CS 575 Supercomputing for the Sciences

MW 3 - 4:15pm, Fall 2002, BAM 256
Dr. Kris Stewart (stewart@rohan.sdsu.edu)
Computer Sciences Department
San Diego State University
Office Hours: MW 1-2:30pm in BAM 223

Calendar to better focus our activitites

Email from Instructor (may not always have most recent email, so please ensure you check your class email account frequently)

Text: High Performance Computing, Second Edition,
Kevin Dowd & Charles Severance, O'Reilly & Associates, 1998

This URL is http://www.stewart.sdsu.edu/cs575/index.html and is maintained solely by the instructor.

CS 575 is an interdisciplinary course to introduce students in the sciences and engineering to advanced computing techniques using the supercomputers at the San Diego Supercomputer Center (SDSC). Additional architectures may also be explored. The computing projects will be focussed on using the IBM Blue Horizon at SDSC, by first using the performance tools available on the SDSU campus.

Prerequisites are a programming background in Fortran or C

Problem solving skills will be enhanced through computational experiments that will involve both individual and group (collaborative) learning exercises. This emphasizes how science is done these days - involving collaboration, investigation and communcation.

The computers at SDSC are fast number crunching machines whose floating point performance is exceptional. Both single processor and multiple processors architectures will be introduced, with parallel programming using MPI, the Message Passing Interface.

Care is taken to introduce UNIX (at a functional level), develop students' familiarity with local computing resources (Rohan) and software tools (timers, profilers, Answerbook, and more), develop students' understanding of the concept of performance and how to measure and interpret it - all in lectures and labs with the instructor.

Monday's lecture will cover Chapter 2 Ch2 HPC of text, which you should read beforehand.
You should also read the first pages of Chapter 6 on Timing. We will discuss Chap. 6 "Profiling" later in the semester.

Scientific Computing overview by Lloyd Fosdick & Elizabeth Jessup, High Performance Scientific Computing, University of Colorado at Boulder, 1995

1986 ByteBuyer SDSC cover story on this widely circulated local flyer give the details on the Cray XMP, the first supercomputer at San Diego Supercomputer Center. (thanks to Keith Thompson)

Class will be held in BAM113 where your class ROHAN accounts will be distributed and we will begin the introduction to computing the HPC way.
Lab 1 Introduction to Xterms and Timers.
This exercise introduced your first computational experiment, which is due via email on 25 Sept 02

16Sept02 (Lecture in BAM 256):
More on performance today, (16Sept02 lecture), to connect our text Chapters 2 and 6 with our lab exercise last week.

18Sept02 (Lab BAM 113)
Lab 2 First Report and File I/O.

23Sept02 (Lecture in BAM 256)
Chapter 3, Ch 03 Memory, in our text starts the discuss of Memory systems for high performance computing.

25Sept02 (Lab BAM113)
Lab 3: Student Survey and Information Overload

30Sept02 (Lecture in BAM 256
Chapter 4, Ch 04 Floating Point Numbers, gives an overview of computer representation of values and the importance of floating point numbers and arithmetic.

2Oct02 Final Lab in BAM 113 (for a while)
Some runtime examples of floating point values, background for the Second Computational Experiment & Report and tips on effectively using the compilers, to prepare for Chapter 5 What a Compiler Does, which we cover in lecture next week. Lab 4: Floating Point Hands-on Example and Prep for Using Compilers

7Oct02 (Lecture in BAM256
Chapter 5, Ch 05 What a Compiles Does, gives an introduction to some of the steps a compiler takes in translation your higher-level language to the machine code of the compute platform you use.

9Oct02 Lecture in BAM256 Grading Rubric, a short overview of how written reports are scored
Report2_Diffusion background lecture begins the discussion for your next computational experiment.

14Oct02 Lecture in BAM256
Ch 06 Timing and Profiling. We began the semester examining the first few pages of Chapter 6 to gain background on timing. This week we continue in more depth. Using gprof on the diffusion code, also used for second report.
Report2 Assignment, an exploration using Linpack benchmarks applied to the Diffusion Model - Due 30 Oct 02 - Web page and Hard Copy in class.

16Oct02 Lecture in BAM256
Lecture covering Chapter 7: Eliminating Clutter.

Calendar to better focus our activitites

The grade will be based on computational experiments. There will be 5 computer projects with written reports and group oral presentations to the class. These projects will start as individual, simple projects to introduce you to the world of High Performance Computing. These computational experiments will involve increased complexity as we cover more materials from our text.

Additional Topics from the San Diego Supercomputer Center

This curriculum was supported in part by NSF cooperative agreement ACI-9619020 through computing resources of the IBM SP2 Blue Horizon provided by the National Partnership for Advanced Computational Infrastructure at the San Diego Supercomputer Center.

Return to CS 575 Home Page [Fall 2002]