Review Index:

Frame Rating: GTX 660 vs HD 7870, plus HD 7790, HD 7850, GTX 650 Ti BOOST

Author: Ryan Shrout
Manufacturer: PC Perspective

DiRT 3 - GTX 660 vs HD 7870

DiRT 3 (DirectX 11)


A continuation of the Colin McRae series, but without his name, DiRT 3 is one of the top racing games in the world and offers stunning imagery along with support for features of DirectX 11. 

Our settings for DiRT 3

View Full Size

View Full Size

In DiRT 3 the single card performance of the single Radeon HD 7870 is clearly better than that of the single GTX 660 from NVIDIA.  When we double up the GPU count for each vendor though we see a couple of drops in observed frame rate on the CrossFire side.

View Full Size

Both the sudden drops in performance as showed in our observed frame rate above matches with the dramatic episodes of frame variance in our frame time plot here.  Clearly the alternating high frame time, low frame time pattern for these several second instances are affecting animation performance and gaming experience. 

View Full Size

Because those episodes of frame variance are only a small portion of the CrossFire result at 1920x1080, the frame rate graph shows interesting results.  The "average" frame rate for the entire run as estimated by the 50th percentile is actually higher on the HD 7870s in CrossFire than on the GTX 660s in SLI, but at the 75th percentile, it swaps and NVIDIA's SLI is the faster setup.  This essentially means that 25% of the time, the GTX 660s in SLI are going to be faster than the HD 7870s in CrossFire. And for that last 5%, pretty dramatically so!

View Full Size

As a result, the frame variance data has the CrossFire result with a deficit throughout the game run with SLI and single GTX 660 results very close.  The best performer is the HD 7870 single card that maintains a very consistent frame variance level throughout. 


View Full Size

View Full Size

At 2560x1440 the tables turn on the multi-GPU results and even at the FRAPS level the GTX 660s look like the faster option.  Taking out the runts results in performance LOWER than a single card by quite a bit.  Single GPU consideration though still leaning heavily towards the HD 7870 over the GTX 660.

View Full Size

Clearly the Radeon HD 7870s are having more problems in CrossFire than they did at 1080p settings, but SLI scales well and also has pretty limited frame time variance with only a handful of spikes in frame time to cause concern. 

View Full Size

The gap between the single HD 7870 and the GTX 660 is more noticeable here with an increased average frame rate advantage of 31%, consistently.  The SLI GTX 660s also have a strong showing with a very flat frame rate graph.

View Full Size

Because of the dropped frames on the CrossFire, its frame variance data doesn't look as bad as you might expect, though it does spike up suddenly at the 95th percentile.  The best performer though is still the single HD 7870.


View Full Size

View Full Size

Because of the number of dropped frames and how it affects our processing scripts, we don't have results for the HD 7870 in CrossFire!  Looking at the results we do have though you can see that the HD 7870 in its single card configuration is faster than the GTX 660 and actually makes Eyefinity quite playable on a single GPU for this title.  SLI does scale well on the GTX 660 though allow for frame rates over the 50 FPS mark most of the time.

View Full Size

The orange line that represents the HD 7870 card has the thinnest, tightest line in our frame times indicating the most consistent frame times.  The GTX 660 is just fine as well though and only the GTX 660 SLI results in a handful of hitches and spikes in frame times.

View Full Size

NVIDIA SLI scales DiRT 3 at 5760x1080 from 30 FPS to 55 FPS on the GTX 660s (83%) but the HD 7870 keeps the single card crown.

View Full Size

For the majority of our frame variance percentile graph the GTX 660, in single card form, actually has the most variance though by eyeing the scale on the left hand side you'll see we are talking about times under 2 ms - very minimal.  Even SLI is able to keep within a 6 ms variance time at the 99th percentile.


April 8, 2013 | 12:00 AM - Posted by Anonymous (not verified)

I just saw a video from valve discussing a tool called Telemetry from RAD games, it seems like it could be useful for analysis of game performance.

April 8, 2013 | 10:41 AM - Posted by Pendulously (not verified)


You have already noted elsewhere that Percentile (1-99) is insufficient, for tracking large SPIKES in Frame Times, spikes which may occur only once every few seconds (i.e., once every few hundred frames, thus well beyond the 99th percentile threshold).

So you need a different dependent variable (x-axis), with 'milliseconds' remaining the independent variable (y-axis).

In a 10 minute gampeplay section (36000 Frames at 60 FPS), 36 Frames is equivalent to the 99.9th percentile (36000 divided by 1000).

If you put '36' on the x-axis (or perhaps multiples of 10), you could easily show people the effects of LARGE SPIKES IN FRAME TIMES. In many cases/circumstances, more illuminating than Frame Variance Graphs which show nothing beyond the 99th percentile.

April 8, 2013 | 11:52 AM - Posted by Stennan (not verified)

Are there any redeeming features to AMDs Crossfire solution?

April 8, 2013 | 02:06 PM - Posted by Anonymous (not verified)

Yes, they drop every other frame in crossfire and count it anyway and sell it to their fans as a superior frame rate than SLI.

AMS CF Frame numbers sold 80!(actual screen rate 40+stutter ! )

Wow it sure beats 76 from SLI !

Yes, a very "redeeming" quality.

April 10, 2013 | 09:12 AM - Posted by Stennan (not verified)

Thank you for not answering my question :)

I just wanted to know if there might be an upside with regards to perhaps input lag. Kind of hard to measure though.

April 11, 2013 | 04:17 PM - Posted by Anonymous (not verified)

Ok, here's a few thoughts. With the AMD runts and drops, and the fans now trying to claim "less input lag", my question is of course, "What are you aiming at?" !

With every other frame dropped or runted, you're getting ~50% of the game screen opponent positions from the frames displayed (first person shooter as an example of course since most games are that ) - so your opponents position on screen is "jumping" from one frame over to two frames ahead, changing position in a lurch - with that type of inaccuracy of on screen opponents, how is "less lag" going to help when one cannot see half the positions of the opposition, and aiming at those in between spots just is not directly occurring? you have no visual data for those positions, half the positions of your opponent !

You can see how that may present some real issues for the gamer, as far as firing accuracy.
Yes, one could develop a sort of compensation with practice, just like a similar amount of consistent input lag is gotten used to as the mind and muscles acclimate and compensate accordingly.

So, it appears to me missing frames and runts are anything but helpful, and the lag thenno lag, or the lag not running in sync with what appears on screen could be a real problem.

With equalized frame time outputs to screen, the "smoothness" factor certainly helps aiming at opponents and learning to time things correctly.

April 10, 2013 | 09:13 AM - Posted by Stennan (not verified)

Thank you for not answering my question :)

I just wanted to know if there might be an upside with regards to perhaps input lag. Kind of hard to measure though.

April 9, 2013 | 06:45 AM - Posted by fadeout (not verified)

Are we seeing that crossfire is inherently borked? Or are we seeing that the current drivers are not leveraging the potential of the hardware?

I'm thinking that drivers can be updated.

A note on the fanboy thingy, surely we need both companies to succeed to push one another to create ever faster and more powerful cards. No?

April 9, 2013 | 10:44 AM - Posted by bystander (not verified)

The problem has persisted at least two series of cards, but based on AMD's response, it likely has always existed. AMD had said they never considered frame metering. Instead, they had been focusing on delivering frames as fast as possible.

That to me would say the drivers were not borked per say, they just weren't trying to do anything about it. They weren't even aware of it.

Nvidia has their metering done with special hardware, but AMD believes they can do the same with software, which they probably can, though it may not be as ideal.

April 9, 2013 | 10:23 PM - Posted by Anonymous (not verified)

Not sure why the 660 is being compared to a 7870. MSRP is over $100 difference. 7850 makes more sense to me but there must be a good reason the 7870 was chosen.

April 9, 2013 | 10:57 PM - Posted by bystander (not verified)

The GTX 660 is the cheaper of the two cards. You must have the GTX 660ti in mind.

April 13, 2013 | 03:32 PM - Posted by Anonymous (not verified)

The reason is a big fat smooch on the behind of amd and their fanboys.
Keep the raging natives a bit less restless.
You see, only 2 pages of comments, they didn't come in screaming bias while their radeon I don't believe any of this and "if it's true" it doesn't matter heads exploded.

They have all been made absolute idiots, as the years of their stupidity is apparent.

The years of them screeching no one can see over 30 fps anyway is exposed. It doesn't matter what they knew or did not know, they made every excuse and lie and fanboy promo they could over the course of years and now it is absolutely clear they were seeing only half the frames gobbled with screen wretching runts, but still claimed it was beauty incarnate.

They are fools, and we all know it.

April 11, 2013 | 03:15 PM - Posted by Arek (not verified)

It would be nice to see how a pair of gtx 580's fares, as I have these in my setup. Pretty please! *_*

April 13, 2013 | 07:21 PM - Posted by Johnny Rook (not verified)

I can't stress enough how amazing this is.

I have one or two questions though:

1. Is the ATI/AMD Dual-GPU cards like the HD7990 have the same "problems" has dual cards in SLi?

I have an HD5970 and I do recognize there are problems as far as stutter is concerned but, I notice, I have a clear visual "feeling" that something is not right in a very few games. Mostly those "heavy" titles like "Metro2033" and the new "Crysis 3".

2. Is the problem something related to the hardware itself, is it drivers or is it a mix of both?

April 13, 2013 | 07:31 PM - Posted by Johnny Rook (not verified)

Sorry, I meant "problems has dual cards in Crossfire?"

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.