Synthetics

We’ll also take a quick look at synthetic performance to see if NVIDIA’s choice of clockspeeds and disabling a SMX had any kind of other impact we haven’t anticipated. We’ll start with 3DMark Vantage’s Pixel Fill test.

Pixel Fill is said to be memory bandwidth limited, and for good reason. Even with the lower clockspeed of the GTX 670, the fact that it has memory bandwidth equal to the GTX 680 means that it achieves equal performance in this test, confirming that GTX 670 can utilize its memory bandwidth just as well as GTX 680 can.

Our second test is 3DMark’s Texel Fill test, which as expected shows a moderate gap between the GTX 670 and GTX 680. Thanks to the loss of an SMX and the lower clocksped the GTX 670 only achieves 85% of the performance of the GTX 680, which thanks to the GTX 670’s more aggressive boost clock is a bit better than what we’d expect from the specifications.

Our third theoretical test is the set of settings we use with Microsoft’s Detail Tessellation sample program out of the DX11 SDK

As expected GTX 670 falls behind GTX 680, but again not by nearly as much as we’d expect. The loss of the SMX means GTX 670 lost a Polymorph Engine, but with only a 4% gap with maximum tessellation you’d never be able to tell.

Our final theoretical test is Unigine Heaven 2.5, a benchmark that straddles the line between a synthetic benchmark and a real-world benchmark as the engine is licensed but no notable DX11 games have been produced using it yet.

With Heaven the gap between the GTX 680 and GTX 670 once again opens up similarly to what we saw in our compute benchmarks with SmallLuxGPU. This means the GTX 670 falls behind by about 10%, reflecting the shader-heavy nature of this benchmark.

Compute Power, Temperature, & Noise
Comments Locked

414 Comments

View All Comments

  • SlyNine - Saturday, May 12, 2012 - link

    I'm starting to think you're alittle crazy.
  • CeriseCogburn - Sunday, May 13, 2012 - link

    Say it 3 more times ( as you have already), it certainly invalidates all the reasons why the amd card loses badly.

    Nice, desperate try there. Not.
  • medi01 - Friday, May 11, 2012 - link

    Let me guess: because you can actually get either 680 or 670 at the announced price (if at all), eh?

    So you can't? And when you will be able to get one, street price would probably be higher than MSRP, eh?

    So what are you buzzing about?
  • CeriseCogburn - Friday, May 11, 2012 - link

    Oh that's too bad, you're wrong again. 670 still 399 at the egg.
    Order, go ahead in STOCK.

    How about someone ban you for just being a smart aleck, isn't that what a zealout of no use whatsoever really is ? Are you going to claim this is your joke and rip on others place ? Why didn't you check availability or read about it in the article the reviewer in fact went into quite some detail and extrapolation on the differences between this and the 680 and 690, but you never read the review did you ?
    You just come here to attack others and smart off for amd points.
  • SlyNine - Saturday, May 12, 2012 - link

    I got a GTX680 for 499$, but still he needs to chill. If someone bought a 7970 before the 670GTX came out it might have been the fast card they could find for the money.

    Not counting dual GPU solutions of course ( I hate those).
  • CeriseCogburn - Sunday, May 13, 2012 - link

    I wonder who that someone would be, yours truly.
    I guess your comprehension skills are not really up to par.
  • Spunjji - Friday, May 11, 2012 - link

    Trololol "viral marketing group". xD

    He's just pissed off because he thinks the other side are getting paid for being mindless bigots...
  • CeriseCogburn - Friday, May 11, 2012 - link

    No it's clear none of you are being paid a dime, not even a single housefire amd 7970 woodscrew.
  • CeriseCogburn - Friday, May 11, 2012 - link

    This should make the amd fans happy, immense amd bias by the reviewer, again.
    TWS2
    " The GTX 570 and it’s increasingly puny 1.25GB of RAM can’t even run this game with our 2560 benchmark settings "
    What the reviewer forgets to mention is that at 2560 and their benchmark settings not a single card present is playable, all under 29 fps and the majority under 20.
    ROFL

    That might be entirely different without the new game patch bug that affects only nVidia, but the very fact that the reviewer moans about "the 570" "puny ram" problem while noting a COMPLETELY UNPLAYABLE GAME BENCHMARK FROM THE HIGHEST TIERED 3G RAM AMD FLAGSHIP CARD...
    Where exactly is the brain ?

    This is the kind of crap we have to put up with here, at least we who have a brain and can see what's going on.
    I guess the amd fanboys can thank the reviewer for further perpetuation of the ram bottleneck MYTH.
    What a JOKE ATTACK on the nVidia card.
    Worse yet, on the very next page, the very same GTX570 beats the amd opposition 2G ram 7870 at 2560 but it can't be mentioned.
  • SlyNine - Saturday, May 12, 2012 - link

    lol, the 7970 runs it at 28. Which is playable in a game like that.

    Funny the 7970 is by far more playable at that res. thanks for pointing that out.

    Of course once Nvidia fixes the bug they should rerun the test.

Log in

Don't have an account? Sign up now