Page 2 of 6 FirstFirst 1234 ... LastLast
Results 11 to 20 of 51

Thread: Open-Source AMD HSA Should Come To Fruition This Year

  1. #11
    Join Date
    Oct 2012
    Location
    Sweden
    Posts
    343

    Default

    Doesn't the on-die GPU take up quite a bit of die space, though? Why not put say two extra CPU cores, or bigger cores on the die instead. Enthusiasts don't need the on-die GPU, do they?

  2. #12
    Join Date
    Apr 2014
    Posts
    157

    Default

    Quote Originally Posted by Khudsa View Post
    A little questions, has AMD abandoned the high end CPU market? No future high end, high performace CPU for the enthusiast market? Or the future for AMD is an high end - high performance APU paired with a high end GPU for the enthusiast - gamer market? Will be an APU with HSA direct rival for Intel core i7 for example?
    AMD's new SMT architecture is in the works for a 2015 release. It is said to be performance oriented.
    Considering this is the first processor to be completely designed around RCM it should be very good. Especially when AMD has Jim Keller at the wheels.

  3. #13
    Join Date
    Aug 2012
    Posts
    415

    Default

    Quote Originally Posted by xeekei View Post
    Doesn't the on-die GPU take up quite a bit of die space, though? Why not put say two extra CPU cores, or bigger cores on the die instead. Enthusiasts don't need the on-die GPU, do they?
    I'm guessing it's easier and cheaper to pack GPU shaders than extra cores, as in a CPU packed full of cores is more expensive than a CPU+GPU sharing the same die space. Theoretically they could probably release a 16 core FX right now though.

  4. #14
    Join Date
    Oct 2012
    Location
    Sweden
    Posts
    343

    Default

    Quote Originally Posted by mmstick View Post
    I'm guessing it's easier and cheaper to pack GPU shaders than extra cores, as in a CPU packed full of cores is more expensive than a CPU+GPU sharing the same die space. Theoretically they could probably release a 16 core FX right now though.
    I also realised they want stuff like floating point to be done on the GPU, which is only a realistic goal if all CPUs have on-die GPUs.

  5. #15
    Join Date
    Feb 2011
    Location
    Dominican Republic
    Posts
    46

    Default

    Quote Originally Posted by mmstick View Post
    I'm guessing it's easier and cheaper to pack GPU shaders than extra cores, as in a CPU packed full of cores is more expensive than a CPU+GPU sharing the same die space. Theoretically they could probably release a 16 core FX right now though.
    Theoretically, i'd be happy with a 6-module (12 core) FX @ 4.5GHz.

    To be honest, i'm quite pleased with my FX-8350, i'd like to see the FX series get a bit better, even if that would mean a new non backwards-compatible socket (AM4 or something).

  6. #16
    Join Date
    Mar 2013
    Location
    Porto
    Posts
    253

    Default amd need

    amd need to improve the single core performance a lot and not put more and more cores in their cpu, why is the point of a 16 core cpu if apps use no more than 6/8?

  7. #17
    Join Date
    Jul 2008
    Location
    Germany
    Posts
    695

    Default

    Quote Originally Posted by mmstick View Post
    Theoretically they could probably release a 16 core FX right now though.
    Look at the Opterons, there are some 16 Core CPUs. They have 2 DIEs on the same Package.

  8. #18
    Join Date
    Jun 2011
    Posts
    1,050

    Default

    Quote Originally Posted by rikkinho View Post
    amd need to improve the single core performance a lot and not put more and more cores in their cpu, why is the point of a 16 core cpu if apps use no more than 6/8?
    And just what real world application do you need more single thread performance for as opposed to more cores?
    Games? Nope, Core 2s are fine in terms of single thread performance for most games
    Compiling? There's a lot more to be gained by going parallel
    Spreadsheets? Nope
    Video Encode/Decode? That's offloaded to the GPU

  9. #19
    Join Date
    Jul 2008
    Location
    Germany
    Posts
    695

    Default

    Quote Originally Posted by Luke_Wolf View Post
    And just what real world application do you need more single thread performance for as opposed to more cores?
    Every Application profits from a higher single thread performance.

    Quote Originally Posted by Luke_Wolf View Post
    Games? Nope, Core 2s are fine in terms of single thread performance for most games
    benchmarks call you a liar.

    Quote Originally Posted by Luke_Wolf View Post
    Compiling? There's a lot more to be gained by going parallel
    Like the first but compiling is for most users irrelevant like weather calculations.

    Quote Originally Posted by Luke_Wolf View Post
    Spreadsheets? Nope
    Speadsheets on the gpu are useless. Look at the calculations. You can create a scenario thats runs very nice on the gpu but thats not the case for everything or the most.

    Quote Originally Posted by Luke_Wolf View Post
    Video Encode/Decode? That's offloaded to the GPU
    Decoding (Only for Playback, copy the frames to the system memory kills many benefits) yes but encoding not. The Hardware encoder doesn't provide the quality like a software encoder on the cpu. You can maybe use the ALU of gpu for some parts of the encoding (x264 can do this for some lookahead with opencl) but thats only interesting for HSA.

  10. #20
    Join Date
    Oct 2009
    Posts
    131

    Default

    Thanks for the responses!


    Thanks Bridgman! Interesting readings.

Posting Permissions

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