[CP2K-user] [CP2K:16171] Regtest Segfaults with PSMP Intel ONEAPI 2021.3.0

Tat tajti.attila at gmail.com
Wed Nov 3 09:20:33 UTC 2021


Dear Matthias,
this indeed seems to have solved the problem, thank you!

Attila

On Tuesday, November 2, 2021 at 2:08:29 PM UTC+1 Matthias Krack wrote:

> Hi Attila
>
>  
>
> Such unspecific segfaults can be caused by a stack size limit which is too 
> small. “ulimit –s” will show the current limit using bash. You may try 
> «ulimit –s unlimited», if the value is small.
>
>  
>
> Best
>
>  
>
> Matthias
>
>  
>
> *Von:* cp... at googlegroups.com <cp... at googlegroups.com> *Im Auftrag von *
> Tat
> *Gesend**et:* Freitag, 29. Oktober 2021 18:11
> *An:* cp2k <cp... at googlegroups.com>
> *Betreff:* [CP2K:16148] Regtest Segfaults with PSMP Intel ONEAPI 2021.3.0
>
>  
>
> Dear all,
>
> after compiling CP2K 8.2 with Intel ONEAPI (mpiifort, MKL, OpenMP, Intel 
> MPI) v. 2021.3.0 I am getting Segfaults for some (57) regression tests. A 
> debug build (-DBG=1) of CP2K with this compiler (uses the command line 
> quoted below) produces the attached sample outputs. 
>
>  
>
> (Libraries are elpa-2021.05.002; libint-v2.6.0-cp2k-lmax-7; libxc-5.1.5; 
> plumed-2.7.2; libxsmm-1.16.3. The machine is a Linux box with 2x16-core 
> Intel Xeon Silver 4216 CPUs with HT, 128GB RAM, kernel v. 4.19.0-14.)
>
>  
>
> Is this a known problem? Can you suggest me how to fix the build? 
>
>  
>
> Thank you in advance,
>
>  
>
> Attila
>
>  
>
>                         
> --------------------------------------------------------
>
>                         Smear method:                                
> FERMI_DIRAC
>
>                         Electronic temperature [K]:                        
> 293.0
>
>                         Electronic temperature [a.u.]:                  
> 9.28E-04
>
>                         Accuracy threshold:                            
>  1.00E-10
>
>                         
> --------------------------------------------------------
>
>                         No outer SCF
>
> forrtl: severe (174): SIGSEGV, segmentation fault occurred
>
> Image              PC                Routine            Line        
> Source             
>
> cp2k.psmp          000000001D10E51A  Unknown               Unknown  Unknown
>
> libpthread-2.28.s  00007F4D1C7C2730  Unknown               Unknown  Unknown
>
> cp2k.psmp          000000000594444C  cp_array_sort_mp_          44  
> cp_array_sort.F
>
> cp2k.psmp          00000000056AEFC3  pw_grids_mp_pw_gr        1804  
> pw_grids.F
>
> cp2k.psmp          000000000569A63B  pw_grids_mp_pw_gr         614  
> pw_grids.F
>
> cp2k.psmp          0000000005699C36  pw_grids_mp_pw_gr         422  
> pw_grids.F
>
> cp2k.psmp          000000000178F578  pw_env_methods_mp         403  
> pw_env_methods.F
>
> cp2k.psmp          0000000001900B39  qs_environment_me         250  
> qs_environment_methods.F
>
> cp2k.psmp          00000000018FEBCC  qs_environment_me         159  
> qs_environment_methods.F
>
> cp2k.psmp          00000000018FA8A8  qs_environment_mp        1596  
> qs_environment.F
>
> cp2k.psmp          00000000018DF729  qs_environment_mp         370  
> qs_environment.F
>
> cp2k.psmp          0000000001237861  f77_interface_mp_         789  
> f77_interface.F
>
> cp2k.psmp          00000000008D46C3  cp2k_runs_mp_cp2k         298  
> cp2k_runs.F
>
> cp2k.psmp          00000000008DD962  cp2k_runs_mp_run_         990  
> cp2k_runs.F
>
> cp2k.psmp          00000000008D37AD  MAIN__                    357  cp2k.F
>
> cp2k.psmp          00000000008CF422  Unknown               Unknown  Unknown
>
> libc-2.28.so       00007F4D1A72F09B  __libc_start_main     Unknown  
> Unknown
>
> cp2k.psmp          00000000008CF32A  Unknown               Unknown  Unknown
>
>  
>
> *mpiifort -c -g -debug -free -fpp -threads -traceback -qopenmp -O0 -xHost 
> -qopt-zmm-usage=low -D__NO_IPI_DRIVER -D__parallel -D__SCALAPACK 
> -D__MPI_VERSION=3 -D__INTEL -D__LIBINT -D__MAX_CONTR=4 -D__LIBXC 
> -D__PLUMED2 -D__ELPA -D__MKL -D__FFTW3 
> -I/home/tat/cp2k-8.2/obj/Linux-x86-64-intelx/psmp/exts/dbcsr 
> -I/home/tat/libint/intel-skx/include -I/home/tat/libxc/intel-skx/include 
> -I/home/tat/elpa/intel-skx-omp/include/elpa_openmp-2021.05.002/elpa/ 
> -I/home/tat/elpa/intel-skx-omp/include/elpa_openmp-2021.05.002/elpa/../modules 
> -I/opt/intel/oneapi/mkl/2021.3.0/include 
> -I/opt/intel/oneapi/mkl/2021.3.0/include/fftw -diag-disable 
> 8290,8291,10010,10212,10411,11060 
> -D__COMPILE_ARCH="\"Linux-x86-64-intelx\"" -D__COMPILE_DATE="\"Fri 29 Oct 
> 2021 02:37:05 PM CEST\"" -D__COMPILE_HOST="\"charon12\"" 
> -D__COMPILE_REVISION="\"git:310b7ab\"" 
> -D__DATA_DIR="\"/home/tat/cp2k-8.2/data\"" 
> -D__SHORT_FILE__="\"tmc/tmc_master.F\"" -I'/home/tat/cp2k-8.2/src/tmc/' 
> -I'/home/tat/cp2k-8.2/obj/Linux-x86-64-intelx/psmp/exts/dbcsr'*
>
> -- 
> You received this message because you are subscribed to the Google Groups 
> "cp2k" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to cp2k+uns... at googlegroups.com.
> To view this discussion on the web visit 
> https://groups.google.com/d/msgid/cp2k/add6fe7d-e125-403f-81a3-b1da94c17935n%40googlegroups.com 
> <https://groups.google.com/d/msgid/cp2k/add6fe7d-e125-403f-81a3-b1da94c17935n%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
>

-- 
You received this message because you are subscribed to the Google Groups "cp2k" group.
To unsubscribe from this group and stop receiving emails from it, send an email to cp2k+unsubscribe at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/cp2k/60904da8-3315-4819-8152-e79df2aaa305n%40googlegroups.com.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20211103/9ee39130/attachment.htm>


More information about the CP2K-user mailing list