Monday October 17, 2005, 19:00 - 21:00. Location: Visionen, House B, Campus Valla.
For most organisations, grid computing is a poorly understood concept meaning different things to different people. For some it is all about supercomputing. For others, it is about scavenging space cycles from desktop PCs. Still others believe the grid is synonymous with utility computing. Who is right? Who is wrong? Does it really matter?
With a wide range of companies adopting grid computing as a key part of their IT strategies, the answer is unfortunately that it does. There is a lot of hype and many false promises surrounding grid computing. Some organisations who have tried it have been disappointed by the results because they have not understood what it really can and cannot do. Compare this with those organisations whose understanding and the resulting implementations make it a "game changing" technology for them.
In this session we will look at a range of systems implemented by a range of different organisations. All of them are classified as "grids", yet as we will see, they are all very different from one another. What are the things that all of these systems have in common, and what can we learn from them to better understand the applicability of grid computing to the "real world"?
John Easton has worked for IBM for 18 years in a variety of UNIX technical roles. He worked in Distributed Filesystems development in Austin during the development of the RS/6000 and holds several patents pertaining to security and distributed systems. Since 2002, he has been part of IBM's Grid Computing organization and the senior grid architect for EMEA. He is responsible for designing and implementing grid solutions for major companies across Europe.
This talk is presented in cooperation with NSC:s 6th Annual Workshop on Linux Clusters for Super Computing. Please visit their web page if you want to attend the workshop.