Allocating hard real-time tasks: an NP-hard problem made easy
Real-Time Systems
IEEE Transactions on Computers
An architecture for embedded software integration using reusable components
CASES '00 Proceedings of the 2000 international conference on Compilers, architecture, and synthesis for embedded systems
A General Resource Reservation Framework for Scientific Computing
ISCOPE '97 Proceedings of the Scientific Computing in Object-Oriented Parallel Environments
Minimizing Memory Utilization of Real-Time Task Sets in Single and Multi-Processor Systems-on-a-Chip
RTSS '01 Proceedings of the 22nd IEEE Real-Time Systems Symposium
Early-stage performance modeling and its application for integrated embedded control software design
WOSP '04 Proceedings of the 4th international workshop on Software and performance
Component Allocation with Multiple Resource Constraints for Large Embedded Real-Time Software Design
RTAS '04 Proceedings of the 10th IEEE Real-Time and Embedded Technology and Applications Symposium
A Model-Based Development Method for SmartOSEK OS
CIT '05 Proceedings of the The Fifth International Conference on Computer and Information Technology
Task Construction for Model-Based Design of Embedded Control Software
IEEE Transactions on Software Engineering
A task generation method for the development of embedded software
ICCS'06 Proceedings of the 6th international conference on Computational Science - Volume Part IV
Adaptive component allocation in scudware middleware for ubiquitous computing
EUC'05 Proceedings of the 2005 international conference on Embedded and Ubiquitous Computing
| Hi-index | 0.00 |
With the increasingly complexity of ubiquitous computing environment, large and distributed embedded software are used more and more widely. After a design model has been completed, assigning components in the design model while meeting multiple runtime constraints is a critical problem in model-based large distributed embedded software development. In this paper, we propose a new method of component assignment. This method uses backtracking algorithm to search the assignment space, and a balance distance function to decide the feasible assignment scheme. Unlike other methods that view computation, communication, and memory resources as independent resources, this method analyzes their holistic influence on component assignment with the goal of keeping the balance between computation resource consumption and memory resource consumption, and the balance of execution density among different processors. Experimental evaluation shows the component assignment method has high success ratios, low time overheads, and good scalability.