• Metz@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    16 hours ago

    Most modern GPUs barely even use the full 4.0 bandwith. Hell, even 3.0 is still enough in many many situations.

    • Luccus@feddit.org
      link
      fedilink
      English
      arrow-up
      0
      ·
      16 hours ago

      Have you considered that we could reduce the number of lanes available and fuck some of our customers?

      • some GPU sales guy, probably
    • Schmuppes@lemmy.today
      link
      fedilink
      English
      arrow-up
      0
      ·
      18 hours ago

      I’ve recently upgraded to a 7900 XT graphics card and am running it at 3.0x16. A new SSD is waiting for me as well, which will actually be bottlenecked by my B450 board. It is what it is and will make no real world difference to me; the B450 will have to make do until AM6 is released.

  • SolidShake@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    23 hours ago

    This is why I’m still on a 3060 and will be for a few more years yet. There’s no point to upgrading.

  • MudMan@fedia.io
    link
    fedilink
    arrow-up
    0
    ·
    23 hours ago

    I’m confused. Are we mad at hardware research and development as a concept now or is what’s left of the tech press just stuck in permanent snark mode and just can’t physically write any other way?

    I mean, not every new standard is meant for home use primarily out of the gate and PCIe devices are backwards compatible with older standards, so… yay, people who need to build a very fast NAS will be able to chuck more, faster drives in there now. Good for them.

    • qaz@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      19 hours ago

      …is what’s left of the tech press just stuck in permanent snark mode and just can’t physically write any other way?

      It feels like it

  • MyOpinion@lemm.ee
    link
    fedilink
    English
    arrow-up
    0
    ·
    23 hours ago

    We can’t get decent video cards hardly at all let alone something that would use this.

    • Dudewitbow@lemmy.zip
      link
      fedilink
      English
      arrow-up
      0
      ·
      edit-2
      23 hours ago

      the advantage for pci-e generations isn’t the gpu side, but SSD side(USB too). CPUs by design, have a limited amount of PCI-E lanes they can distribute. Modern SSD’s primarily use 4x pci-e lanes, but if you have a generation newer, you can allocate half as many lanes to achieve the same speed.

      Since at the moment, the value of even faster SSD’s are useless, what ACTUALLY becomes off value is having multiple m.2 slots for expansion. for example, instead of having 1 m.2 running pci-e 4.0x4lanes, you can achieve the same speed at pci-e 5.0x2lanes, or pci-e 6.0x1lane. Using less lanes on m.2 slots means you can allocate more bandwidth to other components(more m.2, more USB ports, etc).

      this for eaxmple was the reason why experimental gpus like the Asus Dual RTX 4060ti existed, as its a 8 lane gpu, which had an on board to use the other lanes as ssd storage on motherboards that supported bifurcation.

  • remotelove@lemmy.ca
    link
    fedilink
    English
    arrow-up
    0
    ·
    23 hours ago

    I’m ok with this. Standards need to be developed years in advance for proper adoption. Without them, we can get weird arbitrary tech barriers… Like 640k RAM for example.