US Patent Application 18324646. SELECTIVE EXECUTION OF WORKLOADS USING HARDWARE ACCELERATORS simplified abstract

From WikiPatents
Jump to navigation Jump to search

SELECTIVE EXECUTION OF WORKLOADS USING HARDWARE ACCELERATORS

Organization Name

Microsoft Technology Licensing, LLC==Inventor(s)==

[[Category:John Allen Tardif of Bellevue WA (US)]]

[[Category:Bharadwaj Pudipeddi of San Jose CA (US)]]

SELECTIVE EXECUTION OF WORKLOADS USING HARDWARE ACCELERATORS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18324646 titled 'SELECTIVE EXECUTION OF WORKLOADS USING HARDWARE ACCELERATORS

Simplified Explanation

The patent application describes systems and methods for selectively executing workloads using hardware accelerators.

  • The method involves a client application submitting a command to a hardware accelerator for workload execution.
  • The command includes an indication of the performance expectation from the hardware accelerator.
  • The workload can be executed either by a compute core accessible to the client application or by the hardware accelerator.
  • If the hardware accelerator is unable to meet the performance expectation and sends a retry response, the client application executes the workload using the compute core.
  • The hardware accelerator is configured to provide the retry response directly to the client application.


Original Abstract Submitted

Systems and methods for selective execution of workloads using hardware accelerators are described. A method includes a client application submitting a command for execution of a workload directly to a hardware accelerator, where the command includes an indication of a performance expectation from the hardware accelerator, and where the workload can be executed either by a compute core accessible to the client application or by the hardware accelerator. The method further includes upon receiving a retry response from the hardware accelerator, the client application executing the workload using the compute core accessible to the client application, where the hardware accelerator is configured to provide the retry response directly to the client application after determining that the hardware accelerator is unable to meet the performance expectation.