Could next gen consoles focus mainly on CPU?

Discussion in 'Console Technology' started by Theeoo, Jan 8, 2018.

  1. Shifty Geezer

    Shifty Geezer uber-Troll!
    Moderator Legend

    Joined:
    Dec 7, 2004
    Messages:
    42,958
    Likes Received:
    15,057
    Location:
    Under my bridge
    Why? Why not just Ryzen cores if they're putting them in?
     
    HBRU likes this.
  2. sniffy

    Newcomer

    Joined:
    Nov 14, 2014
    Messages:
    35
    Likes Received:
    28
    A cheaper alternative to Ryzen may be reworking Jaguar cores. IIRC AMD added additional pipeline stages when they moved from Bobcat to Jaguar in order to facilitate higher frequencies (originally 2GHz on the desktop, now 2.3GHz in X1X). Adding even more stages, while moving to a 3-wide design may be all that's required to feed beefier GPUs. Imagine a 3GHz Jaguar with 10-15% higher IPC. That's over 50% more CPU.
     
  3. McHuj

    Veteran Regular Subscriber

    Joined:
    Jul 1, 2005
    Messages:
    1,551
    Likes Received:
    735
    Location:
    Texas
    I'd really rather not imagine that. There's no point.

    Moving from one node to another node is not that difficult (companies basically off shore that type of work nowadays) adding a new decoder and additional pipeline stages is basically redoing the CPU design. Why waste the time and resources when their is a good scalable design available?
     
    milk, TheAlSpark and BRiT like this.
  4. sniffy

    Newcomer

    Joined:
    Nov 14, 2014
    Messages:
    35
    Likes Received:
    28
    I’d much prefer Ryzen as well but to play devils advociate, perhaps Sony/MS believe that a beefier GPU is an easier sell. The Pro and X were marketed using GPU TFLOPS and 4K/HDR. Prettier graphics may simply resonate more with the consumer than advanced AI/NPC counts. It’d probably demo better at a show like e3 at least.

    Improved Jaguars could offer acceptable performance while using less area, less power that must be shared with the GPU, all the while possibly offering the benefit of easier back compat. If you look at the X and Pro there’s a clear trend. Massively large GPU with just enough CPU to feed it. Do everything possible to limit CPU overhead and enable the offloading of tasks to the GPU.

    I think it’s working quite well for this generation of consoles tbh. Sony and MS may feel the same.
     
    HBRU likes this.
  5. bunge

    Regular Newcomer

    Joined:
    Nov 23, 2014
    Messages:
    725
    Likes Received:
    513
    What’s the next “best in class” CPU? Imagine whatever that will be and take whatever scraps get thrown to the trash heap because of redundancy failure and that’s what a console will get.
     
    milk likes this.
  6. HBRU

    Regular Newcomer

    Joined:
    Apr 6, 2017
    Messages:
    568
    Likes Received:
    97
    yea sniffy... I think that too... Having a shared memory with GPU a too strong CPU may be not fully used becouse it "steals" bandwidth to the GPU... but perhaps the unified memory approach may change
     
  7. Gubbi

    Veteran

    Joined:
    Feb 8, 2002
    Messages:
    3,580
    Likes Received:
    980
    The amount of bandwidth needed by the CPU is miniscule compared to the GPU.

    A Zen core has roughly three times the single thread performance of a Jaguar core. Comparing die area of 8 Jaguar cores to 8 Zen cores is thus misleading, - the same goes for power. You'd have to have 16 or 24 Jaguar cores to get the same throughput as eight Zen cores.

    Even if your sea of Jag cores matches the throughput of Zen cores, you still have to contend with the much lower single thread performance. That might not matter for titles built specifically for the platform, but it will matter for cross platform titles which use standard game engines. Your Jag based console is just one Player Unknown Battlegrounds-like sleeper hit away from being perceived as "last gen".

    Cheers
     
    DavidGraham, milk, TheAlSpark and 3 others like this.
  8. Shifty Geezer

    Shifty Geezer uber-Troll!
    Moderator Legend

    Joined:
    Dec 7, 2004
    Messages:
    42,958
    Likes Received:
    15,057
    Location:
    Under my bridge
    I guess the point isn't CPU usage, but CPU impact. PS4's bandwidth can get trounced by CPU access. When considering super-high bandwidth solutions, is there any option particularly strong/weak to access contention? Could HBM see massive latency or bandwidth penalties if GPU and CPU were making demands, for example?
     
  9. Gubbi

    Veteran

    Joined:
    Feb 8, 2002
    Messages:
    3,580
    Likes Received:
    980
    What's your definition of trounced ? The maximum impact I've seen is ~20GB/s of the 140GB/s total bandwith or ~15%.

    Cheers
     
  10. Allandor

    Regular Newcomer

    Joined:
    Oct 6, 2013
    Messages:
    367
    Likes Received:
    169
    I don't think so. Unified memory is the most "effective" for the long run. Just because it's up to the developer how to use the resources. Actually I'm a fan of seperate pools, but than your chip must have a second memory interface which also increases the cost for the chip.
    Well, I think I would prefer larger caches and one pool of memory, which also should be cheaper. Only if we have the situation like the xb360, when the memory is so much faster than the main memory, I could imagine 2 memory pools would be a good solution.
    HBM on the other hand ... still have not seen something that really get's better because of HBM. The current vega cards like fiji have other problems than memory bandwidth and GDDR5x can also be a problem for the CPU like we see with the current 1080TI cards and their compute results.
    I really hope GDDR6 memory is available soon and can be used for mass production with the next gen consoles. And I really hope they are not any worse for the CPU than GDDR5.

    The memory contention problem of the PS4 was worse than those 15%. If the CPU needed 10GB/s the bandwidth was reduced by ~30GB/s according to sonys own presentation. So a beefier CPU really need much more memory bandwidth to compensate.
     
    HBRU likes this.
  11. Shifty Geezer

    Shifty Geezer uber-Troll!
    Moderator Legend

    Joined:
    Dec 7, 2004
    Messages:
    42,958
    Likes Received:
    15,057
    Location:
    Under my bridge
    [​IMG]
    Down from ~140 for GPU to ~100 once the CPU has taken 10 GB/s. That's about a 30% drop.
     
  12. Gubbi

    Veteran

    Joined:
    Feb 8, 2002
    Messages:
    3,580
    Likes Received:
    980
    I see from ~135 to 110GB/s, ~19%

    Cheers
     
  13. HBRU

    Regular Newcomer

    Joined:
    Apr 6, 2017
    Messages:
    568
    Likes Received:
    97
    if you put 16 bettered Jaguars (maybe at 3.0 ghz) you have to buy on PC realm a 16 thrad CPU like Ryzen to run the SAME game... That means more sells of new CPUs for AMD and INTEL....
     
  14. Shifty Geezer

    Shifty Geezer uber-Troll!
    Moderator Legend

    Joined:
    Dec 7, 2004
    Messages:
    42,958
    Likes Received:
    15,057
    Location:
    Under my bridge
    That 110 GB/s includes the CPUs BW. It's 100 GB/s for GPU in this rough graph. Furthermore, the RAM is rated 176 GB/s, no? So from the theoretical peak BW available to GPU, we see a 55% reduction to what's actually available to the GPU when the CPU is busy. I can't recall the specifics of that 140 GB/s figure.
     
    BRiT likes this.
  15. HBRU

    Regular Newcomer

    Joined:
    Apr 6, 2017
    Messages:
    568
    Likes Received:
    97
    wich is really a LOT... Interesting to know if either GDDR6 or HBM2 can improve that... As I know even in 2013 for Sony and Ms was possible to use much stronger CPUs... But they choose Jaguars... Why ?
     
  16. Shifty Geezer

    Shifty Geezer uber-Troll!
    Moderator Legend

    Joined:
    Dec 7, 2004
    Messages:
    42,958
    Likes Received:
    15,057
    Location:
    Under my bridge
    AMD didn't have an APU with anything better than Jaguar. A stronger CPU would have meant discrete CPU and GPUs.
     
  17. fehu

    Veteran Regular

    Joined:
    Nov 15, 2006
    Messages:
    1,646
    Likes Received:
    615
    Location:
    Somewhere over the ocean
    Can a bigger smarter cache alleviate the problem?
     
  18. TheAlSpark

    TheAlSpark Moderator
    Moderator Legend

    Joined:
    Feb 29, 2004
    Messages:
    21,441
    Likes Received:
    6,904
    Location:
    ಠ_ಠ
    ala Crystalwell? Debatable if AMD could pull that off. :p
     
  19. fehu

    Veteran Regular

    Joined:
    Nov 15, 2006
    Messages:
    1,646
    Likes Received:
    615
    Location:
    Somewhere over the ocean
    I lack a lot of technical insights, but with infinity fabric moving to PCIe4 (or even 5 depending on timings) and EMIB-like interconnections, can we expect more budget dedicated to a separate cpu?
    Cheaper than a soc, more cache, more cores, less bw contention.
     
  20. MrFox

    MrFox Deludedly Fantastic
    Legend Veteran

    Joined:
    Jan 7, 2012
    Messages:
    6,328
    Likes Received:
    5,660
    Your 55% is mixing apples and oranges.

    You can't get an interface specs bandwidth in a real world usage. Unless all you do is reading the entire chip sequentially.

    You would get only a few % performance with random 1 byte read because the max clock without dead cycles depends on the prefetch size. And there are also penalties every time it switches bank or change read/write direction.

    You'd get the same thing on any memory. Gddr6 manages to increase the prefetch while keeping data granularity the same (256bits just like gddr5) so there's that.
     
    Shifty Geezer and iroboto like this.
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...