Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Heterogeneous multi-core processor dynamic voltage adjustment method and system based on reinforcement learning

A technology of dynamic voltage regulation and multi-core processors, applied in control/regulation systems, regulation of electrical variables, instruments, etc., can solve problems such as inability to adapt to processor platform power consumption and performance requirements, and achieve the effect of protecting technical details

Active Publication Date: 2022-05-31
SUN YAT SEN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method cannot adapt to different types of processor platforms and meet different power consumption and performance requirements.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Heterogeneous multi-core processor dynamic voltage adjustment method and system based on reinforcement learning
  • Heterogeneous multi-core processor dynamic voltage adjustment method and system based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] The present embodiment provides a method for dynamic voltage regulation of heterogeneous multi-core processors based on reinforcement learning, as shown in FIG.

[0065] S6: update the agent according to the reward, select the dynamic voltage regulation command of the next time step;

[0069]s

[0072] a={a

[0078] The agent selects the action a=π according to the current state information s using the ∈ greedy strategy

[0080] Q(s, a)=Q(s, a)+θ·{r+γ·max

[0081] where θ and γ are the learning rate and reward discount factor, respectively.

[0083]r

[0086] The Q value table stored in the non-volatile flash memory needs to be

Embodiment 2

[0097] The terms describing the positional relationship in the accompanying drawings are for illustrative purposes only, and should not be construed as a limitation to this patent;

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a dynamic voltage regulation method for heterogeneous multi-core processors based on reinforcement learning. The method includes the following steps: S1: Obtain the state data of the multi-core processor at each time step, and obtain the state value after processing; S2: Set the dynamic voltage A voltage adjustment instruction to obtain an action set; S3: setting an agent, the agent selects a dynamic voltage adjustment instruction from the action set according to the state value at the current moment; S4: the multi-core processor selects a dynamic voltage adjustment instruction according to the selected dynamic voltage adjustment instruction Perform dynamic voltage adjustment; S5: Obtain the state value of the multi-core processor after dynamic voltage adjustment, and calculate the reward; S6: Update the agent according to the reward, and select the dynamic voltage adjustment instruction for the next time step; S7: Evaluate whether the dynamic voltage adjustment The expected effect is achieved. If it is achieved, the dynamic voltage adjustment is ended. If it is not achieved, return to step S3. The invention can adapt to different types of processor platforms and meet different power consumption and performance requirements.

Description

A method and system for dynamic voltage regulation of heterogeneous multi-core processors based on reinforcement learning technical field [0001] The present invention relates to the field of multi-core processor voltage regulation, and more particularly, to a heterogeneous reinforcement learning-based A multi-core processor dynamic voltage adjustment method and system. Background technique [0002] Most of the existing dynamic voltage regulation techniques perform global dynamic voltage frequency regulation for all cores, or Independent dynamic voltage frequency scaling for each core individually. Hardware Implementation of Global Dynamic Voltage-Frequency Adjustment Simple, but less efficient; independent dynamic voltage frequency regulation can reduce the energy consumption of the system well, but requires complex hardware software support. Using multiple voltage domains can balance hardware overhead with energy efficiency. Heterogeneous multi-core processors typi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05F1/625
CPCG05F1/625Y02D10/00
Inventor 陈弟虎粟涛杨旭明
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com