Dynamic network of supercomputing resources with unified management interface

A computer program product for increasing computing cluster utilization in large scale computing environments, the computer program product comprising:

• one or more non-transitory machine-readable storage media;
• instruction for aggregating a plurality of interconnected computing clusters into a cluster network;
• instruction for accessing the aggregated computing clusters, said instruction for accessing the aggregated computing clusters including at least one of (i) instruction for accessing the aggregated computing clusters via a unified application programming interface (API) for providing one or more API interface services and (ii) instruction for accessing the aggregated computing clusters via a user interface for providing one or more user interface services;
• instruction for creating a plurality of portable containers for one or more applications and executing the plurality of portable containers via a plurality of selected computing clusters in the cluster network;
• wherein the aggregated computing clusters form a dynamic supercomputing resource marketplace system;
• and
• wherein at least one of (i) the one or more API interface services and (ii) the one or more user interface services are hosted publicly.

A method for increasing computing cluster utilization in large scale computing environments, the method comprising:

• forming a dynamic marketplace with supercomputing resources acquirable by a user to execute a computing job via aggregating a plurality of interconnected computing clusters into a cluster network;
• providing the user access to the aggregated computing clusters via a unified application programming interface (API) that provides (i) a single interface to the plurality of interconnected computing clusters and the different resource management software, and (ii) a user interface for providing one or more user interface services;
• wherein different subsets of the plurality of interconnected computing clusters use different resource management software;
• presenting the user with controls for selecting (i) an application to be executed and (ii) a set of nodes to be used to execute the application, wherein the set of nodes are selected from the aggregated computing clusters;
• and
• calculating and presenting to the user an estimated cost and an estimated execution time to execute the selected application on the selected set of nodes.

A method for increasing computing cluster utilization in large scale computing environments, the method comprising:

• aggregating a plurality of interconnected computing clusters into a cluster network, wherein different subsets of the plurality of interconnected computing clusters use different resource management software;
• providing a user access to the aggregated computing clusters via a unified application programming interface (API) that provides (i) a single interface to the plurality of interconnected computing clusters and the different resource management software, and (ii) a user interface for providing one or more user interface services;
• wherein the aggregated computing clusters form a dynamic supercomputing resource marketplace system;
• wherein the plurality of interconnected computing clusters comprise multiple different public clouds and one or more private computing clusters connected via one or more virtual private networks (VPNs) that are automatically configured for the user;
• and
• further including presenting the user with controls for selecting (i) an application to be executed and (ii) a set of nodes to be used to execute the application, wherein the set of nodes are selected from the aggregated computing clusters.