Red Hat will announce its first high performance computing (HPC) optimised distro, the Red Hat HPC, on 7 October.The distro is a step forward from the current Red Hat Enterprise Linux for HPC Compute Nodes.
The current offerings, Red Hat Enterprise Linux HPC Compute Node subscription, are based on the standard distro but tailored for compute nodes running HPC workloads.
The subscription is available for HPC compute nodes used in clusters with four or more systems. Users access compute nodes via head node servers, which of course use the more expensive Red Hat Enterprise Linux ES or AS.
Instead, the upcoming Red Hat HPC is actually a fully integrated software stack using combined technologies from Red Hat and Platform Computing.
Their marketers would say it is meant to reduce cluster complexity and time to deployment, as well as minimise software integration work and project planning. In return, that would reduce resource demands on the cluster IT admin staff.
A part of the new distro is created by a small Project Kusu team in Singapore. Kusu is the foundation for Platform Open Cluster Stack (OCS) which is an integral feature of Red Hat HPC.
It might be sign of things to come, as more of hardware and software development moves to the Far East - even at the top of the computing performance.