Huawei Aims for Desktop PC Market with Motherboard for Kunpeng 920 ARMv8 Processors

In yet another sign that Huawei is seeking to enter new markets, the company has posted details about a new desktop PC motherboard that is designed to house the company's Kunpeng ARMv8 processors that it typically uses for server infrastructure. These chips will come in four- and eight-core 7nm flavors for the initial desktop motherboards, but scale up to 64-cores and support PCIe 4.0 for the full-fledged server models. The new desktop PC motherboards and reference system designs, not to mention access to modern core-heavy chips, indicates that Huawei has plenty of options if it makes a serious effort at grabbing a piece of the desktop PC market. 

(Image credit: Huawei)
Paul Alcorn
Editor-in-Chief

Paul Alcorn is the Editor-in-Chief for Tom's Hardware US. He also writes news and reviews on CPUs, storage, and enterprise hardware.

  • BaRoMeTrIc
    what is up with the pcie full length slots being offset?
    Reply
  • Zizo007
    It won't be as fast as Epyc 64 core but its probably cheaper and have a much lower TDP. which makes it easier to stack. It will compete with AMD if Microsoft emulates x64 apps into ARM.
    Reply
  • AlistairAB
    Bring it! We are all waiting for desktop ARM motherboards.
    Reply
  • redgarl
    AlistairAB said:
    Bring it! We are all waiting for desktop ARM motherboards.

    SUre... and be ready for way inferior performances. As of now, ARM is only more interesting on paper. In real world application, beside the mobile market, there was nothing really spectacular or revolutionary.
    Reply
  • AlistairAB
    redgarl said:
    SUre... and be ready for way inferior performances. As of now, ARM is only more interesting on paper. In real world application, beside the mobile market, there was nothing really spectacular or revolutionary.

    Do you know that a Raspberry Pi is $35? That most of the money for your CPU is Intel's profit margin? I'm pretty sure the Chinese can make motherboards and ARM CPUs that outperform for less. It would only be about $50 for an A77 ARM quad core CPU. $75 for 6/8 cores (the latest Mediatek ARM CPU).

    Amazon has the scale to do something honestly also. Considering how awesome nVidia's plans in this area used to be and then they abandoned everything and made nothing new for 4 years... yeah, who knows.
    Reply
  • bit_user
    BaRoMeTrIc said:
    what is up with the pcie full length slots being offset?
    Maybe a server thing? Some cards won't have any external connectors, and therefore might not slot into the rear of the card cage.
    Reply
  • bit_user
    Zizo007 said:
    It won't be as fast as Epyc 64 core but its probably cheaper and have a much lower TDP. which makes it easier to stack.
    The article says:
    they feature the same 7nm process as AMD's chips, too, which brings about performance and efficiency advantages. For instance, the full-featured 64-core chips have a relatively tame 180W TDP. Those server-focused processors can also scale up to four sockets.

    IIRC, that's about the same as all but the fastest 7 nm Epycs (I'm thinking of the one that requires water cooling...).

    Zizo007 said:
    It will compete with AMD if Microsoft emulates x64 apps into ARM.
    There are other operating systems besides Windows.
    Reply
  • bit_user
    redgarl said:
    SUre... and be ready for way inferior performances. As of now, ARM is only more interesting on paper. In real world application, beside the mobile market, there was nothing really spectacular or revolutionary.
    Eh, we'll see. Amazon's Gravion 2 could be a really big deal, and ARM is supplying the same Neoverse N1 cores to Huawei.

    I'm just surprised they seem to be doubling down on ARM, but I guess they're already so heavily invested in it. I would think they'd head for RISC-V as soon as possible.
    Reply
  • w_barath
    BaRoMeTrIc said:
    what is up with the pcie full length slots being offset?
    They must expect one of the slots to always end up getting used for internal-only expansion. ie a dual NVMe adapter, an AI accelerator, an FPGA accelerator.
    Reply