[mpich-discuss] NASA NAS Paralllel Benchmarks

chan at mcs.anl.gov chan at mcs.anl.gov
Tue Nov 24 17:31:42 CST 2009


Your CompileFT.out shows that you are using NAS 2.4 and your mpif77
is compiled with g77 which seems to complain that 2 common blocks
ucom and sumcomm are too large.  If you want to continue using NAS 2.4
and g77, you may want to try 1) decrease your problem size, i.e. class size,
2) find some way (compiler options) to tell g77 or the linker to allow
bigger common block. 3) or use some other fortran compiler, like gfortran
or ifort, see if they allow bigger common block (I think we do our
nightly testing with NAS 3.3 with gfortran with no problem, but don't
know what size of the problem we tested.)

A.Chan

----- "Andrew Robertson" <andrew.robertson at atk.com> wrote:

> Folks,
> I am trying to get some benchmarking data on my beowulf cluster. I am
> decided to use the NAS benchmarks. I can get all but one of them to
> compile. I am having trouble with the "ft" benchmark.  I have several
> compilers on the system, so all flags and paths were set explicityl
> in
> the make.def file used to compile the benchmarks.
> 
> I am probably still missing something
> 
> Has anyone had any success compiling this? Could I get your make.def
> file?
> My make.def is attached as well as the results of the compile. All
> the
> other benchmarks compile OK at this point though I have yet to run
> them
> 
> Any help is appreciated
> 
> Thanks
> - Andy 
> 
>  <<make.def>> 
>  <<CompileFT.out>> 
> 
> 
> Andrew Robertson P.E.
> CFD Analyst
> GASL Operations
> Tactical Propulsion and Controls
> ATK
> 77 Raynor Avenue
> Ronkokoma NY 11779
> 631-737-6100 Ext 120
> Fax: 631-588-7023
> www.atk.com
> 
> !! Knowledge and Thoroughness Baby !!
> 
> 
> 
> _______________________________________________
> mpich-discuss mailing list
> mpich-discuss at mcs.anl.gov
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss


More information about the mpich-discuss mailing list