Fall ’23 T/T 5:30-6:50 pm

(All lectures are in person with exceptions of Zoom on-demand.)

Offered annually during the Fall semester.

*The course emphasizes practical hands-on experience (in spite of its name “principles of p.c.”); you are required to complete four projects selected (freely) from four clusters of problems and a final presentation, throughout the semester. No midterm and final exams.*

Course Description

Parallel computing is at the heart of many exciting and emerging areas, including big data and machine learning. This course (AMS530) is designed for both academic and industrial scientists interesting in parallel computing and its applications to large-scale scientific and engineering problems. It focuses on the three main issues in parallel computing: analysis of parallel hardware and software systems, design and implementation of parallel algorithms, and parallel computing applications to selected problems in physical and life sciences and engineering. In addition, the course emphasizes hands-on practice and understanding of algorithmic concepts of parallel computing.

Part 1

Topic 0. Course syllabus
Topic 1. HPC perspectives
Topic 2. Hardware introduction
Topic 3. Software and MPI
Topic 4. Performance measurements
Topic 5. Algorithms introduction

Part 2

Topic 6. Linear algebra
Topic 7. Calculus and differential equations
Topic 8. Ordinary DEs and molecular dynamics
Topic 9. Load balance and task mapping
Topic 10. Markov Chain MC and optimization
Topic 11. Fast Fourier transforms
Topic 12. App 1: Discovery of topologies
Topic 13. App 2: Modeling of blood

For the full set of course materials, see Stony Brook Brightspace (starting fall 2022).
A portion of Part I of AMS530 Parallel Computing lectures.
Applied Parallel Computing (Deng, 2011).
Stony Brook HPC User’s Guide.
The University of Kansas, An introduction to the Message Passing Interface (MPI) using C
Quick MPI Guide
MPI 1.3 Guide
MPI 2.2 Guide
MPI 3.0 Guide
MPI Examples
OpenMP Tutorial
Local MPI Guide
Stony Brook HPC Guide

Advanced undergraduate students are encouraged to enroll.

A form called “Permission for Undergraduate Students to Enroll in Grad Courses” that can be obtained from the AMS undergraduate office or downloaded here is needed. Professor Deng will sign it after a brief chat or e-sign it after some email exchanges to ensure prerequisites.