As we wait for the big server juggernaut to support PCIe 4.0, a number of OEMs are busy creating AMD EPYC versions to fill that demand for high-speed connectivity. To date there have been two main drivers for PCIe 4.0: high-bandwidth flash storage servers, and high performance CPU-to-GPU acceleration, as seen with the DGX A100. As the new Ampere GPUs roll out in PCIe form, OEMs are set to update their portfolio with new PCIe 4.0-enabled GPU compute servers, including GIGABYTE, with the new G242-Z11.

One of the key elements to a GPU server is enabling airflow through the chassis to provide sufficient cooling for as many 300W accelerators as can fit, not to mention the CPU side of the equation and any additional networking that is required. GIGABYTE has had some good success with its multi-GPU server offerings, and so naturally updating its PCIe 3.0 platform to Rome with PCIe 4.0 was the next step.

The G242-Z11 is a 2U rackmount server that supports four PCIe 4.0 cards with a full x16 link to each. That includes the new A100 Ampere GPUs, as well as AMD MI50 GPUs and networking cards. The system supports any AMD Rome EPYC processor, even the 280W 7H12 built for high-performance tasks, and also has support for up to 2 TB of DDR4-3200 across eight channels with the MZ12-HD3 motherboard.

With these sorts of builds, it is often the periphery that helps assist integration into current infrastructure, and on top of the four PCIe 4.0 accelerators, the G242-Z11 supports two low profile half-length cards and one OCP 3.0 mezzanine card for other features, such as networking. The G242-Z11 also has support for four 3.5-inch SATA pays at the front, and two NVMe/SATA SSD bays in the rear. Power comes from dual 1600W 80 PLUS Platinum power supplies. Remote management is controlled through the AMI MegaRAC SP-X solution, which includes GIGABYTE proprietary server remote management software platform.

The new G242-Z11 will be available from September. Interested parties should contact their local GIGABYTE rep for pricing information.


Related Reading

Comments Locked


View All Comments

  • eSyr - Thursday, August 6, 2020 - link

    "big server juggernaut"—are you referring to IBM?
  • Spunjji - Friday, August 7, 2020 - link

    Intel - they haven't released PCIe 4.0 capable server hardware yet.
  • eSyr - Sunday, August 9, 2020 - link

    For the record, that was a joke about IBM being a big iron vendor that has PCIe 4.0 since 2017.
  • danjw - Thursday, August 6, 2020 - link

    "The G242-Z11 also has support for four 3.5-inch SATA pays at the front, and two NVMe/SATA SSD bays in the rear."

    I think you mean "3.5-inch SATA bays at the front,"
  • PeachNCream - Thursday, August 6, 2020 - link

    It looks like one GPU will be forced to ingest waste heat from another one in front of it if the server is fully populated. Atop that, there are four system fans supporting 3 GPUs (so ~1.33 fans each) and the one that will eat waste heat is cooled by 1 fan. Maybe it wouldn't be a problem, but its a noteworthy compromise to achieve that sort of density in a 2U chassis.
  • DanNeely - Thursday, August 6, 2020 - link

    The nature of long-narrow rackmount systems is such that some components inevitably get heat soaked by something else. The systems are designed to handle it. Mostly by using extremely high RPM fans so that even hot air is sufficient to keep hardware operating within thermal limits. The catch is that keeping a high TDP part from overheating with hot air requires extremely loud fans; and while it doesn't matter in the data center, it's definitely not going to be something you want to put in your office rack next to your desk.
  • PeachNCream - Thursday, August 6, 2020 - link

    Yes, thank you, but the explanation is not necessary. My professional responsibilities entail a modest data center presently and enterprise scale equipment administration is a substantial chunk of the last couple decades' of my work in information technology.
  • crimsontape - Saturday, August 8, 2020 - link

    Man, the internet is savage and petty.

    Dan, let me apologize on this persona's behalf - he is not peachy nor creamy. All that work and no play.
  • PeachNCream - Tuesday, August 11, 2020 - link

    I'm not sure why an observation about GPU placement and its implications for heat are worth getting so triggered. Some of you infer a lot of meaning that is simply not stated in order to spin yourselves into a frantic rage.
  • Smell This - Thursday, August 6, 2020 - link

    I think you wayyy over-thought this. I suspect residual pressure in the system would suck the chrome off a trailer hitch


Log in

Don't have an account? Sign up now