System characterization and configuration distribution for facilitating improved performance at computing devices

Patent metadata

Field	Value
Publication number	US-11088907-B2
Application number	US-201615080335-A
Country	US
Kind code	B2
Filing date	Mar 24, 2016
Priority date	Mar 24, 2016
Publication date	Aug 10, 2021
Grant date	Aug 10, 2021

Abstract

A mechanism is described for facilitating system characterization and configuration distribution for promoting improved performance at computing devices. A method of embodiments, as described herein, includes selecting a computing device from a plurality of computing devices to perform a test relating to a default configuration corresponding to the computing device, where the computing device is selected based on at least one of a workload being initiated at the computing device or overall performance of the computing device. The method may further include evaluating feedback data resulting from the test to decide whether a change is necessitated for the default configuration, and computing a new configuration to replace the default configuration at the computing device, if the change is necessitated for the default configuration.

First claim

What is claimed is:

1. An apparatus comprising:
a processing core configured to provide a workload; and
a processor coupled to the processing core, the processor to:
select a computing device from a plurality of computing devices to perform a test relating to a default configuration corresponding to the computing device, wherein the computing device is selected based on at least one of the workload being initiated at the computing device or overall performance of the computing device;
select an experiment from an experiment queue based on the experiment matching the workload associated with the computing device, wherein the test corresponding to the experiment is selected for the default configuration and forwarded onto the computing device;
evaluate feedback data resulting from the test to decide whether a change is necessitated for the default configuration to improve performance at the computing device, wherein the feedback data is obtained through an automated feedback loop based on testing of outputs of permutations of one or more configuration settings associated with the workload to meet a threshold identifying a minimum quality;
compute a new configuration to replace the default configuration at the computing device, if the change is necessitated for the default configuration; and
communicate the new configuration to the computing device that implements the new configuration, wherein the computing device is detected from a machine class of a plurality of machine classes prior to selection of the computing device, wherein the plurality of computing devices are clustered into the plurality of machine classes based on hardware composition of each of the computing devices, and wherein one or more other computing devices are selected from the machine class to perform the test, wherein the test is pushed back into an experiment queue when the feedback data is regarded as at least one of incomplete, inconclusive, or insufficient to facilitate a decision on whether the change is necessitated for the default configuration.

2. The apparatus of claim 1 , wherein the processor is further to allow the default configuration to be maintained unchanged at the computing device, if the change is not necessitated for the default configuration.

3. The apparatus of claim 1 , wherein the processor is further to receive the feedback data from the computing device, wherein the feedback data includes performance metrics gathered during the performance of the test at the computing device, wherein the performance metrics include one or more of frame rates, power consumption data, power preservation data, hardware metrics, execution time, display performance metrics, speed, or screenshots.

4. The apparatus of claim 3 , wherein the processor is further to store the feedback data at one or more databases regardless of whether the change is necessitated for the default configuration, wherein the stored feedback data is capable of being used for future testing.

5. The apparatus of claim 1 , wherein the one or more other computing devices of the machine class to facilitate implementation of the new configuration at the computing device and the one or more other computing devices of the machine class.

6. A method comprising:
selecting a computing device from a plurality of computing devices to perform a test relating to a default configuration corresponding to the computing device, wherein the computing device is selected based on at least one of a workload being initiated at the computing device or overall performance of the computing device;
selecting an experiment from an experiment queue based on the experiment matching the workload associated with the computing device, wherein the test corresponding to the experiment is selected for the default configuration and forwarded onto the computing device;
evaluating feedback data resulting from the test to decide whether a change is necessitated for the default configuration to improve performance at the computing device, wherein the feedback data is obtained through an automated feedback loop based on testing of outputs of permutations of one or more configuration settings associated with the workload to meet a threshold identifying a minimum quality;
computing a new configuration to replace the default configuration at the computing device, if the change is necessitated for the default configuration; and
forwarding the new configuration to the computing device that implements the new configuration, wherein the computing device is detected from a machine class of a plurality of machine classes prior to selection of the computing device, wherein the plurality of computing devices are clustered into the plurality of machine classes based on hardware composition of each of the computing devices, and wherein one or more other computing devices are selected from the machine class to perform the test, wherein the test is pushed back into an experiment queue when the feedback data is regarded as at least one of incomplete, inconclusive, or insufficient to facilitate a decision on whether the change is necessitated for the default configuration.

7. The method of claim 6 , further comprising: allowing the default configuration to be maintained unchanged at the computing device, if the change is not necessitated for the default configuration.

8. The method of claim 6 , further comprising: receiving the feedback data from the computing device, wherein the feedback data includes performance metrics gathered during the performance of the test at the computing device, wherein the performance metrics include one or more of frame rates, power consumption data, power preservation data, hardware metrics, execution time, display performance metrics, speed, or screenshots.

9. The method of claim 8 , further comprising: storing the feedback data at one or more databases regardless of whether the change is necessitated for the default configuration, wherein the stored feedback data is capable of being used for future testing.

10. The method of claim 6 , wherein the one or more other computing devices of the machine class to facilitate implementation of the new configuration at the computing device and the one or more other computing devices of the machine class.

11. At least one non-transitory machine-readable storage medium comprising a plurality of instructions, executed on a computing device, to facilitate the computing device to perform operations comprising:
selecting a computing device from a plurality of computing devices to perform a test relating to a default configuration corresponding to the computing device, wherein the computing device is selected based on at least one of a workload being initiated at the computing device or overall performance of the computing device;
selecting an experiment from an experiment queue based on the experiment matching the workload associated with the computing device, wherein the test corresponding to the experiment is selected for the default configuration and forwarded onto the computing device;
evaluating feedback data resulting from the test to decide whether a change is necessitated for the default configuration to improve performance of the computing device, wherein the feedback data is obtained through an automated feedback loop based on testing of outputs of permutations of one or more configuration settings associated with the workload to meet a threshold identifying a minimum quality;
computing a new configuration to replace the default configuration at the computing device, if the change is necessitated for the default configuration; and
forwarding the new configuration to the computing device that implements the new configuration, wherein

Assignees

• Intel Corp

Inventors

• Burke Devan
• Taylor Robert B
• Schluessler Travis T

Classifications

• H04L43/50

  Testing arrangements · CPC title

• H04L41/0816 Primary

  the condition being an adaptation, e.g. in response to network events · CPC title

• H04L43/0817

  by checking functioning · CPC title