Comments Locked

326 Comments

View All Comments

  • Cellar Door - Monday, June 10, 2019 - link

    Ryan - do you know if vega 56 and 64 are EOL?
  • RaV[666] - Monday, June 10, 2019 - link

    Can you think of one reason to make them ?
    I mean they will be made, as in vega10 chips for datacenters but for gaming, theyre gonna have higher MUCH higher asps on 5700
  • AshlayW - Monday, June 10, 2019 - link

    Yes Vega 10 is being made for Google Stadia gaming as they use PRO V340 cards with dual "Vega 56" GPUs. GCN still is better for Compute and HPC I think, but Vega 20 will largely succeed that in HPC. GCN is not going anywhere.

    Oh, I do not think Vega 10 is cheaper to make than Navi 10. Yes the process is mature and cheaper, but the die is almost 2X the size and you factor HBM2 and interposer cost into that and the price is largely in the same ballpark.

    Navi 10 cannot do a "V340" style card easily, or as effectively, as Google Stadia needed graphics density and the on-package memory on Vega 10 makes the overall space requirements much smaller, so yes Vega 10 is likely to be made still, and itself is much cheaper than Vega 20.
  • mode_13h - Monday, June 10, 2019 - link

    Why would 2x Navi's be so much worse than 1x Hawaii? You're talking about 512-bits of memory data bus, in each case - just one compute die vs. two.
  • AshlayW - Tuesday, June 11, 2019 - link

    What? where did you get Hawaii from? V340 uses "Vega 10" which has on-package HBM2 instead of GDDR5. That is a major advantage for space saving when putting multiple GPU packages on the same card.
  • mode_13h - Wednesday, June 12, 2019 - link

    My point was that Hawaii cards use 512-bits of datapath on a single card, so perhaps 2x 256-bit Navi's can fit.

    Regarding density, I don't see your point. From a server's perspective, a PCIe card is a PCIe card, unless it's low-profile, which I don't think it is.
  • olafgarten - Monday, June 17, 2019 - link

    They might not be using standard PCIe or maybe putting multiple chips on a single card. Either way density helps.
  • Acreo_Aeneas - Sunday, June 30, 2019 - link

    Servers would likely have to use PCI-e LP or mini PCI-e. In whichever case, most servers are built more for memory I/O and storage performance and capacity (with also a focus on CPU performance) rather than on how powerful the GPU is onboard. Most servers are even headless and don't even have GPUs on board. The few that do usually use theirs for interfacing with a terminal.

    This does not include server or server farms built specifically for mutli-gpu setups. Usually that is scientific/graphics oriented or with the increasing niche of bitcoin mining.
  • WaltC - Thursday, July 4, 2019 - link

    Pretty sure I heard Su mention that NAVI included (at the "Rdna" level) improvements to compute. We'll know in a few days, of course. (Impatience makes time drag, eh?...;)) I don't usually do this, but *provided I can buy a 5700XT for either $499 (20th anniversary) or $449 MSRP* I'll be buying one next week. I'm going to be rather ticked off if the prices for the card a grossly inflated! Here's hoping AMD will control this much better than than happened at the RX-480's debut--what makes me shudder a bit is that I just read some days ago that Bitcoin stock was on the rise again! Stadia servers are likely only using Vega now because NAVI simply wasn't available when they began. Should change in a couple of weeks, possibly.
  • Ryan Smith - Monday, June 10, 2019 - link

    As far as consumer cards go, they've been drawing down inventory from the market for a couple of months now. I don't know if they've been formally discontinued, but they may as well be de-facto done for.

Log in

Don't have an account? Sign up now