[Pw_forum] mkl problem
Osman Baris Malcioglu
baris.malcioglu at gmail.com
Fri Jun 4 21:35:00 CEST 2010
Dear Giuseppe,
Please notice that you are using an older (obsolete? eh, Intel certainly thinks so) version of MKL, the new standard INTEL has for MKL compile line is different (http://software.intel.com/en-us/articles/intel-mkl-link-line-advisor/)
Newer versions of the espresso configure script look for the latter one.
If there is significant demand for the older version, the configure script can be modified, with a sacrifice in performance in the configuration step of some select cases.
Please let us know,
Baris
On 04.Haz.2010, at 12:28, Giuseppe Mattioli wrote:
> Dear Ricardo
> It seems to work... But I would ask the developers why does the configure
> script not found any mkl even if they are in the path...
> Thank you very much
> Giuseppe
>
> On Thursday 03 June 2010 11:48:56 Ricardo Faccio wrote:
>> Hi
>> I faced almost the same problem but in a single QuadCore PC, I edited the
>> make.sys file by hand and then it looks like as following.
>> And it works!
>> Regards
>> Ricardo
>> -------------------------------------------------
>> Dr. Ricardo Faccio
>> Prof. Adjunto de Física
>> Mail: Cryssmat-Lab., Cátedra de Física, DETEMA
>> Facultad de Química, Universidad de la República
>> Av. Gral. Flores 2124, C.C. 1157
>> C.P. 11800, Montevideo, Uruguay.
>> E-mail: rfaccio at fq.edu.uy
>> Phone: 598 2 924 98 59
>> 598 2 929 06 48
>> Fax: 598 2 9241906
>> Web: http://cryssmat.fq.edu.uy/ricardo/ricardo.htm
>>
>> # make.sys. Generated from make.sys.in by configure.
>>
>> # compilation rules
>>
>> .SUFFIXES :
>> .SUFFIXES : .o .c .f .f90
>>
>> # most fortran compilers can directly preprocess c-like directives: use
>> # $(MPIF90) $(F90FLAGS) -c $<
>> # if explicit preprocessing by the C preprocessor is needed, use:
>> # $(CPP) $(CPPFLAGS) $< -o $*.F90
>> # $(MPIF90) $(F90FLAGS) -c $*.F90 -o $*.o
>> # remember the tabulator in the first column !!!
>>
>> .f90.o:
>> $(MPIF90) $(F90FLAGS) -c $<
>>
>> # .f.o and .c.o: do not modify
>>
>> .f.o:
>> $(F77) $(FFLAGS) -c $<
>>
>> .c.o:
>> $(CC) $(CFLAGS) -c $<
>>
>>
>> # DFLAGS = precompilation options (possible arguments to -D and -U)
>> # used by the C compiler and preprocessor
>> # FDFLAGS = as DFLAGS, for the f90 compiler
>> # See include/defs.h.README for a list of options and their meaning
>> # With the exception of IBM xlf, FDFLAGS = $(DFLAGS)
>> # For IBM xlf, FDFLAGS is the same as DFLAGS with separating commas
>>
>> DFLAGS = -D__INTEL -D__FFTW
>> FDFLAGS = $(DFLAGS)
>>
>> # IFLAGS = how to locate directories where files to be included are
>> # In most cases, IFLAGS = -I../include
>>
>> IFLAGS = -I../include
>>
>> # MOD_FLAGS = flag used by f90 compiler to locate modules
>> # Each Makefile defines the list of needed modules in MODFLAGS
>>
>> MOD_FLAG = -I
>>
>> # Compilers: fortran-90, fortran-77, C
>> # If a parallel compilation is desired, MPIF90 should be a fortran-90
>> # compiler that produces executables for parallel execution using MPI
>> # (such as for instance mpif90, mpf90, mpxlf90,...);
>> # otherwise, an ordinary fortran-90 compiler (f90, g95, xlf90, ifort,...)
>> # If you have a parallel machine but no suitable candidate for MPIF90,
>> # try to specify the directory containing "mpif.h" in IFLAGS
>> # and to specify the location of MPI libraries in MPI_LIBS
>>
>> MPIF90 = ifort
>> #F90 = ifort
>> CC = gcc
>> F77 = ifort
>>
>> # C preprocessor and preprocessing flags - for explicit preprocessing,
>> # if needed (see the compilation rules above)
>> # preprocessing flags must include DFLAGS and IFLAGS
>>
>> CPP = cpp
>> CPPFLAGS = -P -traditional $(DFLAGS) $(IFLAGS)
>>
>> # compiler flags: C, F90, F77
>> # C flags must include DFLAGS and IFLAGS
>> # F90 flags must include MODFLAGS, IFLAGS, and FDFLAGS with appropriate
>> syntax
>>
>> CFLAGS = -O3 $(DFLAGS) $(IFLAGS)
>> F90FLAGS = $(FFLAGS) -nomodule -fpp $(FDFLAGS) $(IFLAGS) $(MODFLAGS)
>> FFLAGS = -O2 -assume byterecl -g -traceback
>>
>> # compiler flags without optimization for fortran-77
>> # the latter is NEEDED to properly compile dlamch.f, used by lapack
>>
>> FFLAGS_NOOPT = -O0 -assume byterecl -g -traceback
>>
>> # Linker, linker-specific flags (if any)
>> # Typically LD coincides with F90 or MPIF90, LD_LIBS is empty
>>
>> LD = ifort
>> LDFLAGS =
>> LD_LIBS =
>>
>> # External Libraries (if any) : blas, lapack, fft, MPI
>>
>> # If you have nothing better, use the local copy :
>> # BLAS_LIBS = /your/path/to/espresso/BLAS/blas.a
>> # BLAS_LIBS_SWITCH = internal
>>
>> BLAS_LIBS = -L/opt/intel/mkl/10.0.5.025/lib/em64t -lmkl_em64t
>> BLAS_LIBS_SWITCH = internal
>>
>> # If you have nothing better, use the local copy :
>> # LAPACK_LIBS = /your/path/to/espresso/LAPACK/lapack.a
>> # LAPACK_LIBS_SWITCH = internal
>>
>> # The following lapack libraries will be available in flib/ :
>> # ../flib/lapack.a : contains all needed routines
>> # ../flib/lapack_atlas.a: only routines not present in the Atlas library
>> # For IBM machines with essl (-D__ESSL): load essl BEFORE lapack !
>> # remember that LAPACK_LIBS precedes BLAS_LIBS in loading order
>>
>> LAPACK_LIBS = -L/opt/intel/mkl/10.0.5.025/lib/em64t -lmkl_lapack
>> -lmkl_sequential -lmkl_core -lmkl_intel_lp64
>> LAPACK_LIBS_SWITCH = internal
>>
>> SCALAPACK_LIBS =
>>
>> # nothing needed here if the the internal copy of FFTW is compiled
>> # (needs -D__FFTW in DFLAGS)
>>
>> FFT_LIBS =
>>
>> # For parallel execution, the correct path to MPI libraries must
>> # be specified in MPI_LIBS (except for IBM if you use mpxlf)
>>
>> MPI_LIBS =
>>
>> # IBM-specific: MASS libraries, if available and if -D__MASS is defined in
>> FDFLAGS
>>
>> MASS_LIBS =
>>
>> # pgplot libraries (used by some post-processing tools)
>>
>> PGPLOT_LIBS =
>>
>> # ar command and flags - for most architectures: AR = ar, ARFLAGS = ruv
>>
>> AR = ar
>> ARFLAGS = ruv
>>
>> # ranlib command. If ranlib is not needed (it isn't in most cases) use
>> # RANLIB = echo
>>
>> RANLIB = ranlib
>>
>> # all internal and external libraries - do not modify
>>
>> FLIB_TARGETS = all
>>
>> LIBOBJS = ../flib/ptools.a ../flib/flib.a ../clib/clib.a
>> ../iotk/src/libiotk.a ../Multigrid/mglib.a
>> LIBS = $(SCALAPACK_LIBS) $(LAPACK_LIBS) $(FFT_LIBS) $(BLAS_LIBS)
>> $(MPI_LIBS) $(MASS_LIBS) $(PGPLOT_LIBS) $(LD_LIBS)
>>
>> # topdir for linking espresso libs with plugins
>> TOPDIR = /home/rfaccio/espresso-4.2
>>
>>> Dear all
>>> I'm facing some problems with mkl & QE 4.2 on a linux cluster. In the
>>> case of
>>> 4.1, the configure script found (and still find...) the installed mkl
>>> 10.0.4.023 version and the make.sys looked like
>>>
>>> BLAS_LIBS = -L/opt/intel/mkl/10.0.4.023/lib/em64t -lmkl_em64t
>>> LAPACK_LIBS = -L/opt/intel/mkl/10.0.4.023/lib/em64t -lmkl_em64t
>>>
>>> QE 4.1 has been succesfully compiled and works fine.
>>>
>>> In the case of 4.2 the configure script does not find any external lapack
>>> or
>>> blas lib. I've tryed to use the './configure LIBDIRS=...' command but it
>>> still does not find any lapack or blas lib. I would like to manually link
>>> the
>>> libs (./configure LAPACK_LIBS=... BLAS_LIBS=...) , but I do not know what
>>> exactly I'm supposed to link...
>>>
>>> /opt/intel/mkl/10.0.4.023/lib/64
>>>
>>> libguide.a libmkl_blacs_openmpi_ilp64.a
>>> libmkl_gf_lp64.a libmkl_intel_sp2dp.so libmkl_sequential.so
>>> libguide.so libmkl_blacs_openmpi_lp64.a
>>> libmkl_gf_lp64.so libmkl_intel_thread.a libmkl.so
>>> libiomp5.a libmkl_blacs_sgimpt_ilp64.a
>>> libmkl_gnu_thread.a libmkl_intel_thread.so libmkl_solver.a
>>> libiomp5.so libmkl_blacs_sgimpt_lp64.a
>>> libmkl_gnu_thread.so libmkl_ipf.a libmkl_solver_ilp64.a
>>> libmkl_blacs_ilp64.a libmkl_cdft.a
>>> libmkl_i2p.so
>>> libmkl_lapack.a libmkl_solver_ilp64_sequential.a
>>> libmkl_blacs_intelmpi20_ilp64.a libmkl_cdft_core.a
>>> libmkl_intel_ilp64.a libmkl_lapack.so libmkl_solver_lp64.a
>>> libmkl_blacs_intelmpi20_lp64.a libmkl_core.a
>>> libmkl_intel_ilp64.so libmkl_scalapack.a
>>> libmkl_solver_lp64_sequential.a
>>> libmkl_blacs_intelmpi_ilp64.a libmkl_core.so
>>> libmkl_intel_lp64.a libmkl_scalapack_ilp64.a libmkl_vml_i2p.so
>>> libmkl_blacs_intelmpi_lp64.a libmkl_gf_ilp64.a
>>> libmkl_intel_lp64.so libmkl_scalapack_lp64.a
>>> libmkl_blacs_lp64.a libmkl_gf_ilp64.so
>>> libmkl_intel_sp2dp.a libmkl_sequential.a
>>>
>>> or
>>>
>>> /opt/intel/mkl/10.0.4.023/lib/em64t
>>>
>>> libguide.a libmkl_blacs_openmpi_lp64.a
>>> libmkl_gnu_thread.a libmkl_lapack.so
>>> libmkl_solver_ilp64_sequential.a
>>> libguide.so libmkl_cdft.a
>>> libmkl_gnu_thread.so libmkl_mc.so libmkl_solver_lp64.a
>>> libiomp5.a libmkl_cdft_core.a
>>> libmkl_intel_ilp64.a libmkl_p4n.so
>>> libmkl_solver_lp64_sequential.a
>>> libiomp5.so libmkl_core.a
>>> libmkl_intel_ilp64.so libmkl_scalapack.a libmkl_vml_def.so
>>> libmkl_blacs_ilp64.a libmkl_core.so
>>> libmkl_intel_lp64.a libmkl_scalapack_ilp64.a libmkl_vml_mc2.so
>>> libmkl_blacs_intelmpi20_ilp64.a libmkl_def.so
>>> libmkl_intel_lp64.so libmkl_scalapack_lp64.a libmkl_vml_mc.so
>>> libmkl_blacs_intelmpi20_lp64.a libmkl_em64t.a
>>> libmkl_intel_sp2dp.a libmkl_sequential.a libmkl_vml_p4n.so
>>> libmkl_blacs_intelmpi_ilp64.a libmkl_gf_ilp64.a
>>> libmkl_intel_sp2dp.so libmkl_sequential.so
>>> libmkl_blacs_intelmpi_lp64.a libmkl_gf_ilp64.so
>>> libmkl_intel_thread.a libmkl.so
>>> libmkl_blacs_lp64.a libmkl_gf_lp64.a
>>> libmkl_intel_thread.so libmkl_solver.a
>>> libmkl_blacs_openmpi_ilp64.a libmkl_gf_lp64.so
>>> libmkl_lapack.a
>>> libmkl_solver_ilp64.a
>>>
>>> However, if I link the /acml/ifort64/lib/libacml.a libs (and it does not
>>> sound
>>> reasonable on a xeon cluster...), everything works fine...
>>>
>>> Any suggestion?
>>>
>>> Giuseppe
>>>
>>> --
>>> ********************************************************
>>> - Article premier - Les hommes naissent et demeurent
>>> libres et ègaux en droits. Les distinctions sociales
>>> ne peuvent être fondèes que sur l'utilitè commune
>>> - Article 2 - Le but de toute association politique
>>> est la conservation des droits naturels et
>>> imprescriptibles de l'homme. Ces droits sont la libertè,
>>> la propriètè, la sùretè et la rèsistance à l'oppression.
>>> ********************************************************
>>>
>>> Giuseppe Mattioli
>>> CNR - ISTITUTO DI STRUTTURA DELLA MATERIA
>>> v. Salaria Km 29,300 - C.P. 10
>>> I 00016 - Monterotondo Stazione (RM)
>>> Tel + 39 06 90672836 - Fax +39 06 90672316
>>> E-mail: <giuseppe.mattioli at ism.cnr.it>
>>> _______________________________________________
>>> Pw_forum mailing list
>>> Pw_forum at pwscf.org
>>> http://www.democritos.it/mailman/listinfo/pw_forum
>>
>> _______________________________________________
>> Pw_forum mailing list
>> Pw_forum at pwscf.org
>> http://www.democritos.it/mailman/listinfo/pw_forum
>
>
>
> --
> ********************************************************
> - Article premier - Les hommes naissent et demeurent
> libres et ègaux en droits. Les distinctions sociales
> ne peuvent être fondèes que sur l'utilitè commune
> - Article 2 - Le but de toute association politique
> est la conservation des droits naturels et
> imprescriptibles de l'homme. Ces droits sont la libertè,
> la propriètè, la sùretè et la rèsistance à l'oppression.
> ********************************************************
>
> Giuseppe Mattioli
> CNR - ISTITUTO DI STRUTTURA DELLA MATERIA
> v. Salaria Km 29,300 - C.P. 10
> I 00016 - Monterotondo Stazione (RM)
> Tel + 39 06 90672836 - Fax +39 06 90672316
> E-mail: <giuseppe.mattioli at ism.cnr.it>
> _______________________________________________
> Pw_forum mailing list
> Pw_forum at pwscf.org
> http://www.democritos.it/mailman/listinfo/pw_forum
More information about the Pw_forum
mailing list