A memory leak?

Guanguri Qian iqiang... at gmail.com
Sat Feb 2 02:28:03 UTC 2013


HI, all

    I met a problem when running CP2K MD (version12507,  Intel 
composer_x3_2013.1.117 + intel MPI 4.1.0.024 + intel MKL + intel FFT on E5 
intel CPU).

    When the jobs are running, the free memory of the nodes will reduce 
quickly! Then cp2k calculations will exit with segment fault.
    To avoid the abuse of the restart files memory usage,   SAVE_MEM  is 
set as .TRUE.. But it still doesnt work, the memory of the nodes reduced 
quickly as well.
   
    Any idea about the problem? Is this a memory leak, maybe from the intel 
compile and libs?
    Thanks a lot.
    
Bests
Guangrui

---------------------------------
INTEL_MKL=/opt/apps/intel/13/composer_xe_2013.1.117/mkl/
INTEL_INC=$(INTEL_MKL)/include/fftw
INTEL_LIB=$(INTEL_MKL)/lib/intel64
FFTW_LIB=/home/qian/Proc/fftw3xf/


CC       = mpiicc
CPP      = 
FC       = mpiifort 
LD       = mpiifort
AR       = ar -r

DFLAGS   = -D__INTEL -D__FFTSG -D__parallel -D__BLACS -D__SCALAPACK 
-D__FFTW3
CPPFLAGS =
FCFLAGS  = $(DFLAGS) -I$(INTEL_INC) -O3 -xhost -heap-arrays 64 
-funroll-loops -fpp -free
FCFLAGS2 = $(DFLAGS) -I$(INTEL_INC) -O1 -msse2 -heap-arrays 64 -fpp -free
LDFLAGS  = $(FCFLAGS) -I$(INTEL_INC)
LIBS     = -L$(FFTW_LIB) -lfftw3xf_intel \
-L${INTEL_LIB} -I${INTEL_INC} -I${INTEL_INC}/intel64/lp64 -lmkl_blas95_lp64 
\
-L${INTEL_LIB} -I${INTEL_INC} -I${INTEL_INC}/intel64/lp64 
-lmkl_lapack95_lp64 \
${INTEL_LIB}/libmkl_scalapack_lp64.a  -Wl,--start-group 
${INTEL_LIB}/libmkl_intel_lp64.a ${INTEL_LIB}/libmkl_sequential.a 
${INTEL_LIB}/libmkl_core.a ${INTEL_LIB}/libmkl_blacs_intelmpi_lp64.a 
-Wl,--end-group -lpthread


OBJECTS_ARCHITECTURE = machine_intel.o


graphcon.o: graphcon.F
$(FC) -c $(FCFLAGS2) $<



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20130201/b2d8db6b/attachment.htm>


More information about the CP2K-user mailing list