Re: [OMPI users] MPI_Send over 2 GB

MPI mandates that the count argument is an "int", which is signed. Hence, the 2GB limit holds true on most modern platforms. If you need to send an aggregate amount of data over 2GB, you should be able to make a composite datatype and send multiple of those. E.g., make a datatype that is

Re: [OMPI users] MPI_Send over 2 GB

My guess would be that your count argument is overflowing. Is the count a signed 32 bit integer? If so it will overflow around 2GB. Try outputting the size that you are sending and see if you get large negative number. Justin Vittorio wrote: Hi! I'm doing a test to measure the transfer rat

[OMPI users] MPI_Send over 2 GB

Hi! I'm doing a test to measure the transfer rates and latency of ompi over infiniband starting from 1 kB everything was doing fine until i wanted to transfer 2 GB and i received this error [tatami:02271] *** An error occurred in MPI_Recv [tatami:02271] *** on communicator MPI_COMM_WORLD [tatami:

Re: [OMPI users] MPI_File_write_ordered does not truncate files

On Wed, Feb 18, 2009 at 02:44:09PM -0800, Brian Austin wrote: > I don't know whether this is the correct behavior, but it is the > correct origin of my confusion. > I suspected this would be attributed to the standard, but it is > contrary to what I'm used to with C's fopen: > I expected MPI_File_

Re: [OMPI users] MPI_File_write_ordered does not truncate files

>>> MPI_File_open( MPI_COMM_WORLD, "foo.txt", >>> MPI_MODE_CREATE | MPI_MODE_WRONLY, >>> MPI_INFO_NULL, &fh ); > > > Since the file was opened with MPI_MODE_CREATE, shouldn't it have been > truncated so the prior contents were removed? I think that's the root > of the confu

Re: [OMPI users] MPI_File_write_ordered does not truncate files

On Wed, Feb 18, 2009 at 02:24:03PM -0700, Ralph Castain wrote: > Hi Rob > > Guess I'll display my own ignorance here: > >>> MPI_File_open( MPI_COMM_WORLD, "foo.txt", >>>MPI_MODE_CREATE | MPI_MODE_WRONLY, >>>MPI_INFO_NULL, &fh ); > > > Since the file was opened with MPI_MODE

Re: [OMPI users] MPI_File_write_ordered does not truncate files

Hi Rob Guess I'll display my own ignorance here: MPI_File_open( MPI_COMM_WORLD, "foo.txt", MPI_MODE_CREATE | MPI_MODE_WRONLY, MPI_INFO_NULL, &fh ); Since the file was opened with MPI_MODE_CREATE, shouldn't it have been truncated so the prior contents were rem

Re: [OMPI users] MPI_File_write_ordered does not truncate files

On Wed, Feb 18, 2009 at 11:10:51AM -0800, Brian Austin wrote: > >> Can you confirm - are you -really- using 1.1.2??? > >> > >> You might consider updating to something more recent, like 1.3.0 or > >>at least 1.2.8. It would be interesting to know if you see the same > >> problem. > > > Also, if yo

Re: [OMPI users] MPI_File_write_ordered does not truncate files

>> Can you confirm - are you -really- using 1.1.2??? >> >> You might consider updating to something more recent, like 1.3.0 or >>at least 1.2.8. It would be interesting to know if you see the same >> problem. > Also, if you could include a short program that reproduces the > problem, that would be

[OMPI users] Error during ./configure.

I have attached the ./configure. The error is " configure: error: Could not determine size of INTEGER*8" Cheerio, Viv ompi-output.tar.gz Description: GNU Zip compressed data

Re: [OMPI users] Ssh problem

Gabriele, If you use PBS/Torque/Maui/Moab, it can update "/etc/security/access.conf" depending on your configuration. If your userid is in this file you will not be allowed to access the node. Thanks, Pat J.W. (Pat) O'Bryant,Jr. Business Line Infrastructure Technica

[OMPI users] compiler_args in wrapper-data.txt files with Portland Group Compilers

I sent this to the mailing list last month but did not get any helpful replies. Can anyone help with this?? I'm trying to use the compiler_args field in the wrappers script to deal with 32 bit compiles on our cluster. I'm using Portland Group compilers and use the following for 32 bit builds:

Re: [OMPI users] MPI_File_write_ordered does not truncate files

On Feb 18, 2009, at 11:17 AM, Ralph Castain wrote: Can you confirm - are you -really- using 1.1.2??? You might consider updating to something more recent, like 1.3.0 or at least 1.2.8. It would be interesting to know if you see the same problem. Also, if you could include a short program

Re: [OMPI users] MPI_File_write_ordered does not truncate files

Can you confirm - are you -really- using 1.1.2??? You might consider updating to something more recent, like 1.3.0 or at least 1.2.8. It would be interesting to know if you see the same problem. On Feb 15, 2009, at 3:27 PM, Brian Austin wrote: Hi, When I use MPI_File_write_ordered to ov

[OMPI users] Euro PVM/MPI'09 CFP

Got an interesting MPI research topic to publish about? Had a few "ah ha!" moments when dealing with parallel programming? Want to meet MPI implementers and other MPI users? Then you should attend Euro PVM/ MPI'09 in Espoo, Finland September 7-10, 2009! Here's a link to the call for paper

Re: [OMPI users] Ssh problem

* Gabriele Fatigati [2009 02 17, 17:10]: > ssh works well. But the problem is still here.. Seems an ssh issue anyway. Maybe your hostfile contains a host you are not allowed to ssh to? Greetings