Today Penguin Computing announced the latest version of its Scyld ClusterWare high performance computing cluster management solution with enhanced functionality for support of large scale clusters.
The release of Scyld ClusterWare 7 continues the growth of Penguin’s HPC provisioning software and enables support of large scale clusters ranging to thousands of nodes,” said Victor Gregorio, Senior Vice President of Cloud Services at Penguin Computing. “We are pleased to provide this upgraded version of Scyld ClusterWare to the community for Red Hat Enterprise Linux 7, CentOS 7 and Scientific Linux 7.”
Scyld ClusterWare 7 also provides support for Intel Omni-Path and Mellanox InfiniBand architectures. Penguin Computing’s years of HPC expertise allow ClusterWare to be highly-tuned for HPC workloads by offering pre-bundled OS optimizations for cluster performance, a single system install for straightforward change management, tools for monitoring cluster health, ready-to-run HPC schedulers, a wide array of optimized MPI implementations, and all the middleware needed to effectively run a compute cluster.
The announcement reinforces a total solutions approach by Penguin Computing. For example, implementing the company’s OCP-compliant Tundra platform with Scyld ClusterWare 7 and Intel Omni-Path or Mellanox InfiniBand fabrics provides an exceptional infrastructure for a large, dense compute environment.
Scyld ClusterWare is designed for extremely rapid provisioning paired with the ability to instantly update compute clusters by applying changes to a single master node, allowing simplified management of HPC clusters without consuming system administration cycles.