18456460. TECHNOLOGIES FOR MANAGING ACCELERATOR RESOURCES BY A CLOUD RESOURCE MANAGER simplified abstract (Intel Corporation)

From WikiPatents
Jump to navigation Jump to search

TECHNOLOGIES FOR MANAGING ACCELERATOR RESOURCES BY A CLOUD RESOURCE MANAGER

Organization Name

Intel Corporation

Inventor(s)

Malini K. Bhandaru of San Jose CA (US)

Sundar Nadathur of Cupertino CA (US)

Joseph Greeco of Saddle Brook NJ (US)

Roman Dobosz of Santa Clara CA (US)

Yongfeng Du of Beijingh (CN)

TECHNOLOGIES FOR MANAGING ACCELERATOR RESOURCES BY A CLOUD RESOURCE MANAGER - A simplified explanation of the abstract

This abstract first appeared for US patent application 18456460 titled 'TECHNOLOGIES FOR MANAGING ACCELERATOR RESOURCES BY A CLOUD RESOURCE MANAGER

Simplified Explanation

The abstract of this patent application describes a technology for managing accelerator resources in a cloud environment. Here is a simplified explanation:

  • A cloud resource manager receives information about the usage of accelerators from multiple compute devices and the parameters of a task to be performed.
  • The cloud resource manager has access to a task distribution policy.
  • Based on the task parameters and the task distribution policy, the cloud resource manager determines which compute device should receive the task.
  • The cloud resource manager assigns the task to the chosen compute device.

Potential applications of this technology:

  • Cloud computing platforms that utilize accelerators, such as GPUs or FPGAs, can benefit from this technology to efficiently manage and distribute tasks to the appropriate compute devices.
  • High-performance computing environments that rely on accelerators can use this technology to optimize resource allocation and improve overall system performance.

Problems solved by this technology:

  • Efficiently managing and distributing tasks to accelerator resources can be challenging in cloud environments with multiple compute devices. This technology provides a solution to this problem by considering task parameters and a task distribution policy to determine the most suitable compute device for each task.

Benefits of this technology:

  • Improved resource utilization: By assigning tasks to the most appropriate compute devices, this technology ensures that accelerator resources are efficiently utilized, leading to better overall system performance.
  • Enhanced scalability: The cloud resource manager can handle a large number of compute devices and tasks, allowing for scalable management of accelerator resources in cloud environments.
  • Optimized task distribution: The task distribution policy helps ensure that tasks are distributed in a way that aligns with specific requirements or priorities, leading to better workload balancing and performance optimization.


Original Abstract Submitted

Technologies for managing accelerator resources include a cloud resource manager to receive accelerator usage information from each of a plurality of node compute devices and task parameters of a task to be performed. The cloud resource manager accesses a task distribution policy. The cloud resource manager determines a destination node compute device of the plurality of node compute devices based on the task parameters and the task distribution policy. The cloud resource manager assigns the task to the destination node compute device. Other embodiments are described and claimed.

Retrieved from "http://wikipatents.org/index.php?title=18456460._TECHNOLOGIES_FOR_MANAGING_ACCELERATOR_RESOURCES_BY_A_CLOUD_RESOURCE_MANAGER_simplified_abstract_(Intel_Corporation)&oldid=18100"