Bharatiya Vidya Bhavan's

Sardar Patel Institute of Technology

(Autonomous Institute Affiliated to University of Mumbai)
Bhavan’s Campus, Munshi Nagar, Andheri (West), Mumbai-400058-India

Department of Computer Engineering

Course
Teaching Scheme (Hrs/week) Credits Assigned
(Category) Course Name
Code L T P O E L T P Total
2 0 2 4 8 2 0 1 3
(PE) High Examination Scheme
Performance Component ISE MSE ESE Total
Computing Theory 50 50 100 200
CS321
Laboratory 50 -- 50 100

Operating Systems, Computer and Communication

Pre-requisite Course Codes, if any
Networks, Computer Architecture and Organization
Course Objective: To familiarize students with the fundamental concepts, techniques and design of
parallel computing and use of parallel computing application area.
Course Outcomes (CO):At the End of the course students will be able to
Comprehend fundamental concepts and communication pattern of parallel programming
CS321.1
in high performance computing.
Use MPI and OpenMP message passing paradigm in parallel programs for loosely and
CS321.2
tightly coupled parallel systems.
CS321.3 Analyze the performance of parallel programs of high performance computing systems.
Design parallel algorithm for achieving high performance of standard single threaded
CS321.4
algorithm

CO-PO Correlation Matrix (3-Strong, 2-Moderate, 1-Weak Correlation)

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CS321.1 3 - - - - - - - - - - -
CS321.2 - - - - 3 - - - - - - -

CS321.3 2 3 - - - - - - - - - -

CS321.4 1 1 3 - - - - - - - - 2

CO-PEO/PSO Correlation Matrix (3-Strong, 2-Moderate, 1-Weak Correlation)

PEO1 PEO2 PEO3 PSO1 PSO2

CS321.1 - - 2 - -
CS321.2 - - - - -
CS321.3 - - - - -
CS321.4 - - 2 - 1

BLOOM’S Levels Targeted

Remember Understand Apply Analyze Evaluate Create ✔

UG Syllabus 2020 iteration/CS(V-VIII) pg. 35

 Bharatiya Vidya Bhavan's
Sardar Patel Institute of Technology
(Autonomous Institute Affiliated to University of Mumbai)
Bhavan’s Campus, Munshi Nagar, Andheri (West), Mumbai-400058-India

Department of Computer Engineering

Theory Component
Module Unit
Topics Ref. Hrs.
No. No.
TitleParallel Programming and Platforms
Implicit Parallelism, Limitations of Memory System Performance,
1.1 Parallel Computing Platforms, Parallel Platforms Physical 1
Organization
1 7
Parallel Machine Communication Costs, Interconnection Networks
Routing, Process-Processor Mapping, Mapping Techniques, MPI and
1.2 1,2
OpenMP, Examples of MPI* and OpenMP* Programming – Conjugate
Gradient Method, Jacobi Method
Title Analytical Modeling of Parallel Programs
Sources of Overhead in Parallel Programs, Performance Metrics for
2.1 Parallel Systems, Granularity Effect on Performance, Parallel Systems 1
Scalability
2 7
Minimum Execution Time and Minimum Cost-Optimal Execution
Time, Asymptotic Analysis of Parallel Programs, Examples of
2.2 1,2
Analysis of Parallel Programming – Boundary Value Problem, n-Body
Problem
Title Parallel Algorithm Design
Decomposition Techniques, Characteristics of Tasks and Interactions,
3.1 Mapping Techniques for Load Balancing, Methods for Containing 1
3 Interaction Overheads 7
Task/Channel Model, Foster's Design Methodology, Examples of
3.2 Parallel Programming Design – Sieve of Eratosthenes, Floyd’s 1,2
Algorithm
Title Communication Operations
One-to-All Broadcast and All-to-One Reduction, All-to-All Broadcast
4.1 1
and Reduction, All-Reduce and Prefix-Sum Operations
4 7
Scatter and Gather, All-to-All Personalized Communication, Circular
4.2 Shift, Examples of Parallel Programming Communication – Matrix 1,2
Vector Multiplication, Matrix Multiplication
• MPI – Building Blocks, Communication-Computation
Overlapping, Collective Communication, Computation
Self Operations, Groups and Communicators
5 1,2 4*
Study • OpenMP – Shared-Memory Model, Critical Sections,
Reductions, Data and Functional Parallelism
• GPU Programming – Basic Programming Concepts.
Total(* Not included) 28

UG Syllabus 2020 iteration/CS(V-VIII) pg. 36

 Bharatiya Vidya Bhavan's
Sardar Patel Institute of Technology
(Autonomous Institute Affiliated to University of Mumbai)
Bhavan’s Campus, Munshi Nagar, Andheri (West), Mumbai-400058-India

Department of Computer Engineering

List of Experiment

Sr. No Title of the Experiment

Implement Circuit Satisfiability Problem and comment on NP-Hard by increasing number
1
of input to Boolean circuit.
Implement Minimum Vertex Cover and comment on NP-hard by increasing number on set
2
size.
Implement Linear Systems solution using Conjugate Gradient Method through Parallel
3
MPI and OpenMP programming and then analyze the algorithm.
Implement Linear Systems solution using Jacobi Method through Parallel MPI and
4
OpenMP programming and then analyze the algorithm.
5 Implement Boundary Value Problem using Foster’s Design Methodology
6 Implement n-Body Problem using Foster’s Design Methodology
Implement Sieve of Eratosthenes with different data decomposition options using Parallel
7
MPI programming
Implement Floyd’s version of All-Pair Shortest-Paths Problem through all steps of parallel
8 algorithm design namely partitioning, communication, agglomeration and mapping using
Parallel MPI programming.
Implement Matrix-Vector Multiplication using various Data Decomposition Options using
9**
Parallel MPI programming and then analyze the algorithm.
Implement Matrix Multiplication algorithm through i) Sequential Algorithm, ii) Parallel
10** Algorithm - a) Rowwise Block-Striped Decomposition and b) Cannon's Algorithm using
Parallel MPI programming and then analyze the algorithm.

** Instructor can consider mini project instead of these two experiments.

Text Books

Sr. No Title Edition Authors Publisher Year

Introduction to Parallel Second Addison
1 Ananth Grama 2003
Computing Edition Wesley,
Parallel programming in C First McGraw-
2 Michael J Quinn 2003
with MPI and Open MP Edition Hill

Reference Books

Sr. No Title Edition Authors Publisher Year

Advanced Computer Architecture:
Second Kai Hwang, McGraw-
1 Parallelism, Scalability, 2008
Edition Naresh Jotwani Hill
Programmability
Georg Hager,
Introduction to High Performance First CRC
2 Gerhard 2010
Computing for Scientists and Engineers Edition Press
Wellein

UG Syllabus 2020 iteration/CS(V-VIII) pg. 37