We use cookies to make your experience better. To comply with the new e-Privacy directive, we need to ask for your consent to set the cookies. Learn more.
GPU Solutions
Supermicro offers a wide variety of high performance GPU server solutions with massive parallel processing processing power and netowrking flexibility. With support for NVIDIA’s Tesla V100 GPUs, these solutions provide the parallelism needed for today’s high performance server applications such as AI. Supermicro GPU solutions are available in a 1U, 2U, 4U and Tower form factors with optomization for HPC workloads, Computational Finance and Oil and Gas Simulation. Nvidia NV-Link greatly improves the efficiency of parallel processing tasks by removing the bandwidth bottleneck associated with PCIe 3.0, which will translate to improved performance in applications such as AI. Supermicro GPU Servers can support up to 6TB DDR4-2933MHz Memory across 24 DIMM slots with support for Intel's 2nd Gen. Scalable CPUs and Optane DC Persistent Memory.
Deployed in fields such as:
Key Features/Applications:
AI/ML, Deep Learning Training and Inference, Big Data Analytics, High Performance Computing (HPC, Research Laboratory/National Laboratory
CPU:
Dual Socket P (LGA 3647) support 2nd Gen Intel® Xeon® Scalable processors
Chassis:
4U / 1 Node
Drive:
24x Hot-swap 3.5" drive bays
RAM:
24x DDR4 DIMM Slots
Network Ports:
2x 10GBase-T LAN ports