalAce at a cost of around £1300.00 GBP, just shy of $2000.00 USD I feel somewhat cheated. I hope AMD's forthcoming "Fixes" will redress these issues. Brilliant article and I am looking forward to all the follow ups.

August 31, 2013 | 11:35 PM - Posted by BryanFRitt (not verified)

What would a game look like if

it got a smooth 120+ fps,
was on a 60Hz display,
and in addition to the regular 'vsync' spot, it would 'vsync' at the '1/2' way spot?
aka update the display at the top and middle, updating at these same two spots every time, and only updating at these two spots.

Would the middle 'vsync' spot be annoying? helpful? noticed? informative? etc...? (This sounds like a good way to see how important fps is)

What's a good name for this?
1/2 x vsync, 2 x vsync, vsync 1/2 x, vsync 2 x, or something else?
What's the logic behind your pick(s)?

September 2, 2013 | 01:39 PM - Posted by lyo (not verified)

(forward note: i have bad english.)
1) is there a diff in observer fps between cards with more ram?
i.e. sli of 2x gtx770 2g vs sli of 2x gtx770 4g?

2) can you publish a min/max/var of partial frame per frame?
insted of runt i wanna know how many different "color" are per frame, and if they are evenly spread.

January 30, 2014 | 09:03 AM - Posted by BBMan (not verified)

Nice review. I'm interested as to how this tech is evolving.
But now I'm curious- I've read some of your test methods- but I may have missed something. I've seen mostly games that are more single player/first-person. Is that part of your methodology? I'm thinking of more intensive object rendering titles like Rome Total War II that has to render myriads of objects and stress memory more. Have you considered something like that?

Post new comment

The content of this field is kept private and will not be shown publicly.
  • Lines and paragraphs break automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <blockquote><p><br>
  • Web page addresses and e-mail addresses turn into links automatically.

More information about formatting options

By submitting this form, you accept the Mollom privacy policy.