[CP2K-user] [CP2K:12331] The Memory Usage is Increasing

Phillip Seeber philli... at googlemail.com
Thu Oct 10 08:21:44 UTC 2019


Dear Ke,
i had the same problem on our cluster, when running MD simulations, as 
memory usage in every MD step increased slowly. In our case OpenMPI was 
causing the problem. Switching to MVAPICH2 solved the problem and also 
increased perfomance quite noticably on our OmniPath network.

Best wishes
Phillip

Am Mittwoch, 9. Oktober 2019 13:57:24 UTC+2 schrieb Ke Zhou:
>
> I test the same input files in our old cluster (cp2k 2.6) and it works 
> well. 
> I thinks the problem could be from compile. 
> I compile the package use intel mpi. The follow is the 
> "Linux-x86-64-intel.popt"  file.
> Can you give me some suggestion on it?
>
>
> LIBXSMM  = /apps/lib/libxsmm/1.9.0/e/gnu
>
> LIBXC    = /apps/lib/libxc/4.0.4/e5/gnu
>
> LIBINT   = /apps/lib/libint/1.1.4/gnu
>
> LIBELPA  = /apps/lib/elpa/2017.05.002/e5/gnu
>
>
> CC       = cc
>
> CPP      = 
>
> FC       = mpif90
>
> LD       = mpif90
>
> AR       = ar -r
>
> CPPFLAGS =
>
> DFLAGS   = -D__MKL -D__FFTW3 -D__HAS_NO_SHARED_GLIBC -D__LIBXSMM \
>
>   -D__parallel -D__SCALAPACK \
>
>   -D__ELPA=201705 \
>
>   -D__LIBXC \
>
>            -D__LIBINT -D__LIBINT_MAX_AM=7 -D__LIBDERIV_MAX_AM1=6 \
>
>            -D__MAX_CONTR=4
>
> CFLAGS   = $(DFLAGS) -O2
>
> FCFLAGS  = $(DFLAGS) -O2 -ffast-math -ffree-form -ffree-line-length-none 
> -ftree-vectorize -funroll-loops -mtune=native -std=f2008
>
> #FCFLAGS  = $(DFLAGS) -O2 -xW -heap-arrays 64 -funroll-loops -fpp -free
>
> #FCFLAGS += -fp-model precise
>
> #FCFLAGS += -g -traceback
>
> FCFLAGS += -I${MKLROOT}/include -I${MKLROOT}/include/fftw
>
> FCFLAGS += -I$(LIBXSMM)/include
>
> FCFLAGS += -I$(LIBXC)/include
>
> FCFLAGS += -I$(LIBELPA)/include/elpa-2017.05.002/modules 
> -I$(LIBELPA)/include/elpa-2017.05.002/elpa
>
> LDFLAGS  = $(FCFLAGS) 
>
> LDFLAGS_C = $(FCFLAGS)  
>
> LIBS     = -L$(LIBELPA)/lib -lelpa
>
> MKL_LIB  = ${MKLROOT}/lib/intel64
>
> LIBS    += $(MKL_LIB)/libmkl_scalapack_lp64.a -Wl,--start-group \
>
>   $(MKL_LIB)/libmkl_intel_lp64.a ${MKL_LIB}/libmkl_sequential.a \
>
>   $(MKL_LIB)/libmkl_core.a \
>
>            ${MKL_LIB}/libmkl_blacs_intelmpi_lp64.a -Wl,--end-group \
>
>            -lpthread -lm
>
> LIBS    += -L$(LIBXSMM)/lib -lxsmmf -lxsmm -ldl
>
> LIBS    += -L$(LIBXC)/lib -lxcf03 -lxc
>
> LIBS    += -L$(LIBINT)/lib -lderiv -lint -lstdc++
>
>
> # Required due to memory leak that occurs if high optimisations are used
>
> mp2_optimize_ri_basis.o: mp2_optimize_ri_basis.F
>
> $(FC) -c $(subst O2,O0,$(FCFLAGS)) $<
>
>
>
> Nikhil Maroli <sc... at gmail.com <javascript:>> 于2019年10月9日周三 下午7:44写道:
>
>> please share your running command here and details of your system. 
>>
>> -- 
>> You received this message because you are subscribed to a topic in the 
>> Google Groups "cp2k" group.
>> To unsubscribe from this topic, visit 
>> https://groups.google.com/d/topic/cp2k/lwPdChE_Iuk/unsubscribe.
>> To unsubscribe from this group and all its topics, send an email to 
>> c... at googlegroups.com <javascript:>.
>> To view this discussion on the web visit 
>> https://groups.google.com/d/msgid/cp2k/CAMEzy6QtQ-Y8r0cA8e_CsXG3MLK-RVUMOEZZ-Lw7dcA8EFgpyg%40mail.gmail.com 
>> <https://groups.google.com/d/msgid/cp2k/CAMEzy6QtQ-Y8r0cA8e_CsXG3MLK-RVUMOEZZ-Lw7dcA8EFgpyg%40mail.gmail.com?utm_medium=email&utm_source=footer>
>> .
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20191010/a9092239/attachment.htm>


More information about the CP2K-user mailing list