Supermicro launched a new high density 4U GPU server which features an NVIDIA HGX A100 8 GPU baseboard. For the most demanding AI workloads, Supermicro has built high performing, fast-to-market servers which are based on NVIDIA A100™ Tensor Core GPUs. These servers can deliver up to 5 PetaFLOPS of AI performance in a single 4U system, with the help of the newest version of NVIDIA® NVLink™ and NVIDIA NVSwitch technologies.
Supermicro SuperMinute
Ideal for large-scale deep learning training and neural network model applications, this new 4U GPU system features up to 6 NVMe U.2 and 2 NVMe M.2, 10 PCI-E 4.0 x16 I/O, with Supermicro's unique AIOM support invigorating the 8-GPU communication and data flow between systems through the latest technology stacks such as NVIDIA NVLink and NVSwitch, GPUDirect RDMA, GPUDirect Storage, and NVMe-oF on InfiniBand.
To find out more about the SuperMinute, watch the video below. As usual, our Sales team are available to answer any questions or queries you may have - or call us on 01727 876100.