• [We mar 12 9:00 am:] Here's the midterm exam.
• [Su 24 Feb 3:30 pm:] HW 3 (due next tuesday) has been posted in the Class Schedule.
• [Th 21 Feb 5:30 pm:] For scribes, I've posted a LyX template that you are strongly encouraged to use.
• [Fri 15 Feb 11:30 am:] Thanks to Alan and Andy, the notes on executing equations have beeen posted.
• [Th 7 Feb 2:15 am:] I have posted a reading assignment for this weekend. Please prepare your critique for discusssion next Tuesday. I will build on it, and we will move on to techniques for automatic derivation os systolic arrays. It should take you about 3 hours (my estimate, I'll take a poll in class on Tuesday). Also, PCP 2 has been postponed to Thursday, Feb 14).
• [Th 7 Feb 11:15 am:] We are all past PCP 1 (choose your project). I would appreciate if for my record, you send me an email confirming this (some of you have already done this).
• [Th 7 Feb 11:00 am:] Homework 2 has been posted (the annnouncement is slightly different from what I handed out (but you don't have to print it out to note the differences) on the following points.
  • I have given a few more details about what to draw in Problem 2.
  • I have noted the points for each problem.
  • I have given a few more instructions (e.g., memoized or not) to the kind of code I'd like you to write for Problems 3 and 4.
  • I have asked an additional small question in Problem 4.
• [Sa 1 Feb 9:30 am:] The list of projects has been posted.
• [Fr 25 Jan 8:30 pm:] HW 0 has been posted on the Class Schedule.
• [Th 24 Jan 2:50 pm:] The notes have been slightly updated (a couple of typos have been corrected, and I changed the font size). If you've already printed out a copy, please don't bother (figuring out the typos will teach you more, and also you'll feel better for saving a few trees).
• [Tu 22 Jan 6:15 pm:] The notes have been posted in the class schedule (Notes 1).
• Here are details about the class projects including a tentative schedule.
• The Tentative Class Schedule is another page that will evolve and grow as we go along. You should refer to it frequently since all homework/lab assignments and readings will be posted there.
• Previous announcements

In this class you will learn the foundations of fine grain parallelism covering (i) the polyhedral model and (ii) stream based and data parallel models. Fine grain parallelism may be studied from an architectural view or as an abstraction for general purpose parallel programming. The first view is appropriate for students with prior experience with FPGAs (i.e., with the CS 460 prerequisite). The second view is relevant to students with a general purpose parallel programming training (e.g., the CS475 prerequisite).

Project: You will transform your understanding of the foundations by demonstrating in your term project, highly tuned parallel implementations of the compute intensive kernels of selected applications on a specific platform of your choice. Depending on your background and aptitude, you may implement your designs on either (i) special purpose hardware on FPGA based platforms; or (ii) parallel programs for the IBM Cell. Specifically, the following platforms will be available.

• The Spartan 3 based Digilent boards used in CS/ECE 460.
• The ADM-XRC-II a high-performance PMC (PCI Mezzanine Card) from Alpha Data that we have available for use in the department's Embedded Systems Lab. It is much more powerful than the boards used in CS460, and capable of delivering sustained high performance (e.g., 20 GOPS on some applications that we have run). Please note that you will be expected to take significant initiative in working with the available tools and libraries. You will also have the option to implement/simulate your fine-grain parallel architectures in VHDL and ModelSim.
• A Sony Playstation 3 (about 150 GFLOP single precision peak performance). We have been able to achieve over 100 GFLOPs sustained on certain applications, and this is the target that we will aim for.

Class Topics: The first part of the course will cover a class of highly parallel architectures called systolic arrays that are used for the compute/data intensive parts of many applications. Next, we will see how to systematically design such architectures from high level equational specifications (programs) using the polyhedral model. We will then study tiling and its relationship to systolic architectures as well as to general purpose parallel programming.

The second part will cover stream based and data parallel programming models, and their compilation to hardware. Specifically, we will study an important model of streams called Kahn process networks, its relation to the SAC language developed at CSU, and the automatic compilation of SAC programs to reconfigurable coprocessors.

Details

• Instructor: Sanjay Rajopadhye USC 223, Sanjay.Rajopadhye@colostate.edu. Office Hours: (subject to change, the most current version is in Sanjay's schedule (off his home page):
  • Monday 8:30-10:00
  • Tuesday 4:00-5:30
  • Thursday 2:00-3:30
• Textbook: There is no text book. There are readings associated with each topic in the class schedule and references are posted there.
• Tentative Grading: Labs and Homeworks 35%, take home midterm 30%, Project 35%.

  Late assignments (labs and homeworks) will be accepted for up to 3 days after the due date or until the solution is posted/discussed in class. A 10% penalty per day (24 hours) will be assessed.

• Important Information: Be sure to read the Computer Science Department Student Information Sheet. You are expected to be aware of the policies outlined there.