HP Opens GPU Technical Center of Excellence with NVIDIA
HP today announced the opening of a new EMEA GPU Technical Centre of Excellence with NVIDIA. Located in Grenoble, France, the centre enables end-users, developers and independent software vendors to solve their high performance computing challenges by making available the latest technologies from both HP and NVIDIA.
Designed to make HPC, simulations and computation more accessible, HP systems based on NVIDIA Tesla GPU accelerators enable scientists and researchers around the world to tackle complex challenges from quantum physics to finding a cure for cancer.
“HPC systems require huge amounts of compute resources to achieve their expected performance, as well as the expertise to integrate them,” says Philippe Trautmann, EMEA sales director HPC, HP. “The goal of this collaborative GPU Technical Centre of Excellence is to enable perennial solution improvements and facilitate the adoption of HP systems based on NVIDIA Tesla GPUs for HPC.”
As part of the HP EMEA HPC Competency Centre in Grenoble, the resources of the new GPU Technical Centre of Excellence can be accessed securely from the HP network or remotely via the Internet. It enables users to optimise their HPC applications by carrying out proofs of concept (PoCs), benchmarks and other testing activities with HP systems based on high performance, energy-efficient NVIDIA GPU accelerators.
The HPC compute resources of the centre are built around a dedicated HP Converged Infrastructure, based on an HP Cluster Platform solution that includes 10 HP ProLiant SL250s, SL270s and ML350p Gen 8 servers with integrated NVIDIA Tesla GPU accelerators, delivering compute power, efficiency and density. Users can interact with large, complex datasets locally via a flexible HP Z820 Workstation or remotely using HP ProLiant WS460c Gen8 Workstation Blades. Some of these resources are also hosting NVIDIA GRID GPUs, allowing them to be used as high performance visualization systems or as virtual workstations. This enables customers to efficiently share GPUs across multiple virtual machines via different hypervisor protocols (Virtual Desktop Infrastructure – VDI). The system architecture includes three internal networks: an administration network, a management network, and a high-speed Infiniband FDR interconnect network. To maximize the effective use of these system resources, experts from HP and NVIDIA are available to provide advice and consultation on development and tuning of applications using GPU acceleration.
