DocumentCode
3255870
Title
Design and implementation of message passing library for PC cluster Maestro
Author
Kulkasem, Pusit ; Yamagiwa, Shinichi ; Ito, Naoki ; Yonezawa, Naoki ; Wada, Koichi
Author_Institution
Dept. of Inf. Sci., Burapha Univ., Thailand
fYear
1999
fDate
1999
Firstpage
597
Lastpage
600
Abstract
The paper gives a detailed implementation of a message passing library called MMP. MMP is a user level library that has been designed and implemented on our Maestro PC (Personal Computer) cluster. By accessing a network interface from a user process directly and performing DMA by a dedicated processor on the network interface, MMP can realize a low latency and high bandwidth message transfer. The implemented MMP achieves a latency of 48 microseconds and a bandwidth of 13.2 Mbytes/sec between 2 nodes of our Maestro PC cluster
Keywords
message passing; network interfaces; software libraries; workstation clusters; DMA; MMP; Maestro PC cluster; PC cluster Maestro; Personal Computer; dedicated processor; high bandwidth message transfer; message passing library; network interface; user level library; user process; Bandwidth; Concurrent computing; Delay; Electronic mail; Indium tin oxide; Message passing; Microcomputers; Network interfaces; Software libraries; Switches;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications, Computers and Signal Processing, 1999 IEEE Pacific Rim Conference on
Conference_Location
Victoria, BC
Print_ISBN
0-7803-5582-2
Type
conf
DOI
10.1109/PACRIM.1999.799608
Filename
799608
Link To Document