Comparative study and performance evaluation of algorithms on interconnected - internetworked computer systems
Abstract
Herein, High Performance Computing systems are investigated in detail, focusing on issues as fault tolerance, load balancing, energy consumption, as well as on metrics from the perspective of performance and energy efficiency. A new algorithm which incorporates mechanisms for supporting: a) fault tolerance and b) load balancing for homogeneous/heterogeneous computer clusters is presented. This new algorithm is experimentally investigated for the behavior that exhibits and as demonstrated by the experimental results, the overhead of integrating the mechanism for fault tolerance is relatively small compared to the overhead that would result from repeating the execution of the application all over. Furthermore, the integration of the load balancing mechanism, in cases of heterogeneity, resulted in a highly significant increase in application’s performance. Today, more than ever, the performance of high performance computing systems and the associated energy consumption should be considere ...
show more
![]() | Download full text in PDF format (7.04 MB)
(Available only to registered users)
|
All items in National Archive of Phd theses are protected by copyright.
|
Usage statistics
VIEWS
Concern the unique Ph.D. Thesis' views for the period 07/2018 - 07/2023.
Source: Google Analytics.
Source: Google Analytics.
ONLINE READER
Concern the online reader's opening for the period 07/2018 - 07/2023.
Source: Google Analytics.
Source: Google Analytics.
DOWNLOADS
Concern all downloads of this Ph.D. Thesis' digital file.
Source: National Archive of Ph.D. Theses.
Source: National Archive of Ph.D. Theses.
USERS
Concern all registered users of National Archive of Ph.D. Theses who have interacted with this Ph.D. Thesis. Mostly, it concerns downloads.
Source: National Archive of Ph.D. Theses.
Source: National Archive of Ph.D. Theses.






