IBM Releases NVIDIA-Equipped Servers

IBM has launched new technology equipped with NVIDIA hardware for high-performance computing (HPC) applications.

The Power System S822LC couples two of IBM’s POWER8 CPUs with four NVIDIA Tesla P100 GPUs connected via our NVLink high-speed interface. This is a custom-built GPU accelerator server, where the NVLink interface is routed on the motherboard and uses our Tesla P100 SXM2 GPU.

The technology is already being used at both Oak Ridge and Lawrence Livermore National Laboratories. ORNL and LLNL will use the new systems as a development platform for optimizing applications to take advantage of NVLink. The systems will serve as a test bed for developing applications for Summit and Sierra, the next-generation supercomputers that IBM expects to deliver to ORNL and LLNL in 2017.

“The user insights and the business value you can deliver with advanced analytics, machine learning and artificial intelligence is increasingly gated by performance,” says Doug Balog, general manager of IBM Power Systems. “Accelerated computing that can really drive big data workloads will become foundational in the cognitive era. Based on OpenPOWER innovations from partners such as NVIDIA, our new OpenPOWER Linux servers with POWERAccel set a new standard for these workloads.”

For more information, visit NVIDIA and IBM.

Sources: Press materials received from the company and additional information gleaned from the company’s website.