Page 92 - B.E CSE Curriculum and Syllabus R2017 - REC

Department of CSE, REC

OUTCOMES:
On successful completion of this course, the student will be able to:
 Define, formulate and analyze a problem
 Solve specific problems independently or as part of a team
 Develop documentation, test specifications and coordinate with various teams to validate and sustain
up to the EoL (End of Life) support activities for engineering customer
 Work independently as well as in teams
 Manage a project from start to finish

TEXT BOOK [INDIAN ECONOMY EDITIONS]:
1. Foundation Skills in Integrated Product Development (FSIPD), First Edition, 2013, NASSCOM.

REFERENCES:
1. Karl T Ulrich and Stephen D Eppinger, Product Design and Development, Tata McGraw Hill, Fifth
Edition, New Delhi, 2011
2. John W Newstorm and Keith Davis, Organizational Behaviour, Tata McGraw Hill, Eleventh Edition,
New Delhi, 2005.
3. Mark S Sanders and Ernest J McCormick, Human Factors in Engineering and Design, McGraw Hill
Education, Seventh Edition, New Delhi, 2013.

ELECTIVE – III

CS17E73 MULTICORE ARCHITECTURE AND PROGRAMMING L T P C
3 0 0 3
OBJECTIVES:
● To be familiar with the architecture of multicore architecture.
● To understand the challenges and design parallel programs.
● To develop Shared memory programs using OpenMP.
● To develop Distributed memory programs using MPI.
● To Program Parallel Processors.

UNIT I MULTI-CORE PROCESSORS 9
Motivation for multicore processors, systems – The differences between processes and threads - Parallel
hardware-SIMD, MIMD, Interconnection networks, Cache coherence, Shared-memory versus distributed
memory Performance-scalability.

UNIT II PARALLEL PROGRAM CHALLENGES 9
Synchronization and data sharing: Data races – Synchronization primitives – deadlocks and livelocks–
communication between threads and processes, Storing thread private data.

UNIT III SHARED MEMORY PROGRAMMING WITH OpenMP 9
OpenMP Execution Mode – Memory Model – OpenMP Directives – Work-sharing Constructs - Library
functions – Handling Data and Functional Parallelism – Handling Loops - Performance Considerations.

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 data types–Performance evaluation.

UNIT V PARALLEL PROGRAM DEVELOPMENT 9
Two n-Body solvers – Tree Search – OpenMP and MPI implementations and comparison.

TOTAL: 45 PERIODS

Curriculum and Syllabus | B.E. Computer Science and Engineering | R2017 Page 92