Title : 
IGCEJ: An Improved Generational Garbage Collector for Embedded Java Processor
         
        
            Author : 
Hu, Guang ; Zhang, Mi ; Tu, Shiliang
         
        
            Author_Institution : 
Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China
         
        
        
        
        
        
            Abstract : 
The embedded Java processor can directly run byte-code, greatly enhance the running speed and reduce the demand for resources. However, simple garbage collectors and pure generational collectors usually require relative large resources and introduce relative long pause time of all the program threads, which are not particularly suitable for the embedded Java processor. This paper gives the analysis and research of the objects allocation feature and the age distribution characteristic in embedded Java processor environment, and proposes an improved generational garbage collector IGCEJ which is suitable for the embedded Java processor, with higher collection efficiency and lower system resources occupancy. In young generation, we adopt a kind of un-stop-the-world strategy, and objects allocation and promotion perform concurrently. As to the mature space, we apply lazy buddy system scheme integrated with mark-sweep algorithm in the garbage collection.
         
        
            Keywords : 
Java; storage management; IGCEJ; age distribution characteristic; embedded Java processor; improved generational garbage collector; lower system resources occupancy; mark sweep algorithm; objects allocation feature; pure generational collectors; un-stop-the-world strategy; Character generation; Computer science; Costs; Environmental management; Information science; Java; Memory management; Resource management; Runtime environment;
         
        
        
        
            Conference_Titel : 
Information Science and Engineering (ICISE), 2009 1st International Conference on
         
        
            Conference_Location : 
Nanjing
         
        
            Print_ISBN : 
978-1-4244-4909-5
         
        
        
            DOI : 
10.1109/ICISE.2009.645