You might write a test of fork() and see if there's a Windows-related problem with that. My guess is that this has nothing to do with MPICH and everything to do with the OS. In any case, there's no point in discussing it further on the list unless you want to install Linux in a VM or something. Jeff On Mon, Aug 19, 2013 at 1:52 PM, Wesley Bland <[email protected]> wrote:
Unfortunately, we haven't supported Windows since MPICH version 1.4.1p1. You can find out more at the FAQ page: http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can....
Since we don't have any test environments or Windows experts, we can't really shed any light onto why you would get this performance. You might try MS-MPI as mentioned in the FAQ post.
Thanks, Wesley
On Aug 19, 2013, at 12:44 PM, Abhishek Kumar Pandey <[email protected]> wrote:
Hi,****
I am using mpich-1.4.1.p1 to launch multiple child processes. On Window Server 2008 all the child processes are launched almost immediately but this takes significant time on Window Server 2012. ****
I am using MPI_Comm_spawn for spawning a process and MPI::Init_thread(argc,argv,MPI_THREAD_MULTIPLE) is used for initializing MPICH2.****
Please let me know if this is a known problem. Is there any workaround ? * ***
Regards,**** Abhishek ****
** ** _______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss
_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss
-- Jeff Hammond [email protected]