HPE Performance Cluster Manager is a fully integrated system management solution offering all the functionalities you need to manage your Linux®-based high performance computing (HPC) clusters. The software provides system setup, hardware monitoring and management, health management, image management and software updates as well as power management for systems of any scale. The HPE Performance Cluster Manager reduces the time and resources spent administering HPC systems - lowering total cost of ownership, increasing productivity and providing a better return on your hardware investments.
- Support for RHEL 7.7, RHEL 8, CentOS 7.7, CentOS 8, TOSS 7.7, and SLES 15 SP1
- Support for HPE Apollo 20, HPE ProLiant DL385, and Mellanox HDR Switch
- Comprehensive system-wide alerts managed and broadcast via Alerta
- Kafka support enables high-performance data movement from system telemetry collection to Elastic Stack repository
- Elastic Stack’s Elasticsearch now includes alerts and system metrics with the system logs
- More ways to visualize telemetry beyond CLI and GUI with Kibana and Grafana
Complete Feature Set
All the functionality you need to manage your HPE high performance computing systems all day, every day.
Fine-grained central monitoring and management of all aspects of your cluster hardware (CPU, memory, GPU, networking, cooling, …) via interface of your choice (GUI, CLI, Grafana, Kibana...).
Streamline maintenance by setting up alerts and automatic reactions to events.
Cluster Health Check tools help to minimize downtime of your system.
Efficient System Management
Guided setup helps to easily install the software, discover hardware components for the cluster nodes and provision nodes.You can quickly provision a cluster with thousands of nodes from bare metal – typically within an hour.
Any software image can be provisioned on all or select cluster nodes to accommodate different user requirements.
Integration with most widely used 3rd party HPC tools (workload management, system management, monitoring and more) to eliminate complexity.
Grow Your Systems Effortlessly
System log, hardware inventory and image repositories are secure and designed for scale.
No disruption to existing system with rolling hardware upgrades.
System management solution of choice for hybrid HPC infrastructure for on-prem and cloud.
- Linux is the registered trademark of Linus Torvalds in the U.S. and other countries. All other third-party trademark(s) is/are property of their respective owner(s).
- HPE Performance Cluster Manager Introduction
- Managing GPUs (Integration with DCGM)
- Integration with Workload Managers
High Performance Computing Software