CSE 8803HNC, Fall 2016

This course is a collaborative, online course with UIUC (University of Illinois) Blue Waters project. The instructor for the course is Dr. David E. Keyes, Director of the Extreme Computing Research and Founding Dean of the Mathematical and Computer Sciences and Engineering Division at King Abdullah University of Science and Technology (KAUST), who is very famous in High Performance Computing Community.  Guest lecturers will be invited to speak on their specialties. Lectures from Extreme Computing Research Center staff members highlighting open source scientific software will be incorporated into the course.

This course introduces high performance computing algorithms and software technology, which an emphasis on using distributed memory systems for scientific computing. The topic includes  

The overall goal is to acquaint students who anticipate doing independent work that may benefit from large-scale simulation with current hardware, software tools, practices, and trends in parallel scientific computing, and to provide an opportunity to build and execute sample parallel codes.The software employed in course examples is freely available. The course is also designed to make students intelligent consumers and critics of parallel scientific computing literature and conferences.

Office Hours

Local Instructors Prof. Fang (Cherry) Liu
Dr. Mehmet Belgin
Dr. Blake Fleischer
Thursday 1:00-2:00pm on webex
Class meets Mon, Wed 4:30 - 6:00, Van Leer Room C457



Prerequisites

Experience using C/C++ in a Unix environment, familiarity with basic numerical algorithms, and familiarity with computer architecture.
This course is designed to be entry level graduate course as well as senior level undergraduate course, and it opens to all GT students. 

Expectations of the students:

  • Students will need their own laptop or desktop system
  • Students are expected to view the recorded lectures on class meeting time
  • Students will be asked to submit quizzes for self-assessment purposes
  • Students will be asked to submit a mid-term and a final exam for determining 

Schedule (tentative)

Date Topic Mon Wed Events
Aug 22, 24 * Course syllabus
* Course survey
* Course introduction
Introduction to Parallelism
slides
video

resource list:
A, B, C
slides 1, 2
video

resource list:
A, B, C, D, E, F
problem set 1 is out

reading list:
A, B, C, D, E, F
Aug 29, 31 The Versatile Laplacian
Computational Science & Engineering
 Lecture 3  Lecture 4
problem set 1 is due
(Wednesday 11:55pm)
 Sep  5,7 Structure and Unstructured Grids
 Holiday  Lecture 5
 problem set 2 is out
A, B, C, D, E
 Sep  12,14 Structure and Unstructured Grids
Introduction to PETSc
 Lecture 6
 Lecture 7
 
 Sep  19,21 Nonlinear Root Finding
 Lecture 8
 Lecture 9
 problem set 3 is out
Sep
26,28
Nonlinear Root Finding
Fast Multipole Methods
Lecture 10
Lecture 11

problem set 2 is due
(Wednesday 11:55pm)
Term project is assigned
Oct
3,5
Direct Solver for Dense Linear System Lecture 12
Lecture 13
problem set 3 is due
(Wednesday 11:55pm)
Oct
10,12
BlueWater Cluster Usage
Fall Break
Lecture 14
Term project proposal is due in email
(Wednesday 11:55pm)
Oct
17,19
Direct Solver for Sparse Liner System Lecture 15
Lecture 16

Oct
24,26
MidTerm review
Algorithmic Adaptations to Exascale 
Lecture 17
Lecture 18
problem set 4 is out
bluewaters usage
Oct
31,2

Lecture 19


Nov 7,9  Course review example
Multigrid Method
Lecture 20  Lecture 21 problem set 4 is due
(Wednesday 11:55pm)
Nov 14,16   Lecture 22  Lecture 23 Term project progress report is due in email
(Monday 11:55pm)
Nov
21

Lecture 24


Nov
28

Lecture 25
Term Project Presentation/Final review
3 slides for 5 mins presentation is due on Tuesday 11:55pm, use default black and white scheme in PowerPoint.
Term project is due Wednesday 11:55pm,suggested format is IEEE report format template

Dec
5

Final Exam


Grading

Evaluation consists of four components: problem sets, project, final exam, and class participation at the flipped local site. Problem sets may be undertaken cooperatively (and this is encouraged), but each student must submit the homework separately under their own name, vouching for their own responsibility for the answers. The quality of the write-up is part of the grade. It is intended that all students should be able to score well on the problem sets, because they will be announced well in advance of their due dates and students have unlimited time for their own reading and research of the topics consultations with one another. The problem sets should create an extended ongoing discussion for the class community. The project is intended to be individual.If students want to team to undertake a "bigger" project and earn the same grade for it, this should be negotiated when projects are launched in mid-course. Projects will be submitted in report form, and each project will be featured for a short presentation to the class at the end of the semester.The final exam is, of course, individual.

Late Submissions Policy

Textbooks, references, and reading materials

None of these written resources are "required," but are of potential reference interest.They are not intended to be interchangeable, but are composed for different audiences, with different objectives, but unified around the challenges and opportunities of HPC.Proceeding chronologically back in time, most are out of date in architectural details, due to the rapid evolution of the field, but the principles are mostly timeless.