3582494093

3582494093



CS6801


MULTI-CORE ARCHITECTURES AND PROGRAMMING


L T P C

3 0 0 3


Subscribe to oitr Telegram Bot @noteskhanbot



OBJECTWES:

The student should be madę to:

•    Understand the challenges in parallel and multi-threaded programming.

•    Learn about the various parallel programming paradigms, and Solutions.

UNIT I MULTI-CORE PROCESSORS    9

Single core to Multi-core architectures - SIMD and MIMD systems - Interconnection networks -Symmetric and Distributed Shared Memory Architectures - Cache coherence - Performance Issues -Parallel program design.

UNIT II PARALLEL PROGRAM CHALLENGES    *f\ \    9

Performance - Scalability - Synchronization and data sharing - Data races - Synchronization primitives (mutexes, locks, semaphores, barriers) - deadlocks and livelocks - communication between threads (condition variables, signals, message gueues and pipes)v

UNIT III    SHARED MEMORY PROGRAMMING WITH OpenMP    9

OpenMP Execution Model - Memory Model - OpenMP Directives - Work-sharing Constructs - Library functions - Handling Data and Functional Parallelism Handling Loops - Performance Considerations.    y

UNIT IV DISTRIBUTED MEMORY PROGRAMMING WITH MPI    9

MPI program execution - MPI constructs - libraries - MPI send and receive - Point-to-point and Collective communication - MPI derived datatypes - Performance evaluation UNIT V    PARALLEL PROGRAM DEVELOPMENT    9

Case studies - n-Body solvers - Tree Search OpenMP and MPI implementations and comparison.

TOTAL: 45 PERIODS

OUTCOMES:

At the end of the course, the student should be able to:

•    Program Parallel Processors.

•    Develop programs using OpenMP and MPI.

•    Compare and contrast programming for serial processors and programming for parallel processors.

TEXT BOOKS:

1.    Peter S. Pacheco, “An Introduction to Parallel Programming", Morgan-Kauffman/Elsevier, 2011.

2.    Darryl Gove, “Multicore Application Programming for Windows, Linux, and Oracle Solaris”, Pearson, 2011 (unit 2)

REFERENCES:

1.    Michael J Ouinn, “Parallel programming in C with MPI and OpenMP”, Tata McGraw Hill, 2003.

2.    Shameem Akhter and Jason Roberts, “Multi-core Programming”, Intel Press, 2006.

Subscribe to our Telegram Bot @noteskhanbot

Subscribe to our Telegram Bot @noteskhanbol



Wyszukiwarka

Podobne podstrony:
5 (828) EVERY ISSUE 11 22 38 50 94 98 Subscribe to CrossStitcher and receive a gorgeous sewing box N
237 HALYNA PETRYSHYN naturę. Good infrastructure, high quality of architecture and access to naturę
DSC00029 (6) Itercise 18. Write a program according to tfae ftCr>vmg signal diagram X Realize STA
Common core peripherals and architecture: STM32 F4 series - High performance with DSP
The (AEAfs Technical Cooperation Programme and its Support to Countries Embarking on Nucie ar
f3 1 C header and source files to implement native methods FIGURE 3.1 How the p rogranis of the JDK
00352 Y81713c432e612628e0c1a55ba8c097 356 Prairie & Zimmer Let Ed be the number of defective un
smpb 29 All Health tends morę or less to strcngth, and all diseasc to weakness poses to lhose who ha
statystyka skrypt82 STRUKTURA I ZASADY DZIAŁANIA PAKIETU STATISTICA PI. Program STATISTICA to zinte

więcej podobnych podstron