Computer Science 531
Advanced Computer Architecture

Spring 2007

Monday 3:00-5:30pm, Cramer Hall 227

 

Instructor: Xiao Qin

 Cramer Hall 231A, 505-5902

Office hours: Wednesday 1:30-3:00pm

                                General Information | Announcements | Syllabus | Projects | Lectures 

Announcements

Course Information

In this graduate class, we will address advanced topics in the arena of computer architecture. We presume that students who will take this class have a basic knowledge of computer architecture and operating systems. This course will be research intensive, aiming at deriving practical and achievable ground rules for computer architecture design. Each student is expected to do a project including a written report and an in-class presentation on a topic to be arranged with the instructor. You will be expected to collaborate with other students toward the completion of the research project related to computer architecture.  

Students who have completed this course should be capable of doing the following:

  • Understand fundamental issues in computer architecture design
  • Understand the advanced computer architecture topics like shared memory multiprocessors and cache coherence
  • Improve technical writing and oral presentation skills.

Topics Covered  (These topics may change)

  • Fundamental computer architecture design issues
  • Perspective on parallel programming
  • Performance across the hardware/software boundary
  • Shared memory multiprocessors
  • Evaluating protocol design tradeoffs
  • Snoop-based multiprocessor design
  • Scalable multiprocessors
  • Directory-based cache coherence
  • Hardware/software tradeoffs
  • Latency tolerance
  • Interconnection network design

Prerequisite: CS 331 Computer Architecture

Office Hours: Dr. Qin will have office hours on Wednesday at 1:30-3:00p in his office (Cramer Hall 231A). 

                        To get the most out of office hours, it is recommended to send an email in advance.

Textbooks:  

  • Parallel Computer Architecture: A Hardware/Software Approach

    • David E. Culler, University of California, Berkeley; 
    Jaswinder Pal Singh, Princeton University; 
    with Anoop Gupta, Stanford University. 

    ISBN 1-55860-343-3.

    Resources

    Study Hints