Print

Cluster and Grid Computing

Course Instructor: Nicolae Țăpuș

Syllabus:

The course covers the specific concepts of Cluster and Grid computing. It is presented the basic concepts of cluster, as a new approach of parallel and distributed processing system, which consists of a collection of interconnected stand-alone heterogeneous systems cooperatively working together as a single, integrated computing resource.

In the course are presented the type of clusters, cluster architecture, new concept in OS services for distributed processing , physical cluster interconnections and interconnect support, cluster programming environments, monitoring and performance analysis tools.

The lecture also presents the essence of Grid systems, how to utilize highly flexible network architectures, and how to share various computing resources, not just data. Grid technologies are presented, as well as an extensible and open Grid architecture, general aspects of basic components that enable interoperability among different Grid resources.

 
 

Principal Grid systems characteristics are explained, such as: Wide geographical distribution, Heterogeneous, Resource sharing, Multiple admin policies, Resource coordination, Transparent access, Dependable, Consistent, Pervasive. A Sample Grid Computing Environment is described, with Resource Sharing & Aggregation and Grid Architecture for Computational Economy. The Layered Grid Architecture is finally presented. 

In the second part of the course the students have to choose a topic of application on Grid computing and have to present an essay about it. During laboratory activities students will elaborate projects concerning parallel and distributed systems, starting from current research in this domain.

Students will thus learn the top-down approach in project design and implementation, and will propose technologies for testing and analyzing the performance of their designed systems.

After completing the course, students will master the main concepts, models and specific technologies for parallel and large scale distributed systems. Through their projects, students will acquire skills in effective use of design tools, in implementing and evaluating systems addressing specific needs.