Compilation problem with PGI 7.1
Posted: Tue Feb 26, 2008 2:14 pm
Dear VASP users,
I tried to compile the serial version of VASP by using PGI fortran compiler 7.1 and GotoBLAS. During the compilation, every thing goes fine and I get the executable vasp. But I meet some problems when I execute the vasp, the erro message is as following:
*** glibc detected *** /cluster/home/matl/yxie/vasp4/vasp.4.6/vasp: corrupted double-linked list: 0x0000000012284fb0 ***
======= Backtrace: =========
/lib64/libc.so.6[0x365866f41c]
/lib64/libc.so.6(cfree+0x8c)[0x3658672b1c]
/cluster/home/matl/yxie/vasp4/vasp.4.6/vasp[0x4fe137]
======= Memory map: ========
00400000-00ae3000 r-xp 00000000 00:17 45778483 /cluster/home/matl/yxie/vasp4/vasp.4.6/vasp
00ce2000-00d10000 rwxp 006e2000 00:17 45778483 /cluster/home/matl/yxie/vasp4/vasp.4.6/vasp
00d10000-01089000 rwxp 00d10000 00:00 0
11d0a000-124ce000 rwxp 11d0a000 00:00 0
3658200000-365821a000 r-xp 00000000 08:02 1998850 /lib64/ld-2.5.so
3658419000-365841a000 r-xp 00019000 08:02 1998850 /lib64/ld-2.5.so
365841a000-365841b000 rwxp 0001a000 08:02 1998850 /lib64/ld-2.5.so
3658600000-3658746000 r-xp 00000000 08:02 1998853 /lib64/libc-2.5.so
3658746000-3658946000 ---p 00146000 08:02 1998853 /lib64/libc-2.5.so
3658946000-365894a000 r-xp 00146000 08:02 1998853 /lib64/libc-2.5.so
365894a000-365894b000 rwxp 0014a000 08:02 1998853 /lib64/libc-2.5.so
365894b000-3658950000 rwxp 365894b000 00:00 0
3658e00000-3658e82000 r-xp 00000000 08:02 1998900 /lib64/libm-2.5.so
3658e82000-3659081000 ---p 00082000 08:02 1998900 /lib64/libm-2.5.so
3659081000-3659082000 r-xp 00081000 08:02 1998900 /lib64/libm-2.5.so
3659082000-3659083000 rwxp 00082000 08:02 1998900 /lib64/libm-2.5.so
3659200000-3659215000 r-xp 00000000 08:02 1998876 /lib64/libpthread-2.5.so
3659215000-3659414000 ---p 00015000 08:02 1998876 /lib64/libpthread-2.5.so
3659414000-3659415000 r-xp 00014000 08:02 1998876 /lib64/libpthread-2.5.so
3659415000-3659416000 rwxp 00015000 08:02 1998876 /lib64/libpthread-2.5.so
3659416000-365941a000 rwxp 3659416000 00:00 0
365a200000-365a207000 r-xp 00000000 08:02 1998884 /lib64/librt-2.5.so
365a207000-365a407000 ---p 00007000 08:02 1998884 /lib64/librt-2.5.so
365a407000-365a408000 r-xp 00007000 08:02 1998884 /lib64/librt-2.5.so
365a408000-365a409000 rwxp 00008000 08:02 1998884 /lib64/librt-2.5.so
365c200000-365c20d000 r-xp 00000000 08:02 1999021 /lib64/libgcc_s-4.1.2-20070626.so.1
365c20d000-365c40d000 ---p 0000d000 08:02 1999021 /lib64/libgcc_s-4.1.2-20070626.so.1
365c40d000-365c40e000 rwxp 0000d000 08:02 1999021 /lib64/libgcc_s-4.1.2-20070626.so.1
2aaaaaaab000-2aaaaaab1000 rwxp 2aaaaaaab000 00:00 0
2aaaaaabc000-2aaaab0e5000 rwxp 2aaaaaabc000 00:00 0
2aaaac000000-2aaaac021000 rwxp 2aaaac000000 00:00 0
2aaaac021000-2aaab0000000 ---p 2aaaac021000 00:00 0
7fff42a18000-7fff42a2e000 rwxp 7fff42a18000 00:00 0 [stack]
ffffffffff600000-ffffffffffe00000 ---p 00000000 00:00 0 [vdso]
Here is my makefile:
.SUFFIXES: .inc .f .f90 .F
#-----------------------------------------------------------------------
# Makefile for Portland Group F90/HPF compiler release 3.0-1, 3.1
# and release 1.7
# (http://www.pgroup.com/ & ftp://ftp.pgroup.com/x86/, you need
# to order the HPF/F90 suite)
# we have found no noticable performance differences between
# any of the releases, even Athlon or PIII optimisation does
# not seem to improve performance
#
# The makefile was tested only under Linux on Intel platforms
# (Suse X,X)
#
# 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
#-----------------------------------------------------------------------
#
# Mind that some Linux distributions (Suse 6.1) have a bug in
# libm causing small errors in the error-function (total energy
# is therefore wrong by about 1meV/atom). The recommended
# solution is to update libc.
#
# Mind that some Linux distributions (Suse 6.1) have a bug in
# libm causing small errors in the error-function (total energy
# is therefore wrong by about 1meV/atom). The recommended
# solution is to update libc.
#
# 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
# for a list of optimized BLAS try
# http://www.kachinatech.com/~hjjou/scilib/opt_blas.html
#
# 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.
#
#-----------------------------------------------------------------------
# all CPP processed fortran files have the extension .f
SUFFIX=.f
#-----------------------------------------------------------------------
# fortran compiler and linker
#-----------------------------------------------------------------------
FC=pgf90
# fortran linker
FCL=$(FC)
#-----------------------------------------------------------------------
# whereis CPP ?? (I need CPP, can't use gcc with proper options)
# that's the location of gcc for SUSE 5.3
#
# CPP_ = /usr/lib/gcc-lib/i486-linux/2.7.2/cpp -P -C
#
# that's probably the right line for some Red Hat distribution:
#
# CPP_ = /usr/lib/gcc-lib/i386-redhat-linux/2.7.2.3/cpp -P -C
#
# SUSE 6.X, maybe some Red Hat distributions:
CPP_ = ./preprocess <$*.F | /usr/bin/cpp -P -C -traditional >$*$(SUFFIX)
#-----------------------------------------------------------------------
# possible options for CPP:
# 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 P4
# RPROMU_DGEMV use DGEMV instead of DGEMM in RPRO (usually faster)
# RACCMU_DGEMV use DGEMV instead of DGEMM in RACC (faster on P4)
# **** definitely use -DRACCMU_DGEMV if you use the mkl library
#-----------------------------------------------------------------------
CPP = $(CPP_) -DHOST=\"LinuxIFC\" \
-Dkind8 -DNGXhalf -DCACHE_SIZE=8000 -DPGF90 -Davoidalloc \
# -DRPROMU_DGEMV
#-----------------------------------------------------------------------
# general fortran flags (there must a trailing blank on this line)
# the -Mx,119,0x200000 is required if you use older pgf90 versions
# on a more recent LINUX installation
# the option will not do any harm on other 3.X pgf90 distributions
#-----------------------------------------------------------------------
FFLAGS = -Mfree -tp k8-64 -i4 -Bstatic
#-----------------------------------------------------------------------
# optimization,
# we have tested whether higher optimisation improves
# the performance, and found no improvements with -O3-5 or -fast
# (even on Athlon system, Athlon specific optimistation worsens performance)
#-----------------------------------------------------------------------
OFLAG = -O3
OFLAG_HIGH = $(OFLAG)
OBJ_HIGH =
OBJ_NOOPT =
DEBUG = -O0
INLINE = $(OFLAG)
#-----------------------------------------------------------------------
# the following lines specify the position of BLAS and LAPACK
# what you chose is very system dependent
# P4: VASP works fastest with Intels mkl performance library
# Athlon: Atlas based BLAS are presently the fastest
# P3: no clue
#-----------------------------------------------------------------------
# Atlas based libraries
#ATLASHOME= $(HOME)/Linux_HAMMER64SSE2_2/lib
#BLAS= -L$(ATLASHOME) -LLIBDIR -lf77blas -latlas
# use specific libraries (default library path points to other libraries)
#BLAS= $(ATLASHOME)/libf77blas.a $(ATLASHOME)/libatlas.a
# use the mkl Intel libraries for p4 (www.intel.com)
#BLAS=-L/opt/intel/mkl/lib/32 -lmkl_p4 -lpthread
# even faster Kazushige Goto' BLAS
BLAS= /cluster/home/matl/yxie/GotoBLAS/libgoto_opteron-r1.23.a
# 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) -Bstatic
# options for linking (none required)
LINK = -tp k8-64
#-----------------------------------------------------------------------
# fft libraries:
# VASP.4.5 can use FFTW (http://www.fftw.org)
# since the FFTW is very slow for radices 2^n the fft3dlib is used
# in these cases
# if you use fftw3d you need to insert -lfftw in the LIB line as well
# please do not send us any querries reltated to FFTW (no support)
# if it fails, use fft3dlib
#-----------------------------------------------------------------------
FFT3D = fft3dfurth.o fft3dlib.o
#FFT3D = fftw3d.o fft3dlib.o /cluster/home/matl/yxie/fftw3/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
# compiler however appends only one underscore.
# Precompiled mpi version will also not work !!!
#
# We found that mpich.1.2.1 and lam-6.5.X are stable
# mpich.1.2.1 was configured with
# ./configure -prefix=/usr/local/mpich_nodvdbg -fc="pgf77 -Mx,119,0x200000" \
# -f90="pgf90 -Mx,119,0x200000" \
# --without-romio --without-mpe -opt=-O \
#
# lam was configured with the line
# ./configure -prefix /usr/local/lam-6.5.X --with-cflags=-O -with-fc=pgf90 \
# --with-f77flags=-O --without-romio
#
# lam was generally faster and we found an average communication
# band with of roughly 160 MBit/s (full duplex)
#
# 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 lines
#-----------------------------------------------------------------------
#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=\"LinuxPgi\" \
# -Dkind8 -DNGZhalf -DCACHE_SIZE=2000 -DPGF90 -Davoidalloc -DRPROMU_DGEMV
#-----------------------------------------------------------------------
# location of SCALAPACK
# if you do not use SCALAPACK simply uncomment the line SCA
#-----------------------------------------------------------------------
BLACS=/usr/local/BLACS_lam
SCA_= /usr/local/SCALAPACK_lam
SCA= $(SCA_)/scalapack_LINUX.a $(SCA_)/pblas_LINUX.a $(SCA_)/tools_LINUX.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: only option fftmpi.o with fft3dlib of Juergen Furthmueller
#FFT3D = fftmpi.o fftmpi_map.o fft3dlib.o
#-----------------------------------------------------------------------
# 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
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)
Your advice would be a great help for me.
Thanks very much.
Yours sincerely,
Yu
I tried to compile the serial version of VASP by using PGI fortran compiler 7.1 and GotoBLAS. During the compilation, every thing goes fine and I get the executable vasp. But I meet some problems when I execute the vasp, the erro message is as following:
*** glibc detected *** /cluster/home/matl/yxie/vasp4/vasp.4.6/vasp: corrupted double-linked list: 0x0000000012284fb0 ***
======= Backtrace: =========
/lib64/libc.so.6[0x365866f41c]
/lib64/libc.so.6(cfree+0x8c)[0x3658672b1c]
/cluster/home/matl/yxie/vasp4/vasp.4.6/vasp[0x4fe137]
======= Memory map: ========
00400000-00ae3000 r-xp 00000000 00:17 45778483 /cluster/home/matl/yxie/vasp4/vasp.4.6/vasp
00ce2000-00d10000 rwxp 006e2000 00:17 45778483 /cluster/home/matl/yxie/vasp4/vasp.4.6/vasp
00d10000-01089000 rwxp 00d10000 00:00 0
11d0a000-124ce000 rwxp 11d0a000 00:00 0
3658200000-365821a000 r-xp 00000000 08:02 1998850 /lib64/ld-2.5.so
3658419000-365841a000 r-xp 00019000 08:02 1998850 /lib64/ld-2.5.so
365841a000-365841b000 rwxp 0001a000 08:02 1998850 /lib64/ld-2.5.so
3658600000-3658746000 r-xp 00000000 08:02 1998853 /lib64/libc-2.5.so
3658746000-3658946000 ---p 00146000 08:02 1998853 /lib64/libc-2.5.so
3658946000-365894a000 r-xp 00146000 08:02 1998853 /lib64/libc-2.5.so
365894a000-365894b000 rwxp 0014a000 08:02 1998853 /lib64/libc-2.5.so
365894b000-3658950000 rwxp 365894b000 00:00 0
3658e00000-3658e82000 r-xp 00000000 08:02 1998900 /lib64/libm-2.5.so
3658e82000-3659081000 ---p 00082000 08:02 1998900 /lib64/libm-2.5.so
3659081000-3659082000 r-xp 00081000 08:02 1998900 /lib64/libm-2.5.so
3659082000-3659083000 rwxp 00082000 08:02 1998900 /lib64/libm-2.5.so
3659200000-3659215000 r-xp 00000000 08:02 1998876 /lib64/libpthread-2.5.so
3659215000-3659414000 ---p 00015000 08:02 1998876 /lib64/libpthread-2.5.so
3659414000-3659415000 r-xp 00014000 08:02 1998876 /lib64/libpthread-2.5.so
3659415000-3659416000 rwxp 00015000 08:02 1998876 /lib64/libpthread-2.5.so
3659416000-365941a000 rwxp 3659416000 00:00 0
365a200000-365a207000 r-xp 00000000 08:02 1998884 /lib64/librt-2.5.so
365a207000-365a407000 ---p 00007000 08:02 1998884 /lib64/librt-2.5.so
365a407000-365a408000 r-xp 00007000 08:02 1998884 /lib64/librt-2.5.so
365a408000-365a409000 rwxp 00008000 08:02 1998884 /lib64/librt-2.5.so
365c200000-365c20d000 r-xp 00000000 08:02 1999021 /lib64/libgcc_s-4.1.2-20070626.so.1
365c20d000-365c40d000 ---p 0000d000 08:02 1999021 /lib64/libgcc_s-4.1.2-20070626.so.1
365c40d000-365c40e000 rwxp 0000d000 08:02 1999021 /lib64/libgcc_s-4.1.2-20070626.so.1
2aaaaaaab000-2aaaaaab1000 rwxp 2aaaaaaab000 00:00 0
2aaaaaabc000-2aaaab0e5000 rwxp 2aaaaaabc000 00:00 0
2aaaac000000-2aaaac021000 rwxp 2aaaac000000 00:00 0
2aaaac021000-2aaab0000000 ---p 2aaaac021000 00:00 0
7fff42a18000-7fff42a2e000 rwxp 7fff42a18000 00:00 0 [stack]
ffffffffff600000-ffffffffffe00000 ---p 00000000 00:00 0 [vdso]
Here is my makefile:
.SUFFIXES: .inc .f .f90 .F
#-----------------------------------------------------------------------
# Makefile for Portland Group F90/HPF compiler release 3.0-1, 3.1
# and release 1.7
# (http://www.pgroup.com/ & ftp://ftp.pgroup.com/x86/, you need
# to order the HPF/F90 suite)
# we have found no noticable performance differences between
# any of the releases, even Athlon or PIII optimisation does
# not seem to improve performance
#
# The makefile was tested only under Linux on Intel platforms
# (Suse X,X)
#
# 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
#-----------------------------------------------------------------------
#
# Mind that some Linux distributions (Suse 6.1) have a bug in
# libm causing small errors in the error-function (total energy
# is therefore wrong by about 1meV/atom). The recommended
# solution is to update libc.
#
# Mind that some Linux distributions (Suse 6.1) have a bug in
# libm causing small errors in the error-function (total energy
# is therefore wrong by about 1meV/atom). The recommended
# solution is to update libc.
#
# 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
# for a list of optimized BLAS try
# http://www.kachinatech.com/~hjjou/scilib/opt_blas.html
#
# 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.
#
#-----------------------------------------------------------------------
# all CPP processed fortran files have the extension .f
SUFFIX=.f
#-----------------------------------------------------------------------
# fortran compiler and linker
#-----------------------------------------------------------------------
FC=pgf90
# fortran linker
FCL=$(FC)
#-----------------------------------------------------------------------
# whereis CPP ?? (I need CPP, can't use gcc with proper options)
# that's the location of gcc for SUSE 5.3
#
# CPP_ = /usr/lib/gcc-lib/i486-linux/2.7.2/cpp -P -C
#
# that's probably the right line for some Red Hat distribution:
#
# CPP_ = /usr/lib/gcc-lib/i386-redhat-linux/2.7.2.3/cpp -P -C
#
# SUSE 6.X, maybe some Red Hat distributions:
CPP_ = ./preprocess <$*.F | /usr/bin/cpp -P -C -traditional >$*$(SUFFIX)
#-----------------------------------------------------------------------
# possible options for CPP:
# 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 P4
# RPROMU_DGEMV use DGEMV instead of DGEMM in RPRO (usually faster)
# RACCMU_DGEMV use DGEMV instead of DGEMM in RACC (faster on P4)
# **** definitely use -DRACCMU_DGEMV if you use the mkl library
#-----------------------------------------------------------------------
CPP = $(CPP_) -DHOST=\"LinuxIFC\" \
-Dkind8 -DNGXhalf -DCACHE_SIZE=8000 -DPGF90 -Davoidalloc \
# -DRPROMU_DGEMV
#-----------------------------------------------------------------------
# general fortran flags (there must a trailing blank on this line)
# the -Mx,119,0x200000 is required if you use older pgf90 versions
# on a more recent LINUX installation
# the option will not do any harm on other 3.X pgf90 distributions
#-----------------------------------------------------------------------
FFLAGS = -Mfree -tp k8-64 -i4 -Bstatic
#-----------------------------------------------------------------------
# optimization,
# we have tested whether higher optimisation improves
# the performance, and found no improvements with -O3-5 or -fast
# (even on Athlon system, Athlon specific optimistation worsens performance)
#-----------------------------------------------------------------------
OFLAG = -O3
OFLAG_HIGH = $(OFLAG)
OBJ_HIGH =
OBJ_NOOPT =
DEBUG = -O0
INLINE = $(OFLAG)
#-----------------------------------------------------------------------
# the following lines specify the position of BLAS and LAPACK
# what you chose is very system dependent
# P4: VASP works fastest with Intels mkl performance library
# Athlon: Atlas based BLAS are presently the fastest
# P3: no clue
#-----------------------------------------------------------------------
# Atlas based libraries
#ATLASHOME= $(HOME)/Linux_HAMMER64SSE2_2/lib
#BLAS= -L$(ATLASHOME) -LLIBDIR -lf77blas -latlas
# use specific libraries (default library path points to other libraries)
#BLAS= $(ATLASHOME)/libf77blas.a $(ATLASHOME)/libatlas.a
# use the mkl Intel libraries for p4 (www.intel.com)
#BLAS=-L/opt/intel/mkl/lib/32 -lmkl_p4 -lpthread
# even faster Kazushige Goto' BLAS
BLAS= /cluster/home/matl/yxie/GotoBLAS/libgoto_opteron-r1.23.a
# 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) -Bstatic
# options for linking (none required)
LINK = -tp k8-64
#-----------------------------------------------------------------------
# fft libraries:
# VASP.4.5 can use FFTW (http://www.fftw.org)
# since the FFTW is very slow for radices 2^n the fft3dlib is used
# in these cases
# if you use fftw3d you need to insert -lfftw in the LIB line as well
# please do not send us any querries reltated to FFTW (no support)
# if it fails, use fft3dlib
#-----------------------------------------------------------------------
FFT3D = fft3dfurth.o fft3dlib.o
#FFT3D = fftw3d.o fft3dlib.o /cluster/home/matl/yxie/fftw3/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
# compiler however appends only one underscore.
# Precompiled mpi version will also not work !!!
#
# We found that mpich.1.2.1 and lam-6.5.X are stable
# mpich.1.2.1 was configured with
# ./configure -prefix=/usr/local/mpich_nodvdbg -fc="pgf77 -Mx,119,0x200000" \
# -f90="pgf90 -Mx,119,0x200000" \
# --without-romio --without-mpe -opt=-O \
#
# lam was configured with the line
# ./configure -prefix /usr/local/lam-6.5.X --with-cflags=-O -with-fc=pgf90 \
# --with-f77flags=-O --without-romio
#
# lam was generally faster and we found an average communication
# band with of roughly 160 MBit/s (full duplex)
#
# 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 lines
#-----------------------------------------------------------------------
#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=\"LinuxPgi\" \
# -Dkind8 -DNGZhalf -DCACHE_SIZE=2000 -DPGF90 -Davoidalloc -DRPROMU_DGEMV
#-----------------------------------------------------------------------
# location of SCALAPACK
# if you do not use SCALAPACK simply uncomment the line SCA
#-----------------------------------------------------------------------
BLACS=/usr/local/BLACS_lam
SCA_= /usr/local/SCALAPACK_lam
SCA= $(SCA_)/scalapack_LINUX.a $(SCA_)/pblas_LINUX.a $(SCA_)/tools_LINUX.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: only option fftmpi.o with fft3dlib of Juergen Furthmueller
#FFT3D = fftmpi.o fftmpi_map.o fft3dlib.o
#-----------------------------------------------------------------------
# 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
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)
Your advice would be a great help for me.
Thanks very much.
Yours sincerely,
Yu