Skip to main content

Linux Driver Indicates AMD Vega 20 Graphics Could Support PCIe 4.0

A piece of code from AMD's latest Linux driver indicates that the company's upcoming Vega 20 graphics cards will come with support for the high-speed PCI-Express 4.0 interface.

The PCI-Express 3.0 interface has been around for quite some time now. Strangely enough, the eight-year-old standard has been holding up strong. Not even the current graphics cards on the market come close to saturating a PCI-Express 3.0 x16 slot. Nevertheless, the next-generation of graphics cards could possibly change that--or at least that's what AMD might be trying to tell us.

AMD's Vega 20 graphics cards were already the subject of numerous rumors, even before the company revealed one at Computex this year. One of those rumors was that the Vega 20 architecture could possibly make use of the latest PCI-Express 4.0 interface. Thanks to AMDGPU, AMD's open-source Linux graphics driver for Radeon graphics cards, it seems that rumor has some truth to it. A snippet of the driver revealed an entry that references to the recent PCI-Express 4.0 specification. So, the company's soon-to-be-released (at least we hope) Vega 20 graphics cards may be the first products on the market to exploit the PCI-Express 4.0 specification's attributes.

PCI-SIG officially finalized the PCI-Express 4.0 specification not so long ago. Among the specification's numerous advancements, it promised to deliver up to 16 GT/s (1.969 GB/s) of bandwidth per PCI-Express lane, doubling the previous PCI-Express 3.0's 8 GT/s (985 MB/s) bandwidth. Doing some simple math shows that a PCI-Express 4.0 x16 slot bears up to 31.51 GB/s of bandwidth--a massively wide pipe for pixel pushing. It will be interesting to see whether AMD's Vega 20 graphics card with its 32GB of HBM2 memory can effectively make a PCI-Express 4.0 x16 lane sweat. 

Since cutting-edge technology normally takes a bit to proliferate, it might take a while before motherboards with PCI-Express 4.0 slots become vailable. Hopefully by the time AMD's Vega 20 graphics card is out, there is a motherboard capable of taking advantage of the new super-fast interface. Here's hoping we'll soon see a single card that's capable of pushing those new Asus and Acer 4K 144Hz monitors to their limits. Our eyes are ready--even if our wallets aren't.

  • Giroro
    I must not understand what "Vega 20" is, because based on AMD's current naming scheme that would make it a chopped down current-gen GPU with 1/3 the compute units of Vega 64.
    But there's no way they would pair 32GB HBM2 with something like that.
    Reply
  • jeremyj_83
    Vega 20 refers to the project code. The current Vega 64 is based on the Vega 10 core. Therefore Vega 20 is the next iteration of Vega 10.
    Reply
  • Martell1977
    So maybe this is a view into what Ryzen 2 will bring with a new chipset.

    People with current Ryzen products would still be able to use the Ryzen 2 CPUs, as all PCIe standards are backwards compatible, but without the new chipset, will remain on PCIe3. Since AMD said they will stay on the same socket for the next year and a half.
    Reply
  • Gillerer
    As far as anyone (outside AMD) knows, the 7 nm Vega 20 will only make its way into professional Radeon Instinct Vega cards (the one in the "reveal" link in the article). At least AMD have given no indication of planning on releasing new consumer/gaming GPUs before Navi. That means there is really no need for PCIe 4 to be supported by Ryzen CPUs or on AM4 motherboards for now - at least not due to Vega 20 - Navi may be another matter.

    The reason AMD went with pro-only for Vega 7 nm has supposedly to do with adopting GlobalFoundries' new 7 nm process and the expectation of difficulties in sustaining high-enough yields in the first few months to a year. By selling the GPUs as professional products (with appropriate high margins), AMD can make a profit with considerably lower number of viable dies off the wafer. The volumes on professional GPUs are also lower than consumer ones, so GF can more easily continue to tune their production without affecting end output too much.
    Reply
  • jimmysmitty
    21100300 said:
    As far as anyone (outside AMD) knows, the 7 nm Vega 20 will only make its way into professional Radeon Instinct Vega cards (the one in the "reveal" link in the article). At least AMD have given no indication of planning on releasing new consumer/gaming GPUs before Navi. That means there is really no need for PCIe 4 to be supported by Ryzen CPUs or on AM4 motherboards for now - at least not due to Vega 20 - Navi may be another matter.

    The reason AMD went with pro-only for Vega 7 nm has supposedly to do with adopting GlobalFoundries' new 7 nm process and the expectation of difficulties in sustaining high-enough yields in the first few months to a year. By selling the GPUs as professional products (with appropriate high margins), AMD can make a profit with considerably lower number of viable dies off the wafer. The volumes on professional GPUs are also lower than consumer ones, so GF can more easily continue to tune their production without affecting end output too much.

    Much like Tesla. Makes sense. They probably want to break into the HPC and professional market more.

    It will be interesting to see what the 7nm yields are like to start.

    Also I don't think HBM2 can make PCIe 4 sweat. PCIe 3 is fine with current GPUs with HBM2. In fact PCIe 4 will probably further increase the odds that consumer cards wont saturate the lanes.
    Reply
  • DerekA_C
    21100521 said:
    21100300 said:
    As far as anyone (outside AMD) knows, the 7 nm Vega 20 will only make its way into professional Radeon Instinct Vega cards (the one in the "reveal" link in the article). At least AMD have given no indication of planning on releasing new consumer/gaming GPUs before Navi. That means there is really no need for PCIe 4 to be supported by Ryzen CPUs or on AM4 motherboards for now - at least not due to Vega 20 - Navi may be another matter.

    The reason AMD went with pro-only for Vega 7 nm has supposedly to do with adopting GlobalFoundries' new 7 nm process and the expectation of difficulties in sustaining high-enough yields in the first few months to a year. By selling the GPUs as professional products (with appropriate high margins), AMD can make a profit with considerably lower number of viable dies off the wafer. The volumes on professional GPUs are also lower than consumer ones, so GF can more easily continue to tune their production without affecting end output too much.

    Much like Tesla. Makes sense. They probably want to break into the HPC and professional market more.

    It will be interesting to see what the 7nm yields are like to start.

    Also I don't think HBM2 can make PCIe 4 sweat. PCIe 3 is fine with current GPUs with HBM2. In fact PCIe 4 will probably further increase the odds that consumer cards wont saturate the lanes.

    I would agree with not saturating the lanes until they start doing mGPU or 3d stacked GPU pcb's which GF said they are now capable of doing as of 2 months ago.
    Reply
  • P1nky
    21100300 said:
    The reason AMD went with pro-only for Vega 7 nm has supposedly to do with adopting GlobalFoundries' new 7 nm process and the expectation of difficulties in sustaining high-enough yields in the first few months to a year.

    AMD publicly said that Vega 7nm is built by TSMC.

    Reply
  • Giroro
    If you replaced PCIe 3.0 x16 with PCIe 4.0 x8, then that would most likely free up some high speed lanes for other stuff.
    Reply
  • Martell1977
    I wonder how much difference in lane traffic there is between SLI and Crossfire considering that Crossfire doesn't use a bridge.
    Reply
  • bit_user
    21099832 said:
    It will be interesting to see whether AMD's Vega 20 graphics card with its 32GB of HBM2 memory can effectively make a PCI-Express 4.0 x16 lane sweat.
    In the linked Computex article, there's mention of Vega 10 using PCIe for inter-device communication and reference to NVLink. Much like NVLink, AMD's Infinity Fabric can run a cache-coherent interconnect over PCIe. That's what it's about - multi-GPU configurations for deep learning and HPC.

    I expect EPYC 7 nm will also support PCIe 4.0.
    Reply