NVIDIA Accelerators for HPE ProLiant Servers

Hewlett Packard Enterprise supports, on select HPE ProLiant servers, computational accelerator modules based on NVIDIA® Tesla™, NVIDIA® GRID™, and NVIDIA® Quadro™ Graphical Processing Unit (GPU) technology.

Based on NVIDIA’s CUDA™ architecture, the NVIDIA accelerators enable seamless integration of GPU computing with HPE ProLiant servers for high-performance computing, large data center graphics and virtual desktop deployments. These accelerators deliver all of the standard benefits of GPU computing while enabling maximum reliability and tight integration with system monitoring and management tools such as HPE Insight Cluster Management Utility.

The NVIDIA Tesla GPUs are general purpose accelerators which excel at boosting performance of structured numerical algorithms. These GPUs are powered by CUDA® and include technologies like Dynamic Parallelism and Hyper-Q to boost performance as well as power efficiency. Applications which benefit from accelerators include deep learning, seismic processing, biochemistry simulations, weather and climate modeling, image, video and signal processing, computational finance, computational physics, CAE, CFD, and data analytics.

The NVIDIA GRID GPUs are optimized for virtual desktop infrastructures (VDI). The Grid K1 adaptor has 4 GPUs on a single PCIe card, and supports large numbers of users with standard desktop applications. Also, together with NVIDIA GRID 2.0 software (to be purchased separately), VDI supported adapters can be used as GRID GPUs for highest-end virtual desktop applications. See https://www.hpe.com/us/en/product-catalog/storage/complete-storage-solution/pip.hpe-complete-nvidia-gridsolutions.1009949096.html for details on required NVIDIA GRID software licenses.

The HPE GPU Ecosystem includes HPE Cluster Platform specification and qualification, HPE-supported GPU-aware cluster software, and also third-party GPU-aware cluster software for NVIDIA Tesla, Quadro and GRID Modules on HPE ProLiant Servers. In particular, the HPE Insight Cluster Management Utility (CMU) will monitor and display GPU health sensors such as temperature. Insight CMU will also install and provision the GPU drivers and the CUDA software. Insight CMU is integrated with popular schedulers such as Adaptive Moab, Altair PBS Professional, and Univa Grid Engine – all of which have the capability of scheduling jobs based on GPU requirements.

NVIDIA Accelerators

NOTE: Please see the HPE ProLiant server Quickspecs for configuration rules including requirements for enablement kits.

More Standard Features, Additional Options, you can visit: https://h20195.www2.hpe.com/v2/GetDocument.aspx?docname=c04123180&doctype=quickspecs&doclang=EN_US&searchquery=&cc=ph&lc=en