Review Index:
Feedback

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

Crysis 3 – HD 7970 versus GTX 680

View Full Size

Crysis 3 is the currently the biggest GPU hog and both the GTX 680 and HD 7970 handle it equally well at 1920x1080.  Even using our FRAPS metrics though, GTX 680s in SLI are scaling better than the HD 7970s in CrossFire.

View Full Size

The frame time plot from our Frame Rating system shows another instance though of CrossFire’s inability to keep consistent animation on the screen.  The single card configurations are pretty consistent with each other but both also exhibit some tiny bumps in frame times on a repeating pattern, obviously a particular of the CryEngine.  SLI does have some increases in frame time variance across the board with a few minor “hitches” as well.  CrossFire though appears to be alternating between 2ms frame times and up to 50ms frame times resulting in…

View Full Size

Not only a lower observed frame rate but a frame rate that is LOWER than the single card!  I can tell you from first-hand experience that this definitely was the case in play through as well; it felt slower than the single card experience.

View Full Size

SLI looks fantastic in this graph and is able to take the matching performance of the GTX 680 and HD 7970 up from 30 FPS average for the entire run to 57 FPS.

View Full Size

Our custom ISU rating tells me that the GTX 680 SLI configuration looks GREAT and only differs from the single card configurations at 95% and above percentile.  The HD 7970 in CrossFire though shows huge amounts of variance from the outset and in fact does exhibit a lot of stutter in game as well.

 

View Full Size

At the higher resolution the single card HD 7970 as a slight edge over the GTX 680 this time around and this time the scaling of CrossFire appears to be faster than SLI.

View Full Size

A quick glance at our results from the observed frame rate clearly shows that isn't the case though as only in short bursts does the CrossFire experience actually match that of the dual GTX 680s in SLI.

View Full Size

Our frame time plot indicates where the alternating frame times in Crysis 3 occur with CrossFire and how it relates to the performance of SLI.  Other than the single large hitch seen at the 12 second mark or so in SLI, the GTX 680s handle Crysis 3 much better.

View Full Size

The GTX 680s are able to scale from about 19 FPS on average to 36 FPS - a solid 89% scaling factor.  The HD 7970 GHz Edition cards are not so impressive, only going from 21 FPS to 25 FPS but that quickly falls down to just even performance with a single card.

View Full Size

Ouch, another very poor result here for HD 7970s in CrossFire with Crysis 3 at 2560x1440 with as much as 25 ms of frame variance (nearly two full refresh cycels). 

 

View Full Size

This is one of the few Eyefinity runs for the HD 7970 CrossFire configuration that was able to run until completion and generate the necessary graphs for us.  So we’ll finally get to see some interesting results.  Even at first glance, we can tell that something here isn't quite right.  According to FRAPS, the HD 7970 is pushing out more than 200 FPS to the screen on Crysis 3 at 5760x1080, which is obviously inaccurate. 

View Full Size

Ouch, there are definitely some problems here, not the least of which is the graphs poor setting of range maximums (will fix soon!)  Notice the spots on the plot of the orange line (HD 7970 CF) where there is no data – that indicates a dropped frame and a lot of frame time variance. 

View Full Size

Removing those and any runts we find that the observed FPS is actually right in line with that of the single HD 7970 graphics card.  Also, without the CrossFire misreported results out of the window, the update scale helps us see the scaling that the GTX 680s in SLI. 

View Full Size

Here again is another one of our RUN files to show you the affects of dropped frames on Eyefinity testing.  FRAPS based frame rates sky rocket up though the observed frame rate is much lower, in line with a single HD 7970 GHz Edition card.  There are some runts involved in this but the biggest factor is obviously the dropped frames (missing colors in our pattern).

View Full Size

Again, for comparison, here is the RUN graph for the GTX 680s running in SLI at 5760x1080.  Notice that the frame rate is consistent with no drops or runts.

View Full Size

Interesting results here with the CrossFire setup taking a lower position across the board in our percentile minimum frame rate graphs. Also, we see the pair of GTX 680s in SLI start out much faster than anything else tested but at the 94th percentile or so fall below that of the HD 7970.

View Full Size

Keeping mind that we are looking at pretty low frame rates across the board, the HD 7970 has the best overall result here in our ISU graph with the least amount of frame variance over the course of our 60 second run.  Obviously CrossFire has a big issue once again and see significant variance starting at the 50th percentile and it only gets worse from there.

March 29, 2013 | 01:16 PM - Posted by John Doe (not verified)

Horse shit:

http://hardforum.com/showthread.php?t=1703048

March 27, 2013 | 11:36 AM - Posted by John Doe (not verified)

Moral of the story, get this before it goes out of stock:

http://www.newegg.com/Product/Product.aspx?Item=N82E16814187196

It's a card of very limited availability and is one hell of a damn good card.

Best cooler, only Tantalum caps and no cylindrical caps over VRM area, backplated, best looking. Such a boss. Reminds me of those black 68 Mustang Bosses.

March 27, 2013 | 09:30 AM - Posted by Mountainlifter (not verified)

Great Job, Ryan and team. No, Amazing job. I've been following your frame rating articles from the first one and I've been waiting for this full reveal for a long time.

I do hope you show some frame rating benches for the GTX TITAN too (cause I own one now).

I am finding it tough not to conclude that AMD's two GPU system is completely broken although it baffles me that a company of their scale could not detect/think of such issues.

They have been known to take shortcuts on drivers before. http://forum.notebookreview.com/sager-clevo/567681-should-i-switch-out-m... (I'm only getting this from a reliable NBR forumer).

March 27, 2013 | 10:38 AM - Posted by John Doe (not verified)

AMD drivers are put out by a single guy called Catalyst Maker... he has a little team to help him out, but after all, he's just one guy.

That's why they suck.

It's been this way for AGES. The last cards that didn't in one way or another suck, were the X1950's which were made by ATi and not AMD.

Also, dual 7900 setups aren't "completely broken". That's just your pointless assumption.

If there's anything that's "completely broken", it's your wallet for shelling out $1000 for a dumbass card.

March 27, 2013 | 10:51 AM - Posted by Josh Walrath

AMD/ATI used to have a smaller driver team than NV, but actually when AMD bought ATI and started down the APU path... they hired a lot more folks to support these products.  Catalyst Maker was originaly Terry Makedon, but he has moved onto marketing more than software development.  There are (iirc) several groups now working on drivers, but their workload is arguably greater than it was before.  Supporting several different architectures spanning from GPUs to APUs is certainly no easy task, and I think they continue to hire more people.  Reviews like this provide a lot more impetus inside companies to improve their products, and the software drivers certainly are the quick fix are for AMD now.

I think that NV still has a larger driver team, and that massive server room that pretty much only works on nightly builds of drivers from NV is still much bigger than what AMD has.  However, AMD is not as far behind as many think.  But obviously from what we have seen here, and read about from other sources, their focus was not exactly where it needed to be.

March 29, 2013 | 12:12 AM - Posted by Anonymous (not verified)

That's nice and all to amd but it looks like half a decade of total screw job right now, and outright fraud.

March 27, 2013 | 07:27 PM - Posted by Mountainlifter (not verified)

just leave this website man.

March 27, 2013 | 07:29 PM - Posted by Mountainlifter (not verified)

Would you kindly... leave this website man. Thanks.

March 27, 2013 | 07:29 PM - Posted by Mountainlifter (not verified)

Would you kindly... leave this website man. Thanks.

March 27, 2013 | 07:31 PM - Posted by Mountainlifter (not verified)

Was addressing john doe, not walrath.

March 27, 2013 | 09:16 PM - Posted by Josh Walrath

Heh, you can address me.  It won't offend.  As long as I don't offend Ryan, I could be good.

March 29, 2013 | 02:43 AM - Posted by John Doe (not verified)

Hey mountainlifter, would you lift my T-Bird if it gets stuck on a mountain?

Lift my cock while you're there as well.

GG.

March 29, 2013 | 09:14 AM - Posted by Justin Anderson (not verified)

I agree John Doe is retarded and needs to leave. I think he's is trying to pick up dudes on this site he keeps telling people to suck his dick. Why don't you just go to chat roulette if you want to get your rocks off man.

March 29, 2013 | 09:14 AM - Posted by Justin Anderson (not verified)

I agree John Doe is retarded and needs to leave. I think he's is trying to pick up dudes on this site he keeps telling people to suck his dick. Why don't you just go to chat roulette if you want to get your rocks off man.

March 29, 2013 | 09:15 AM - Posted by Justin Anderson (not verified)

I agree, John Doe is retarded and needs to leave. I think he's is trying to pick up dudes on this site he keeps telling people to suck his dick. Why don't you just go to chat roulette if you want to get your rocks off man.

March 29, 2013 | 12:43 PM - Posted by John Doe (not verified)

LOL that's hilarious.

That's all.

Hahaha.

April 2, 2013 | 07:51 PM - Posted by Anonymous (not verified)

Don't tell the truth, the haterz then come forth...

I mean how many times can we give AMD the most gigantic pass ?

Not on this - this new tech with the single card to suck up the actual frames delivered to the end gamer screen with the quad SSD's to take all that in on the fly - this is called PROGRESS, and it has exposed a huge, huge amd flaw.

I feel sorry for all those foolish amd fanboys who screamed at me to buy two amd and crossfire it's a better deal and OC and blah blah blah blah - it's now a big joke.

All those "top crossfire amd gamerz" denying what was right on their screens before them - now the scientific facts show what was before them runts and ghost frames...

I haven't seen a bigger emerging scandal in the video card wars ever.

I am very interested in seeing how it plays out. Of course I will accept NO EXCUSES from amd or their fans. I never have before, but this is an even bigger mess up than even I considered AMD capable of pulling, and that is saying an aweful lot.

You just keep doing your thing and laughing at the haterz, they should be ashamed of themselves honestly.

I want to see if they went with runt and ghost frames after the 69xx series was outed as junk for crossfire by HardOcp with Terry Makedon there in the forums- AMD "became aware" according to that head Cat Maker that there "was a problem" and my guess is the solution was runts and ghosts.
That would keep the DAMAGE to the last 2 major series - but I want data all the way back to 3870/3870X2 to see how deep the rabbit hole goes.

March 27, 2013 | 10:52 AM - Posted by Anonymous (not verified)

so basically what i'm getting from this story and the one at anand is that amd has been reviewed over the years with inflated fraps #s due to more runt and drop frames that are no good to gamers?

March 27, 2013 | 11:30 AM - Posted by Noah Taylor (not verified)

You are absolutely right, AMD's setups have fraudulently inflated their benchmark numbers for years which have helped them sell products and grow their % of discrete market share. This really is the most groundbreaking reveal I've ever come across in the gaming industry.

March 27, 2013 | 11:42 AM - Posted by John Doe (not verified)

It's not like nVidia hasn't done it either:

http://tpucdn.com/reviews/NVIDIA/7950GX2/images/singlebenchlow.jpg

March 27, 2013 | 11:43 AM - Posted by Anonymous (not verified)

Yeah, I'm sure AMD's share of the discrete market has grown thanks to inflated Xfire numbers. I mean, so many people have multi-GPU setups in the first place, amirite?

Plus, jumping to the conclusion that there's deliberate "fraud" going on can only be the result of deluded fanboy thought processes. Considering FCAT is the first tool that can really show this behavior, it's rather more reasonable to believe that AMD was simply unaware of it.

March 27, 2013 | 01:04 PM - Posted by John Doe (not verified)

Alright, let me get it the easily way for you.

What the hell does the inflated CF performance figures have to do with the frame latencies? NOTHING.

The frame latency is a problem only because AMD has yet to be able to completely man up the GCN architecture.

April 3, 2013 | 08:27 PM - Posted by Anonymous (not verified)

No, fraps showed the problem, and the extended FCAT has only highlighted it even more.
The other thing that showed the problem - countless end user complaints, many times raging radeon fanboys screaming you cannot see beyond 30fps because "the human eye is incapable of it", something we call fanboy fantasy, apologetics, excuses, denial, brain washed psycho hardcore amd total verdetrol absolutist.
There are a lot of them, and that unfortunately has allowed amd to scam the entire industry for this long.

You see we still have a boatload of deniers here. Total amd fanboys, nothing will ever change their minds, no facts are facts they can accept if the facts prove amd sucks.

March 29, 2013 | 09:15 AM - Posted by Anonymous (not verified)

Yes it is, but the river in Egypt will start to grow to cover the entire earth for the amd fanboys, oh wait it already has.

BURNED in the extreme, the failure of crossfire, the scam of the decade.
Ghosts and runts, but boy oh boy our fps looks frappalicious !

LOL - so, so pathetic.

nVidia's SLI monsters ? ZERO runts, ZERO ghost frames.
PERFECTION incarnate.

Let's review:
nVidia - perfect execution, no cheating no runts, no ghost frames
amd - lying failure, HALF OF THE FRAMERATE IS A LIE. ghost runt every other frame !

ROFL amd you truly suck as bad as I have been saying for half a decade, wait no, you are worse.

Now we will get treated to endless excuses, denials, it doesn't matter, who cares, and all the rest of the radeon ragers standard operating apologetic procedures they have gang banged on the net for years.

Watch for this development: amd fanboys new spewing propaganda
" using two cards is a hassle, you should buy a single card, and just upgrade when the next best single card comes out like the 7970 with how great it is. Who wants to waste money on two cards, it's like <1% of gamers, so no one really does this at any end user level except fanatics, it's just not needed and is a budget buster. "

LOL - A thousand excuses already coming

March 27, 2013 | 12:21 PM - Posted by Wingless (not verified)

How does changing Render Frame Ahead/Pre-Rendering affect Crossfire and SLI? In Battlefield 3, people are saying it gets smoother if you change it to 0 or 1 vs the default value of 3.

Thanks for your great analysis and extremely informative video.

March 28, 2013 | 06:56 AM - Posted by Wingless (not verified)

Battlefield 3
Guide: How to Fix Low FPS - Stuttering - Lag
http://battlelog.battlefield.com/bf3/forum/threadview/2832654347723598222/

There is a well documented stuttering fix for both Nvidia and AMD users on multiple forums. I've tried this for my HD 4870 Crossfire setup and it works. This particular user from the above link has a NVIDIA GTX 470.

5.Open notepad and paste this into it and save it as "user.cfg" inside your "program files/origingames/battlefield3" folder:

RenderDevice.TripleBufferingEnable 0
RenderDevice.ForceRenderAheadLimit 1
WorldRender.SpotLightShadowmapResolution 256
WorldRender.SpotlightShadowmapEnable 0
Render.DrawFps 1

With this applied to the game, are there any differences? Render Ahead seems to really affect these results and it would be nice if it were tested with FCAT.

Thanks

March 29, 2013 | 01:40 PM - Posted by John Doe (not verified)

Do you like Winger?

They're really a crappy band but they have some decent stuff LOL.

http://www.youtube.com/watch?v=rWSVGcivuGs

March 27, 2013 | 12:43 PM - Posted by Randy (not verified)

Absolutely fantastic work Ryan. This article really blew me away and gave me a lot of tools to better understand what I've been dealing with at home. One question though: you point out that vsync can solve most of amds problems provided the frame rate doesn't have to drop from 60 to 30, in which case the drastic stutter caused by such a change adversely impacts smoothness. What if instead of using vsync you used a frame rate limit that corresponded with the apps average framerate? This way when the frame rate dips below that threshold it isn't cutting its' self in half as it would with vsync and in theory not introducing nearly as much stutter.

I advised my friend to do this with his dual 6950 setup in far cry 3 and he said it gave excellent subjective performance. I used the same method for my single 7970 and also noticed a nice bump to the smoothness of the game, but again this is all subjective. It would be awesome if you could test this as if proven correct it would give a lot of amd owners the tools to make the best of a bad situation.

Again thanks for the tremendous work you've done here, this is truly awesome work.

March 27, 2013 | 01:43 PM - Posted by grommet

Quick question- Could Lucidlogix's Virtual Vsync technology help out with the CrossFire issues?
http://www.lucidlogix.com/technology-virtual-v-sync.html
Not that this would let AMD off the hook as this needs to be taken care of in-house, but could it help?

March 27, 2013 | 02:02 PM - Posted by Anon (not verified)

That's a nice question.

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.