Phenom II: Unlocking Cores, Cache, And A Free Lunch

Test System And Benchmarks

We didn’t run our entire benchmark suite for this little project. After all, our main goal in running tests was to verify that what we were seeing in CPUz and Everest was correct.

Test Hardware
Processor
AMD Phenom II X4 810 (Deneb) 2.6 GHz, 4 MB L3 cache

AMD Phenom II X2 720 Black Edition (Deneb) 2.8 GHz, 6 MB L3 cache
Cooler
Thermalright Ultra 120 Extreme
Motherboard
ASRock M3A790GXH/128M (Socket AM3) 790GX/SB750
Hard Drive
Western Digital VelociRaptor WD3000GLFS 300 GB 10,000 RPM SATA 3 Gb/s HDD
Graphics Card
Zotac GeForce GTX 260 Core 216 896 MB
Power Supply
Cooler Master UCP 1100 W
System Software and Drivers
Operating System
Microsoft Windows Vista Ultimate Edition x64 Service Pack 1
DirectX
DirectX 10
Platform Driver
Catalyst 9.3
Graphics Driver
GeForce 185.63
Benchmark Configuration
Mainconcept Reference 1.6.1
MPEG-2 to H.264, 28 second HDTV clip (1920x1080)
TMPGEnc 4.0 XPress
DivX 6.8.5, Xvid 1.2.1 Video: Terminator 3 SE DVD (720x576) 5 min. Audio: Dolby Digital, 48000 Hz, 6-channel, English
Lame 3.98
64-bit .exe, Audio CD "Terminator II SE," 53 min., .wav to .mp3 @ 160 kbps
WinRAR 3.80
Compression = Best, Benchmark: THG Workload


In Mainconcept, an extra 2 MB of cache buys a second off of the encoding job's time. But the addition of a fourth core to the X3 knocks 41 seconds off of the same task. Clearly, in applications able to take advantage of multiple cores, turning an X3 into an X4 yields more performance than getting a slightly higher overclock, for instance.

Again, we see the cache help a little bit. But the 2.8 GHz Phenom II X3 turns in better times for the latest version of Xvid due to its clock speed advantage over the X4 810. In DivX 6.8.5, the fourth core helps AMD's Phenom II X4 810 turn in better times. But a combination of four cores and an extra 200 MHz shows the unlocked X3 720 in the most favorable light.

Clock speed reigns supreme here, and LAME doesn't care about more cache or a fourth core.

WinRAR is the only application that we ran able to demonstrate the gains of an extra 2 MB of L3 cache. Because the app is also threaded, the quad-core X4 810 ends up performing close to the quicker X3 720.

Create a new thread in the US Reviews comments forum about this subject
This thread is closed for comments
65 comments
Comment from the forums
    Your comment
    Top Comments
  • cangelini
    Well, but the point isn't the benchmarks. We already know that most games are going to be limited more by graphics horsepower versus whether a CPU has three or four cores/4MB shared L3 or 6MB shared L3.

    In fact, when it comes to gaming, you're going to be better off looking for the fastest overclock possible with your three good cores or 4MB of known-good cache, really.
    13
  • Other Comments
  • dirtmountain
    Good article. Now if you can just get your ad clowns from sticking us with those annoying ads.....!
    7
  • Anonymous
    test them with games... some people care about that :P
    2
  • cangelini
    Well, but the point isn't the benchmarks. We already know that most games are going to be limited more by graphics horsepower versus whether a CPU has three or four cores/4MB shared L3 or 6MB shared L3.

    In fact, when it comes to gaming, you're going to be better off looking for the fastest overclock possible with your three good cores or 4MB of known-good cache, really.
    13
  • Anonymous
    omg you replied to me... i'm so honoured :P

    but yes, i agree... but if you had crossfire gpus, this would make a difference. but then again, i think you'd have the money to buy the real thing (phenom II 920)
    1
  • tacoslave
    i like this article toms should do more stuff like this.
    5
  • apache_lives
    Page 3 "it ran for an hour sans error before we shut it down" - mistake?

    Me wonders if extra v's would help both to the memory, HTT and cores etc, or underclock that extra core if possible....

    On the other hand as all overclockers/modders should be aware THERE'S NO GUARANTEE on what you can get out of your hardware etc.

    Out of interest, is the third core ("Core 2"... LOL) still always the culprit of every X3 (unlockable or not)?

    Now if only there was some super secret on modding my Q6600 into a i7 940.....
    -11
  • cangelini
    Hey Apache! No error, sans = without.
    2
  • apache_lives
    still reads wrong to me?
    -10
  • Summer Leigh Castle
    Good article but can someone explain how ACC % works? Also, where do we start in terms of ACC % if we're tweaking for stability?
    2
  • ravenware
    cangeliniHey Apache! No error, sans = without.


    The only reason I know that is because of Wayne's World2.
    -1
  • cangelini
    I do wish I could give you more detail on ACC, but AMD has played that card close to its chest. In terms of where to start, I'd say "Auto" is your best bet, and then move up and down in 2% increments in each direction.
    0
  • raden_muaz
    can you compare it with PII 910? PII 810 have higher clock speed.
    0
  • Slobogob
    Great article. Reminds me of how Tomshardware used to be.
    9
  • empstar
    this reminds me of the 1st Athlon with gold finger and the athlon with the "tape" on top to link connection for Socket A. 1998 I start reading this web..... :-) where is Dr. Toms P go ? I wonder..
    3
  • apache_lives
    tom sold it ;)
    0
  • empstar
    sold it to Bestofmedia? omg since when?
    0
  • Pei-chen
    AMD is not overclocker friendly by locking the multiplier, cores and cache. What happened to the AMD in Athlon and Athlon XP era?
    0
  • apache_lives
    Pei-chenAMD is not overclocker friendly by locking the multiplier, cores and cache. What happened to the AMD in Athlon and Athlon XP era?


    its called sales - if your $100 processor was the same as your $500 processor why would you buy the $500 processor?
    2
  • neiroatopelcc
    I supposed it wouldn't be impossible to custom tailor a bios for a non asrock board. I haven't dared try (nor needed to), but I expect it to be quite likely you could just extract the microcode from an older, working, asrock bios, and replace the code in your gigabyte, asus or whatever bios with it. All I think that is required, apart from knowledge on bios tinkering I don't have, is a 750 chip on the board.
    1
  • apache_lives
    i believe it depends partly on the IO chip too (usually one of those ITE 87xx chips), then flash part type, rom size, bios brand (award, AMI etc) - beyond most of us and more for the motherboard engineers etc.
    -1