Parallel Programming with MPI
Description
This two-day course focuses on using the Message Passing
Interface (MPI) standard to write parallel programs on several of the
OSC supercomputers in order to demonstrate the portability of the
library.
MPI topics to be covered include a variety of
processor-to-processor communication routines, collective operations
performed by groups of processors, defining and using high-level
processor connection topologies, and user-specified derived data types
for message creation.
The MPI workshop will be a combination of lectures and
hands-on lab session in which the participants will write and execute
sample MPI programs.
Prerequisites
Experience with C or Fortran programming language
Target Audience
Anyone interested in using or writing parallel programs
Method of Delivery
Lecture and hands-on laboratory
Handouts
- February 5-6, 2007, by Troy Baer and Armen Ezekielian
Handouts:
- Parallel Computing and MPI (PDF)
- MPI Framework (PDF)
- Point-to-Point Communications (PDF)
- Non-blocking Communications (PDF)
- Collective Communications (PDF)
- MPI Datatypes (PDF)
- Virtual Topologies (PDF)
- May 2007 (PDF), by Armen Ezekielian
- April 2005 (PDF), by Troy Baer (troy@osc.edu)
For the next scheduled workshop, see Notices
|
