Android 2.2 - as fast as you wished!

Discussion in 'Android News' started by RinTinTigger, May 12, 2010.

  1. RinTinTigger
    Offline

    RinTinTigger Premium Member Premium Member

    Joined:
    Nov 4, 2009
    Messages:
    2,905
    Likes Received:
    2
    Trophy Points:
    0
    Location:
    Germany, Near Frankfurt/Main
    [​IMG]

    AndroidPolice now got a Nexus One with Froyo (Android 2.2) for testing and one thing they did, was Benchmarking the System, to show how fast it is. Expectations are pretty high, as FroYo is expected to come with JIT (Just in Time Compilation).

    Now, they used the app Linpack, which measures all Benchmarks in FLOPS (floating point operations per secound).

    the nexus one has been tested with 6.5 MegaFLOPS, which is very fast, compared to a Hero with 2 MFLOPS. but now, how is FroYo doin on the Nexus?

    PWNAGE! It shot 37.5 MFLOPS!! this is 5 times faster as 2.1 is....just one more reason to sincerely wait for android 2.2!!

    Tigger
    via
  2. Hugh Jass
    Offline

    Hugh Jass Well-Known Member

    Joined:
    Feb 7, 2010
    Messages:
    1,568
    Likes Received:
    67
    Trophy Points:
    48
    I'm dying to know how this will translate to the Droid. Hopefully we get similar results with the JIT working good.
  3. J. Dub
    Offline

    J. Dub New Member

    Joined:
    Nov 30, 2009
    Messages:
    220
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    In yo intanetz!!!
    I'm confused. Did you say this cause there are some that aren't on 2.1 yet?
  4. JhankG
    Offline

    JhankG New Member

    Joined:
    Nov 1, 2009
    Messages:
    3,098
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    Summerfield, NC
    ^I think he meant 2.2.
  5. Darkseider
    Offline

    Darkseider New Member

    Joined:
    Mar 12, 2010
    Messages:
    1,866
    Likes Received:
    0
    Trophy Points:
    0
    Just ran the linpack on BB v1.0 running @ 800Mhz and I score a consistent 6.4xx MFlops. So it seems that the Droid at 800Mhz is roughly the equivalent to the Nexus at 1Ghz when it comes to floating point ops. Now the question is whether or not JIT translates to real world performance or just some increase on a synthetic benchmark.
  6. Data
    Offline

    Data Member

    Joined:
    Jan 30, 2010
    Messages:
    42
    Likes Received:
    0
    Trophy Points:
    6
    Location:
    N.E. Ohio
    is moto droid going to get 2.2 ?
  7. Hugh Jass
    Offline

    Hugh Jass Well-Known Member

    Joined:
    Feb 7, 2010
    Messages:
    1,568
    Likes Received:
    67
    Trophy Points:
    48
    I get 9.915mflops in linpack with BB1.0 at 1.2ghz lv. The JIT is doing something, that's for sure be it synthetic or not.
  8. Darkseider
    Offline

    Darkseider New Member

    Joined:
    Mar 12, 2010
    Messages:
    1,866
    Likes Received:
    0
    Trophy Points:
    0
    Umm... from what I see here LinPack scales nearly linearly with clockspeed.

    800 Mhz Droid = 6.4
    1.2 Ghz Droid = 9.9

    6.4 / 8 = .8
    .8 * 12 = 9.6

    So now the question is what JIT does to increase those numbers and is it an artificial result solely based on the benchmark? In order to see a real impact one would need to run some type of process intensive task, say converting a file to an .mp3, from the Droid console on a rooted device. Otherwise I would take this with a grain of salt.
  9. Zarniwoop
    Offline

    Zarniwoop New Member

    Joined:
    Nov 6, 2009
    Messages:
    21
    Likes Received:
    0
    Trophy Points:
    0
    Benchmarks, shmenchmarks.

    I don't give two craps about benchmarks...

    I want the snappy response the Incredible seems to have out of the box, and the battery life of a Saharan Camel. :)
  10. gatewayad
    Offline

    gatewayad New Member

    Joined:
    Nov 6, 2009
    Messages:
    521
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    St. Louis, MO
    I wonder how fast it is on 3g vs. the wifi they are running, haven'tweI seen high 25's on the droid on wifi
  11. gatewayad
    Offline

    gatewayad New Member

    Joined:
    Nov 6, 2009
    Messages:
    521
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    St. Louis, MO
    Where did the edit button go :(
  12. Darkseider
    Offline

    Darkseider New Member

    Joined:
    Mar 12, 2010
    Messages:
    1,866
    Likes Received:
    0
    Trophy Points:
    0
    What are you talking about?
  13. Hugh Jass
    Offline

    Hugh Jass Well-Known Member

    Joined:
    Feb 7, 2010
    Messages:
    1,568
    Likes Received:
    67
    Trophy Points:
    48
    The Droid News section has no edit, for whatever reason.
  14. gatewayad
    Offline

    gatewayad New Member

    Joined:
    Nov 6, 2009
    Messages:
    521
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    St. Louis, MO
    Sorry what I'm saying is isn't there a big speed difference doing a benchmark test on WiFi vs doing it on 3G
  15. gatewayad
    Offline

    gatewayad New Member

    Joined:
    Nov 6, 2009
    Messages:
    521
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    St. Louis, MO
    Thanks I will have to be better at spell checking then... Ha!
  16. Hugh Jass
    Offline

    Hugh Jass Well-Known Member

    Joined:
    Feb 7, 2010
    Messages:
    1,568
    Likes Received:
    67
    Trophy Points:
    48
    Then what explains the variation between the results for Droid and Nex? Differences in on board memory or cache?
  17. doublejack
    Offline

    doublejack New Member

    Joined:
    Apr 13, 2010
    Messages:
    76
    Likes Received:
    1
    Trophy Points:
    0
    I'm very skeptical that JIT could actually have this big of an impact in real world applications. I guess we'll see when it arrives.

    If you look at the records, people have scored into the 30's already on a Droid.
  18. Hugh Jass
    Offline

    Hugh Jass Well-Known Member

    Joined:
    Feb 7, 2010
    Messages:
    1,568
    Likes Received:
    67
    Trophy Points:
    48
    The linpack benchmarks are assessing the performance of the processor inside your phone, where as other benchmarks might assess the speed of your internet connection (such as speedtest.net) therefor the data connection is irrelevant in these tests. :)
  19. doublejack
    Offline

    doublejack New Member

    Joined:
    Apr 13, 2010
    Messages:
    76
    Likes Received:
    1
    Trophy Points:
    0
    LinPack scales linearly on a given platform. The Nexus One has a different CPU than the Droid, thus 1GHz on the Nex does not equal 1GHz on the Droid.
  20. Darkseider
    Offline

    Darkseider New Member

    Joined:
    Mar 12, 2010
    Messages:
    1,866
    Likes Received:
    0
    Trophy Points:
    0

    THIS. I don't see JIT having a huge impact on real world applications. There may be some performance boost but nothing like the 4.5 - 5x increase that the benchmark is seeing.