ENVS 1200 Lecture Notes - Lecture 16: Beowulf Cluster, Grid Computing, Distributed Computing
ENVS 1200 Lecture 16 Notes – High-performance computing
Introduction
• Most systems allow this operation to take place without powering down or rebooting
the cluster.
• With their distributed processing capability, Beowulf clusters can also be used
effectively for shared or parallel processing
• Where a single large task is divided into subtasks that can be processed simultaneously
by different computers within the cluster
• Many interesting and important problems are not amenable to normal computer
solution
• Either because the problem is so complex computationally or because the volume of
data to be processed is prohibitively large
• Example problems include the analysis of weather patterns, the behavior of physics
particles, models of the effects of various factors on global warming
• Prediction of the economic and social effects of a particular political policy
• The field of high-performance computing, sometimes called supercomputing
• Arose in an attempt to meet the challenge of solving difficult problems that require
massive amounts of computing power
• There have been a number of different approaches to high-performance computing
• Recently developed systems tend to fall loosely into one of two architectural categories
• Systems that are built from clusters of powerful machines or larger Beowulf blade
clusters
• These were discussed in the previous section.
• Systems that use the spare processing capacity of computers connected to a network.
• Each computer is given a small portion of the task to process in its spare time.
• This technique is called grid computing.
• Their distributed processing capability, Beowulf clusters can also be used effectively for
shared or parallel processing
find more resources at oneclass.com
find more resources at oneclass.com