[gmx-users] Installation - can I skip auto-vectorization?

[David van der Spoel]

On Wed, 2005-06-01 at 15:48 -0500, Nathan Moore wrote:
> Here's more detail on the problem, to restate, cross-compiling on ppc64
> system for use on a ppc32 parallel machine:
> 
> I configure with the following script,
> 
> ./configure \
>         --enable-mpi \
>         F77='/opt/ibmcmp/xlf/9.1/bin/blrts_xlf' \
>         CC='/opt/ibmcmp/vac/7.0/bin/blrts_cc' \
>         MPICC='/opt/ibmcmp/vac/7.0/bin/blrts_cc' \
>         CFLAGS="-g -I/bgl/BlueLight/ppcfloor/bglsys/include" \
>         CPPFLAGS="-I/bglhome/usr2/ntmoore/lib/fftw-mpi-single/include" \
>         LDFLAGS="-L/bgl/BlueLight/ppcfloor/bglsys/lib
> -L/bglhome/usr2/ntmoore/lib/fftw-mpi-single/lib" \
>         LIBS=" -lmpich.rts -lmsglayer.rts -lrts.rts -ldevices.rts -lfftw
> -lfftw_mpi -lrfftw -lrfftw_mpi" \
>         --build=ppc-linux-gnu \
>         --target=ppc-bgl-blrtsgnu \
>         --host=powerpc
> 
> Then, following your suggestion, I make,
> 
> cd ./src/gmxlib
> make CFLAGS=-g mkinl
> cd ../..
> make
> 
> Finally, I see the failure in make,
> 
> >>> This is the GROMACS code generator for MD & MC inner loops
> >>> It will generate single precision C code in file innerc.c
> >>> Using gromacs invsqrt code
> >>> Inlining gromacs invsqrt code
> >>> Using normal solvent optimized loops
> >>> Prefetching forces in loops: none
> >>> Nonthreaded inner loops
> >>> Vectorizing invsqrt in loops:none
> Error creating file innerc.c
> make[3]: *** [innerc.c] Error 255
> make[3]: Leaving directory
> `/bglhome/usr2/ntmoore/GROMACS/gromacs-3.2/src/gmxlib'
> make[2]: *** [all-recursive] Error 1
> make[2]: Leaving directory `/bglhome/usr2/ntmoore/GROMACS/gromacs-3.2/src'
> make[1]: *** [all] Error 2
> 
> Any insight into why things fail would be appreciated,

Since you are cross compiling you may need to run mkinl on the target
processor, or better compile mkinl for the compiling processor.

Try running the mkinl program manually, and do also issue the command
file mkinl
to see whether it is supposed to work on your compiling system.
> 
> regards,
> 
> Nathan Moore
> _______________________________________________
> gmx-users mailing list
> gmx-users at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-users
> Please don't post (un)subscribe requests to the list. Use the 
> www interface or send it to gmx-users-request at gromacs.org.
-- 
David.
________________________________________________________________________
David van der Spoel, PhD, Assoc. Prof., Molecular Biophysics group,
Dept. of Cell and Molecular Biology, Uppsala University.
Husargatan 3, Box 596,          75124 Uppsala, Sweden
phone:  46 18 471 4205          fax: 46 18 511 755
spoel at xray.bmc.uu.se    spoel at gromacs.org   http://xray.bmc.uu.se/~spoel
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++