The #1 Supercomputers Depend on Mellanox HPC Solutions

The need to analyze growing amounts of data, to support complex simulations, to overcome performance bottlenecks and to create intelligent data algorithms requires the ability to manage and carry out computational operations on the data as it is being transferred by the data center interconnect. Mellanox InfiniBand solutions incorporate In-Network Computing technology that performs data algorithms within the network devices, delivering ten times higher performance, and enabling the era of “data-centric” data centers. By delivering the fastest data speed, lowest latency, smart accelerations and highest efficiency and resiliency, InfiniBand is the best choice to connect the world’s top HPC and artificial intelligence supercomputers.

SYSTEX HPC Management Solution-GAIA

 

Systex HPC Solution with architecture design combines HPC, OpenStack, Docker, Ceph & Lustre technology, and the administrators & users are able to manage & use this platform via a single portal. This design delivers following benefits:

1.       This architecture combined both of HPC & private cloud design which benefits the users to maximize the computation resource for researchers, professors & students without isolated computation resource in one piece. 

2.       Central management portal to reduce the workload of administrator. 

 

3.       Applications will be implemented by Virtual Machine & Container versions for experiential purpose of performance & user experience in difference usage scenarios. 

Gaia Director User Portal

 * 2 servers with high availability design for User Portal services. (Note: Gaia is the product name of the user portal services)

2. Management Pool

 * The design provides two types of service. One is HPC service which incl. login, Master, Job Scheduler & Management; another one is Openstack management powered by RedHat. Be reminded all of the management nodes are high availability design.

3. Computing Pool

* The computing pool are separated to two types of computing pool. Physical Compute is designated for HPC usage, the user scenarios could be for research purpose; and OpenStack Compute provides virtual machine computation resources, and usage scenario could be generic learning subjects.

4. Storage Pool

* Same as Computing pool that the storage pool separated to Lustre Pool for HPC and Ceph storage pool. For supporting & stability consideration, Ceph storage is powered by RedHat.

 

Our Reference customer:

 

We have build more than 13 reference customers from FSI, Healthcare, Hi-Tech, Education, Government Research, Manufacture and Telecom industries.