VASP.5.2.12编译：Intel Fortran+MPI+MKL

# MKL及其FFTW路径
MKLROOT=/share/apps/intel/composer_xe_2013.2.146/composer_xe_2013.2.146/mkl
FFTWROOT=${MKLROOT}/include/fftw

# 扩展名
.SUFFIXES: .inc .f .f90 .F

# 预处理扩展名
SUFFIX=.f90

# MPI Fortran编译器, 链接器, 可使用绝对路径
# 增加FFTW路径, 以便使用MKL自带的FFTW
FC=mpiifort -I${FFTWROOT}
FCL=$(FC)

# fpp预处理选项
CPP_=fpp -f_com=no -free -w0 $*.F $*$(SUFFIX)

# 编译选项. 注意
# 1. 行尾必须有空格, 数目不限
# 2. byterecl必须使用, 否则WAVECAR文件极大
FFLAGS =  -FR -lowercase -assume byterecl

# 优化选项
# 增加 -xHost -axAVX
OFLAG=-O2 -ip -ftz -xHost -axAVX

# 其他编译选项
OFLAG_HIGH = $(OFLAG)
OBJ_HIGH =
OBJ_NOOPT =
DEBUG  = -FR -O0
INLINE = $(OFLAG)

# MKL, BLAS, LAPACK使用选项
# 1. CPP选项中必须设置 -DRPROMU_DGEMV -DRACCMU-DGEMV
# 2. 使用静态库, 速度可能稍快
# 3. 可参考https://software.intel.com/en-us/articles/intel-mkl-link-line-advisor
BLAS=$(MKLROOT)/lib/intel64/libmkl_blas95_lp64.a
LAPACK=$(MKLROOT)/lib/intel64/libmkl_lapack95_lp64.a

# 链接选项, 使用静态库
LINK=-Wl,--start-group \
	$(MKLROOT)/lib/intel64/libmkl_intel_lp64.a \
	$(MKLROOT)/lib/intel64/libmkl_core.a \
	$(MKLROOT)/lib/intel64/libmkl_intel_thread.a \
	-Wl,--end-group \
	-lpthread -liomp5 -lmpi -lm

# CPP并行选项
# NGZhalf               charge density   reduced in Z direction
# wNGZhalf              gamma point only reduced in Z direction
# scaLAPACK             use scaLAPACK (usually slower on 100 Mbit Net)
# 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
# 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)
# tbdyn                 MD package of Tomas  Bucko
CPP = $(CPP_) -DMPI  -DHOST=\"LinuxIFC\" -DIFC \
	-DCACHE_SIZE=4000 -DPGF90 -Davoidalloc -DNGZhalf \
	-DMPI_BLOCK=8000 \
	-DRPROMU_DGEMV  -DRACCMU_DGEMV

# MPI库
LIB = -L../vasp.5.lib -ldmy  \
	../vasp.5.lib/linpack_double.o $(LAPACK) $(BLAS)

# 使用MKL自带的FFTW
FFT3D   = fftmpiw.o fftmpi_map.o fftw3d.o fft3dlib.o
# 或使用VASP自带的FFTW
#FFT3D   = fftmpi.o fftmpi_map.o fft3dfurth.o fft3dlib.o

# 一般规则, 编译命令行, 以下不可修改
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  \
         $(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  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 \
         steep.o    chain.o    dyna.o     sphpro.o    us.o  core_rel.o \
         aedens.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  \
         chgloc.o   fast_aug.o fock.o     mkpoints_change.o sym_grad.o \
         mymath.o   internals.o dynconstr.o dimer_heyden.o dvvtrajectory.o vdwforcefield.o \
         hamil_high.o nmr.o    pead.o     mlwf.o     subrot.o   subrot_scf.o \
         force.o    pwlhf.o  gw_model.o optreal.o   davidson.o  david_inner.o \
         electron.o rot.o  electron_all.o shm.o    pardens.o  paircorrection.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 linear_response.o   \
         setlocalpp.o  wannier.o electron_OEP.o electron_lhf.o twoelectron4o.o \
         ratpol.o screened_2e.o wave_cacher.o chi_base.o wpot.o local_field.o \
         ump2.o bse_te.o bse.o acfdt.o chi.o sydmat.o dmft.o \
         rmm-diis_mlr.o  linear_response_NMR.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 *.f90; 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.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 -O2 -c $*$(SUFFIX)

fft3dfurth.o : fft3dfurth.F
	$(CPP)
	$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

fftw3d.o : fftw3d.F
	$(CPP)
	$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

wave_high.o : wave_high.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)

wave_mpi.o : wave_mpi.F
	$(CPP)
	$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

wave.o : wave.F
	$(CPP)
	$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

dynbr.o : dynbr.F
	$(CPP)
	$(FC) -FR -lowercase -O1 -c $*$(SUFFIX)

asa.o : asa.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)

LDApU.o : LDApU.F
	$(CPP)
	$(FC) -FR -lowercase -O2 -c $*$(SUFFIX)