| ²é¿´: 2497 | »Ø¸´: 10 | |||
zhangguangpingľ³æ (ÖøÃûдÊÖ)
|
[½»Á÷]
¡¾ÇóÖú¡¿vasp¼ÆËã³öÏÖµÄvery serious problem¡¾Íê½á¡¿ ÒÑÓÐ2È˲ÎÓë
|
±¾È˸ոտªÊ¼Ñ§Ï°vasp£¬±àÒë±È½Ï˳Àû£¬µ«ÊǼÆËãµÄʱºò³öÏÖÏÂÃæµÄÎÊÌ⣺![]() ±àÒëµÄʱºò²ÉÓõÄmakefileÈçÏ£º ==== .SUFFIXES: .inc .f .f90 .F #----------------------------------------------------------------------- # 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 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/home/zhanggp/intel/mkl/10.0.2.018/lib/em64t -lmkl_intel_lp64 -lguide -lpthread -lmkl_core -lmkl_sequential # 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=-L/home/zhanggp/intel/mkl/10.0.2.018/lib/em64t -lmkl_lapack -lguide ¨Clpthread #----------------------------------------------------------------------- #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=mpif90 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 \ #/home/zhanggp/intel/mkl/10.0.2.018/lib/em64t/libfftw3xf_intel.a # 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 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 -prefetch- -unroll0 -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) ===== ±àÒëµÄʱºòÊÔͼÓÃmklµÄlibfftw3xf_intel.a£¬µ«ÊÇÓÃÉϾͱàÒë³ö´í£¬²»ÓþͺÜ˳Àû¡£ ллָµã£¡ [ Last edited by zhangguangping on 2010-10-27 at 13:33 ] |
» ²ÂÄãϲ»¶
µ÷¼Á
ÒѾÓÐ6È˻ظ´
Ò»Ö¾Ô¸ ½ÄÏ´óѧ 085602 »¯¹¤×¨Ë¶ 338·ÖÇóµ÷¼Á
ÒѾÓÐ12È˻ظ´
²ÄÁÏר˶(0856) 339·ÖÇóµ÷¼Á
ÒѾÓÐ8È˻ظ´
377Çóµ÷¼Á
ÒѾÓÐ5È˻ظ´
0703µ÷¼Á£¬Ò»Ö¾Ô¸Ìì½ò´óѧ319·Ö
ÒѾÓÐ6È˻ظ´
Ò»Ö¾Ô¸Äϲý´óѧ£¬085600£¬344·ÖÇóµ÷¼Á
ÒѾÓÐ5È˻ظ´
308Çóµ÷¼Á
ÒѾÓÐ8È˻ظ´
ÕÒµ÷¼Á
ÒѾÓÐ9È˻ظ´
Ò»Ö¾Ô¸Ö£ÖÝ´óѧ085600Çóµ÷¼Á
ÒѾÓÐ12È˻ظ´
316Çóµ÷¼Á
ÒѾÓÐ3È˻ظ´
» ±¾Ö÷ÌâÏà¹Ø¼ÛÖµÌùÍÆ¼ö£¬¶ÔÄúͬÑùÓаïÖú:
vasp¼ÆËã¹ý¶É̬ÎÊÌâ
ÒѾÓÐ13È˻ظ´
vasp¼ÆËãµÄ°ëµ¼Ìå½á¹¹£¬bands´øÏ¶±ÈdosÀïÃæµÄ´ó£¬ºÎ¹Ê£¿
ÒѾÓÐ33È˻ظ´
vasp¼ÆËãÖУ¬ÈçºÎÑ¡ÔñÕýÈ·µÄKµã
ÒѾÓÐ7È˻ظ´
VASP¼ÆË㣺LORBITÉèÖóöÏÖÎÊÌâ
ÒѾÓÐ5È˻ظ´
VASP±¨´í£ºVERY BAD NEWS!
ÒѾÓÐ5È˻ظ´
vasp¼ÆË㾲̬³öÏÖ´íÎó£¡
ÒѾÓÐ5È˻ظ´
vasp¼ÆËãÔÚ½øÐо²Ì¬¼ÆËãʱ£¬³ö´í¡£
ÒѾÓÐ3È˻ظ´
VASP¼ÆËã̬ÃܶȳöÏÖÎÊÌâ
ÒѾÓÐ12È˻ظ´
¡¾ÇóÖú¡¿vasp¾²Ì¬¼ÆËã³öÏÖµÄWARNING
ÒѾÓÐ18È˻ظ´

bingmou
½ð³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 5
- Ó¦Öú: 2 (Ó×¶ùÔ°)
- ¹ó±ö: 0.446
- ½ð±Ò: 431.9
- É¢½ð: 171
- ºì»¨: 17
- Ìû×Ó: 1207
- ÔÚÏß: 114.8Сʱ
- ³æºÅ: 487243
- ×¢²á: 2007-12-28
- רҵ: ²ÄÁÏ¿ÆÑ§/°ëµ¼Ìå
- ¹ÜϽ: µÚÒ»ÐÔÔÀí
¡ï ¡ï ¡ï
Сľ³æ(½ð±Ò+0.5):¸ø¸öºì°ü£¬Ð»Ð»»ØÌû½»Á÷
mazuju028(½ð±Ò+2):лл»Ø¸´ 2010-10-24 20:18:22
Сľ³æ(½ð±Ò+0.5):¸ø¸öºì°ü£¬Ð»Ð»»ØÌû½»Á÷
mazuju028(½ð±Ò+2):лл»Ø¸´ 2010-10-24 20:18:22
|
Õâ¸öÓ¦¸ÃºÍ±àÒëûÓÐÌ«¶à¹ØÏµ£¬ÕâÊÇÈí¼þ¼ÆËãµÄʱºòµÄ´íÎó¡£ ÄãÊÇ·ñÐÞ¸ÄÁ˵ç×ÓÊý£¿¼ÆËãÏÔʾ£¬ÄãÕâ´Î¼ÆËãµÄµçºÉÊýºÍÉϴεĴÓWAVECARµÃµ½µÄµçºÉÊýÁ¿²»Í¬ ¿ÉÒÔ¿´¿´¹Ù·½£ºhttp://cms.mpi.univie.ac.at/vasp-forum/forum_viewtopic.php?3.1417 ¾Ý˵ÊÇINTEL±àÒëÆ÷µÄÎÊÌâ Èç²»ÓÃÕâ¸ölibfftw3xf_intel.a¾²Ì¬¿â¶øÄÜͨ¹ý£¬ÎÒ¾õµÃºÜ¿ÉÄÜÊDZàÒëµÄʱºòÕÒµ½ÁËlibfftw3xf_intel.soÕâ¸ö¶¯Ì¬¿â£¬×Ô¶¯²ÉÓö¯Ì¬¿âÁË [ Last edited by bingmou on 2010-10-24 at 17:35 ] |
2Â¥2010-10-24 17:31:25
zhangguangping
ľ³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 23
- Ó¦Öú: 71 (³õÖÐÉú)
- ¹ó±ö: 0.031
- ½ð±Ò: 1973.1
- É¢½ð: 9059
- ºì»¨: 79
- Ìû×Ó: 2681
- ÔÚÏß: 2128.8Сʱ
- ³æºÅ: 529624
- ×¢²á: 2008-03-20
- ÐÔ±ð: GG
- רҵ: Ô×ӺͷÖ×ÓÎïÀí

3Â¥2010-10-24 17:40:01
bingmou
½ð³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 5
- Ó¦Öú: 2 (Ó×¶ùÔ°)
- ¹ó±ö: 0.446
- ½ð±Ò: 431.9
- É¢½ð: 171
- ºì»¨: 17
- Ìû×Ó: 1207
- ÔÚÏß: 114.8Сʱ
- ³æºÅ: 487243
- ×¢²á: 2007-12-28
- רҵ: ²ÄÁÏ¿ÆÑ§/°ëµ¼Ìå
- ¹ÜϽ: µÚÒ»ÐÔÔÀí
¡ï
Сľ³æ(½ð±Ò+0.5):¸ø¸öºì°ü£¬Ð»Ð»»ØÌû½»Á÷
Сľ³æ(½ð±Ò+0.5):¸ø¸öºì°ü£¬Ð»Ð»»ØÌû½»Á÷
|
Äã¿ÉÒÔÊÔÊÔ¹Ù·½µÄ·½·¨¡£ËƺõÎÒÒÔǰҲÓöµ½Õâ¸öÎÊÌ⣬4.6.31°æºÃÏñ×îºÃÓÃINTEL 9.0µÄ±àÒëÆ÷£¬Ì«ÐµıàÒëÆ÷»áÓÐÎÊÌ⡣ͬʱ¿ÉÒÔÊÔÊÔÔö¼ÓKµãºÍÉèÖÃFFT¸ñµã |
4Â¥2010-10-24 17:41:50
zhangguangping
ľ³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 23
- Ó¦Öú: 71 (³õÖÐÉú)
- ¹ó±ö: 0.031
- ½ð±Ò: 1973.1
- É¢½ð: 9059
- ºì»¨: 79
- Ìû×Ó: 2681
- ÔÚÏß: 2128.8Сʱ
- ³æºÅ: 529624
- ×¢²á: 2008-03-20
- ÐÔ±ð: GG
- רҵ: Ô×ӺͷÖ×ÓÎïÀí

5Â¥2010-10-24 17:48:29
zhangguangping
ľ³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 23
- Ó¦Öú: 71 (³õÖÐÉú)
- ¹ó±ö: 0.031
- ½ð±Ò: 1973.1
- É¢½ð: 9059
- ºì»¨: 79
- Ìû×Ó: 2681
- ÔÚÏß: 2128.8Сʱ
- ³æºÅ: 529624
- ×¢²á: 2008-03-20
- ÐÔ±ð: GG
- רҵ: Ô×ӺͷÖ×ÓÎïÀí

6Â¥2010-10-25 09:36:02
bingmou
½ð³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 5
- Ó¦Öú: 2 (Ó×¶ùÔ°)
- ¹ó±ö: 0.446
- ½ð±Ò: 431.9
- É¢½ð: 171
- ºì»¨: 17
- Ìû×Ó: 1207
- ÔÚÏß: 114.8Сʱ
- ³æºÅ: 487243
- ×¢²á: 2007-12-28
- רҵ: ²ÄÁÏ¿ÆÑ§/°ëµ¼Ìå
- ¹ÜϽ: µÚÒ»ÐÔÔÀí
¡ï
Сľ³æ(½ð±Ò+0.5):¸ø¸öºì°ü£¬Ð»Ð»»ØÌû½»Á÷
Сľ³æ(½ð±Ò+0.5):¸ø¸öºì°ü£¬Ð»Ð»»ØÌû½»Á÷
| ±àÒëÓÅ»¯¹ý¸ß×ÜÊÇÓзçÏյģ¬ÕâҪȨºâ¡£ºÃµÄ³¬ËãÖÐÐĵÄЧÂʺܸߣ¬¹À¼ÆËûÃǾÍÊǰÑÓÅ»¯×öµÄºÜºÃ¶øÓÖ²»³ö´í |
7Â¥2010-10-25 10:12:42
zhangguangping
ľ³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 23
- Ó¦Öú: 71 (³õÖÐÉú)
- ¹ó±ö: 0.031
- ½ð±Ò: 1973.1
- É¢½ð: 9059
- ºì»¨: 79
- Ìû×Ó: 2681
- ÔÚÏß: 2128.8Сʱ
- ³æºÅ: 529624
- ×¢²á: 2008-03-20
- ÐÔ±ð: GG
- רҵ: Ô×ӺͷÖ×ÓÎïÀí
¡ï
bingmou(½ð±Ò+1):ºÃµÄ£¬¸Ðл·ÖÏí 2010-10-25 19:13:55
bingmou(½ð±Ò+1):ºÃµÄ£¬¸Ðл·ÖÏí 2010-10-25 19:13:55
|
½ñÌìÎÒÓÃ9.1µÄifortÔÚ-O3µÄˮƽϱàÒëÁË,˳Àûͨ¹ý£¬²¢ÇÒ¼ÆËãҲûÎÊÌâ¡£µ«ÊÇ·¢ÏÖ»¹²»Èç10.1µÄÔÚ-O1µÄˮƽϱàÒëµÄÊÇ¿ìÄØ£¡Ö»ÊÇ¿ìÒ»µãµã¡£µ«ÊǼÆËã½á¹ûÍêȫһÑù¡£ µ±È»Õâ¶ùÒ²ÓÐÎÊÌâ´æÔÚ¡£9.1µÄʹÓõÄÊÇRed Hat Enterpise Linux,ÓõÄÊÇ9.1µÄmkl,10.1µÄʹÓõÄÊÇOpensuse,ÓõÄÊÇ10.02µÄmkl. ÎÒÏÂÃæ°ÑÎҵıàÒëµÄmakefile·ÖÏíһϣ¬¹©ºóÀ´µÄС³æÃÇÒÔºó²Î¿¼¡£ |

8Â¥2010-10-25 18:57:31
zhangguangping
ľ³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 23
- Ó¦Öú: 71 (³õÖÐÉú)
- ¹ó±ö: 0.031
- ½ð±Ò: 1973.1
- É¢½ð: 9059
- ºì»¨: 79
- Ìû×Ó: 2681
- ÔÚÏß: 2128.8Сʱ
- ³æºÅ: 529624
- ×¢²á: 2008-03-20
- ÐÔ±ð: GG
- רҵ: Ô×ӺͷÖ×ÓÎïÀí
|
??Red Hat Enterprise Linux Server release 5.4????openSUSE 10.3 (X86-64)??(?????????Intel(R) Xeon(R) CPU E5430)?????Intel Fortran Compiler 10.1.012??MKL 10.0.2.018???OpenMPI-1.4.1???VASP-4.6,??????,???????§Ö???????? ============================= BRMIX: very serious problems the old and the new charge density differ old charge density: 128.00000 new 127.99784 ============================= ?????????bingmou???????VASP????????http://cms.mpi.univie.ac.at/vasp ... ????????·Ú?????? ?????????????? 1)??????????????-O3???-O1,???????????? 2)???????Intel Fortran Compiler 9.1.052 ??MKL 9.1.023???OpenMPI-1.4.3(???????¦Í1.2.6,1.4.1,1.4.3???????????1.4.1??1.4.3??????·Ú?????????????)????,??-O3?????????,???????????????????? ?????????-O3(Red Hat Enterprise Linux Server release 5.4,Intel Fortran Compiler 9.1.052 ,MKL 9.1.023,OpenMPI-1.4.3)??????-O1(openSUSE 10.3 (X86-64),Intel Fortran Compiler 10.1.012,MKL 10.0.2.018,OpenMPI-1.4.1)????????????? ??? (Red Hat Enterprise Linux Server release 5.4,Intel Fortran Compiler 9.1.052 ,MKL 9.1.023,OpenMPI-1.4.3)??-O3??-O1????????,??????????-O3????13??04??,-O1????13??00?????-O3??-O1???????????????????? (Red Hat Enterprise Linux Server release 5.4,Intel Fortran Compiler 10.1.012,MKL 10.0.2.018,OpenMPI-1.4.1)?????????????12??54??,???????????????????MKL???MPI??????????????§³???????????? ????(openSUSE 10.3 (X86-64),Intel Fortran Compiler 10.1.012,MKL 10.0.2.018,OpenMPI-1.4.1)???-O1????11??55???????????????????????????????????????? ?????????????§¹?????????????(openSUSE 10.3 (X86-64),Intel Fortran Compiler 10.1.012,MKL 10.0.2.018,OpenMPI-1.4.1)-O1??8????????11??55??715???????????28??59??1739??,?????30.4%,4??????1093???????39.7%??2??????1507???????57.7%??????????????????????????????????????????????????§¹??????????VASP?????§¹?????????¨¢??? ?????????????????????MKL??libfftw3xf.a,??????????????????????.????????·ÚMKL??libfftw3xf.a??????????GNU??gcc?????,??????icc????????????????????,??????¨¹???? ???????????????????????????????????????¦Ï?????????????????????§Õ???????.???§Ý§Ý?????????????? [ Last edited by zhangguangping on 2010-10-25 at 15:45 ] |

9Â¥2010-10-25 19:26:55
zhangguangping
ľ³æ (ÖøÃûдÊÖ)
- 1STÇ¿Ìû: 23
- Ó¦Öú: 71 (³õÖÐÉú)
- ¹ó±ö: 0.031
- ½ð±Ò: 1973.1
- É¢½ð: 9059
- ºì»¨: 79
- Ìû×Ó: 2681
- ÔÚÏß: 2128.8Сʱ
- ³æºÅ: 529624
- ×¢²á: 2008-03-20
- ÐÔ±ð: GG
- רҵ: Ô×ӺͷÖ×ÓÎïÀí
|
-O1µÄ±àÒë²ÎÊý(openSUSE 10.3 (X86-64),Intel Fortran Compiler 10.1.012,MKL 10.0.2.018,OpenMPI-1.4.1)£º =================================== .SUFFIXES: .inc .f .f90 .F SUFFIX=.f90 FC=mpif90 FCL=$(FC) FFLAGS = -FR -lowercase -assume byterecl OFLAG= -O1 OFLAG_HIGH = $(OFLAG) OBJ_HIGH = OBJ_NOOPT = DEBUG = -FR -O0 INLINE = $(OFLAG) LINK = CPP_ = ./preprocess <$*.F | /usr/bin/cpp -P -C -traditional >$*$(SUFFIX) CPP = $(CPP_) -DMPI -DHOST=\"LinuxIFC\" -DIFC \ -Dkind8 -DNGZhalf -DCACHE_SIZE=4000 -DPGF90 -Davoidalloc \ -DMPI_BLOCK=500 \ -DRPROMU_DGEMV -DRACCMU_DGEMV BLAS=-L/home/zhanggp/intel/mkl/10.0.2.018/lib/em64t -lmkl_intel_lp64 -lguide -lpthread -lmkl_core -lmkl_sequential LAPACK=-L/home/zhanggp/intel/mkl/10.0.2.018/lib/em64t -lmkl_lapack -lguide ¨Clpthread SCA= LIB = -L../vasp.4.lib -ldmy \ ../vasp.4.lib/linpack_double.o $(LAPACK) \ $(SCA) $(BLAS) 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) # 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 -prefetch- -unroll0 -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) ============================================= |

10Â¥2010-10-25 19:28:20















»Ø¸´´ËÂ¥