Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2023/2024
UPOZORNĚNÍ: Jsou dostupné studijní plány pro následující akademický rok.

Multicore CPU Computing

Login to KOS for course enrollment Display time-table
Code Completion Credits Range Language
NIE-MCC Z,ZK 5 2P+1C English
Garant předmětu:
Ivan Šimeček
Lecturer:
Daniel Langr, Ivan Šimeček
Tutor:
Ivan Šimeček
Supervisor:
Department of Computer Systems
Synopsis:

Students will get acquainted in detail with hardware support and programming technologies for the creation of parallel multithreaded computations on multicore processors with shared and virtually shared memory, which are today the most common computing nodes of powerful computer systems. Students will gain knowledge of architecturally specific optimization techniques used to reduce the decrease in computing power due to the widening performance gap between the computational requirements of multi-core CPUs and memory interface throughput. On specific non-trivial multithreaded programs, students will also learn the basics of the art of creating these applications.

Requirements:

Basics of programming in C and C ++ (at the level of subjects BIE-PA1 and BIE-PA2), completion of the subject Parallel and Distributed Programming (MI-PDP). Recommended completion of the course Effective Programming in C ++ (NIE-EPC).

Syllabus of lectures:

1. Multiprocessor, multicore and multithreaded architectures.

2.-3. (2) Sequence code optimization.

4. Models of relaxed consistency of shared memory.

5. Optimization of synchronization operations in multithreaded algorithms.

6. Memory allocators for parallel calculations.

7.

8. Shared memory, memory locations, shared and exclusive access, atomic operations.

9. Atomic operations.

10. Ordering of memory operations, memory models.

11. Spinlock, cache coherence, scalable memory allocators.

12. Threads and C++, thread pools.

Syllabus of tutorials:

In computer exercises, students solve problems related to lectures; the instructor provides consultations and advice.

Study Objective:
Study materials:

1. Solihin, Y. : Fundamentals of Parallel Multicore Architectures (1st Edition). Chapman & Hall/CRC Computational Science, 2015. ISBN 9781482211184.

2. Sorin, D. J. - Hill, M. D. - Wood, D. A. : A Primer on Memory Consistency and Cache Coherence. Morgan & Claypool Publishers, 2012. ISBN 1608455645.

3. Pllana, S. - Xhafa, F. (Eds) : Programming Multicore and Many-core Computing Systems. Wiley, 2017. ISBN 0470936908.

Note:
Further information:
https://courses.fit.cvut.cz/NI-MCC/
Time-table for winter semester 2023/2024:
06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon
Tue
Wed
Thu
roomT9:348
Šimeček I.
09:15–10:45
ODD WEEK

(lecture parallel1
parallel nr.101)

Dejvice
NBFIT PC ucebna
roomT9:343
Langr D.
Šimeček I.

14:30–16:00
(lecture parallel1)
Dejvice
NBFIT učebna
Fri
Time-table for summer semester 2023/2024:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2024-03-27
Aktualizace výše uvedených informací naleznete na adrese https://bilakniha.cvut.cz/en/predmet6628806.html