1.Title of subject

compliantprotectiveΛογισμικό & κατασκευή λογ/κού

1 Δεκ 2013 (πριν από 3 χρόνια και 11 μήνες)

83 εμφανίσεις



1.

Title of subject



Parallel Processing


2.

Subject code


TCE3411



3.

Status of subject


Major


4.

Version

Date of Previous Version: Year 2006

Date of New Version :
December 2007



4.

Credit Hour





3

28 Hours of lecture

14 Hours of tutorial lab

LAN’s C
redit Hours Equivalent: 2.67



5.

Semester


Trimester 3 (Delta Level)



6.

Pre
-
Requisite


TCS1011 Data Structures and Algorithms



7.

Methods of teaching



28 Hours of Lecture

14 Hours of Lab



8.

Assessment



Coursework: 60 %

Final Exam : 40 %

Total :
100%



9.

Teaching staff (Proposed)


Nithiapidary



10.

Objective of subject



The objective of the subject is to provide the knowledge of
parallel processing concepts, parallel environments and
architectures, parallel algorithms and parallel programming.



11.

Synopsis of subject




This course addresses the basic concepts of parallel paradigms or
parallel processing. Various parallel programming models will be
practiced throughout the course. The students will be educated to
develop parallel applications fo
r distributed and shared memory
parallel systems using various API(s). In addition, this course also
focuses on parallel algorithm analytical and evaluation skills.


Sinopsis Kursus


Kursus ini mendedahkan pelajar kepada konsep asas
pemprosesan parallel.

Pelbagai model yang dirangkumi di
dalam pengaturcaraan parallel akan dibincangkan. Pelajar
akan dididik untuk membangunkan aplikasi parallel bagi
‘distributed’ dan ‘shared’ sistem memori dengan
menggunakan pelbagai aplikasi pengaturcaraan antaramuka
(API)
. Di samping itu, kursus ini akan mempertingkatkan
kebolehan pelajar dalam pentaksiran dan penilaian
algorithma parallel.



12. Learning Outcomes


On successful completion, students will be able to:

1.

describe different types of parallelism, their principle
s and
structures

2.

design, develop and analyse parallel algorithms for
distributed and shared memory parallel systems

Programme Outcomes

% of

contribution


Ability to apply soft skills in work and career
related activities

5

Good understanding of funda
mental concepts

30

Acquisition and mastery of knowledge in
specialized area


20

Acquisition of analytical capabilities and
problem solving skills


30

Adaptability and passion for learning


5

Cultivation of innovative mind and
development of entrepr
eneurial

skills


5

Understanding of the responsibility with moral
and professional ethics


5


13. Details of subject



Topics Covered


Hours


1.

Introduction to Parallel Computing

Motivations for parallelism, scope of parallel
computing, parallel para
digms, parallel
programming environments, physical
organization of parallel platforms and the
relevant communication methods.


4

2.

Analytical Modelling of Parallel Programs

Basics of message passing programming,
performance metrics for parallel systems
(execution time, overhead, speedup, efficiency,
cost, etc), analytical evaluation of
communication operations and parallel
programs.



2

3.

Message Passing Paradigms

Message Passing Interface (MPI), Parallel
Virtual Machine (PVM),
sample
applications/pro
grams
.


4

4.

Parallel Algorithm Design

Partitioning and divide
-
and
-
conquer strategies,
pipelined computations, embarrassingly
parallel computations, other parallel algorithm
models (data
-
parallel, task graph, work pool,
master slave, hybrid, etc),
sample
applications/programs
.


8

5.

Synchronization

Barriers, synchronized computations, sample
applications/programs.


2

6.

Parallel Processing on Shared Memory

Shared memory multiprocessors and chip
-
level
multiprocessor (CMP or multi
-
core),
concurrent proces
s creation (UNIX
heavyweight process and threads), shared data
access, shared memory synchronization (lock,
barrier, semaphores, deadlock, etc), POSIX
Thread API (pthreads), OpenMP, sample
applications/programs.


8


Total Contact Hours

28


Laboratories:


Theoretical exercises, cluster programming
(MPI, PVM), shared memory programming
(pthread, OpenMP).


14


14. Text



Text Books


1.

Barry Wilkinson & Michael Allen,
"PARALLEL PROGRAMMING:
Techniques and Applications Using
Networked Workstations and
Parallel

Computers (2
nd

Edition)",
Pearson Prentice Hall, 2004.

2.

Ananth Grama, Anshul Gupta,
George Karypis & Vipin Kumar,
“Introduction to Parallel Computing
(2
nd

Edition)”, Addison
-
Wesley,
2003.




Reference
Books



1.

Harry F. Jordan & Gita Alaghband,
“FUNDAMENTA
LS OF
PARALLEL PROCESSING”,
Prentice Hall, 2003.


2.

Peter S. Pacheco, “PARALLEL
PROGRAMMING with MPI”,
Morgan Kaufmann Publishers, Inc.,
1999.

3.

Rajkumar Buyya, “High
Performance Cluster Computing:
Programming and Applications,
Volume 2”, Prentice Hall PTR,
19
99.