Comments Locked

21 Comments

Back to Article

  • testbug00 - Wednesday, May 17, 2017 - link

    I wonder if we will see a situation like with ARM. Where different design teams end up favoring different things. It *sounds* to me like AMD is having the Polaris Team to Navi, than Vega do Navi+1, and if it stays as planned, Polaris team on Navi+2, and Vega team on Navi +3.
  • testbug00 - Wednesday, May 17, 2017 - link

    An example for this is A72 versus A73.
  • milli - Wednesday, May 17, 2017 - link

    ATI has always had two concurrent working design teams. It's nothing new.
  • Gasaraki88 - Wednesday, May 17, 2017 - link

    nVidia has 2 design teams also since forever
  • FanboysMustDie - Wednesday, August 2, 2017 - link

    @Gasaraki88

    Who asked???
  • ingwe - Wednesday, May 17, 2017 - link

    Shouldn't Next Gen be 7nm- instead of 7nm+ :D
  • MrSpadge - Wednesday, May 17, 2017 - link

    Dude, you're so negative!
  • Stochastic - Wednesday, May 17, 2017 - link

    Is the designation "Next Gen" hinting at AMD finally moving beyond the GCN architecture, or am I reading too much into the name?
  • Tabalan - Wednesday, May 17, 2017 - link

    I really doubt "Next-gen" is not GCN based. Vega will bring many uarch improvements, Navi is supposed to greatly improve scalability (my prediction is that it will be multiple dies working as 1 GPU, but we will see). I assume that after Navi there will be one more GCN iteration summing up GCN archi and after this GPU division will follow CPU - completely new archi, but expanding GCN strong points. But well, that's just my assumption.
  • WinterCharm - Wednesday, May 17, 2017 - link

    My prediction for Navi is a bunch of modular GPU dies (think little Polaris or little Vega) joined with infinity fabric to each other and HBM....
  • mode_13h - Thursday, May 18, 2017 - link

    If you're saying CPU and GPU architectures will fuse, you're just wrong. GPU cores will be in-order, because that's where the power efficiency is. CPU cores will need to remain out-of-order, because that's how to get best single-thread performance. I used to think "hey, why not fuse them?", but then you end up with Xeon Phi, which is about half as fast as a GP100.

    Also, cache hierarchies & memory consistency guarantees rob CPUs of some power-efficiency & performance.
  • Tabalan - Thursday, May 18, 2017 - link

    That's not what I mean. I said that GPU division will follow CPU division - they will create brand new uarch, but it will be more of an expanse of GCN strong points. The same way they did with Ryzen.
  • peevee - Saturday, May 20, 2017 - link

    " GPU cores will be in-order, because that's where the power efficiency is. "

    Out-of-order can be still efficient, if it is not speculative.

    "CPU cores will need to remain out-of-order"

    Only because of some stupid inefficiencies in the current computer architecture.

    BTW, I have invented CPU/computer architecture which can replace not just GPUs, DSPs, ISPs and even fixed-function blocks (the latter with some efficiency loss, but not nearly as big as currently). Not Von Neumann-based at all. Nor it is Harvard. The future is bright. Physics will soon limit their ability to "innovate" by making transistors smaller and smaller (they already fail to produce honest reductions since 32nm, even having to prolong development cycles and switch from 2 y to 3 y cadence). Just like physics limited their ability to just raise frequency beyond 4GHz 12 years ago.
  • extide - Thursday, May 18, 2017 - link

    Honestly, I don't think scalability means multiple GPU dies... yet. I think it is referring to something different. What has been common all the way from Tahiti to Vega...? 4 chunks of CU's and thus 4 geometry engines. I am betting Navi will finally split that out more like nVidia does and have a finer granularity on the geometry engines because that has ALWAYS been a bottleneck on AMD GPU's.

    I think we are still a few more years away from multi-die GPU's acting as one... but yes, I do believe that will eventually be the future. I mean, 800+mm^2 GPU's are just ridiculous...
  • MajGenRelativity - Thursday, May 18, 2017 - link

    Vega already has the geometry engine improvements that you mentioned, but maybe Navi will be the first time we see chips actually go beyond a 4-wide frontend?
  • vladx - Wednesday, May 17, 2017 - link

    Wow that's bad, it's like he's saying "we actually have no plan".
  • jordanclock - Wednesday, May 17, 2017 - link

    That's not true at all. CPU and GPU architectures are planned and designed starting years in advance.
  • p1esk - Wednesday, May 17, 2017 - link

    Nvidia is crushing them so bad, they have no clue what to do next. Deep learning is where the money is/will be, and they don't even mention it.
  • Nicolii - Wednesday, May 17, 2017 - link

    You will find that AMD is partnering with Google in terms of deep learning, I don't think visibility will be a problem there.

    http://www.amd.com/en-us/press-releases/Pages/amd-...
  • p1esk - Wednesday, May 17, 2017 - link

    Yeah, that "partnership" was announced more than 6 months ago. No news since, and still no AMD GPUs on Google cloud...
  • peevee - Saturday, May 20, 2017 - link

    Well, this way I could update their "roadmap" until the year 3000. Just add more columns with "Next Gen" above them. Not like it is a binding promise or anything, AMD can be gone tomorrow with or without a roadmap.

Log in

Don't have an account? Sign up now