Aim
The purpose of the course is that the students should use knowledge from the course EDA115 Algorithm Implementation when writing software for multiprocessors, ie to learn how to implement and algorithm as efficiently as possible on a particular multiprocessor.

Knowledge and understanding
For a passing grade the student must

• understand how cache memories work on multiprocessors,

• understand the importance of reducing the number of cache misses,

• understand the importance of load-balancing between different processors,

• understand how a sequential C program can be parallelised while taking the above into consideration.

Skills and abilities
For a passing grade the student must

• be able to use Pthreads to create threads and synchronise these on a multiprocessor,

• be able to improve the performance of a given sequential program by parallelising it in a way which maximises its performance.

Contents
Multiprocessors, classification of cache misses, decomposition of the computation into tasks. Assignment of tasks to threads. Mapping of threads to processors. Programming models, synchronisation, and communication. Owner computes rule. Memory consistency models. Sequential consistency. Weak ordering. Release consistency. Current research trends in multiprocessor computer architecture. Pthreads.

Literature
Please refer to EDA115 Algorithm Implementation.