ECTS credits ECTS credits: 6
ECTS Hours Rules/Memories Student's work ECTS: 108 Hours of tutorials: 1 Expository Class: 25 Interactive Classroom: 16 Total: 150
Use languages Spanish, Galician, English
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Departments: Electronics and Computing, External department linked to the degrees
Areas: Computer Architecture and Technology, Área externa M.U en Computación de Altas Prestacións
Center Higher Technical Engineering School
Call: First Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
In this course, the students complete their knowledge about HPC architectures, to this end, we consider modern parallel architectures both from the functional point of view to their design. Thi knowledge will facilitate the student to design correct and efficient parallel algorithms based on the architectural characteristics of the target systems. Courses related with the programming will benefited from this one.
Chapter 1. Parallel computers
Historic introduction
Levels of parallelism: form microarchitecture to supercomputers
Classification
Chapter 2. Design of multiprocessors, multicores and manycores
Introduction
Architecture of multiporcessors, multicores and manycores
Memoru architecture
Chapter 3. Cache Coherence
Protocols
Snooping (UMA systems)
Protecols based on directories (CC-NUMA sustems)
Chapter 4. Synchronization and memory consistency
Synchronization primitives
Hardware support
Software support
Consistency models
Comparative studies
Chapter 5. Interconexion networks
Types of networks
Main components
Performance
Design
Chapter 6. Distributed systems: clusters
Introduction
Cluster architecture
Nodes
Interconexion networks
Software
Tools
Applicacions
Load balance
Chapter 7. Introduction to performance analysis.
Motivation
Basic concepts
Characterization of performance issues
Architecture features related to performance
Basic books:
1. Arquitectura de Computadores, Xullo Ortega, Mancia Anguita e Alberto Prieto. Thompson. 2005.
2. High Performance Cluster Computing, Rajkumar Buyya, ed., Prentice Hall PTR, 1999. ISBN 0-13-013784-7, 0-13-013785-5.
Complementary books:
1. Parallel Computer Architecture, David E. Culler, Jaswinder Pal Singh e Anoop Gupta. Morgan Kaufmann Publishers. 1999.
2. In Search of Clusters, 2ª ed., Gregory Pfister, Prentice Hall, 1998, ISBN: 0138997090.
3. Organización e Arquitectura de Computadores (7ª edición), W. Stallings. Prentice Hall. 2007.
4. Computer Architecture: a Quantitative Approach (6ª edición), John L. Hennessy e David A. Patterson. Morgan Kaufmann Publishers. 2017.
The basic and general skils are: CG1, CG2, CG4, CG5, CB6, CB7, CB9 and CB10 (See page 6 of the master description).
The specific skils are: CE1, CE2, CE3, CE4 and CE8.
Trasversal skils: CT1.
Teaching will focus on tutorial sessions, in which the student can ask questions to the lecturer. Aditionally, the student can attend presential classes as well as programming practices and exercises.
Remote comunication tools will be aviailable.
Teaching will be mainly in English.
Personal exercises and homework (60%), and programming practices (20%), and the personal participation in tutor sessions (20%).
The student can be requested to identify themselves by an official identification document in the evaluation process.
1. Tutorial sessions: 52 hours.
2. Evaluation: 2 hours.
The course will be taught in English
Dora Blanco Heras
- Department
- Electronics and Computing
- Area
- Computer Architecture and Technology
- Phone
- 881816462
- dora.blanco [at] usc.es
- Category
- Professor: University Professor
Francisco Fernández Rivera
Coordinador/a- Department
- Electronics and Computing
- Area
- Computer Architecture and Technology
- Phone
- 881816470
- ff.rivera [at] usc.es
- Category
- Professor: University Professor
Pablo Quesada Barriuso
- Department
- Electronics and Computing
- Area
- Computer Architecture and Technology
- Phone
- 881813538
- pablo.quesada [at] usc.es
- Category
- Professor: Temporary PhD professor