Review Index:
Feedback

NVIDIA GeForce GTX TITAN Performance Review and Frame Rating Update

Author: Ryan Shrout
Manufacturer: NVIDIA

Pricing, Testing Setup and why we aren't testing CrossFire

The details of the GTX TITAN graphics card and pricing have been quite the discussion based on the comments in our first article and the YouTube video posted on Tuesday as well.  It seems the price tag of $999 has set quite a few people off knowing that in some cases the new GK110-based part would be slower than the GeForce GTX 690 and only modestly faster than the GTX 680 alone. 

We obviously have a lot of performance numbers to look at before we can make those distinctions but there may be valid complaints there.  Here is the pricing stack the cards we are testing today:

View Full Size

Testing Configuration

The specifications for our testing system haven't changed much.

Test System Setup
CPU Intel Core i7-3960X Sandy Bridge-E
Motherboard ASUS P9X79 Deluxe
Memory Corsair Dominator DDR3-1600 16GB
Hard Drive OCZ Agility 4 256GB SSD
Sound Card On-board
Graphics Card NVIDIA GeForce GTX TITAN 6GB
NVIDIA GeForce GTX 690 4GB
AMD Radeon HD 7970 3GB
NVIDIA GeForce GTX 680 2GB
Graphics Drivers AMD: 13.2 beta 5
NVIDIA: 313.97 beta (GTX 680, 690)
NVIDIA: 314.09 beta (GTX TITAN)
Power Supply Corsair AX1200i
Operating System Windows 8 Pro x64

View Full Size

What you should be watching for

  1. GTX TITAN vs GTX 680 vs HD 7970 - Does the new GeForce GTX TITAN become the fastest GPU on the market and by how much?
  2. GTX TITAN vs GTX 690 - From a single card perspective, how do the two flagship offerings from NVIDIA with $999 price tags compare?
  3. GTX TITAN vs GTX 680 SLI - A pair of GTX 680s in SLI will cost you about $930 so they are basically the head-to-head competition for a single TITAN.

 

Why are you not testing CrossFire??

One question I know will be asked about this review is that in our benchmarks today you will not see results from AMD CrossFire configurations in 2-Way or 3-Way combinations.  AMD is only represented by a single Radeon HD 7970 GHz Edition card while we are using both the GTX 690 dual-GPU card, GTX 680s in SLI and GTX TITANs in SLI. 

Why the bias?

If you haven't been following our sequence of stories that investigates a completely new testing methodology we are calling "frame rating", then you are really missing out.  (Part 1 is here, part 2 is here.)  The basic premise of Frame Rating is that the performance metrics that the industry is gathering using FRAPS are inaccurate in many cases and do not properly reflect the real-world gaming experience the user has.

Because of that, we are working on another method that uses high-end dual-link DVI capture equipment to directly record the raw output from the graphics card with an overlay technology that allows us to measure frame rates as they are presented on the screen, not as they are presented to the FRAPS software sub-system.  With these tools we can measure average frame rates, frame times and stutter, all in a way that reflects exactly what the viewer sees from the game.

We aren't ready to show our full sets of results yet (soon!) but the problems lie in that AMD's CrossFire technology shows severe performance degradations when viewed under the Frame Rating microscope that do not show up under FRAPS.  As such, I decided that it was simply irresponsible of me to present data to readers that I would then immediately refute on the final pages of this review - it would be a waste of time for the reader and people that skip only to the performance graphs wouldn't know our theory on why the results displayed were invalid.

Many other sites will use FRAPS, will use CrossFire, and there is nothing wrong with that at all.  They are simply presenting data that they believe to be true based on the tools at their disposal.  More data is always better. 

As I said, check on the last two pages or so this article for more information on this, and feel free to leave your feedback below!

February 25, 2013 | 07:21 AM - Posted by Elvis (not verified)

Great Article. Nice to see original thought and work in a tech Blog (instead of more useless fps number) .
The Titan has impressive performance, too bad the price is outta my reach :'(
BTW Anyone else notice that 7970GE is starting to kick 680 butt. AMD driver team is on a roll! However CF looks bad and they need to correct it, seeing as they have no single chip competitor to Titan.
@Ryan : To make things interesting, why not benchmark some games which are not as "popular", i.e driver optimized.
Also, in my (humble?) opinion your articles would be more professional(better) if you avoided superlatives and words like beast (so clichéd). They make refutation of bias harder.
Once again, great work.

February 25, 2013 | 07:24 AM - Posted by Elvis (not verified)

@Ryan could you please block the ip of the rabid fan-atic. Really spoils the whole comments section...
@Anonymous : obvious troll. Not gonna bother replying. Sod off!

February 25, 2013 | 07:44 AM - Posted by Trey Long (not verified)

This business of runt frames significantly padding Crossfire's fps numbers is a huge story in the GPU world. There needs to be a major effort to expose the truth of this, whatever it is.

February 25, 2013 | 02:56 PM - Posted by Epoq (not verified)

I agree wholeheartedly. If this is true in it's entirety it would destroy AMD's credibility in the multi-GPU realm. Before this, most people were in agreeance that for high res and multi-display configurations, AMD is the way to go. This would change everything.

March 2, 2013 | 03:19 AM - Posted by Max Klar (not verified)

I doubt that the new 3dMark is reliable. Maybe it's just created to boost Titan.
I did the benchies with GTX680SLI/i7-3930K/X79. In 3dMark11 I get about nearly P16000 @stock and +P18000 occed.
But in Firestrike:
GTX680 single: 6300
GTX680SLI: 4200 (!)

And it's not only my system, you can find these biased or faulty results easily.

So the 3dMark benchmark is a joke at the actual state and should not be used in a professional environment.

March 2, 2013 | 10:06 PM - Posted by Anonymous (not verified)

Little bumed with your test???? this is a 2d surround card I am running 3 evga 680`s sc at 6000×1200 please let's see the real meat and potatoes people buying this card ( me) want to see ....well let's say three 680`s at 6000×1200 and two titans sli at same res that I think is all that really matters here rite? the 680 only having 2gb men must fail hard against two Titans with its 6gb the titan card is very specifically a hi-res surround gaming card I know you need to test everything but I think you should have started the other way around IMO..

March 3, 2013 | 12:02 PM - Posted by KansasCityTom (not verified)

I just spent a little over $1100 on 3 x 7970's and against my friends new Titan, I basically walk over him in all benchmarks.

March 4, 2013 | 04:55 PM - Posted by Trey Long (not verified)

Except that Crossfire is a sham. You get no better performance than one card. Read the article before spouting. And Tech Report and Hardocp. Runt frames a real disaster for Crossfire as they can be seen, measured, and exposed, unlike the fraps number which includes totally degraded frames in their fps number you rely on. Latencies have long been an issue with AMD cards and this clarifies in Crossfire.

April 2, 2013 | 10:49 PM - Posted by Anonymous (not verified)

Great work Ryan keep up the great work...by the way how do we support your site make donations !!!!! p.s I'm loving my tri sli titans this is the card I have been waiting for my hole life... been builbing systems starting back in the voodoo days finally 6000×1200 plays like butter nvidia is really something eh!!

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.