DocumentCode
3091309
Title
Minimizing memory utilization of task sets in SmartOSEK
Author
Chen, Wei ; Wu, Zhaohui ; Wang, Xiang
Author_Institution
Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Volume
2
fYear
2005
fDate
28-30 March 2005
Firstpage
552
Abstract
There has been a rapid growth in the amount and the importance of software in automobiles in the past two decades. This trend makes us view automobile space as a set of smart services. The basic platform for managing these services is a real-time operating system. Due to the limited resource in ECU, this operating system must be efficient in some aspects especially in memory utilization. We have implemented an operating system SmartOSEK, an OSEK-compliant OS. Some features and optimizations to reduce the RAM needed by the operating system are presented in this paper. First, an upper bound for the register set of each task that has to be stored can be calculated off-line. It also calls for the extension of the compiler to allocate registers across tasks for task contexts. We provide an experimental implementation with its result shown in this paper. Second, the stack space is saved based on some properties of tasks and interrupt handling.
Keywords
automobiles; interrupts; minimisation; operating systems (computers); program compilers; random-access storage; real-time systems; resource allocation; OSEK-compliant OS; RAM reduction; SmartOSEK; automobile software; interrupt handling; memory utilization minimization; optimizations; program compiler; real-time operating system; register allocation; smart services; stack space; task handling; Automobiles; Automotive engineering; Control systems; Operating systems; Random access memory; Read-write memory; Real time systems; Registers; Resource management; Standards development;
fLanguage
English
Publisher
ieee
Conference_Titel
Advanced Information Networking and Applications, 2005. AINA 2005. 19th International Conference on
ISSN
1550-445X
Print_ISBN
0-7695-2249-1
Type
conf
DOI
10.1109/AINA.2005.247
Filename
1423753
Link To Document