Overclocking

Both the Athlon II X2 and the Phenom II X2 managed to overclock to about the same levels. Without any additional core voltage they were able to run at 3.5 - 3.6GHz, with the Athlon II being able to go a bit higher thanks to being free of any L3 cache. With less than 10% additional core voltage I was able to get both chips up to 3.7GHz. The Athlon II X2 250, when overvolted, managed to reliably hit 3.75GHz.

Gary's sample was able to work solid at 4.0GHz while mine would fail at 3.8GHz or above.

Processor Highest Overclock (Stock Voltage) Highest Overclock (Overvolted) % Increase over stock
AMD Phenom II X2 550 BE 3.5GHz 3.7GHz 19%
AMD Athlon II X2 250 3.6GHz 3.75GHz 25%
Intel Pentium E6300 3.40GHz 3.57GHz 28%

 

The Pentium E6300 topped out just under 3.6GHz with ~10% additional voltage. I noticed a strange trend when overclocking the E6300. I set the FSB to 340MHz, which when multiplied with the CPU's 10.5x multiplier should yield 3.57GHz. Yet with no additional voltage, the CPU would hardly ever go above a 10.0x multiplier once in Windows - resulting in a 3.40GHz clock speed:

The chip wasn't throttling due to heat, it simply would not run at 3.57GHz without any additional voltage. As soon as I gave it more voltage or as soon as I disabled EIST, the CPU ran at its correct frequency:


All I did was disable EIST, although increasing the VID also resulted in the same thing

Even with additional voltage however I wasn't able to get the E6300 stable at above 3.57GHz.

Processor x264 Pass 2 Cinebench XCPU Crysis Warhead
AMD Phenom II X2 550 BE @ 3.7GHz 11.0 fps 8224 74.5 fps
AMD Athlon II X2 250 @ 3.75GHz 11.0 fps 7968 75.0 fps
Intel Pentium E6300 @ 3.57GHz 11.7 fps 8096 80.8 fps

 

The Pentium E6300 is actually quite competitive when overclocked and appears to scale very well with additional clock speed. It also helps that AMD's clock speed advantage shrinks once we overclock these chips a bit.

Power Consumption Final Words
Comments Locked

55 Comments

View All Comments

  • haplo602 - Tuesday, June 2, 2009 - link

    can you include linux kernel compilation tests, or something similar or larger (gcc, libqt, X) ??? would help me much more than gaming and 3d rendering benches :-)
  • virvan - Tuesday, June 2, 2009 - link

    Anand, I BEG you to include some kind of compilation tests in the "bench" application; some of us are actually programmers that spend more time building than watching or transcoding movies ;)
    A Linux Kernel bench + some kind of MS Visual C++ benchmark would be extremely welcome.
    Btw, when could we expect the old CPUs to be added to Bench? I am specifically waiting for Athlon XP and P3/P4's.
    10x
  • Anand Lal Shimpi - Tuesday, June 2, 2009 - link

    I really do want to include a software build test, the question is what is the simplest to setup and run, most representative and most repeatable test I can run?

    I'd prefer something under Windows because it means one less OS/image change (which matters if you're trying to run something on ~70 different configurations) but I'm open to all suggestions.

    Thoughts? Feel free to take this conversation offline over email if you'd like to help.

    Take care,
    Anand
  • virvan - Wednesday, June 3, 2009 - link

    You could try building a CGAL demo program (http://www.cgal.org/FAQ.html)">http://www.cgal.org/FAQ.html). It is cross platform and big enough (but not too big).
    I am really a Linux programmer but I could try to help if you are not a programmer. I haven't booted Windows for years but, hey, we have virtual machines nowadays :)
  • adiposity - Tuesday, June 2, 2009 - link

    A fairly decent size build that I do is Qt under VS 2008.

    Instructions are here:

    http://wiki.qtcentre.org/index.php?title=Qt4_with_...">http://wiki.qtcentre.org/index.php?title=Qt4_with_...

    Download source here:

    http://www.qtsoftware.com/downloads/windows-cpp">http://www.qtsoftware.com/downloads/windows-cpp

    You can use VS2008 Express.

    -Dan
  • haplo602 - Wednesday, June 3, 2009 - link

    I have no experience with VS 2008. Can it be manualy set to certain amount of compile threads ? make has a command line parameter for this, so you can even test a single threaded compile and scale the number of threads used to exploit the drop off limit (where more threads do not yield better performance).

    qt is quite huge, but that's ok, since a compilation of a few minutes (linux kernel) won't tell much in the future, when processing power increases.
  • smitty3268 - Wednesday, June 3, 2009 - link

    Yes, you can add the /MP parameter in Visual Studio.
  • adiposity - Wednesday, June 3, 2009 - link


    From the page I linked before:

    Add these line to the .pro file for release version:

    QMAKE_CXXFLAGS_RELEASE += -MP[processMax]


    -Dan
  • smitty3268 - Wednesday, June 3, 2009 - link

    All of Qt might be a bit large for a simple benchmark.

    Something like Paint.NET or NDepend might make a good C# test.
  • adiposity - Wednesday, June 3, 2009 - link

    Use:

    nmake sub-src

    It only compiles qt libraries, not the tools or examples.

    It really does not take very long (less than 10 minutes on a Core2Duo 2.4).

    -Dan

Log in

Don't have an account? Sign up now