From: Gerdjan Busker <g.busker@ic.ac.uk>
Newsgroups: comp.parallel.mpi
Subject: Re: Linux MPI_BCAST Problem
Date: 21 Jun 1999 10:42:13 +0000
Organization: Imperial College, London, UK
Message-Id: <gbjaettsum2.fsf@jimb.mt.ic.ac.uk>
References: <Pine.GSO.4.10.9906181008180.3461-100000@glsn15.ews.uiuc.edu>
    <376DDF57.7AA1DBE0@ti.uni-mannheim.de>
Xref: ukc comp.parallel.mpi:5234


Lars Rzymianowicz <larsrzy@ti.uni-mannheim.de> writes:

> Will Reed wrote:
> > p2_2229:  p4_error: interrupt SIGSEGV: 11
> > rm_l_2_2230:  p4_error: interrupt SIGINT: 2
> > p1_5730:  p4_error: interrupt SIGSEGV: 11
> > rm_l_1_5731:  p4_error: interrupt SIGINT: 2
> > p3_2232: (5.008455) Trying to receive a message when there are no
> > connections; Bailing out
> > bm_list_5727:  p4_error: net_recv read:  probable EOF on socket: 1
> 
> 
> Strange that it works under SGI...

I have noticed that SGI code often doesn't care if you access array 
elements that are out of bounds (by a bit).  Running the code in 
Linux doesn't work then and gives a segmentation fault.


GJ.