Overclocking at Stock Voltages

The Phenom II X4 940 was AMD's first Phenom II to hit the market, the downside being that it wasn't the best example of AMD's 45nm manufacturing process. While the chips could overclock, their headroom without increasing their default core voltage just wasn't that high. The 940 we used for this review could only make it to 3.2GHz with a 2.2GHz NB frequency without increasing core voltage beyond the default 1.35V (as reported by the BIOS, 1.336V as reported by CPU-Z):


Phenom II X4 940 max overclock at stock voltage

The Core 2 Quad Q8400 on the other hand is based on a core that's been shipping for quite a while, at stock voltage using the stock cooler I was able to hit 3.08GHz:

Now remember that Phenom II isn't faster than Intel's Core 2 Quad clock for clock. AMD gets an advantage only because it sells higher clocked Phenom IIs at the same price as lower clocked Core 2 Quads. With only a 4% clock speed advantage, the performance is distinctly in Intel's favor:

Processor Adobe Photoshop CS4 x264 HD - 2nd pass POV-Ray Far Cry 2 Idle Power Load Power
AMD Phenom II X4 940 @ 3.2GHz 22.3s 19.0 fps 2539 51.5 fps 120.2W 209W
Intel Core 2 Quad Q8400 @ 3.08GHz 19.7s 20.4 fps 2597 53.5 fps 131.9W 181.5W

 

Photoshop and Far Cry 2 were both Q8400's strengths at stock clock speeds, so it makes sense that the Q8400 would widen the gap after we overclocked both chips. The x264 and POV-Ray tests were equal and in AMD's favor, respectively, at stock clocks. When overclocked without touching anything but the clock multiplier in the case of the Phenom II or FSB frequency and memory ratios in the case of the Core 2 Quad.

There is merit to looking at this sort of overclocking performance since it's the simplest way to overclock, but if you're willing to give your chip a little more voltage you can get a lot more clock speed...

Power Consumption Overclocking with a 10% Increase in Core Voltage
Comments Locked

60 Comments

View All Comments

  • eXistenZ - Thursday, May 7, 2009 - link

    Obviously, AMD is no good in Far Cry 2 game. K8, K10, K10.5, al these architectures were always slower than intel's competitors. And it is really crappy game, so i don't see any reason why are you testing right on this one. I think, more fair testing is with Crysis or CPU-eaters = RTS...
  • Goty - Thursday, May 7, 2009 - link

    Anand seems to be buying into all the FUD about AMD lately. Sure, AMD's not doing so hot right now, but they're not in much worse a position than they were in the middle of the P4 era (probably about the same position, all told).
  • Anand Lal Shimpi - Friday, May 8, 2009 - link

    I'm not sure I would call it FUD. AMD lost $2.36B before taxes in the last four quarters combined. Their chief competitor made $6.13B. Now Intel has always made more than AMD, but the issue now is that AMD is losing a considerable amount every quarter. That can only continue for so long.

    What I'm more worried about is the impact this is having on the next-generation cores that AMD is developing. While engineering budgets are the last things to go, if you're losing a few hundred million a quarter everyone from marketing to engineering gets hurt.

    Ignoring the problem isn't going to make it go away, I felt that it would be important to at least bring some of this stuff to the table so we can at least be thinking about it.

    Take care,
    Anand
  • microAmp - Thursday, May 7, 2009 - link

    Actually, it's worse, they are running out of cash.
  • ssj4Gogeta - Thursday, May 7, 2009 - link

    "It's the beauty of Moore's Law: with fewer transistors crammed into a much smaller area, we're able to see the same performance."

    Shouldn't it be "MORE transistors crammed into a much smaller area"?

    :)
  • hooflung - Thursday, May 7, 2009 - link

    I am another that buys based on the ability of Virtualization via virt functionality. I got a P2 940 because I wanted the ability to have 4 cores to split up to VM's running Hyper-V, Xen and KVM. I just can't do that on new intel chips that fall in the price range right now.

    My C2D is still rocking a venerable 1ghz OC on a e4300 and P35 chipset. For me to install an OS to do development as the top level is just wasting wattages at my home.


  • snakeoil - Thursday, May 7, 2009 - link

    ''Phenom II Earns a Financially Troubled AMD Less per Chip than Core 2 Quad''

    well you are saying that amd make less money because phenom 2 has a little more area,but in your happy calculations you forgot that bad quad core dies are used to make tricores and soon dual cores phenoms.
    harvesting.

    what are you doing little annand
  • crimson117 - Thursday, May 7, 2009 - link

    One wafer costs a fixed amount to make; let's say $200.

    Let's say AMD can get 10 CPUs made from each wafer, while intel can get 20 smaller CPUs from each wafer. They each sell their chips for $180.

    AMD puts $200/10 = $20 worth of wafer into each $180 CPU.
    Intel only has to put in $200/20 = $10 worth of wafer into each $180 CPU.

    So assuming all other things are equal, Intel makes $5 more on each CPU sale than AMD.
  • crimson117 - Thursday, May 7, 2009 - link

    *clicks Edit button*

    So assuming all other things are equal, Intel makes $10 more on each CPU sale than AMD.
  • mkruer - Thursday, May 7, 2009 - link

    You are also forgetting that AMD and Intel use two different lithphogathy technologies to AMD uses submersion and Intel uses double pattering. The Submersion takes slightly longer then a single pattering, and yeild fewer defects. This meas that AMD should be able to preduce a high volume of chips per platter then Intel. Adding to the confusion, is that neiter intel nor AMD releases what there yeilds are and as such, too comepare based upon die size alone is folly. People can crunch the numbers anyway they want, but in the end it should be a, for more or less, wash.

Log in

Don't have an account? Sign up now