Google llc (20240126596). SCHEDULING OPERATIONS ON A COMPUTATION GRAPH simplified abstract

From WikiPatents
Jump to navigation Jump to search

SCHEDULING OPERATIONS ON A COMPUTATION GRAPH

Organization Name

google llc

Inventor(s)

Erik Nathan Vee of Hillsborough CA (US)

Manish Deepak Purohit of Fremont CA (US)

Joshua Ruizhi Wang of Mountain View CA (US)

Shanmugasundaram Ravikumar of Piedmont CA (US)

Zoya Svitkina of Mountain View CA (US)

SCHEDULING OPERATIONS ON A COMPUTATION GRAPH - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240126596 titled 'SCHEDULING OPERATIONS ON A COMPUTATION GRAPH

Simplified Explanation

The abstract describes methods, systems, and apparatus for scheduling operations represented on a computation graph. One of the methods involves receiving a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph, generating a separator of the computation graph, and generating the schedule to perform the operations represented in the computation graph.

  • Simplified Explanation:
 - The patent application describes a system for scheduling operations on a computation graph by generating a schedule based on the graph's structure.
  • Explanation:
 - Receiving a request to generate a schedule for processing a computation graph.
 - Obtaining data representing the computation graph.
 - Generating a separator of the computation graph.
 - Initializing the schedule with zero nodes.
 - Adding predecessor nodes to the schedule for each node in the separator.
 - Adding nodes in subgraphs that are not predecessors to any node in the separator.
      1. Potential Applications:

- Task scheduling in computer systems - Resource allocation in cloud computing

      1. Problems Solved:

- Efficient scheduling of operations in complex computation graphs - Optimizing resource utilization in processing tasks

      1. Benefits:

- Improved performance in task execution - Better resource management in computing environments

      1. Potential Commercial Applications:
        1. Optimizing Task Scheduling in Cloud Computing
      1. Possible Prior Art:

- Prior research on task scheduling algorithms in computer systems - Existing methods for resource allocation in distributed computing environments

        1. Unanswered Questions:
      1. How does this system handle dynamic changes in the computation graph during scheduling?

- The abstract does not provide information on how the system adapts to changes in the computation graph structure during scheduling.

      1. What types of computation graphs are most suitable for this scheduling method?

- The abstract does not specify the characteristics of computation graphs that are best suited for the described scheduling approach.


Original Abstract Submitted

methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. one of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.

Retrieved from "http://wikipatents.org/index.php?title=Google_llc_(20240126596)._SCHEDULING_OPERATIONS_ON_A_COMPUTATION_GRAPH_simplified_abstract&oldid=56643"