Working with the market leaders in HPC server hardware including Dell, Fujitsu, Huawei, IBM, Lenovo, Supermicro. Whatever your requirements - air-cooled or water-cooled, x86 or Power, GPU’s or FPGA’s, we have the perfect solution for you in our portfolio
Our customers are always looking to push the limits, so delivering technology 'firsts' whether it is a new network, storage or processor technology, is business as usual for OCF and our service delivery team.
With OCF’s extensive compute hardware partner ecosystem including Dell, Fujitsu, Huawei, IBM, Lenovo, NVIDIA, and Supermicro, we can delivery any form factor, memory, processor or accelerator requirement you may have. Using state of the art technology from our carefully selected partners, we will ensure that your server hardware will work flawlessly while integrating with the rest of your data centre.
With our consultative sales approach we work closely with our customers to understand the most appropriate technologies to meet individual requirements.
An overview of some of the technologies we offer is described below.
OCF supplies servers based on the latest 2 Socket and 4 Socket Intel Scalable Processors.
The 2nd Generation Intel Scalable Processors support up to 56 Cores per socket.
OCF supply servers based on the latest 2 Socket and 4 Socket Intel Scalable Processors, with the 2nd Generation Intel Scalable Processors supporting up to 56 Cores per socket.
Intel x86 Servers are available in a number of form factors including air-cooled, water-cooled, high density and GPU capable. This means OCF are more than capable of tackling any requirements you may have with a variety of partners in mind. Whether you have restraints around power consumption or rack space, we will do our best to find the ideal solution.
Dell, Fujitsu, Huawei, Lenovo and Supermicro are just some of the established technology partners we work closely with.
OCF supplies servers based on the latest 1 Socket and 2 Socket AMD EPYC Processors.
The 2nd Generation AMD EPYC Processors support up to 64 Cores per socket.
AMD x86 Servers are available in a number of form factors including high density and GPU capable.
OCF AMD Server Partners include: Dell, Fujitsu, Lenovo and Supermicro.
OCF is able to supply the latest NVIDIA hardward including, Tesla T4, Tesla V100, Tesla V100s, Quadro RTX6000 GPU’s hosted in NVIDIA OEM servers from Dell, Fujitsu, Huawei, IBM, Lenovo, NVIDIA and Supermicro, along with dedicated NVIDIA DGX Station, NVIDIA DGX-1 and NVIDIA DGX A100 deep learning platforms.
IBM POWER9 Servers make use of state of the art IBM POWER9 processors optimised for HPC, analytics and AI workloads.
IBM standalone ‘scale out’ and accelerator enabled solutions such as the IBM Power System Accelerated Compute Server which supports up to 6 NVIDIA Tesla V100 GPUs.
More information on IBM POWER can be found below (external link).
In addition to the technologies described above, OCF is always keeping abreast of the latest technologies available from our partners including ARM processors, AMD GPU's, and Field Programmable Gate Array’s (FPGA’s). If any of the latest new and novel technologies are of interest, please contact the OCF team who would be happy to advise and assist in the development of solutions based on these latest technologies.
Our customers are always looking to push the limits, so delivering technology 'firsts', whether it is a new network, storage or processor is business as usual for OCF and our service delivery team.
With HPC computing components continuing to increase in density and power consumption, they are becoming increasingly difficult to cool in traditional air-cooled data centres. OCF is able to offer servers racks with rear doors heat exchangers and servers with direct-to-chip water-cooled components such as the Lenovo ThinkSystem SD650 (right).
By increasing the energy efficiency of a supercomputer, organisations can save huge amounts of money over the total lifecycle of the system. With ever-increasing CPU core counts, utilisation of GPUs and increasingly large supercomputers, the drive for increased computational power comes at a cost.
Reducing the amount of energy spent on running these systems, HPC centres and academic institutions can put that investment into other areas benefiting research or product development.