CENG577 PARALLEL COMPUTING
| Course Code: | 5710577 |
| METU Credit (Theoretical-Laboratory hours/week): | 3 (3.00 - 0.00) |
| ECTS Credit: | 8.0 |
| Department: | Computer Engineering |
| Language of Instruction: | English |
| Level of Study: | Graduate |
| Course Coordinator: | Prof.Dr. MURAT MANGUOĞLU |
| Offered Semester: | Fall or Spring Semesters. |
Course Objectives
To design and analyze parallel algorithms for large scale scientific and engineering problems, and to get experience on parallel systems.
Course Content
Classification of computers and introduction to parallel architectures. Pipelining and vector processing. Organization of data and parallel storage. Design and analysis of parallel algorithms. Performance measures of parallel algorithms. Examples of parallel algorithms. Programming assignments for parallel solution of some problems on the PVM and the Transputer system.
Course Learning Outcomes
While the fastest computers are large parallel clusters today, programming them remains a challenge. The best algorithm and their implementation could be quite different than the sequential counterpart on a parallel platform. Programmer needs to consider multiple issues like how to load balance and how to effectively use multiple levels of caches and the communication network. Today parallel computing is every- where, it is not only the fastest computers, but also from your laptop to cellphone, most devices contain multiple processors. This course will focus on the architecture of the modern parallel computing platforms and the design, analysis and implementation of parallel algorithms for solving large scale science and engineering problems.