• Thu Aug 18 (5:00 am): We have set up the email address cs475@cs.colostate.edu to automatically forward to the whole teaching team: instructor and TAs. Please send any questions about the course to that address. This ensures that we are all aware of the issue and its resolution, and that the first available person answers, so that our response is faster.
• Thu Aug 18 (5:00 am): In addition to the two on-campus classes (CS475 and GRAD510), this is also the common web site for the on-line section of CS475. Our department is committed to ensuring that the on-line and the on-campus sections are as close as possible. To this end, all students do essentially the same work (assignments, same exams, quizzes, labs, and project).
• Thu Aug 18 (5:00 am): The on-campus lectures are recorded and made available to (all) students under RamCT. All other material (lecture slides, HW announcements, schedule, lab schedule, instructions, reference material, etc.) is available at this public site.
• Thu Aug 18 (5:00 am): This class uses a number of systems. Your programming assignments are done on the Carver supercomputer at NERSC. You will also use RamCT and the CS department machines.
  • 10% of your grade is based on quizzes, discussions, and labs. This is done under RamCT. Also, HW reports are submitted under RamCT.
  • Program development and debugging should be done on the department machines. HW code submission should be done on the department machines.
  • Final program runs, and performance data collection should be done on Carver (batch submissions). We will grade your carver programs.
  We will soon post instructions to obtain your NERSC accounts. This is a rather involved process, requiring you to fax your personal information, and then waiting for us to approve the account. You will be allocated adequate but not unlimited time on this machine, and should be careful about the usage. This is why you should do program development/debugging on the department machines.
• Here are previous announcements.

However, parallel programming is not easy. Patterson's keynote talk at LCPC 2006 (here are his slides) eloquently makes that argument that we were, even then, at the end of the "La-Z-Boy Programming" era, so this is a huge challenge.

This course will train you to respond to the challenge. It will teach you the basic concepts of writing, debugging, analyzing, benchmarking, and designing parallel programs. It covers the two main paradigms: shared memory, and message passing. We will also examine a number of parallel algorithms for a range of problems. The class is intended to be very hands-on: you will

1. write a number of programs (in C);
2. run them on the CS department's Unix platforms and on a large scale supercomputer at NERSC;
3. measure the running time as a function of two parameters (problem size and number of processors);
4. analyze your observations; and
5. write reports on your observations and analyses.

Prerequisites: CS 370 System Architecture and Software or instructor consent. Another key prerequisite is intellectual curiosity.

Tentative Syllabus & Schedule

• Class meets: Tuesday, Thursday 9:30-10:45 AM in Behavioral Sciences 107.
• Instructor: Sanjay Rajopadhye 340 CSB, (email: Sanjay.Rajopadhye@colostate.edu), (phone: 491-7323).
  Office Hours: Please see Sanjay's weekly schedule.
• Graduate Teaching Assistants: TBA
  GTA Office Hours: TBA
• Textbook: Parallel Programming in C with MPI and OpenMP, Michael J. Quinn (Mc Graw Hill, 2003 ISBN 0-07-282256-2). This textbook is out of print in North America. If you are able to get it from any other source (eBay, Amazon, international, etc.) that's fine, but we have worked out an arrangement with the publisher to make the required chapters available to students. This will cost about $30, and can be purchased at the CSU bookstore.
• Tentative Grading: Homework 40%, Labs/Discussions/Quizzes 10%, Midterms 30%, Final Project 20%.
  • Most homeworks will involve writing programs and analyzing them, both analytically and empirically. Assignments must be submitted at the beginning of class on the due date. Programming assignments must be checked in by the time indicated. Late assignments will not be accepted (exceptions may be announced in class or posted).
  • There will be two midterms and a project, but no final exam.
• Final Project For your final project, you will work with a partner and parallelize the dynamic programming algorithm for the knapsack problem using a number of alternative strategies that you have not seen in the homework assignments. The goal is to achieve the best possible performance. More on this later.

  The university calendar has scheduled the final exam on Monday, December 12, 6:20-8:20 PM, in the classroom. We do not have a final exam, but your final project report and code (the last thing that you will turn in for this class) will be due Monday (midnight).

• Important Information: Be sure to read the Computer Science Department Student Information Sheet. You are expected to be aware of the policies outlined there as well as the department's Code of Conduct.