Advanced Computer Architectures

Course guarantor:

Pavel Tvrdík

Lecturer:

Tutor:

Pavel Tvrdík

Supervisor:

Department of Computer Systems

Synopsis:

Students will learn the mechanisms for multilevel branch prediction, speculative instruction execution, and speculative data prefetching techniques in ILP processors. The second part is on memory hierarchy systems, memory consistency models, and memory coherence protocols in parallel computer systems with virtual shared distributed memory. The third part is devoted to synchronization mechanisms in parallel systems with distributed memory.

Requirements:

BIE-APS, MIE-PAR, MIE-PAP or equivalents

Syllabus of lectures:

1. Multilevel branch predictors in ILP processors.

2. Speculative instruction execution in ILP processors.

3. Speculative data prefetching techniques in ILP processors.

4. Distributed memoru coherence and consistency models.

5. Memory coherence protocols for virtual shared memory systems.

6. Distributed memory synchronization mechanisms.

Syllabus of tutorials:

No exercises.

Study Objective:

To explain more complex algorithmic and architectural solutions used in modern advanced processors and computers.

Study materials:

Hennessy, J. L., Patterson, D.A.. Computer Architecture: A Quantitative Approach. The Fourth Edition. Morgan Kaufmann, 200X, ISBN 1-55860-724-2.

Shen, J., Lipasti, M.. Modern Processor Design: Fundamentals of Superscalar Processors, McGraw Hill 2005, ISBN 0-07-057064-7.

D. E. Culler, J.P. Singh and A. Gupta. Parallel Computer Architecture: A Hardware/Software Approach. Morgan Kaufmann. ISBN 1-55860-343-3.

Note:

To be open in summer semesters.

Time-table for winter semester 2025/2026:

Time-table is not available yet

Time-table for summer semester 2025/2026:

Time-table is not available yet

The course is a part of the following study plans:

• Informatics (doctoral) (compulsory elective course)
• Informatics (compulsory elective course)