TYAN, an industry-leading server platform design manufacturer and subsidiary of MITAC Computing Technology Corporation, today introduced new AMD EPYC processor-based server solutions featuring large memory capacity and NVMe connectivity for high performance storage applications.
The AMD EPYC processor-based, 2U single-socket TN70A-B8026 server and single-socket S8026 server motherboard are designed for all-flash, high performance storage applications. The TN70A-B8026 supports 16 DDR4 DIMM slots, 24 hot-swap NVMe U.2 drives and 2 NVMe M.2 drives; the S8026 supports 8 OCuLink 8x (for NVMe U.2 drive connections), 2 NVMe M.2 and 2 SATA 6G connectors in EATX form factor. TYAN’s EPYC storage server platform and motherboard leverages the features of EPYC processor to provide a large number of direct-connected NVMe SSDs in a dense form factor without the use of PCIe switches.
“AMD EPYC processors are based on the 14nm “Zen” x86 core architecture with 32 cores and 64 threads, featuring 8 memory channels and up to16 DIMMs per socket. The new powerful processor allows TYAN to offer the optimal balance of computing, memory and I/O for our customers,” said Danny Hsu, Vice President of MiTAC Computing Technology Corporation's TYAN Business Unit. “By adopting the latest AMD EPYC processor technology, TYAN brings high memory channel bandwidth and PCI Express high speed I/O connectivity features to enterprises and datacenters.”
“The EPYC CPU is optimized to offer unprecedented levels of performance, bandwidth and connectivity for server platforms. TYAN maximizes the EPYC processor’s value in a 2U single-socket system to deliver high memory bandwidth, high I/O throughput, and high I/O & storage connectivity, and the performance normally seen in a dual-socket platform,” said Scott Aylor, CVP and GM, AMD Enterprise Solutions. “Our collaboration with TYAN not only enables customers to enjoy dual-socket capability with single-socket economics, but also drives the innovation to better address the needs of existing and emerging datacenter workloads.”
