vasp46_intel_serial

.SUFFIXES: .inc .f .f90 .F

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

# Makefile for Intel Fortran compiler for P4 systems

#

# The makefile was tested only under Linux on Intel platforms

# (Suse 5.3- Suse 9.0)

# the followin compiler versions have been tested

# 5.0, 6.0, 7.0 and 7.1 (some 8.0 versions seem to fail compiling the code)

# presently we recommend version 7.1 or 7.0, since these

# releases have been used to compile the present code versions

#

# it might be required to change some of library pathes, since

# LINUX installation vary a lot

# Hence check ***ALL**** options in this makefile very carefully

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

#

# BLAS must be installed on the machine

# there are several options:

# 1) very slow but works:

# retrieve the lapackage from ftp.netlib.org

# and compile the blas routines (BLAS/SRC directory)

# please use g77 or f77 for the compilation. When I tried to

# use pgf77 or pgf90 for BLAS, VASP hang up when calling

# ZHEEV (however this was with lapack 1.1 now I use lapack 2.0)

# 2) most desirable: get an optimized BLAS

#

# the two most reliable packages around are presently:

# 3a) Intels own optimised BLAS (PIII, P4, Itanium)

# http://developer.intel.com/software/products/mkl/

# this is really excellent when you use Intel CPU's

#

# 3b) or obtain the atlas based BLAS routines

# http://math-atlas.sourceforge.net/

# you certainly need atlas on the Athlon, since the mkl

# routines are not optimal on the Athlon.

# If you want to use atlas based BLAS, check the lines around LIB=

#

# 3c) mindblowing fast SSE2 (4 GFlops on P4, 2.53 GHz)

# Kazushige Goto's BLAS

# http://www.cs.utexas.edu/users/kgoto/signup_first.html

#

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

# all CPP processed fortran files have the extension .f90

SUFFIX=.f90

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

# fortran compiler and linker

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

FC=ifort

# fortran linker

FCL=$(FC)

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

# whereis CPP ?? (I need CPP, can't use gcc with proper options)

# that's the location of gcc for SUSE 5.3

#

# CPP_ = /usr/lib/gcc-lib/i486-linux/2.7.2/cpp -P -C

#

# that's probably the right line for some Red Hat distribution:

#

# CPP_ = /usr/lib/gcc-lib/i386-redhat-linux/2.7.2.3/cpp -P -C

#

# SUSE X.X, maybe some Red Hat distributions:

CPP_ = ./preprocess <$*.F | /usr/bin/cpp -P -C -traditional >$*$(SUFFIX)

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

# possible options for CPP:

# NGXhalf charge density reduced in X direction

# wNGXhalf gamma point only reduced in X direction

# avoidalloc avoid ALLOCATE if possible

# IFC work around some IFC bugs

# CACHE_SIZE 1000 for PII,PIII, 5000 for Athlon, 8000-12000 P4

# RPROMU_DGEMV use DGEMV instead of DGEMM in RPRO (depends on used BLAS)

# RACCMU_DGEMV use DGEMV instead of DGEMM in RACC (depends on used BLAS)

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

CPP = $(CPP_) -DHOST=\"LinuxIFC\" \

-Dkind8 -DNGXhalf -DCACHE_SIZE=12000 -DPGF90 -Davoidalloc \

# -DRPROMU_DGEMV -DRACCMU_DGEMV

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

# general fortran flags (there must a trailing blank on this line)

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

FFLAGS = -FR -lowercase -assume byterecl

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

# 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

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

OFLAG=-O3 -xW -tpp7

OFLAG_HIGH = $(OFLAG)

OBJ_HIGH =

OBJ_NOOPT =

DEBUG = -FR -O0

INLINE = $(OFLAG)

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

# the following lines specify the position of BLAS and LAPACK

# on P4, VASP works fastest with the libgoto library

# so that's what I recommend

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

# Atlas based libraries

#ATLASHOME= $(HOME)/archives/BLAS_OPT/ATLAS/lib/Linux_P4SSE2/

#BLAS= -L$(ATLASHOME) -lf77blas -latlas

# use specific libraries (default library path might point to other libraries)

#BLAS= $(ATLASHOME)/libf77blas.a $(ATLASHOME)/libatlas.a

# use the mkl Intel libraries for p4 (www.intel.com)

# mkl.5.1

# set -DRPROMU_DGEMV -DRACCMU_DGEMV in the CPP lines

#BLAS=-L/opt/intel/mkl/lib/32 -lmkl_p4 -lpthread

# mkl.5.2 requires also to -lguide library

# set -DRPROMU_DGEMV -DRACCMU_DGEMV in the CPP lines

#BLAS=-L/opt/intel/mkl/lib/32 -lmkl_p4 -lguide -lpthread

# even faster Kazushige Goto's BLAS

# http://www.cs.utexas.edu/users/kgoto/signup_first.html

BLAS= /opt/libs/libgoto/libgoto_p4_512-r0.6.so

# LAPACK, simplest use vasp.4.lib/lapack_double

LAPACK= ../vasp.4.lib/lapack_double.o

# use atlas optimized part of lapack

#LAPACK= ../vasp.4.lib/lapack_atlas.o -llapack -lcblas

# use the mkl Intel lapack

#LAPACK= -lmkl_lapack

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

LIB = -L../vasp.4.lib -ldmy \

../vasp.4.lib/linpack_double.o $(LAPACK) \

$(BLAS)

# options for linking (for compiler version 6.X, 7.1) nothing is required

LINK =

# compiler version 7.0 generates some vector statments which are located

# in the svml library, add the LIBPATH and the library (just in case)

#LINK = -L/opt/intel/compiler70/ia32/lib/ -lsvml

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

# fft libraries:

# VASP.4.6 can use fftw.3.0.X (http://www.fftw.org)

# since this version is faster on P4 machines, we recommend to use it

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

#FFT3D = fft3dfurth.o fft3dlib.o

FFT3D = fftw3d.o fft3dlib.o /opt/libs/fftw-3.0.1/lib/libfftw3.a

#=======================================================================

# MPI section, uncomment the following lines

#

# one comment for users of mpich or lam:

# You must *not* compile mpi with g77/f77, because f77/g77

# appends *two* underscores to symbols that contain already an

# underscore (i.e. MPI_SEND becomes mpi_send__). The pgf90/ifc

# compilers however append only one underscore.

# Precompiled mpi version will also not work !!!

#

# We found that mpich.1.2.1 and lam-6.5.X to lam-7.0.4 are stable

# mpich.1.2.1 was configured with

# ./configure -prefix=/usr/local/mpich_nodvdbg -fc="pgf77 -Mx,119,0x200000" \

# -f90="pgf90 " \

# --without-romio --without-mpe -opt=-O \

#

# lam was configured with the line

# ./configure -prefix /opt/libs/lam-7.0.4 --with-cflags=-O -with-fc=ifc \

# --with-f77flags=-O --without-romio

#

# please note that you might be able to use a lam or mpich version

# compiled with f77/g77, but then you need to add the following

# options: -Msecond_underscore (compilation) and -g77libs (linking)

#

# !!! Please do not send me any queries on how to install MPI, I will

# certainly not answer them !!!!

#=======================================================================

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

# fortran linker for mpi: if you use LAM and compiled it with the options

# suggested above, you can use the following line

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

#FC=mpif77

#FCL=$(FC)

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

# additional options for CPP in parallel version (see also above):

# NGZhalf charge density reduced in Z direction

# wNGZhalf gamma point only reduced in Z direction

# scaLAPACK use scaLAPACK (usually slower on 100 Mbit Net)

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

#CPP = $(CPP_) -DMPI -DHOST=\"LinuxIFC\" -DIFC \

# -Dkind8 -DNGZhalf -DCACHE_SIZE=4000 -DPGF90 -Davoidalloc \

# -DMPI_BLOCK=500 \

## -DRPROMU_DGEMV -DRACCMU_DGEMV

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

# location of SCALAPACK

# if you do not use SCALAPACK simply uncomment the line SCA

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

BLACS=$(HOME)/archives/SCALAPACK/BLACS/

SCA_=$(HOME)/archives/SCALAPACK/SCALAPACK

SCA= $(SCA_)/libscalapack.a \

$(BLACS)/LIB/blacsF77init_MPI-LINUX-0.a $(BLACS)/LIB/blacs_MPI-LINUX-0.a $(BLACS)/LIB/blacsF77init_MPI-LINUX-0.a

SCA=

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

# libraries for mpi

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

#LIB = -L../vasp.4.lib -ldmy \

# ../vasp.4.lib/linpack_double.o $(LAPACK) \

# $(SCA) $(BLAS)

# FFT: fftmpi.o with fft3dlib of Juergen Furthmueller

#FFT3D = fftmpi.o fftmpi_map.o fft3dlib.o

# fftw.3.0.1 is slighly faster and should be used if available

#FFT3D = fftmpiw.o fftmpi_map.o fft3dlib.o /opt/libs/fftw-3.0.1/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 setex.o radial.o \

pseudo.o mgrid.o mkpoints.o wave.o wave_mpi.o $(BASIC) \

nonl.o nonlr.o dfast.o choleski2.o \

mix.o charge.o xcgrad.o xcspin.o potex1.o potex2.o \

metagga.o constrmag.o pot.o cl_shift.o force.o dos.o elf.o \

tet.o hamil.o steep.o \

chain.o dyna.o relativistic.o LDApU.o sphpro.o paw.o us.o \

ebs.o wavpre.o wavpre_noio.o broyden.o \

dynbr.o rmm-diis.o reader.o writer.o tutor.o xml_writer.o \

brent.o stufak.o fileio.o opergrid.o stepver.o \

dipol.o xclib.o chgloc.o subrot.o optreal.o davidson.o \

edtest.o electron.o shm.o pardens.o paircorrection.o \

optics.o constr_cell_relax.o stm.o finite_diff.o \

elpol.o setlocalpp.o aedens.o

INC=

vasp: $(SOURCE) $(FFT3D) $(INC) main.o

rm -f vasp

$(FCL) -o vasp $(LINK) main.o $(SOURCE) $(FFT3D) $(LIB)

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

poscar.o: poscar.inc poscar.F

mkpoints.o: mkpoints.inc mkpoints.F

wave.o: wave.inc 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 are cummulative (that is once failed

# in one compiler version, stays in the list forever)

# -tpp5|6|7 P, PII-PIII, PIV

# -xW use SIMD (does not pay of on PII, since fft3d uses double prec)

# all other options do no affect the code performance since -O1 is used

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

fft3dlib.o : fft3dlib.F

$(CPP)

$(FC) -FR -lowercase -O1 -tpp7 -xW -unroll0 -e95 -vec_report3 -c $*$(SUFFIX)

fft3dfurth.o : fft3dfurth.F

$(CPP)

$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

radial.o : radial.F

$(CPP)

$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

symlib.o : symlib.F

$(CPP)

$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

symmetry.o : symmetry.F

$(CPP)

$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

dynbr.o : dynbr.F

$(CPP)

$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

broyden.o : broyden.F

$(CPP)

$(FC) -FR -lowercase -O2 -c $*$(SUFFIX)

us.o : us.F

$(CPP)

$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

wave.o : wave.F

$(CPP)

$(FC) -FR -lowercase -O0 -c $*$(SUFFIX)

LDApU.o : LDApU.F

$(CPP)

$(FC) -FR -lowercase -O2 -c $*$(SUFFIX)