Description  Books and References  Guest Lectures  Schedule and class materials  Projects 

 

 

CSC 585/485/469: Special Topic:

High Performance Computing, Multicore & Resilience Computing Course

 

Guest Lecturers:

 

Times: M and W 2:00pm-3:50am

Place: NH 216

Instructor: Dr. Box Leangsuksun, box@latech.edu

facebook: www.facebook.com/naibox

Office: room 237 Nethken Hall, 318-257, 3291

Office Hours: M-F 11-2pm or by appointment

 

Guest Lecturers:

 

Guest Speakers

Tentative Schedule and Topic

TBA

 

 

Descriptions:

The course will expose student to state-of-the-art research and development in High Availability and Performance Computing (HAPC) and related fields. This class is a reading, research and hand-on-oriented education. Activities include studies of HAPC systems and techniques and selected research topics of the current interest.  Topics include but not limited to:

  • computer architectures, interconnectivity and programming paradigms, design and analysis and techniques in HAPC applications and systems,
  • multithread, multicore, GPGPU & many core & cluster computing,
  • heterogeneous computing
  • data and task parallel computing
  • parallel programming in multithreading, openMP, CUDA, openCL, openACC (optional)
  • data-intensive distributed & bigdata applications such as hadoop
  • reliability and performance modeling,
  • a complete life cycle (design, analysis, development, operation, maintenance) for HAP computing,
  • performance evaluation, reliability analysis,
  • parallel and network storage etc.

 

Class Materials:

1)   http://webct.ncsa.uiuc.edu:8900/public/MPI/

2)   Parallel Programming with MPI by Peter Pacheco Morgan Kaufmann; 1st edition (October 1996) ISBN: 1558603395 (optional).

Other class activities: research, experiment, term projects. The activities will be on an HA-OSCAR Linux cluster[†]

Grading Policies:

    Since this class is research (reading) oriented, I think it is more appropriate to evaluate your learning and mastering level of our class objectives into three following categories:

1) Hand-on Term project (30%)

2) Paper (20%)

3) Exam (40) and Homework (5%)

4) Attendance (5%)

    Grading scheme:

   

91 and up

A

81- 90

B

71-80

C

below 70

F

 

Schedules:

Dec 28

 HAPC introduction

Dec 30

 The current trends of HPC

Jan 3

HAPC intro & Performance & Reliability standard Evaluation 

Jan 5

Performance & Reliability standard Evaluation 

Jan 10

 Shared memory programming & Paradigm- Pthreads and sample code

 

Jan 12

Guest lecture & thread programming paradigm (continued)

 

Jan 17

openMP

Jan 19

1st Midterm

Jan 7

Intro to GPGPU

Jan 9

 Intermediate GPGPU programming in CUDA  & hw2 (pthread matrix multiplication)

 

Jan 14

Intro to MPI,  how to  run MPI on Azul    and homework #3 & optional 4

Jan 16

 Hybrid openMP & MPI by John Zollweg, Cornell Advanced Computing..and an overview

 

Jan 21

MLK

Jan 23

Hybird openMP& MPI

Jan 28

Parallel File System & hadoop

 

Jan 30

 

 

Feb 4

 A list of class term paper/project topics &  Term paper presentations

 

Feb 6

  A list of class term paper/project topics &  Term paper presentations

 

 

Feb 8

project Demos

Feb 19

Take home final exam

 

Suggested term projects:

·      HA-cluster with Windows

·      Workload Characterization, Performance Modeling and Evaluation for HPC systems/applications

·      Applying HPC/HA to solve a specific problem (e.g. sensor networks)

·      HA-OSCAR cluster with Windows

·      HA and DR-enabled storage system

·      Open ACC

·      Hadoop

·      IPMI-based cluster management.

·      HA-cluster and load balancer to support e-commerce/internet services

·      HA-cluster and Fault tolerant HPC job schedulers

·      Hot-swap Cluster OS

·      HA-OSCAR and grid computing

·      Performance benefits analysis from HA-OSCAR.

·      Beneficial factors from Standards for HAPC environments

·      FT LAM/MPI in HA-Cluster

 

 

 

[†] powered by nine Intel dual Xeon servers and supported in part by an Intel HPC equipment loan