[mpich-discuss] Very long configuration time

Kenneth Raffenetti raffenet at mcs.anl.gov
Wed May 21 13:50:43 CDT 2014


The Intel compilers could also be a source of slowdown. Are they 
installed on a network filesystem? They may also call out to a network 
license server each time they are invoked for a compile test. Does just 
compiling a small program take a long time with icc, ifort, etc.?

On 05/21/2014 01:42 PM, Yida Wang wrote:
> It is still running, so definitely more than a few minutes. Any other
> thing that I did wrong?
>
>
> On Wed, May 21, 2014 at 2:32 PM, "Antonio J. Peña" <apenya at mcs.anl.gov
> <mailto:apenya at mcs.anl.gov>> wrote:
>
>
>     On a decent system, I'd expect it to finish in a few minutes at most.
>
>        Antonio
>
>
>
>     On 05/21/2014 01:30 PM, Yida Wang wrote:
>>     Thanks for your reply, Antonio! Yes, I was using NFS before, am
>>     trying on local disk now. BTW, what will a normal time be?
>>
>>
>>     On Wed, May 21, 2014 at 2:20 PM, "Antonio J. Peña"
>>     <apenya at mcs.anl.gov <mailto:apenya at mcs.anl.gov>> wrote:
>>
>>
>>         Hi YW,
>>
>>         Although 8h looks like a very long time to me, it's likely due
>>         to a network filesystem. If that's the case, configuring MPICH
>>         in a local filesystem (e.g. /temp, /tmp, /scratch) should go
>>         back to normal times.
>>
>>           Antonio
>>
>>
>>
>>         On 05/21/2014 01:17 PM, Yida Wang wrote:
>>>         Hi Guys,
>>>
>>>         I would like to try out the feature of talking to Intel-MIC
>>>         in MPICH2. Therefore I downloaded mpich-3.1 and configured it as
>>>
>>>             "./configure --host=x86_64-k1om-linux CC=icc CXX=icpc
>>>             F77=ifort FC=ifort CFLAGS=-mmic CXXFLAGS=-mmic
>>>             FFLAGS=-mmic FCFLAGS=-mmic LDFLAGS=-mmic"
>>>
>>>
>>>         However, it took a very long time (i.e. 8 hours) for me to
>>>         finish the configuration. Is it normal? Notice that my system
>>>         doesn't have Infiniband but 10GigE connection. However, I
>>>         don't think this would affect the configuration time.
>>>
>>>         Thanks,
>>>         YW
>>>
>>>
>>>         _______________________________________________
>>>         discuss mailing listdiscuss at mpich.org  <mailto:discuss at mpich.org>
>>>         To manage subscription options or unsubscribe:
>>>         https://lists.mpich.org/mailman/listinfo/discuss
>>
>>
>>         --
>>         Antonio J. Peña
>>         Postdoctoral Appointee
>>         Mathematics and Computer Science Division
>>         Argonne National Laboratory
>>         9700 South Cass Avenue, Bldg. 240, Of. 3148
>>         Argonne, IL 60439-4847
>>         apenya at mcs.anl.gov  <mailto:apenya at mcs.anl.gov>
>>         www.mcs.anl.gov/~apenya  <http://www.mcs.anl.gov/%7Eapenya>
>>
>>
>>         _______________________________________________
>>         discuss mailing list discuss at mpich.org <mailto:discuss at mpich.org>
>>         To manage subscription options or unsubscribe:
>>         https://lists.mpich.org/mailman/listinfo/discuss
>>
>>
>>
>>
>>     _______________________________________________
>>     discuss mailing listdiscuss at mpich.org  <mailto:discuss at mpich.org>
>>     To manage subscription options or unsubscribe:
>>     https://lists.mpich.org/mailman/listinfo/discuss
>
>
>     --
>     Antonio J. Peña
>     Postdoctoral Appointee
>     Mathematics and Computer Science Division
>     Argonne National Laboratory
>     9700 South Cass Avenue, Bldg. 240, Of. 3148
>     Argonne, IL 60439-4847
>     apenya at mcs.anl.gov  <mailto:apenya at mcs.anl.gov>
>     www.mcs.anl.gov/~apenya  <http://www.mcs.anl.gov/~apenya>
>
>
>     _______________________________________________
>     discuss mailing list discuss at mpich.org <mailto:discuss at mpich.org>
>     To manage subscription options or unsubscribe:
>     https://lists.mpich.org/mailman/listinfo/discuss
>
>
>
>
> _______________________________________________
> discuss mailing list     discuss at mpich.org
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/discuss
>



More information about the discuss mailing list