14 DAY TRIAL // Microsoft is making headway toward the availability of the gold build of Windows for supercomputers, reportedly planned for RTM on September 22, 2008. At the same time, the Redmond giant is offering for download documentation set up to describe in detail the design and deployment process associated with Windows HPC Server 2008. The resources delivered by Microsoft are set up to streamline the tasks and procedures necessary for designing and installing a Windows HPC Server 2008-based high performance computing cluster, according to the company.
These are "the software requirements for the head node and the compute nodes in a Windows HPC Server 2008 cluster: Windows Server 2008 HPC Edition (or another 64-bit edition of Windows Server 2008); and Microsoft HPC Pack 2008. To enable users to submit jobs to your HPC cluster, you can install the utilities included with Microsoft HPC Pack2008 on client computers. Those client computers must be running any of the following operating systems: XP Professional SP3 (x86- or x64-based); Windows Vista; and Windows Server 2003 [including Compute Cluster Edition]," Microsoft stated.
The Design and Deployment Guide for Windows HPC Server 2008 will offer comprehensive information set up to permit not only the planning of a Windows HPC Server 2008 cluster but also the finalization of the deployment process. The guide integrates directions for deploying and configuring the head node, adding compute nodes to the cluster, and in the end testing the cluster.
"You can configure your HPC cluster for high availability by installing the head node in the context of a failover cluster. If the server that is acting as the head node fails, the other server in the failover cluster automatically begins acting as the head node (through a process known as failover)," Microsoft reveals in the guide.
The Design and Deployment Guide for Windows HPC Server 2008 is available for download here.