#!/bin/bash

#-------
#  multi-threaded run: needs to set environment var. OMP_NUM_THREADS 
#    and generally, needs to increase the stack-size:
#   -  sh,bash:
#     > export OMP_NUM_THREADS=2
#     > export KMP_STACKSIZE=400m
#   - csh,tcsh:
#     > setenv OMP_NUM_THREADS 2
#     > setenv KMP_STACKSIZE 400m
#-------

# Composed and tested by ce107 on ross/weddell (Opteron system)
# Should work fine on EM64T and other AMD64 compatible Intel systems
# a) Processor specific flags:
#    1) for more speed on Core2 processors replace -xW with -xT
#    2) for more speed on Pentium4 based EM64T processors replaces -xW with -xP
# b) For more speed, provided your data size doesn't exceed 2GB you can
# remove -fPIC which carries a performance penalty of 2-6%.
# c) Provided that the libraries you link to are compiled with -fPIC this
# optfile should work.
# d) You can replace -fPIC with -mcmodel=medium which may perform faster
# than -fPIC and still support data sizes over 2GB per process but all
# the libraries you link to must be compiled with -fPIC or -mcmodel=medium
# e) Changed from -O3 to -O2 to avoid buggy Intel v.10 compilers. Speed
# impact appears to be minimal.
#
# DON'T FORGET to set environment variable MPI_INC_DIR to the include
# directory of your MPI implementation

NETCDF_ROOT='/opt/intel/netcdf-3.6.2'
MPI_INC_DIR='/opt/intel/mpich-1.2.7p1_ic-10.1.012/include'

FC=mpif77
F90C='mpif90 -fixed'
CC=mpicc
LINK='mpif90 -i-dynamic -no-ipo'
#LINK='mpif90 -i-static -no-ipo'

DEFINES='-DALLOW_USE_MPI -DALWAYS_USE_MPI -DWORDLENGTH=4'
CPP='cpp  -traditional -P'
F90FIXEDFORMAT='-fixed -Tf'
EXTENDED_SRC_FLAG='-132'
OMPFLAG='-openmp'

NOOPTFLAGS='-O0 -g -m64 -fPIC'
NOOPTFILES=''

INCLUDEDIRS=''
INCLUDES=''
LIBS=''

if test "x$DEVEL" != x ; then
    FFLAGS='-r8 -i4 -w95 -W0 -WB -convert big_endian -assume byterecl -fPIC -O0 -g -noalign -fp-stack-check -check all -fpe0 -traceback -ftrapuv -fp-model except -warn all'
else
    FFLAGS='-r8 -i4 -w95 -W0 -WB -convert big_endian -assume byterecl -fPIC'
fi

#  Note that the -mp switch is for ieee "maintain precision" and is
#  roughly equivalent to -ieee
if test "x$IEEE" = x ; then
    #  No need for IEEE-754
    FOPTIM='-O2 -align -xW -ip'
else
    #  Try to follow IEEE-754
#   FOPTIM='-O0 -align -xW -ip -fp-model precise'
    FOPTIM='-O0 -align -xW -ip -fp-model strict'
    FOPTIM="$FOPTIM -g -noalign -fp-stack-check -check all -fpe0 -traceback -ftrapuv"
#   FFLAGS="$FFLAGS -warn all -warn nounused"
fi
F90FLAGS=$FFLAGS
F90OPTIM=$FOPTIM
CFLAGS='-O0 -ip -fPIC'

if [ "x$NETCDF_ROOT" != x ] ; then
    INCLUDEDIRS="${NETCDF_ROOT}/include"
    INCLUDES="-I${NETCDF_ROOT}/include"
    LIBS="-L${NETCDF_ROOT}/lib"
elif [ "x$NETCDF_HOME" != x ]; then
    INCLUDEDIRS="${NETCDF_HOME}/include"
    INCLUDES="-I${NETCDF_HOME}/include"
    LIBS="-L${NETCDF_HOME}/lib"
elif [ "x$NETCDF_INC" != x -a "x$NETCDF_LIB" != x ]; then
    NETCDF_INC=`echo $NETCDF_INC | sed 's/-I//g'`
    NETCDF_LIB=`echo $NETCDF_LIB | sed 's/-L//g'`
    INCLUDEDIRS="${NETCDF_INC}"
    INCLUDES="-I${NETCDF_INC}"
    LIBS="-L${NETCDF_LIB}"
elif [ "x$NETCDF_INCDIR" != x -a "x$NETCDF_LIBDIR" != x ]; then
    INCLUDEDIRS="${NETCDF_INCDIR}"
    INCLUDES="-I${NETCDF_INCDIR}"
    LIBS="-L${NETCDF_LIBDIR}"
elif test -d /usr/include/netcdf-3 ; then
    INCLUDEDIRS='/usr/include/netcdf-3'
    INCLUDES='-I/usr/include/netcdf-3'
    LIBS='-L/usr/lib/netcdf-3 -L/usr/lib64/netcdf-3'
elif test -d /usr/include/netcdf ; then
    INCLUDEDIRS='/usr/include/netcdf'
    INCLUDES='-I/usr/include/netcdf'
elif test -d /usr/local/netcdf ; then
    INCLUDEDIRS='/usr/include/netcdf/include'
    INCLUDES='-I/usr/local/netcdf/include'
    LIBS='-L/usr/local/netcdf/lib'
elif test -d /usr/local/include/netcdf.inc ; then
    INCLUDEDIRS='/usr/local/include'
    INCLUDES='-I/usr/local/include'
    LIBS='-L/usr/local/lib64'
fi


INCLUDES="$INCLUDES -I$MPI_INC_DIR"
INCLUDEDIRS="$INCLUDEDIRS $MPI_INC_DIR"
MPIINCLUDEDIR="$MPI_INC_DIR"
MPI_HEADER_FILES='mpif.h mpiof.h'
MPI_HEADER_FILES_INC='./mpi_headers/mpif.h ./mpi_headers/mpiof.h'