DocumentCode
1644227
Title
Design and implementation of a high performance computing system using distributed compilation
Author
Singh, S.K. ; Madaan, Aman ; Aggarwal, A. ; Dewan, Ankur
Author_Institution
Comput. Sci., BVCOE, New Delhi, India
fYear
2013
Firstpage
1352
Lastpage
1357
Abstract
The idea of using the idle resources of a system for some other useful purpose is not new. seti@home pioneered this concept of “public resource computing” by bringing together millions of users worldwide who were ready to donate their idle CPU cycles to the cause of searching the extra terrestrial intelligence. In this paper, we describe a system that uses the same concept for reducing build times by using free cycles on idle computer systems in computer labs of our institute. The challenge of distributing compilation is tackled by a distributing compiler. We use distcc for the purpose. The challenge then is to design a system that keeps track of free helpers, dividing the work fairly among the helpers and most importantly, providing an intuitive interface to the clients who would use the system oblivious of the complexities of the back end.
Keywords
parallel processing; program compilers; distributed compilation; distributing compiler; high performance computing system; public resource computing concept; IP networks; Informatics; Kernel; Linux; Resource management; Servers; cloud computing; resource monitoring; service-oriented; virtualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Advances in Computing, Communications and Informatics (ICACCI), 2013 International Conference on
Conference_Location
Mysore
Print_ISBN
978-1-4799-2432-5
Type
conf
DOI
10.1109/ICACCI.2013.6637374
Filename
6637374
Link To Document