AMD Ryzen CPU Reviews and Previews (3000 series)

Discussion in 'PC Industry' started by xEx, Jul 7, 2019.

  1. xEx

    xEx
    Regular Newcomer

    Joined:
    Feb 2, 2012
    Messages:
    939
    Likes Received:
    398
    By 2022 AMD will probably be at 5nm...Oh the irony...
     
  2. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    1,175
    Likes Received:
    578
    Location:
    France
    Yeah but not all XXnm are equals. The first 10nm by Intel was very ambitious, being better in some aspect that today 7nm by tsmc. It didn't work out, but "5" isnt always better than "7".
     
  3. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,496
    Likes Received:
    910
    TSMC's 5nm is fairly likely to be better than Intel's 10nm, though, at least in power-efficiency around 4.5GHz.
     
  4. DieH@rd

    Legend Veteran

    Joined:
    Sep 20, 2006
    Messages:
    6,122
    Likes Received:
    2,050
  5. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    The chiplet layout is very compact and "skinny" regarding I/O. AMD made a wise choice to separate all the PHY junk away from the high-speed CPU design.
     
    #45 fellix, Jul 12, 2019
    Last edited: Jul 12, 2019
  6. DieH@rd

    Legend Veteran

    Joined:
    Sep 20, 2006
    Messages:
    6,122
    Likes Received:
    2,050
    Next up, they could add a small GPU on every IO die.
     
    Lightman likes this.
  7. fehu

    Veteran Regular

    Joined:
    Nov 15, 2006
    Messages:
    1,462
    Likes Received:
    395
    Location:
    Somewhere over the ocean
    How much space is taken by IF?
    The IO chiplet is so big that until some point I was sure that all the L3 cache was there.
     
  8. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    On the chiplet, the IF phy is right smack in the middle between the two CCX clusters (flanked by the L3 arrays).
    Looking at the I/O chip, the Rx and Tx pads of the IF phy does seem to be symmetrical in size, so no evidence of half-width upstream link there, unless the upstream link is half wired in the substrate package.
     
    #48 fellix, Jul 12, 2019
    Last edited: Jul 12, 2019
    fehu likes this.
  9. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    #49 fellix, Jul 12, 2019
    Last edited: Jul 12, 2019
    Lightman, Alexko and BRiT like this.
  10. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
    Asus publishes X470 and B450 PCIe Gen 4 compatibility chart

    https://hexus.net/tech/news/mainboard/132656-asus-publishes-x470-b450-pcie-gen-4-compatibility-chart/


     
    Lightman and BRiT like this.
  11. sir doris

    Regular

    Joined:
    May 9, 2002
    Messages:
    651
    Likes Received:
    110
    Seems odd that the ROG boards are the ones which DON'T support PCI-e Gen 4 :shock:
     
    digitalwanderer likes this.
  12. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    Thread sync latency charts:

     
  13. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    1,175
    Likes Received:
    578
    Location:
    France
    I don't get why 3700x is "slower" than 3900 in this thing ?
     
  14. digitalwanderer

    digitalwanderer Dangerously Mirthful
    Legend

    Joined:
    Feb 19, 2002
    Messages:
    17,270
    Likes Received:
    1,785
    Location:
    Winfield, IN USA
    I agree, Asus seems to like to throw everything and the kitchen sink in their ROG stuff regardless of cost 'cause they just jack the price up and pass it along to the consumer, I don't get why they don't have it either.
     
  15. digitalwanderer

    digitalwanderer Dangerously Mirthful
    Legend

    Joined:
    Feb 19, 2002
    Messages:
    17,270
    Likes Received:
    1,785
    Location:
    Winfield, IN USA
    3700 < 3900, DUH!

    (Just teasing, I have no clue what I'm talking about but it sounded perfectly sarcastic so I couldn't resist. My apologies. ;) )
     
    Rootax likes this.
  16. Pressure

    Veteran Regular

    Joined:
    Mar 30, 2004
    Messages:
    1,338
    Likes Received:
    271
    Doesn't the ROG boards reserve 4 lanes from the CPU to the chipset or something?
     
  17. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,496
    Likes Received:
    910
    The 3700X seems to be locked at 4.0GHz here. Presumably, the 3900X isn't, so since the results are in ns and not cycles, it could simply be due to the clock speed difference.
     
    Lightman, Rootax and BRiT like this.
  18. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    The IO chiplet's size is very near the estimated non-core area of a Summit Ridge Zen, which leaves little leeway for a die still at 12/14nm. The Zen 2 CPU chiplet is smaller, but the L3 looks to be the dominant consumer of area on that chip and its area would be noticeable on the IO die. Since the IO die can support 2 CPU chiplets, having the L3 for two would be very noticeable.

    I didn't see any major asymmetry in those arrays either, although I'm curious if the area the IO die devotes to those presumed IFOP links is similar to what they were on Summit Ridge. I recall it being stated that the links are double in width, but they seem bigger or at least the PHY appear more noticeable than before.
    I'm not seeing a visually similar area on the CPU die, unless it's lost in the glare on one side. Perhaps the PHY chosen for the chiplets differ so much because of the node difference. Although if perhaps the CPU-side PHY sacrificed drive strength for area or somehow didn't match well with the chunky PHY on the IO die, running the data path that the CPU side needs to drive at a slower speed could save power or allow for better compatibility.
     
  19. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    Hi-res chiplet shot:


    Is it me, or the L1i cache array is way too large for 32KB? The L1d cache looks fine, though.
    Another thing, the two FMA/SIMD pipes are now clearly distinguishable. Looks like AMD made a new layout for that part of the architecture, not just extend the data paths to 256-bit.
     
  20. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    8,184
    Likes Received:
    1,840
    Location:
    Finland
    All the boards do, it's the connection AMD uses between SoC and FCH or whatever the latest acronym for their "chipset" is
     
Loading...

Share This Page

  • About Us

    Beyond3D has been around for over a decade and prides itself on being the best place on the web for in-depth, technically-driven discussion and analysis of 3D graphics hardware. If you love pixels and transistors, you've come to the right place!

    Beyond3D is proudly published by GPU Tools Ltd.
Loading...