Huawei: HPC Platform FusionServer X6000

Huawei Technologies Co., Ltd. launched a new-generation HPC platform, the FusionServer X6000, at the Supercomputing Conference 2016 (SC16).

It will aid computing-intensive workloads and provide enterprise customers with a choice for an HPC platform that has higher efficiency and greater flexibility.

“Faced with the challenges of digital transformation, enterprises are eager for service reconstruction, which drives the convergence of traditional HPC and cutting-edge technologies such as cloud computing and big data,” said William Dong, VP of data center solution sales, Huawei Enterprise BG. “With outstanding R&D capabilities and comprehensive product portfolios in the IT domain, Huawei joins hands with industry partners to build joint innovation centers around the globe. We are dedicated to providing our customers IT infrastructures with leading technologies, as well as innovative HPC cloud, HPC, and big data solutions to help customers achieve business success.“

The X6000 HPC platform adopts a liquid cooling solution, which features a skive fin micro-channel heat sink for CPU heat dissipation and processing technology where water flows through memory modules. The platform delivers a node liquid cooling percentage greater than 85%. Its modular design and 50°C warm water cooling function offers customers high energy-efficiency and flexible deployment, and reduces TCO by up to 40% for large-scale deployment.

The platform also accommodates four 2-socket server nodes in a 2U chassis and presents an all-flash storage capability of 24x NVMe SSDs per chassis.

Based on the high bandwidth and low latency features of 100Gb/s networks, it can achieve a single-node throughput of 4.8 million IO/s.

As a partner of Huawei in the IT domain, Intel Corp. was invited to join and witness the launch of FusionServer X6000.

“Huawei’s new-generation FusionServer X6000 HPC platform, based on the Intel Scalable System Framework, provides the balanced performance, scalability, and flexibility to efficiently handle a ide range of HPC workloads,” said Hugo Saleh, director of marketing and enabling, Intel scalable datacenter solutions. “The FusionServer X6000 is a great example of how Intel Xeon processors and Intel Omni-path architecture can combine to build industry leading solutions with innovative fabric features that optimize performance, resiliency, and traffic movement.”

Huawei is showcasing its HPC solutions for industry scenarios at SC16. Among the HPC solutions on show are Huawei’s high-density servers FusionServer E9000 and X6800 with 100Gb/s high-speed interconnect technology and powerful cluster scalability. These servers can accelerate industrial CAE simulation.

Huawei is also displaying its KunLun supercomputer, which features the company’s proprietary Node Controller interconnect chips. KunLun supports up to 32 CPUs and is for research scenarios that require frequent in-memory computing. Additionally Huawei’s high-performance storage solutions, OceanStor 9000 and ES3000 SSD, which can improve data transmission bandwidth and latency, are on display.

A series of other milestones and achievement’s based on Huawei’s cooperation with industry partners were also announced (or demonstrated) during SC16:

• The company and ANSYS, Inc. announced the two parties’ partnership in building industrial computer aided engineering (CAE) solutions, and jointly released their Fluent Performance white paper, which details optimal system configurations in fluid simulation scenarios for industry customers.
• The firm and A*STAR Computational Resource Centre (A*CRC) jointly presented InfiniCortex during SC16, an international project led by A*CRC Singapore which demonstrates a high-speed fabric which brings together supercomputing facilities from four continents.
• Huawei and Bright Computing, Inc. showcased an HPC cloud cluster management solution, which enables organizations to easily and efficiently consume HPC resources from the cloud.

Huawei has become more prominent in the HPC market. It has deployed HPC clusters for a number of global vehicle producers, large-scale supercomputing centers, and research institutions. These HPC platforms are optimized for industry applications which can help customers simplify service processes and improve work efficiency.