| 11:15:32 PM PDT - Sun, Aug 7th 2011 |
|
The following is what I did using the latest versions of the Intel compilers (version 2011 update 4 I believe). Does the use TCGMSG affect the performance significantly?
- !/bin/bash
export LARGE_FILES=TRUE
export ENABLE_COMPONENT=yes
export TCGRSH=/usr/bin/ssh
export USE_MPIF=y
export FOPTIMIZE="-O3 -axSSE2,SSE3,SSSE3,SSE4.1,xSSE4.2 -no-prec-div -funroll-loops -unroll-aggressive"
export COPTIMIZE="-O3 -axSSE2,SSE3,SSSE3,SSE4.1,SSE4.2 -no-prec-div -funroll-loops"
export BLASOPT="-L/opt/intel/composerxe/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_sequential -lmkl_core"
export FC=ifort
export CC=icc
- export USE_GPROF=yes
export USE_SUBGROUPS=yes
export USE_MPI=yes
- export OLD_GA=yes
export MSG_COMMS=MPI
export USE_PYTHON64=yes
export MPI_LOC=/usr
export MPI_INCLUDE=$MPI_LOC/include
export MPI_LIB=$MPI_LOC/lib64/MPICH/p4/intel
export LIBMPI="-lmpich-intel -lmpi -lmpichfarg -lbproc -lmpe"
- export LIBMPI="-lfmpich -lmpich -lpthread" # MPICH2 1.2
- export LIBMPI="-lmpichf90 -lmpich -lmpl -lpthread" # MPICH2 1.3.1
export PYTHONHOME=/usr
export PYTHONVERSION=2.4
export NWCHEM_TOP=`pwd`
export NWCHEM_TARGET=LINUX64
export NWCHEM_MODULES="all python"
export NWCHEM_EXECUTABLE=$NWCHEM_TOP/bin/LINUX64/nwchem
export PYTHONPATH=./:$NWCHEM_TOP/contrib/python/
cd $NWCHEM_TOP/src
- make DIAG=PAR FC=gfortran CC=gcc CDEBUG="-g -ffpe-trap=invalid,zero,overflow" FDEBUG="-g -ffpe-trap=invalid,zero,overflow" FOPTIMIZE="-g -ffpe-trap=invalid,zero,overflow" COPTIMIZE="-g -ffpe-trap=invalid,zero,overflow" nwchem_config
- make DIAG=PAR FC=gfortran CC=gcc CDEBUG="-g -ffpe-trap=invalid,zero,overflow" FDEBUG="-g -ffpe-trap=invalid,zero,overflow" FOPTIMIZE="-g -ffpe-trap=invalid,zero,overflow" COPTIMIZE="-g -ffpe-trap=invalid,zero,overflow" $1
- make DIAG=PAR FC=gfortran CC=gcc CDEBUG="-pg -g" FDEBUG="-pg -g" FOPTIMIZE="-pg -g -O0" COPTIMIZE="-pg -g -O0" nwchem_config
- make DIAG=PAR FC=gfortran CC=gcc CDEBUG="-pg -g" FDEBUG="-pg -g" FOPTIMIZE="-pg -g -O0" COPTIMIZE="-pg -g -O0" $1
make DIAG=PAR FC=ifort CC=icc LARGE_FILES=TRUE ENABLE_COMPONENT=yes TCGRSH=/usr/bin/ssh USE_MPIF=y FOPTIMIZE="-O3 -axSSE2,SSE3,SSSE3,SSE4.1,xSSE4.2 -no-prec-div -funroll-loops -unroll-aggressive" COPTIMIZE="-O3 -axSSE2,SSE3,SSSE3,SSE4.1,SSE4.2 -no-prec-div -funroll-loops" BLASOPT="-L/opt/intel/composerxe/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_sequential -lmkl_core" USE_SUBGROUPS=yes USE_MPI=yes MSG_COMMS=MPI USE_PYTHON64=yes MPI_LOC=/usr MPI_INCLUDE=/usr/include MPI_LIB=/usr/lib64/MPICH/p4/intel LIBMPI="-lmpich-intel -lmpi -lmpichfarg -lbproc -lmpe" PYTHONHOME=/usr PYTHONVERSION=2.4 NWCHEM_TOP=/home/sli/source/nwchem-6.0 NWCHEM_TARGET=LINUX64 NWCHEM_MODULES="all python" NWCHEM_EXECUTABLE=/home/sli/source/nwchem-6.0/bin/LINUX64/nwchem PYTHONPATH=./:/home/sli/source/nwchem-6.0/contrib/python/ nwchem_config
make DIAG=PAR FC=ifort CC=icc LARGE_FILES=TRUE ENABLE_COMPONENT=yes TCGRSH=/usr/bin/ssh USE_MPIF=y FOPTIMIZE="-O3 -axSSE2,SSE3,SSSE3,SSE4.1,xSSE4.2 -no-prec-div -funroll-loops -unroll-aggressive" COPTIMIZE="-O3 -axSSE2,SSE3,SSSE3,SSE4.1,SSE4.2 -no-prec-div -funroll-loops" BLASOPT="-L/opt/intel/composerxe/mkl/lib/intel64 -lmkl_intel_ilp64 -lmkl_sequential -lmkl_core" USE_SUBGROUPS=yes USE_MPI=yes MSG_COMMS=MPI USE_PYTHON64=yes MPI_LOC=/usr MPI_INCLUDE=/usr/include MPI_LIB=/usr/lib64/MPICH/p4/intel LIBMPI="-lmpich-intel -lmpi -lmpichfarg -lbproc -lmpe" PYTHONHOME=/usr PYTHONVERSION=2.4 NWCHEM_TOP=/home/sli/source/nwchem-6.0 NWCHEM_TARGET=LINUX64 NWCHEM_MODULES="all python" NWCHEM_EXECUTABLE=/home/sli/source/nwchem-6.0/bin/LINUX64/nwchem PYTHONPATH=./:/home/sli/source/nwchem-6.0/contrib/python/ $1
|