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

Single-task multi-core scheduling method based on critical path and task duplication

A critical path and task duplication technology, which is applied to multi-program devices, program startup/switching, instruments, etc., can solve problems such as the inability of processor cores to perform effective scheduling, shorten product completion time, and task completion time delays, etc., to achieve Reduce inter-kernel communication, shorten overall time, process adequate effects

Active Publication Date: 2016-12-28
HARBIN UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the weighted directed acyclic graph (Directed Acyclic Graph, DAG) is converted into a task graph containing only join nodes by means of task duplication, the join task graph and the tree structure process graph can be converted to each other; and because the product processing tree Using the critical path scheduling method can shorten the product completion time by prioritizing the processes on the critical path, but the previous algorithms did not consider that the task graph can be converted into the corresponding product processing tree form, and by prioritizing the scheduling of the task nodes on the critical path The method shortens the total task execution time, so there will be a delay in the task completion time. At the same time, because the scheduling sequence cannot be adjusted according to the number of processor cores, effective scheduling cannot be performed when the processor cores are insufficient.

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
  • Single-task multi-core scheduling method based on critical path and task duplication
  • Single-task multi-core scheduling method based on critical path and task duplication
  • Single-task multi-core scheduling method based on critical path and task duplication

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A kind of single-task multi-core scheduling method based on critical path and task duplication, it is characterized in that: the method mainly comprises the steps: DAG task diagram processing module adopts the method for task duplication, the fork node in DAG task diagram is copied to its successor The task node forms a join structure task graph, and further converts the join graph into a product processing tree; the task node scheduling and allocation module introduces the critical path idea in comprehensive scheduling, searches for the critical path of the product processing tree, and prioritizes the nodes on the critical path, Try to advance the execution time of nodes on the critical path; the scheduling sequence adjustment optimization module adopts the method of merging the scheduling sequences with the largest similarity, and merges the scheduling sequences so that the number of scheduling sequences is not greater than the number of processor cores, so as to achiev...

Embodiment 2

[0053] The above-mentioned single-task multi-core scheduling method based on critical path and task replication, the specific implementation steps of the scheduling method are as follows:

[0054] Step 1: traverse the DAG task graph, and copy the fork node in the task graph to its successor task node to form a task graph containing only join nodes;

[0055] Step 2: Convert the join task graph into a corresponding product processing tree;

[0056] Step 3: Calculate the path length from the root node to each leaf node in the product processing tree, find the longest path, and use it as the key path, if the path lengths are the same, find the path that contains the most nodes, and use it as the key path;

[0057] Step 4: Add the critical path to the queue sequentially from the first node;

[0058] Step 5: Determine whether the queue is empty, if it is not empty, continue to execute downwards, otherwise jump to step 14;

[0059] Step 6: Take the first task node in the queue, jud...

Embodiment 3

[0076] In the above single-task multi-core scheduling method based on critical path and task replication, the length of the path from the root node to each leaf node is the sum of the processing time of each process on the path and the communication time between nodes.

[0077] In the above single-task multi-core scheduling method based on critical path and task replication, the task node scheduling assignment module introduces the critical path strategy in comprehensive scheduling, and adopts the early scheduling strategy of the immediately preceding node group to schedule nodes on the critical path.

[0078] In the above-mentioned single-task multi-core scheduling method based on critical path and task replication, the scheduling sequence adjustment optimization module adopts the strategy of merging the maximum similarity, and adjusts the number of scheduling sequences according to the number of processor cores.

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 single-task and multi-core scheduling method based on critical path and task duplication. A conventional multi-core task scheduling algorithm cannot perform effective scheduling when inner cores of a processor are insufficient. The method comprises the following steps that a directed acyclic graph (DAG) task graph processing module duplicates a fork node in a DAG task graph to a subsequent task node by using a task duplication method, forms a join structure graph, and further converts the join graph into a product processing tree; a task node scheduling allocation module introduces a key path idea in integrated scheduling, searches a key path of the product processing tree, and schedules nodes in the key path preferentially to start executing the nodes in the key path in advance to the greatest extent; and a scheduling sequence adjustment optimization module combines scheduling sequences in a mode of combining the scheduling sequences with the maximum similarity, so as to make the quantity of the scheduling sequences not greater than that of the inner cores of the processor, so the inner cores of the processor can fully process in parallel. The method is applicable to single-task and multi-core scheduling based on homogeneous multi-core processors which are interconnected on chip.

Description

Technical field: [0001] The invention relates to a single-task multi-core scheduling method based on critical path and task duplication. Background technique: [0002] Multi-core processors are the main trend of processor development today and in the future, and the number of cores integrated in a single processor has grown from two to four, eight or even more. The multi-core processors used on microcomputers all use an on-chip multi-core processor architecture, and an on-chip multi-core processor (Chip Multi-Processor, CMP) integrates multiple processor cores into one processor chip, thereby improving computing power. CMP can be divided into homogeneous multi-core and heterogeneous multi-core according to whether the computing cores are equivalent or not. Now the multi-core processors mainly promoted by Inter and AMD are homogeneous multi-core processors. [0003] An efficient communication mechanism is an important guarantee for the high performance of a CMP processor. Cu...

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): G06F15/163G06F9/48
Inventor 谢志强韩英杰
Owner HARBIN UNIV OF SCI & TECH
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