The DDR2 Issue

As we mentioned earlier, the Conroe system was supposed to be running at 4-4-4-15 timings but was instead configured at 5-5-5-15, giving Conroe a bit of a disadvantage.  We re-ran all of our tests with the timings correctly set to 4-4-4-15, the results are below:

Intel Conroe Platform
5-5-5-15
4-4-4-15
Quake 4 - 1280 x 960 (Avg Frame Rate)
257.8 fps
259.1 fps
F.E.A.R. - 1024 x 768 (Avg Frame Rate)
186.0 fps
189.0 fps
Windows Media Encoder 9 (Encode Time)
66 seconds
66 seconds
DivX 6.1 (Encode Time)
31 seconds
31 seconds
iTunes 6.0.1.3 (Encode Time)
65 seconds
65 seconds

 

While the faster timings gave Intel a small performance boost in the games, it’s nothing to write home about. 

The F.E.A.R. Issue Updated Performance Charts
Comments Locked

96 Comments

View All Comments

  • Questar - Thursday, March 9, 2006 - link

    I think you have confused AMD for ATI.
  • amano - Thursday, March 9, 2006 - link

    Not really: "Why Ati drivers where modified to recognize the Conroe processor?"
    Indeed, why ? Perhaps to fix the disadvantage that the FEAR benchmark gives to ATI?
    If this disadvantage was fixed for the INTEL-setup, and not for the AMD-setup, then the 2 setups can not be compared and the benchmark-results are flawed.
    (sorry, my first post was a bit confusing..)
  • Accord99 - Thursday, March 9, 2006 - link

    That was fixed several driver revisions ago. All it was was a mistake in one If statement.
  • DSaum - Thursday, March 9, 2006 - link

    So the 41% Conroe advantage over AMD has suddenly become 20%? After this sorry episode I have serious doubts as to Anandtech's objectivity as an unbiased reviewer.

    "Believe it or not, Intel doesn't seem malicious in their intent." LOL
  • clnee55 - Thursday, March 9, 2006 - link

    After a great review and re-test by Anand, I hope i don't see fanboism comment again. Unfortunately, there are still kids around, who cannot understand a simple review.
  • Bladen - Thursday, March 9, 2006 - link

    ^And the AMD fanboy of the year award goes too...

    BTW for thoes wondering if Conroe and the others are 64 bit, the answer is yes.

    I highly doubt Intel will release a processor that is not 64 bit in the future. Well for any processor designed for laptop, desktop or server anyway...
  • Bladen - Thursday, March 9, 2006 - link

    Ohh crap, I failed to realise my post would not be directly below DSaum...
  • matthewfoley - Thursday, March 9, 2006 - link

    Um, would they have released a follow up article telling you about it if they were trying to hide something?
  • Sunrise089 - Thursday, March 9, 2006 - link

    It was a 41% advantage in one game during one total hour of testing. In addition, not only did Anand explain how they messed up, but also provided new graphs only 2 days later. What are you really thinking here, that Anand's mistake will increase Conroe's sales even though the corrected numbers are out and its 6 months away from launch? I'm pretty sure even Intel fanboys didn't just read the first story and then plan on not visitng another hardware site before launch.
  • Aileur - Thursday, March 9, 2006 - link

    Way to be able to read
    quote:

    on average we’re still seeing a bit over a 20% increase in performance over an overclocked Athlon 64 FX-60.

    quote:

    Especially looking at titles like F.E.A.R. where Conroe's performance advantage averages over 40%



    Now, thats not the same as dropping from 40 to 20%, is it?

Log in

Don't have an account? Sign up now