On 08/12/10 21:53, Jed Brown wrote:
> Or OMPI_CC=icc-xx.y mpicc ...
If we enable a different set of run time library paths for Intel
compilers than those used to build OMPI when we compile and execute the
MPI app these new run-time libs will be accessible to OMPI libs to run
against instead of those used when OMPI was being built right? I would
think that this may cause some problems if for some reason something in
the modern run-time libfs differs from the ones used when OMPI was built ?
A user is hoping to avoid rebuilding his OMPI app but i guess just
change LD_LIBRARY_PATH to the latest Intel compile run-time libs and
just launch it with teh latest and greatest Intel Libs.... I mentioned
to him that the right way is to build the combination of OMPI + Intel
run-time that the application is known to work with (since some may
fail) but he wants me to insert a fixed run-time lib path for OMPI libs
but use different and variable one for the run-time libs of the OMPI
application! It is frustrating with people who get "great ideas" but
then they presss someone else to make them work instead of doing this
>> On Aug 12, 2010 5:18 PM, "Ralph Castain" <rhc_at_[hidden]
>> <mailto:rhc_at_[hidden]>> wrote:
>> On Aug 12, 2010, at 7:04 PM, Michael E. Thomadakis wrote:
>> > On 08/12/10 18:59, Tim Prince wrote:
>> The "easy" way to accomplish this would be to:
>> (a) build OMPI with whatever compiler you decide to use as a "baseline"
>> (b) do -not- use the wrapper compiler to build the application.
>> Instead, do "mpicc --showme" (or whatever language equivalent you
>> want) to get the compile line, substitute your "new" compiler library
>> for the "old" one, and then execute the resulting command manually.
>> If you then set your LD_LIBRARY_PATH to the "new" libs, it might work
>> - but no guarantees. Still, you could try it - and if it worked, you
>> could always just explain that this is a case-by-case situation, and
>> so it -could- break with other compiler combinations.
>> Critical note: the app developers would have to validate the code
>> with every combination! Otherwise, correct execution will be a
>> complete crap-shoot - just because the app doesn't abnormally
>> terminate does -not- mean it generated a correct result!
>> > Thanks for the information on this. We indeed use Intel Compiler
>> set 11.1.XXX + OMPI 1.4.1 and ...
>> users mailing list
>> users_at_[hidden] <mailto:users_at_[hidden]>
> users mailing list