Systems and methods for improving computational speed of planning by enabling interactive processing in hypercubes

A method for assigning a workload to compute resources, comprising:

• receiving a workload;
• breaking the workload into a set of subproblems using a processor;
• and
• for a subproblem of the set of subproblems, wherein the subproblem comprises a set of sheets of a hypercube:
• determining whether evaluation of the subproblem benefits in computational speed from intersheet parallelism or intrasheet parallelism;
• in response to a determination that evaluation of the subproblem does not benefit computational speed from intersheet parallelism or instrasheet parallelism:
• determining whether the subproblem benefits in computational speed from directed acyclic graph (DAG) partitioning;
• and
• in response to a determination that evaluation of the subproblem benefits in computational speed from DAG partitioning, assign and evaluate the subproblem using DAG partitioning, wherein evaluating the subproblem using DAG partitioning comprises computing a first disconnected subgraph of the subproblem and a second disconnected subgraph of the subproblem in parallel on separate compute resources.

A computer program product for assigning a workload to compute resources, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

• receiving a workload;
• breaking the workload into a set of subproblems;
• and
• for a subproblem of the set of subproblems, wherein the subproblem comprises a set of sheets of a hypercube:
• determining whether evaluation of the subproblem benefits in computational speed from intersheet parallelism or intrasheet parallelism;
• in response to a determination that evaluation of the subproblem does not benefit computational speed from intersheet parallelism or instrasheet parallelism:
• determining whether the subproblem benefits in computational speed from directed acyclic graph (DAG) partitioning;
• and
• in response to a determination that evaluation of the subproblem benefits in computational speed from DAG partitioning, assign and evaluate the subproblem using DAG partitioning, wherein evaluating the subproblem using DAG partitioning comprises computing a first disconnected subgraph of the subproblem and a second disconnected subgraph of the subproblem in parallel on separate compute resources.