Page 1 of 7 123 ... LastLast
Results 1 to 10 of 69

Thread: AMD Radeon HD 8670D: Gallium3D vs. Catalyst

  1. #1
    Join Date
    Jan 2007
    Posts
    15,659

    Default AMD Radeon HD 8670D: Gallium3D vs. Catalyst

    Phoronix: AMD Radeon HD 8670D: Gallium3D vs. Catalyst

    This morning there were the RadeonSI Gallium3D vs. AMD Catalyst Linux benchmarks for the high-end Radeon HD 7850/7950 "Southern Islands" graphics cards. While the new Southern Islands GPUs understandingly have a long way to catch up on their new open-source Linux Gallium3D driver compared to Catalyst, how is the AMD Radeon HD 8670D "Richland" APU performance between the open and closed-source drivers? Here are some benchmarks.

    http://www.phoronix.com/vr.php?view=18874

  2. #2
    Join Date
    Dec 2012
    Posts
    459

    Default

    Doesn't make sense to do benchmarking of these cards while their most apparent and prominent performance bottleneck is being alleviated in a version that is +1 of the current one.

    Will be nice to compare differences though...

  3. #3
    Join Date
    Jun 2009
    Posts
    1,191

    Default

    well having in mind with kernel 3.10 APU can't reclock easily, it should improve by a lot with 3.11, i expect michael to try it once RC1 is out in the open

  4. #4
    Join Date
    Aug 2008
    Posts
    88

    Default

    Still no benchmarks with Source games like Left 4 Dead 2?

  5. #5
    Join Date
    Nov 2009
    Location
    Italy
    Posts
    1,000

    Default

    I will not even open page: without DPM it's completely useless. Also please benchmark an R600g (pre-radeonsi) APU too.

    Edit: Left 4 Dead 2 please.

  6. #6
    Join Date
    Jul 2009
    Posts
    99

    Default

    A10 6800k with the 8670 HD is an r600 APU (it's VLIW4)
    Last edited by ObiWan; 07-05-2013 at 06:30 PM.

  7. #7
    Join Date
    Jun 2009
    Posts
    2,937

    Default

    Quote Originally Posted by ObiWan View Post
    A10 6800k with the 8670 HD is an r600 APU (it's VLIW4)
    Indeed. And like all AMD APUs, it defaults to a low power state upon boot.

    So either you use a kernel with dynamic power management, or you manually set high profile, otherwise it's not a meaningful test. I'm assuming that the power state was left in a "default" state here.

    It's a lot like comparing a car with automatic transmission to a car with manual, but refusing to shift out of the first gear, because this is "the default" that new users will see. :P

  8. #8

    Default

    Quote Originally Posted by Rexilion View Post
    Doesn't make sense to do benchmarking of these cards while their most apparent and prominent performance bottleneck is being alleviated in a version that is +1 of the current one.

    Will be nice to compare differences though...
    Especially considering he's also using ram that is HALF of the rated stock speed for these chips. What little meaningless data he does get using the old kernel is further thrown off by having the GPU be constantly starved for data from memory.

    Phoronix should be renamed UselessReviews.com

  9. #9
    Join Date
    Jul 2009
    Posts
    99

    Default

    1066 Mhz is DDR3 2133,

    DDR3 1066 would be 533 Mhz

  10. #10

    Default

    Quote Originally Posted by darkbasic View Post
    I will not even open page: without DPM it's completely useless. Also please benchmark an R600g (pre-radeonsi) APU too.

    Edit: Left 4 Dead 2 please.
    Quote Originally Posted by ChemicalBrother View Post
    Still no benchmarks with Source games like Left 4 Dead 2?
    It's not like Valve doesn't make a dedicated benchmarking tool... I've got it installed here, and it most definitely is a native Linux program.

Posting Permissions

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