Unlock instant, AI-driven research and patent intelligence for your innovation.

Pruning method based on tree search in DAG parallel task scheduling

A task scheduling and tree search technology, applied in program startup/switching, resource allocation, program control design, etc., can solve problems such as a large number of repeated access scheduling effects, and achieve the effects of improving efficiency, improving search efficiency, and speeding up computing speed.

Active Publication Date: 2020-05-29
HANGZHOU DIANZI UNIV
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0020] The present invention is to overcome the problem that the DAG task scheduling method in the prior art will repeatedly visit some nodes with poor scheduling effect, and provides a DAG task scheduling method with pruned Monte Carlo tree search

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
  • Pruning method based on tree search in DAG parallel task scheduling
  • Pruning method based on tree search in DAG parallel task scheduling
  • Pruning method based on tree search in DAG parallel task scheduling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] Embodiment: a pruning method based on tree search in DAG parallel task scheduling, for figure 2 The shown DAG topology diagram uses the method described in the present invention, and its process is as follows:

[0050] Step S1: use the CPOP algorithm to find the critical path of the DAG graph;

[0051] Step S2: lower bound The upper bound β=+∞.

[0052] In step S1, the CPOP algorithm is used to obtain the critical path of the DAG graph to provide the basis for the following steps. In step S2, the values ​​of the upper and lower bounds are given to provide initial values ​​for the beginning of the following steps. , this value is the cumulative value of the execution time of all critical path nodes on their respective fastest processors, which is the ideal lower limit time for scheduling,

[0053] Step S3: Initialize the search tree and the ready queue, mark the root node of the search tree as False, add the entry node tasks of the DAG graph to the ready queue, and ...

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 invention discloses a pruning method based on tree search in DAG parallel task scheduling, and the method comprises the steps: a selection stage: starting from a root node s0, selecting a sub-nodes with the maximum UCT value on a path until a leaf node is reached, and judging the sub-node s with the maximum UCT value; a pruning stage: judging makespan values of all nodes on a path from a rootnode to a current node and accumulated values of execution time of unscheduled key path task nodes on processors which are completed fastest respectively; an extension stage: judging whether the leafnode selected in the step S4 is a termination node or not, creating a new child node according to a judgment result, adding the new child node to the search tree, and updating a mark of the new childnode; a simulation stage: starting from the expansion node, performing a simulation task scheduling process on the remaining tasks; and a returning stage: after the simulation is finished, returningthe obtained information to the root node. The invention provides a DAG task scheduling method for Monte Carlo tree search added with pruning.

Description

technical field [0001] The invention relates to the field of task scheduling systems, in particular to a DAG parallel task scheduling method. Background technique [0002] Currently, how to optimize DAG task scheduling in distributed heterogeneous computing systems is an open research problem. The goal of DAG task scheduling is to provide a scheduling scheme to schedule the tasks in the DAG graph to the processor in a certain order to minimize the scheduling length. Its model is as follows: [0003] Workflow applications are generally described by a directed acyclic graph (DAG) G(N,E,P). where N={n 1 ,n 2 ...n m} represents the set of m tasks in the application. E={e 1 ,e 2 ... e s} is a set of s directed edges, edge e(i,j)∈E represents priority constraint, task n j have to wait until n i It can only be executed after completion. Q={p 1 ,p 2 ...p T} represents a set of T processors. W i,j Indicates task n i dispatched to processor p j Computational overhea...

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 Applications(China)
IPC IPC(8): G06F9/48G06F9/50
CPCG06F9/4881G06F9/5038Y02D10/00
Inventor 程雨夏刘奎吴志伟吴卿
Owner HANGZHOU DIANZI UNIV