Sign in with
Sign up | Sign in

Updated: Tuning C'n'Q: Maximize Power And Performance, Part 2

Updated: Tuning C'n'Q: Maximize Power And Performance, Part 2
By

Editor's Note: This story first went live in November of 2009. After its publication, we went back and forth with AMD's power experts, discussing some of the conclusions drawn. With feedback from AMD, we've retested to clarify where optimizations are most likely to be made. We've also addressed a problem with Cool'n'Quiet observed in the previous piece, which turned out to be caused by an implementation of the technology, rather than the technology itself. Special thanks to AMD for its input. You can find Part 1 of this exploration right here.

Earlier this week we discussed the inner-workings of AMD's Cool'n'Quiet technology and what you could do as an enthusiast with the right tools to further-optimize an Athlon or Phenom processor.

Now it's time to talk about performance. Like most of the processor-oriented reviews you read, we're going to use several benchmarks to measure the speed of our various samples. But we're going to go even further this time around. In addition to performance numbers and test results, we're also going to include power consumption measurements for each benchmark.

The purpose is actually quite simple. Different applications utilize processors differently. Some will make full use of all available cores, while many others will not. This also means power consumption with each scenario will likely be different. By measuring the power consumption of single- and multi-threaded applications, we can get a reasonable idea of the performance and power consumption in a handful of scenarios, addressing whether or not our optimizations had a positive effect.

There’s also a different type of scenario we wanted to test. Many benchmarks apply a 100% load to each core, so the processor will be in its highest p-state during the test. We wanted to observe performance with idle p-states, or at least intermediary p-states. After all, the processor is idle through much of time we spend on the desktop, whether you're Web browsing, writing e-mails, playing music, or watching standard definition video--all of which hardly load the processor. For our purposes, we'll be measuring system power consumption when playing high definition video with and without hardware acceleration.

We're also going to look at the core/processor utilization levels. Why? To see whether or not the benchmarks really make use of all available processor resources. We can see just how often the processor is idle and to what degree. We can also see whether or not all cores are fully-utilized. To do this, we record processor utilization by using Vista's built-in Performance Monitor.

These measurements were taken with different power profiles: No Management (we turned off Cool'n'Quiet in the BIOS), Balanced (Cool'n'Quiet is enabled in the BIOS and the Windows power policy is set to Balanced), and Optimized (Cool'n'Quiet is enabled in the BIOS, the Windows power policy is set to Balanced, and the processor is running with lower core and northbridge voltages, shorter p-state transition times, and synchronous clock changes or “Ganged” in K10Stat). These settings are selected because we want to focus on performance and consumption with power management features enabled.

Note: We re-tested the Athlon II X2 250 and Phenom II X4 955 on a new platform, swapping in a Biostar TA790GX A3+ (a dual-power plane, AM3-equipped motherboard) and four modules of Team Elite DDR3 memory. The power supply was also swapped to a lower-wattage unit (Enermax's 405W Tomahawk). We also obtained an Athlon II X4 620 to see how it compares to the Phenom II X4 955 BE.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 24 comments.
This thread is closed for comments
Top Comments
  • 10 Hide
    nzprogamer , November 19, 2009 5:33 AM
    GO AMD go
    i am telling you my next build AMD/ATI
    """I WILL BE BACK"""
Other Comments
  • 10 Hide
    nzprogamer , November 19, 2009 5:33 AM
    GO AMD go
    i am telling you my next build AMD/ATI
    """I WILL BE BACK"""
  • 5 Hide
    jedimasterben , November 19, 2009 11:29 AM
    I'd be interested to see the tests performed on Windows 7 to see what the effect of reducing thread "jumping" would be.
  • -9 Hide
    cnox , November 19, 2009 11:54 AM
    Dammit...how can this part 2 article be posted before the Building the Balanced PC Part 2?

    Cumon....
  • 4 Hide
    melangex3 , November 19, 2009 12:55 PM
    Great Stuff. Keep up the good work. This is the type of review that will keep me coming back. How about throwing in the ever popular 720 BE and the new 620 or 630 just for giggles?
  • 0 Hide
    Ryun , November 19, 2009 1:45 PM
    jedimasterbenI'd be interested to see the tests performed on Windows 7 to see what the effect of reducing thread "jumping" would be.


    I was thinking the same thing as well.

    Also, were the BIOSs all updated? The asynchronous clocks problem you're experiencing with Athlon II X2 was supposed to be fixed with updated CPU microcode.
  • 1 Hide
    Summer Leigh Castle , November 19, 2009 2:58 PM
    620 and 720? :D 
  • 0 Hide
    redgarl , November 19, 2009 5:27 PM
    I must admit that lately AMD is impressive. I got a PII X3 720 BE unleashed at PII X4 20 fully stable with an Asus M4A78T-E latest BIOS. Let simply add that my 2 radeon 4850 OC in Crossfire are running as fast as 2 stock 4870...

    If you take into account that the 2 cards only cost 82$ each for a total of 165$ for the two... I can hardly believe that so little money can give so much results.
  • 2 Hide
    JimmiG , November 19, 2009 6:55 PM
    With my Phenom X4 9650, I found Cool n Quiet to be pretty much worthless without tweaks. There were huge performance drops across the board, especially with tasks that didn't use all four cores, or only loaded cores partially. Videos and games would stutter and skip every couple of frames, compressing files would take longer etc. I basically had a 1.1 GHz CPU that would sometimes run at 2.3 GHz, if it felt like it. Too bad there was no tweak guide available then. I just disabled CnQ which solved all problems but made the system use more power and run hotter.

    With my 955BE, I haven't really had a need to tweak CnQ. It might cause a slight performance hit in some rare cases, but generally when I need a 3.2 GHz CPU, that's what it delivers.
  • 0 Hide
    tacoslave , November 19, 2009 8:46 PM
    Nice, amd owns in the graphics department now with that $1.2 billion im sure amd is heading to pwn BOTH markets.
  • 0 Hide
    saint19 , November 21, 2009 2:48 PM
    Good!!!, I have my 955 to 3.8GHz at 1.5V....
  • -2 Hide
    marraco , November 21, 2009 11:09 PM
    Quote:
    For this test, we've selected a 616MB folder full of files (the installer for Adobe Photoshop CS4)

    Bad choice. You are "compressing" already compressed files.
    A better choice would be to copy 600 MB from windows "program files" folder, and play with it.
  • 0 Hide
    eyemaster , November 30, 2009 6:20 PM
    marracoBad choice. You are "compressing" already compressed files.A better choice would be to copy 600 MB from windows "program files" folder, and play with it.


    Bad choice if you're trying to compress file, but not a bad choice if you're just trying to stress a CPU. It will still have to do a whole lot of calculations regardless of the files.
  • 2 Hide
    b23h , December 3, 2009 4:20 AM
    Thank you very much for this article. It came at the perfect time for me. I’ve just upgraded from a 65 watt AMD Athlon 64 X2 4600 to the AMD Phemon II X3 720. Since I’m running a fanless CPU heatsink (ZEROtherm BTF95) I was concerned that the 95 watts of power of the 720 would be too much for the BTF95. I was planning on underclocking the CPU in order to approximate what I thought the heatsink could handle. However with the help of the article I don’t need to underclock it at all. Using the chart of the 710 I estimated some beginning settings for the 720. While I may be able to further lower the voltages I’ve stressed test my current settings by running a program called the Intel Burn Test plus an immoderate amount of Borderlands.

    The 720 seems to have four p-states. The defaults were 1.25/1.15/1.05/.95 I am currently running the CPU at 1.15/1.125/1.0250/.9 I really haven’t thoroughly stress tested all the possibilities so I expect I may still be able to optimize further P-states one through three.

    The timing of this article was excellent for me and I appreciate all the information I’ve gotten at Tom’s Hardware Guide all these years.
  • 0 Hide
    volks1470 , March 25, 2010 6:30 AM
    Typo! Phenom II X3-X4 720-965 only have 6MB of L3 cache, not 8MB. Not a big deal but for a second there I though the 955 had more L3 cache than my 965.
  • 0 Hide
    4ILY45 , March 25, 2010 7:48 AM
    melangex3Great Stuff. Keep up the good work. This is the type of review that will keep me coming back. How about throwing in the ever popular 720 BE and the new 620 or 630 just for giggles?


    YES PLEASE!!!! :) 
  • 1 Hide
    shreeharsha , March 25, 2010 8:29 AM
    I still need to sell my intel Pentium 660 system to build a AMD system. I am a AMD fan (converted) stuck with intel processor system.
  • 0 Hide
    JohnnyLucky , March 25, 2010 11:45 AM
    Thanks for a very informative article that helps put things in perspective.
  • -1 Hide
    chaitanya_mkin , March 25, 2010 6:18 PM
    Im Telling u AMD wll be the king in HISTORY theres no other name than AMD.
    Quote:
    AMD the BEST
  • -1 Hide
    chaitanya_mkin , March 25, 2010 6:21 PM
    And this comparision is great for amd users, ofcourse for me tooooo cause im using AMD since 6 years.(my brain is AMD ATHLON X2 6000+ WINDSOR 3.02GHz)
  • 0 Hide
    arnawa_widagda , March 25, 2010 11:27 PM
    Hello,

    We've updated this article (and the first part) with results from an AM3 motherboard and an Athlon II X4 620. The p-state settings we tested with the Athlon II X4 620 can be found in the first part (along with some power consumption numbers).
Display more comments