HIGH PERFORMANCE COMPUTING I, Fall 2003

E. Bruce Pitman

Lectures are Tuesday/Thursday 2-3:20 in Math250

Outline: This semester we will concentrate on a few topics: (1) understanding (a bit) the design of modern high performance computers, including shared memory machines like the SGI Origin and distributed memory machines like the IBM SP and clusters, (2) programming for these architectures using OpenMP (on shared memory machines) and MPI (shared and distributed machines), (3) how some libraries (like BLAS) make efficient use of hardware to provide a framework for writing codes.

I assume you have good coding skills in either FORTRAN or C or C++. This is NOT a course in which to learn coding. If you are not comfortable writing code, please do not stay in this course - you will not enjoy it. A more appropriate course might be Mth 537 or Computational Physics. You do need some familiarity with numerical analysis/numerical methods.

See COR501 from Fall 2000 and 2001, and COR502 notes (on my courses page), and Dr. Patra's COR501 notes, and references therein.

• Lecture 1 August 26
• Lecture 2 August 28
• Lecture 3 Sept 2
• Lecture 4 Sept 4
• Lecture 5 Sept 4
• Lecture 6 Sept 9
• Lecture 7 Sept 11 - Maui High Performance Computing Center Workshop Notes
• Lecture 8 Sept 16 - example codes
• See also Tom Furlani's notes and lectures from Argonne and notes from the Ohio Supercomputing Center (C++ programmers should see Day 4 of the Intermediate MPI tutorial).
• See the story from HPC Wire about an IBM chip design
• Lecture 9 Sept 16
• Lecture 10 Sept 18
• homework assignment 2 Sept 18
• Dr. Jones' links PBS info
• Dr. Jones' links SGI info
• Dr. Jones' links Sun info
• Lecture 11 Sept 30
• Lecture 12 OpenMP Oct 7
• Lecture 12 and assignment Oct 14
• Lecture 13
• Project outline
• Linear Algebra 1
• PLAPACK
• Templates
• A reference on LAPACK and numerical linear slgebra
• Multigrid
• Homework 4 assignment
• The Future of HPC