326.295, KV Parallel Computing, Wolfgang Schreiner / Alois Zoitl, 2023S

Topic outline

• 

  Parallel Computing (SS 2023)

  342.295, Time: Tuesday, 8:30-11:00, Room: S3 057, Start: March 7, 2023
  

  This course introduces basic techniques and models for parallel computing. We will discuss the basic theory, algorithms, programming models, and design principles for building parallel programs on multi-core processors, shared memory multiprocessors, and distributed memory multiprocessors respectively cluster systems. Class presentation will be accompanied by hands-on experience, e.g., on an SGI UV-1000 distributed shared memory multiprocessor.
  

  Background in programming in C/C++ and Java is assumed. Course grades will be based on practical programming assignments.
  

  • Announcements Forum
  • Questions and Answers Forum
• 

  Videos

  As an extra service, we intend to live-stream and record the lectures via the following Zoom meeting. However, no guarantee is given with respect to completeness and quality of the stream/recordings. The basic course format is on-site, not hybrid.
  

  • Zoom Meeting
    https://jku.zoom.us/j/821203635?pwd=NExrVElZOTUzcWxLeWR1SVVDc0RjZz09
    Meeting-ID: 821 203 635 Password: parallel
    

  • Lecture Video March 7, 2023 (Schreiner) URL
  • Lecture Video March 14, 2023 (Zoitl) URL
• 

  Topics and Schedule

  The (preliminary) course schedule is as follows:

  1. March 7 (Schreiner): Parallel Architectures and Performance.
  2. March 14 (Zoitl): Parallel Algorithms and Complexity.
  3. March 21 (Schreiner): Concurrency in Java and OpenMP.
  4. March 28 (Zoitl): Shared Memory Programming.
     
  5. April 18 (Zoitl): Lockless Data Structures and Work Stealing.
  6. April 25 (Schreiner): Presentations of Solutions 1.
  7. May 2 (Schreiner): Message Passing Programming with MPI.
     
  8. May 9 (Schreiner): Designing Parallel Programs.
     
  9. May 16 (Zoitl): Presentation of Solutions 2.
     
  10. May 23 (Zoitl):  Parallel Computing With Modern C++.
  11. June 6 (Schreiner): Presentations of Solutions 3.
      
  12. June 27 (Zoitl): Presentation of Solutions 4.
      

  Individual meetings may be organized for discussing the assignments.
• 

  Basics

  • Introduction and Organization File
  • Parallel Architectures File
  • Technical Advances in the SGI® UV Architecture File
  • Performance and Productivity Breakthroughs with Very Large Coherent Shared Memory: The SGI® UV Architecture File
  • SGI UV Data Sheet File
  • JKU Data Sheet File
  • How to Use the Parallel Computing Server Page
  • How to Use the Server From Other Networks (Restricted) URL
  • Some More Information (in German) Page
  • The Supercomputer "MACH-2" URL
  • Performance Analysis File
  • Algorithms and Complexity File
• 

  High-Level Parallel Programming

  • Concurrency in Java File
  • Sources File
  • Lesson: Concurrency URL
  • Trail: Custom Networking URL
  • OpenMP File
  • Sources File
  • OpenMP URL
  • OpenMP Tutorial URL
  • Intel OpenMP* Support URL
  • OpenMP* Pragmas Summary URL
  • Worksharing Using OpenMP* URL
  • Thread Affinity Interface URL
  • GNU libgomp URL
  • Enabling OpenMP URL
  • GOMP_CPU_AFFINITY URL
  • MPI File
  • Sources File
  • MPI Forum URL
  • MPI Tutorial URL
  • Parallel Program Design File
  • Ian Foster: Designing and Building Parallel Programs URL
• 

  Assignments

  We will hand out four assignments that have to be worked out individually. At least three assignments have to be turned in and graded positively to pass the course. Submitters may be asked for presentations of their solutions; be prepared to give at least one such presentation.
  

  • Assignment 1 (April 18)
  • Assignment 2 (May 9)
  • Assignment 3 (May 30)
  • Assignment 4 (June 20)