Servers

Polywell Computers has extensive experience in building server systems of all types. Currently, we are focusing on high-performance rack systems in 1U, 2U and 4U form factors based on Intel Xeon and AMD EPYC processors. These systems can be divided into 3 groups:

• General purpose servers
• Multi-site servers
• GPU Servers

General purpose servers are intended for use as file, cloud, virtual, computing servers, and database servers. They feature state-of-the-art Xeon and EPYC server processors, significant RAM support, and hot-swappable disk drives. The latter can have both a SATA interface and the fastest NVMe interface for solid state drives. There are also two connectors for connecting SATA-DOM modules. They feature various network interfaces - including 10 GbE Ethernet, SFP+, IPMI 2.0, OCP 3.0.

Multi-site servers combine 4 servers in a single 2U chassis. This is useful when you need to save rack space. Shared power supplies (2 2600 W power supplies installed) also save space and energy for powering and cooling servers. This layout is especially useful for computer or failover clusters, or for virtualization. The most popular solutions are from Microsoft, Stratus, Citrix, VMware. All of them will utilize redundant hardware resources. Each of the four nodes supports the latest Intel or AMD processors, up to 4 TB of memory, six 2.5" disk drives, 1 slot OCP 3.0 for network modules , and one IPMI 2.0 (Intelligent Platform Management Interface) module.

GPU servers are designed for high performance computing (HPC), GPU computer clusters, artificial intelligence, and deep machine learning. These are available in a 2U form factor, with 4 GPUs NVIDIA® HGX A100 GPU 40GB / 80GB, NVLink, NVSwitch and 4U form factor with 8 GPUs NVIDIA® HGX A100 GPU 40GB / 80GB, NVLink, NVSwitch. Some models can support up to 8 TB (12 TB) of memory, have up to 4 (6) drives in the 2.5 ”form factor, and 2 x 10GbE network adapters or 1 OCP 3.0 slot for network modules. With the GPU-powered Polywell servers, AI acceleration can increase up to 20x and HPC acceleration up to 2.5x, over previous generations of GPUs.

_______________________________________________________________________________________________________________________________________________