DocumentCode :
1982815
Title :
Selective main memory compression by identifying program phase changes
Author :
Nakar, Doron ; Weiss, Shlomo
Author_Institution :
EE-Syst., Tel Aviv Univ., Israel
fYear :
2004
fDate :
6-7 Sept. 2004
Firstpage :
137
Lastpage :
140
Abstract :
We present a new approach to main memory compression in which a mostly software solution is suggested but without the processing power penalty that usually accompanies such a solution. Compression is only performed during phases which exhibit good spatial locality. These phases are identified by detecting changes in the program\´s working set. By comparing the current working set\´s "signature" with the signature at the end of the previous instruction window, a difference parameter is calculated and, when the difference is low enough, the program is in a phase that exhibits good locality and thus compression may begin. Simulation results confirm that this new approach to main memory compression provides good compression ratios for most SPEC CPU2000 programs.
Keywords :
paged storage; program processors; storage management; compression ratios; difference parameter; instruction window; memory paging; processing power penalty; program phase changes; program working set; selective main memory compression; software solution; spatial locality; Availability; Costs; Hardware; Memory management; Performance gain; Phase detection; Read-write memory; Runtime; Yarn;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical and Electronics Engineers in Israel, 2004. Proceedings. 2004 23rd IEEE Convention of
Print_ISBN :
0-7803-8427-X
Type :
conf
DOI :
10.1109/EEEI.2004.1361108
Filename :
1361108
Link To Document :
بازگشت