Page 1 of 5 123 ... LastLast
Results 1 to 10 of 43

Thread: AMD Fusion A8-3850 APU "Llano" On Linux

  1. #1
    Join Date
    Jan 2007
    Posts
    15,378

    Default AMD Fusion A8-3850 APU "Llano" On Linux

    Phoronix: AMD Fusion A8-3850 APU "Llano" On Linux

    Late last month there were the first Radeon HD 6550D graphics benchmarks under Linux that were published on Phoronix. There has also been a stream of A8-3850 benchmark result uploads -- among other AMD Fusion APUs -- to OpenBenchmarking.org. In this review we are providing a set of computational benchmarks from this "Llano" Fusion APU compared to a handful of other systems in our labs.

    http://www.phoronix.com/vr.php?view=16292

  2. #2
    Join Date
    Dec 2007
    Location
    Edinburgh, Scotland
    Posts
    591

    Default

    The i3 and i5 processors aren't quad core, they're dual core with multi-threading, which you've shown in your own benchmarks doesn't make that much difference

  3. #3
    Join Date
    Oct 2010
    Posts
    74

    Default

    the i5 2500k nexuiz benchmarks dont look very realistic compared to toher nexuiz benchmarks of i5 2500k on phoronix .com.
    my own benchmarks show far more fraps with nexuiz and sandybridge.will present values soon

  4. #4
    Join Date
    Aug 2008
    Posts
    233

    Default

    Quote Originally Posted by FireBurn View Post
    The i3 and i5 processors aren't quad core, they're dual core with multi-threading, which you've shown in your own benchmarks doesn't make that much difference
    The i5 IS a quad core.

  5. #5
    Join Date
    Aug 2011
    Posts
    42

    Thumbs up

    Like to have in the system description sent to openbenchmark more detailed about the RAM. The size of the ram is not as important as the frequency of it for APU products. As far as I see the APU results differ for A8-3850 APU more than 33% with different RAM in the system. As is there is no evidence if the result of the processor is good or bad. I know phoronix is an one man show, so it may take longer to change this.

  6. #6
    Join Date
    Oct 2009
    Posts
    213

    Default

    Quote Originally Posted by FireBurn View Post
    The i3 and i5 processors aren't quad core, they're dual core with multi-threading, which you've shown in your own benchmarks doesn't make that much difference
    Wrong, the i5 is a physical quad-core.

  7. #7
    Join Date
    Oct 2010
    Posts
    74

    Default

    btw does sandy bridge and mesa support antialiasing?

  8. #8

    Default

    Quote Originally Posted by _ONH_ View Post
    Like to have in the system description sent to openbenchmark more detailed about the RAM. The size of the ram is not as important as the frequency of it for APU products. As far as I see the APU results differ for A8-3850 APU more than 33% with different RAM in the system. As is there is no evidence if the result of the processor is good or bad. I know phoronix is an one man show, so it may take longer to change this.
    Phoronix Test Suite already supports doing the DIMM modules, including frequencies. However, under Linux, this only works when PTS is run as root since it needs DMI access.... So either the Phoronix Test Suite needs to always be run as root or there needs to be a new way to export RAM information in Linux.

  9. #9
    Join Date
    Jul 2008
    Location
    Berlin, Germany
    Posts
    847

    Default

    Very nice review. Now that you have that USB power meter, could you publish power consumption figures for idle/gaming/compute too?

  10. #10
    Join Date
    Apr 2008
    Location
    Saskatchewan, Canada
    Posts
    466

    Default

    Quote Originally Posted by blackshard View Post
    Wrong, the i5 is a physical quad-core.
    Depends on which i5 you're talking about. I believe all the desktop i5s are quad-core, but my laptop's i5 is a dual core with hyperthreading (basically an i3 with Turbo enabled).

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •