[Beowulf] Re: [Dulug] Parallel debuggers (fwd)
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Matt Rosing rosing at peakfive.comThu Oct 18 09:01:57 PDT 2007
- Previous message: [Beowulf] Re: [Dulug] Parallel debuggers (fwd)
- Next message: [Beowulf] Re: [Dulug] Parallel debuggers (fwd)
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
>Dear MPI Mavens, > >What is the current state of the art for MPI (or PVM or other parallel >code) debuggers? I vaguely recall some review articles on this on CWM >and/or CM, and of course there has been list discussion in the past, but >a quick summary would be very useful. We use two different debuggers, print* and write. I know, a little sarcastic, but true. Part of this is because there's too much information to look at using a regular debugger except for the most basic problems (like where did it crash), part is due to the fact that many of our nasty problems only show up with large processor counts (making one window per process impossible), and the third is that, being remote, the fancy gui based debuggers run like a ruptured turtle over the internet. We can also run our code in serial, so that's where we do most of our debugging. Matt > > rgb
- Previous message: [Beowulf] Re: [Dulug] Parallel debuggers (fwd)
- Next message: [Beowulf] Re: [Dulug] Parallel debuggers (fwd)
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
