What are you looking for ?
Infinidat
Articles_top

Inspur Unveils Open Compute Project Standard Rack Server Solutions

Helping drive transformation of traditional to hyper-scale data centers based on open infrastructure

Inspur Electronic Information Industry Co.,Ltd jointly announced with the Open Compute Project (OCP) an OCP Standard Rack Server solution to help drive the transformation of traditional data centers to hyper-scale data centers based on open infrastructure.

Click to enlarge

Inspur OCP Rack-Scale

The announcement at the 2018 OCP Regional Summit in Amsterdam, The Netherlands, highlighted the server’s technical advancements and design attributes that deliver hyper-scale datacenter performance at lower CAPEX and OPEX.

The core value of open computing is to reduce the technical cost and lower technical threshold, so as to have stronger competitiveness and vitality. The development of open computing is gradually changing the needs of data centers-from traditional standardization to open technology-based customization,” said John Hu, CTO, Inspur. “Inspur’s vast experience in serving CSPs and our deep understanding of customer application scenarios is augmented by a willingness to share technology and co-design utilizing our joint design manufacture model to identify precise customer needs and achieve customized solutions through rapid innovation and productization. This new Rack Server solution announced with OCP demonstrates Inspur’s commitment to promote industry openness and integration.

The company’s rack server solution incorporates five node configurations; including three compute nodes based on Inspur San Jose Motherboard – the first OCP accepted Xeon Scalable processor motherboard-one JBOD and one GPU box.

These enrich the OCP hardware portfolio and create a new generation of rack scale solutions.

Meeting the increasing compute and storage demands being driven by emergent complex application scenarios and evolving business needs, Inspur improves functionality by enabling dynamic matching of requirements through advanced resource pooling, breaks the core IT resource expansion limit, and allows for the flexible allocation of resources, such as storage and co-processing calculations through the utilization of SAS and PCIe switching technologies. Key technical aspects include:

  • Compute node 1 (ON5163M5) – Designed for search engine acceleration, deep learning inference, data analysis application scenarios. This two-socket 1OU3 nodes, 96 nodes can be deployed in a standard Open Rack V2.0 cabinet. It can support 16 DIMMs, one M.2 interface, one OCP NIC and one PCIe x16 which can be configured with 10/25/40GbE cards and other full-length half-length network cards.

  • Compute node 2 (ON5283M5) – Designed for data acceleration, I/O expansion, transaction processing, image search application scenarios. This is two-socket 20U3 nodes with high flexibility, 16 DIMMs, one M.2, four 2.5″ HDD/NVMe SSD, three PCIe x8 can also support different kind of half-height and half-length external cards.

  • Compute node 3 (ON5273M5) – For NFV application scenarios, with a range of half-height and half-length external cards, which can also support 100GbE. It’s a 2-socket 2OU3 nodes, can support 16 DIMMs, two M.2, two 2.5″ NVMe SSD/HDD, two PCIe x16.

  • Storage node (ON5266M5) – 20U JBOD 34HDD, can support NVMe SSD/HDD, the highest density storage expansion box, which can be used as a storage expansion module for compute nodes or as a storage pool for the entire rack with SAS switch

  • AI node (ON5488M5) – GPU resource pooling solution, supporting up to 16GPU in 40U form factor, the highest density with most powerful computing performance available for AI training and inference scenarios. Providing flexible GPU typologies to meet different customer demands. PCIe switch enabled to offer GPU pooling solution.

  • Converge Redfish and OpenBMC – Company’s first converged OpenBMC with Redfish solution developed specifically for the firm’s OCP-certified solutions, a server solutions with a Redfish OCP baseline profile.

Click to enlarge

Inspur OCP Rack-Scale
Open source hardware is essential to the further advancement of efficient, open and scalable data centers, and Inspur has fully embraced these principles of open sourcing cloud technology with the contribution of its San Jose Motherboard. They are continuing to support OCP with technology leveraged from servicing hyper-scale cloud providers,” said Bill Carter, CTO, OCP Foundation. “We are encouraged by our engagement with Inspur in its new product development-one based upon integrating open computing technology and helping to build a complete open source ecosystem that brings technology and benefits to enterprises and businesses worldwide.

Click to enlarge

Inspur and Open Compute Project

Articles_bottom
AIC
ATTO
OPEN-E