> Home > Metz's Campus > Degree Courses > Option IIC > Core Curriculum Modules
Option IIC
 
Metz's campus
Presentation
Staff
Degree Courses
Continuing Education
Research
Library
 
 
Parallel and distributed computing and GRID computing
 
15h L / 12h R / 1 WE + 1 OE / 4 ECTS credits in common with IIC_ARS/ IIC_PAR
 
Stéphane VIALLE (12h), Virginie GALTIER (3h)
 
This course introduces the architectures and development environments for parallel and distributed computing (supercomputers, clusters and grids). It includes theoretical and practical learning of parallel and distributed algorithm design and programming.
 
Basic knowledge of parallel and distributed architectures
 
Main steps of MIMD architecture evolution, economic issues of supercomputer design, analyse of past breaks in high performance architecture and current evolution.
 
Parallel and distributed programming languages
 
Main development tools for modern parallel and distributed architectures (MPI, OpenMP, Grid-Services) and modern trends (JavaSpaces, Active Objects, new libraries for high performance computing).
 
Basic parallel and distributed algorithmic
 
Static domain partitioning, with boarder exchange or data circulation. Computation and communication overlap. Performance modelling and experiment analysis. Introduction to IO parallelisation.
 
Performance modelling, measurement and analysis
 
Difficulties and methodology of performance measurement. Performance modelling, Amdahl’s and Gustafson’s laws, links between these laws.
 
Advanced parallel and distributed algorithmic
 
Regular and irregular parallel sorts, looking for compromise between spWEd and regularity. Comparison of experiments and thOEretical modelling.
 
Introduction to Grid-Computing
 
Motivations, economic issues, famous projects and industrial products.
 
Grid middleware
 
Introduction to the basic topics of Grid middleware. Focus on Globus-4, based on web-services. Current limits of Grid middleware.
 
Grid algorithm design and programming
 
Specific issues about Grid algorithmic and programming. Considerations about Grid resource heterogeneity and volatility: fault tolerance and dynamic resource discovering.
 
 
 
References
I. Foster. Designing and building parallel programs. Addison-Wesley publishing company. 1994.
V. Kumar, A. Grama, A. Gupta, G. Karypis. Introduction to parallel computing. The Benjamin/Cummings publishing company. 1994.
I. Foster and C. Kesselman editors. The Grid 2: Blueprint for a New Computing Infrastructure. Morgan Kaufmann publisher. 2004.
F. Berman, G. Fox and T. Hey. Grid Computing: Making the Global Infrastructure a Reality. Wiley Series in Communications Networking and Distributed Systems. 2003.