2013FS: 12027/22027 Concurrency: Foundations and Algorithms

The course covers the foundations of concurrent systems and multiprocessor synchronization. Students who take this course will learn the basics of multicore programming, the new paradigm of computer science.

The main topics covered in the course include foundations of concurrency: concurrent objects and consistency, foundations of shared memory, the relative power of synchronization operations, universality of consensus; and practical algorithms: mutual exclusion, spin locks and contention, lock-free and wait-free algorithms, concurrent data structures (linked lists, skip lists, queues, stacks, hash tables), scheduling and work distribution, barriers, transactional memory.

The course will be complemented by practical, hands-on exercises on multi-core computers (32+ cores) using Java and C.

Upon successful completion of this class, students will be able to:
- Understand how today's multicore hardware supports concurrent programming.
- Reason about concurrent specifications and consistency models such as linearizability and sequential consistency.
- Know a collection of concurrent obstruction-free, lock-free, and wait-free data structures.
- Design scalable concurrent algorithms without locks (e.g., using atomic operations like compare-and-swap).

CourseDescription.pdf (Dateigröße : 49204 Bytes)

Deutsch

This work has all rights reserved by the owner.

Prof. Pascal Felber

pascal.felber@unine.ch

Unbegrenzt – wenn online geschaltet

Sie können diesem Kurs direkt beitreten.

Unbegrenzt

Anmeldename
Vorname
Nachname
E-Mail