Home / Products / Platform LSF MultiCluster
 

Overview

 

Complete workload processing faster utilizing enterprise-wide compute resources across clusters resulting in increased computing power, enhanced productivity and faster turnaround to results.

 

Platform LSF MultiCluster, a product in the Platform Accelerate suite, extends an organization’s reach to share resources beyond a single Platform LSF cluster to span across multiple clusters across various geographical locations. It provides a single machine image when connecting multiple hardware clusters together. With Platform LSF MultiCluster, local ownership and control is maintained ensuring priority access to any local cluster while providing global access across an enterprise’s entire HPC infrastructure. 

How you can benefit from Platform LSF MultiCluster:

 

  • Optimize IT resources across departments and organizations spanning geographical locations – including desktops, servers and mainframes.
  • Enable more work to be done faster, while leveraging existing IT investments by distributing daytime workload from one location to geographically distant locations to run overnight.
  • Complete high priority work on time – aligning IT resources and business priorities.
  • Deliver more cost effective compute power for time-sensitive and data-intensive work.
  • Minimize the amount of time users spend submitting and managing their jobs by providing a common, consistent interface. This also minimizes training and support requirements.

 

Facts about Platform LSF MultiCluster:

 

  • Intelligent, policy-driven batch application workload processing across multiple Platform LSF clusters.
  • Join geographically dispersed clusters by forwarding jobs to remote clusters as the local cluster becomes busy.
  • “Hub-and-spoke” model allows smaller design centers to access powerful, centralized resources.
  • Global access and coordination while maintaining local control and ownership of resources.
  • Production quality solution to build enterprise HPC environments.
  • Resources are shared on a lease model which allows administrators to manage leased resources as if they were local.
  • Sophisticated accounting tools allow resource usage tracking across clusters to enable utility-based computing ‘pay-as-you-use’ charge-back models.
  • Multiple security features allow authentication of remote job requests to ensure local cluster security protocols are not violated.
  • Instant alerts on job performance and overall grid efficiencies help optimize usage workloads.