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

High-level comprehensive scheduling method based on difference constraint system and iterative model

A high-level synthesis and differential constraint technology, applied in the direction of program startup/switching, multi-program device, etc., can solve the problems of complex scheduling process, failure to meet the needs of integrated circuit design and development, scheduling, etc.

Active Publication Date: 2015-02-18
SUN YAT SEN UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are basically two types of high-level scheduling methods, one is cyclic scheduling, and the other is acyclic scheduling. In the current high-level scheduling methods, there is no clear distinction between these two situations, and they are all based on existing technologies. Scheduling by methods such as construction method, transformation method or integer linear programming method, the scheduling process is more complicated, and it is impossible to schedule in a timely and comprehensive manner, the scheduling efficiency is low, and gradually cannot meet the development needs of integrated circuit design

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
  • High-level comprehensive scheduling method based on difference constraint system and iterative model
  • High-level comprehensive scheduling method based on difference constraint system and iterative model
  • High-level comprehensive scheduling method based on difference constraint system and iterative model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention provides a high-level comprehensive scheduling method based on a differential constraint system and an iterative module, including:

[0058] S1. Construct the corresponding control data flow graph after obtaining the input circuit description;

[0059] S2. Divide the control data flow graph into a cyclic part and an acyclic part;

[0060] S3. Using an iterative modular scheduling algorithm to schedule the loop part of the control data flow graph;

[0061] S4. Using a differential constraint system scheduling algorithm to schedule the acyclic part of the control data flow graph;

[0062] S5. After mathematically integrating the scheduling results obtained in steps S3 and S4, a comprehensive scheduling result is obtained.

[0063] Further as a preferred embodiment, the step S2 includes:

[0064] S21. Using the depth-first algorithm to sort all the operation nodes in the control data flow graph;

[0065] S22. Using a dominator graph iterative algo...

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 high-level comprehensive scheduling method based on a difference constraint system and an iterative model. The high-level comprehensive scheduling method based on the difference constraint system and the iterative model is characterized in that the method comprises steps of constructing a corresponding control data flow diagram after obtaining input circuit description; dividing the control data flow diagram into a circulating part and a non-circulating part; scheduling the circulating part of the control data flow diagram by adopting an iterative model scheduling algorithm; scheduling the non-circulating part of the control data flow diagram by adopting a difference constraint system scheduling algorithm; mathematically integrating the obtained scheduling results to obtain a comprehensive scheduling result. The high-level comprehensive scheduling method based on the difference constraint system and the iterative model has the advantages that the high-level comprehensive scheduling flow is optimized, the scheduling performance is improved, the scheduling realization process is convenient and quick, the scheduling can be comprehensively realized in real time, the scheduling efficiency is high and the method can be widely applied to the high-level comprehensive scheduling field.

Description

technical field [0001] The invention relates to a high-level comprehensive scheduling method, in particular to a high-level comprehensive scheduling method based on a differential constraint system and an iterative module. Background technique [0002] The goal of high-level synthesis is to obtain a structural result based on the algorithm-level behavior description and constraint conditions of the established digital system in the target set. The high-level synthesis process includes: compilation and conversion, operator scheduling, resource allocation, register allocation, connection network generation and optimization. Among them, the operator scheduling, that is, the scheduling algorithm is to assign each operation and operation in the control data flow graph generated for compilation and transformation to each control step, so as to realize the optimal or better operator scheduling scheme under the constraint conditions, which is a high-level The most important step in...

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
IPC IPC(8): G06F9/48
Inventor 陈弟虎王自鑫涂玏李静波
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