.SUFFIXES: .inc .f .f90 .F
#-----------------------------------------------------------------------
# Makefile for Intel Fortran compiler for Pentium/Athlon/Opteron
# based systems
# we recommend this makefile for both Intel as well as AMD systems
# for AMD based systems appropriate BLAS (libgoto) and fftw libraries are
# however mandatory (whereas they are optional for Intel platforms)
#-----------------------------------------------------------------------
#-----------------------------------------------------------------------

# all CPP processed fortran files have the extension .f90
SUFFIX=.f90

#-----------------------------------------------------------------------
# fortran compiler and linker
#-----------------------------------------------------------------------
FC=mpif90
# fortran linker
FCL=$(FC)


#-----------------------------------------------------------------------
#CPP_ =  ./preprocess <$*.F | /usr/bin/cpp -P -C -traditional >$*$(SUFFIX)
# this release should be fpp clean
# we now recommend fpp as preprocessor
# if this fails go back to cpp
CPP_=fpp -f_com=no -free -w0 $*.F $*$(SUFFIX)

#-----------------------------------------------------------------------
# possible options for CPP:
# DMPI                compile parallel version of vasp
# noSTOPCAR           do not check for a stopcar at each electronic iteration
# NGZhalf             charge density   reduced in Z directio
# wNGXhalf            gamma point only reduced in X direction
# avoidalloc          avoid ALLOCATE if possible
# PGF90               work around some for some PGF90 / IFC bugs
# CACHE_SIZE          1000 for PII,PIII, 5000 for Athlon, 8000-12000 P4, PD
# tbdyn                 MD package of Tomas  Bucko
#-----------------------------------------------------------------------

CPP     = $(CPP_) -DMPI -DHOST=\"LinuxIFCmkl\" -DIFC  \
          -DCACHE_SIZE=12000 -DPGF90 -Davoidalloc -DNGZhalf \
          -DnoSTOPCAR -Duse_collective -DMPI_BLOCK=26144

#-----------------------------------------------------------------------
# general fortran flags  (there must a trailing blank on this line)
# byterecl is strictly required for ifc, since otherwise
# the WAVECAR file becomes huge
#-----------------------------------------------------------------------
# -ftz flush denormal results to zero
        FFLAGS =  -free -names lowercase -assume byterecl -ftz

#-----------------------------------------------------------------------
# optimization
# we have tested whether higher optimisation improves performance
# -axK  SSE1 optimization,  but also generate code executable on all mach.
#       xK improves performance somewhat on XP, and a is required in order
#       to run the code on older Athlons as well
# -xW   SSE2 optimization
# -axW  SSE2 optimization,  but also generate code executable on all mach.
# -tpp6 P3 optimization
# -tpp7 P4 optimization
#-----------------------------------------------------------------------

# -host
OFLAG=-O1 -ip  -xhost
OFLAG_HIGH = $(OFLAG)
OBJ_HIGH =
OBJ_NOOPT =
DEBUG  = -FR -O0
INLINE = $(OFLAG)

#-----------------------------------------------------------------------
# we recommend to use mkl, that is simple and most likely
# fastest in Intel based machines
#-----------------------------------------------------------------------


MKL_PATH=$(MKLROOT)/lib/intel64/
MKL_FFTW_PATH=$(MKLROOT)/interfaces/fftw3xf/

BLAS= -L$(MKL) -lmkl_cdft_core -lmkl_intel_lp64 -lmkl_core -lmkl_sequential -lmkl_blacs_intelmpi_lp64 -lpthread -lm


# LAPACK from mkl, usually faster and contains scaLAPACK as well
LAPACK= $(MKL_PATH)/libmkl_intel_lp64.a

#-----------------------------------------------------------------------

#-----------------------------------------------------------------------
# fft libraries:
# VASP.5.2 can use fftw.3.1.X (http://www.fftw.org)
# since this version is faster on P4 machines, we recommend to use it
#-----------------------------------------------------------------------

FFT3D   = fft3dfurth.o fft3dlib.o

# alternatively: fftw.3.1.X is slighly faster and should be used if available
#FFT3D   = fftw3d.o fft3dlib.o   /opt/libs/fftw-3.1.2/lib/libfftw3.a

# you may also try to use the fftw wrapper to mkl (but the path might vary a lot)
# it seems this is best for AMD based systems
#FFT3D   = fftw3d.o fft3dlib.o $(MKL_FFTW_PATH)/libfftw3xf_intel.a
#INCS = -I$(MKLROOT)/include/fftw
INCS = -I$(MPI_HOME)/include

#BLACS= -lmkl_blacs_openmpi_lp64
#BLACS = -lmkl_blacs_lp64.a
#SCA= $(MKL_PATH)/libmkl_scalapack_lp64.a $(BLACS)
#SCA= $(MKL_PATH)/libmkl_scalapack_lp64.a

#-----------------------------------------------------------------------
# libraries
#-----------------------------------------------------------------------

LIB     = -L../vasp.5.lib -ldmy  \
      ../vasp.5.lib/linpack_double.o \
      $(SCA) $(LAPACK) $(BLAS) -L$(MPI_LIBDIR) $(MPI_LIBS)

#-----------------------------------------------------------------------
# parallel FFT
#-----------------------------------------------------------------------

# FFT: fftmpi.o with fft3dlib of Juergen Furthmueller
#FFT3D   = fftmpi.o fftmpi_map.o fft3dfurth.o fft3dlib.o

# alternatively: fftw.3.1.X is slighly faster and should be used if available
FFT3D   = fftmpiw.o fftmpi_map.o fftw3d.o fft3dlib.o
#/opt/libs/fftw-3.1.2/lib/libfftw3.a

#-----------------------------------------------------------------------
# general rules and compile lines
#-----------------------------------------------------------------------
BASIC=   symmetry.o symlib.o   lattlib.o  random.o


SOURCE=  base.o     mpi.o      smart_allocate.o      xml.o  \
         constant.o jacobi.o   main_mpi.o  scala.o   \
         asa.o      lattice.o  poscar.o   ini.o  mgrid.o  xclib.o  vdw_nl.o  xclib_grad.o \
         radial.o   pseudo.o   gridq.o     ebs.o  \
         mkpoints.o wave.o     wave_mpi.o  wave_high.o  spinsym.o \
         $(BASIC)   nonl.o     nonlr.o    nonl_high.o dfast.o    choleski2.o \
         mix.o      hamil.o    xcgrad.o   xcspin.o    potex1.o   potex2.o  \
         constrmag.o cl_shift.o relativistic.o LDApU.o \
         paw_base.o metagga.o  egrad.o    pawsym.o   pawfock.o  pawlhf.o   rhfatm.o  hyperfine.o paw.o   \
         mkpoints_full.o       charge.o   Lebedev-Laikov.o  stockholder.o dipol.o    pot.o \
         dos.o      elf.o      tet.o      tetweight.o hamil_rot.o \
         chain.o    dyna.o     k-proj.o    sphpro.o    us.o  core_rel.o \
         aedens.o   wavpre.o   wavpre_noio.o broyden.o \
         dynbr.o    hamil_high.o  rmm-diis.o reader.o   writer.o   tutor.o xml_writer.o \
         brent.o    stufak.o   fileio.o   opergrid.o stepver.o  \
         chgloc.o   fast_aug.o fock_multipole.o  fock.o  mkpoints_change.o sym_grad.o \
         mymath.o   internals.o npt_dynamics.o   dynconstr.o dimer_heyden.o dvvtrajectory.o subdftd3.o \
         vdwforcefield.o nmr.o      pead.o     subrot.o   subrot_scf.o  paircorrection.o \
         force.o    pwlhf.o    gw_model.o optreal.o  steep.o    davidson.o  david_inner.o \
         electron.o rot.o  electron_all.o shm.o    pardens.o  \
         optics.o   constr_cell_relax.o   stm.o    finite_diff.o elpol.o    \
         hamil_lr.o rmm-diis_lr.o  subrot_cluster.o subrot_lr.o \
         lr_helper.o hamil_lrf.o   elinear_response.o ilinear_response.o \
         linear_optics.o \
         setlocalpp.o  wannier.o electron_OEP.o electron_lhf.o twoelectron4o.o \
         gauss_quad.o m_unirnk.o minimax_tabs.o minimax.o \
         mlwf.o     ratpol.o screened_2e.o wave_cacher.o chi_base.o wpot.o \
         local_field.o ump2.o ump2kpar.o fcidump.o ump2no.o \
         bse_te.o bse.o acfdt.o chi.o sydmat.o \
         lcao_bare.o wnpr.o dmft.o \
         rmm-diis_mlr.o  linear_response_NMR.o wannier_interpol.o linear_response.o  auger.o getshmem.o \
         dmatrix.o

vasp: $(SOURCE) $(FFT3D) $(INC) main.o
        rm -f vasp
        $(FCL) -o vasp main.o  $(SOURCE)   $(FFT3D) $(LIB) $(LINK)
makeparam: $(SOURCE) $(FFT3D) makeparam.o main.F $(INC)
        $(FCL) -o makeparam  $(LINK) makeparam.o $(SOURCE) $(FFT3D) $(LIB)
zgemmtest: zgemmtest.o base.o random.o $(INC)
        $(FCL) -o zgemmtest $(LINK) zgemmtest.o random.o base.o $(LIB)
dgemmtest: dgemmtest.o base.o random.o $(INC)
        $(FCL) -o dgemmtest $(LINK) dgemmtest.o random.o base.o $(LIB)
ffttest: base.o smart_allocate.o mpi.o mgrid.o random.o ffttest.o $(FFT3D) $(INC)
        $(FCL) -o ffttest $(LINK) ffttest.o mpi.o mgrid.o random.o smart_allocate.o base.o $(FFT3D) $(LIB)
kpoints: $(SOURCE) $(FFT3D) makekpoints.o main.F $(INC)
        $(FCL) -o kpoints $(LINK) makekpoints.o $(SOURCE) $(FFT3D) $(LIB)

clean:
        -rm -f *.g *.f *.o *.L *.mod ; touch *.F

main.o: main$(SUFFIX)
        $(FC) $(FFLAGS)$(DEBUG)  $(INCS) -c main$(SUFFIX)
xcgrad.o: xcgrad$(SUFFIX)
        $(FC) $(FFLAGS) $(INLINE)  $(INCS) -c xcgrad$(SUFFIX)
xcspin.o: xcspin$(SUFFIX)
        $(FC) $(FFLAGS) $(INLINE)  $(INCS) -c xcspin$(SUFFIX)

makeparam.o: makeparam$(SUFFIX)
        $(FC) $(FFLAGS)$(DEBUG)  $(INCS) -c makeparam$(SUFFIX)

makeparam$(SUFFIX): makeparam.F main.F
#
# MIND: I do not have a full dependency list for the include
# and MODULES: here are only the minimal basic dependencies
# if one strucuture is changed then touch_dep must be called
# with the corresponding name of the structure
#
base.o: base.inc base.F
mgrid.o: mgrid.inc mgrid.F
constant.o: constant.inc constant.F
lattice.o: lattice.inc lattice.F
setex.o: setexm.inc setex.F
pseudo.o: pseudo.inc pseudo.F
mkpoints.o: mkpoints.inc mkpoints.F
wave.o: wave.F
nonl.o: nonl.inc nonl.F
nonlr.o: nonlr.inc nonlr.F

$(OBJ_HIGH):
        $(CPP)
        $(FC) $(FFLAGS) $(OFLAG_HIGH) $(INCS) -c $*$(SUFFIX)
$(OBJ_NOOPT):
        $(CPP)
        $(FC) $(FFLAGS) $(INCS) -c $*$(SUFFIX)

fft3dlib_f77.o: fft3dlib_f77.F
        $(CPP)
        $(F77) $(FFLAGS_F77) -c $*$(SUFFIX)

.F.o:
        $(CPP)
        $(FC) $(FFLAGS) $(OFLAG) $(INCS) -c $*$(SUFFIX)
.F$(SUFFIX):
        $(CPP)
$(SUFFIX).o:
        $(FC) $(FFLAGS) $(OFLAG) $(INCS) -c $*$(SUFFIX)

# special rules
#-----------------------------------------------------------------------
# these special rules have been tested for ifc.11 and ifc.12 only

fft3dlib.o : fft3dlib.F
        $(CPP)
        $(FC) -FR -lowercase -O2 -c $*$(SUFFIX)
fft3dfurth.o : fft3dfurth.F
        $(CPP)
        $(FC) -FR -lowercase -O1 -c $*$(SUFFIX)
fftw3d.o : fftw3d.F
        $(CPP)
        $(FC) -FR -lowercase -O1 $(INCS) -c $*$(SUFFIX)
fftmpi.o : fftmpi.F
        $(CPP)
        $(FC) -FR -lowercase -O1 -c $*$(SUFFIX)
fftmpiw.o : fftmpiw.F
        $(CPP)
        $(FC) -FR -lowercase -O1 $(INCS) -c $*$(SUFFIX)
wave_high.o : wave_high.F
        $(CPP)
        $(FC) -FR -lowercase -O1 -c $*$(SUFFIX)
# the following rules are probably no longer required (-O3 seems to work)
wave.o : wave.F
        $(CPP)
        $(FC) -FR -lowercase -O2 -c $*$(SUFFIX)
paw.o : paw.F
        $(CPP)
        $(FC) -FR -lowercase -O1 -c $*$(SUFFIX)
cl_shift.o : cl_shift.F
        $(CPP)
        $(FC) -FR -lowercase -O2 -c $*$(SUFFIX)
us.o : us.F
        $(CPP)
        $(FC) -FR -lowercase -O1 -c $*$(SUFFIX)
LDApU.o : LDApU.F
        $(CPP)
        $(FC) -FR -lowercase -O2 -c $*$(SUFFIX)
#LDApU.o : davidson.F
#       $(CPP)
#       $(FC) -FR -lowercase -O1 -c $*$(SUFFIX)