Skip to Main Content
Multicore and GPU Programming
book

Multicore and GPU Programming

by Gerassimos Barlas
December 2014
Intermediate to advanced content levelIntermediate to advanced
698 pages
19h 8m
English
Morgan Kaufmann
Content preview from Multicore and GPU Programming
Appendix B

Running MPI programs: preparatory configuration steps

B.1 Preparatory Steps

The problem with having a Network of Workstations (NoW) as a parallel platform is that each of the workstations must provide a mechanism for remotely starting a process. The usual way of doing this is, either through Remote Shell (RSH), or through Secure Shell (SSH). The former is obsolete because it is highly insecure (passwords are communicated in plaintext form).

SSH would normally require an interactive login process to take place on each of the workstations in order for a MPI program to execute! This lengthy and tedious procedure can be avoided by having an authentication agent perform the login transaction on our behalf. The following steps achieve ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

The CUDA Handbook: A Comprehensive Guide to GPU Programming

The CUDA Handbook: A Comprehensive Guide to GPU Programming

Nicholas Wilt
PThreads Programming

PThreads Programming

Dick Buttlar, Jacqueline Farrell, Bradford Nichols

Publisher Resources

ISBN: 9780124171374