KEMBAR78
Syllabus ID5130 Parallel ScientifiC Computing | PDF | Numerical Analysis | Message Passing Interface
Scribd
Upload
153 views2 pages

Syllabus ID5130 Parallel ScientifiC Computing

This document provides information about the Parallel Scientific Computing course taught by Dr. Kameswararao Anupindi. The course is a 10-credit course that meets for 3 lectures and 1 lab session per week. It aims to teach parallel programming using distributed-memory, shared-memory and GPU systems and implement numerical methods using these parallel environments. The syllabus covers topics like OpenMP, MPI, OpenACC and numerical methods using these paradigms. The course will be evaluated based on assignments, exams, projects and attendance.

Uploaded by

SK Tamilan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
153 views2 pages

Syllabus ID5130 Parallel ScientifiC Computing

This document provides information about the Parallel Scientific Computing course taught by Dr. Kameswararao Anupindi. The course is a 10-credit course that meets for 3 lectures and 1 lab session per week. It aims to teach parallel programming using distributed-memory, shared-memory and GPU systems and implement numerical methods using these parallel environments. The syllabus covers topics like OpenMP, MPI, OpenACC and numerical methods using these paradigms. The course will be evaluated based on assignments, exams, projects and attendance.

Uploaded by

SK Tamilan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

ID5130: Parallel Scientific Computing

Instructor
Dr. Kameswararao Anupindi, Room no. 326, NAC-I, kanupindi@iitm.ac.in, Phone: 4695.

Teaching assistants
Kiran Sivadas, me22d037@smail.iitm.ac.in
Gouri Sankar Pattanaik, me22d021@smail.iitm.ac.in

General information
• 10 credit course

• 3 lectures and 1 lab-hour per week in ‘F’ slot

– Tuesday 17:00 – 17:50


– Wednesday 11:00 – 11:50
– Thursday 9:00 – 9:50
– Friday 8:00 – 8:50
– Venue: CRC 103

• Announcements via moodle: https://coursesnew.iitm.ac.in/course/view.php?id=4565

Learning outcomes
• To learn parallel programming using distributed-memory, shared-memory and graphics processing unit
(GPU) based systems.

• To understand and implement numerical methods to be run using parallel environments.

Syllabus
1. Introduction (1 week): Motivation and need for parallelization, Examples and applications in scientific
computing, Parallel programming paradigms, Terminology.

2. OpenMP programming (2 weeks): Basics, scope of variables, parallel loop directives, scheduling,
critical directives.

3. Numerical Methods using OpenMP (2 weeks): Numerical integration, explicit and implicit finite-
differences, solution of system of linear equations, solution of partial differential equations.

4. MPI Programming (2 weeks): Basics, point-to-point and collective communication, MPI derived data
types, performance evaluation, advanced function calls, performance analysis.

5. Numerical Methods using MPI (3 weeks): The same applications as for OpenMP.

6. OpenACC Programming (1 week): Motivation, Compute Constructs (Kernel, Parallel, Loop, Rou-
tine), Data Directives, Reductions, Atomics, Data Transfers, Asynchronous Processing, Multi-Device
Programming.

1
ID 5130: Parallel Scientific Computing January - May 2024

7. Numerical Methods using OpenACC (3 weeks): The same applications as for OpenMP and MPI, with
focus on optimizing for GPUs. Time permitting, new topics such as Programming in Julia can be covered

Textbooks
1. An Introduction to Parallel Programming, Peter S. Pacheco, Morgan Kaufmann, 2011

2. Parallel programming in C with MPI and OpenMP, Michael Quinn, McGraw Hill Education, 2017

3. OpenACC for Programmers: Concepts and Strategies, Sunita Chandrasekaran, Guido Juckeland, Addison
Wesley, 2017

4. Parallel Scientific Computing in C++ and MPI, George Em Karniadakis, and Robert Kirby II, Cambridge
Universities Press, 2003

Reference books
1. Using MPI, William Gropp, Ewing Lusk, Anthony Skjellum, The MIT Press, 2014

2. Using OpenMP, Barbara Chapman, Gabriele Jost, Ruud van der Pas, The MIT Press, 2008

Grading policy
• Number of Assignments: 3

• Average of Assignments: 20%

• Mid-term Exam: 20%

• Final Exam: 40%

• Project: 20%

• Attendance: 100% expected, however, the institute norm is ≥ 75% to be eligible to write the final exam.

You might also like