LS Dyna

LS Dyna

Trouble running MPP LS- DYna 10.20 on Red Hat 8.4

    • Amadi
      Subscriber

       

      One research group here in the College is having issues with LS-DYNA 10.2 .
      They are using the MPP version of LS-DYNA 10.2, and when our HPC cluster was upgraded in August from CENTOS7 to Red Hat 8,4 , the 10.2 binary started giving

      "*** buffer overflow detected ***

      errors . The research group that uses R10.2.0 is not able to switch to a new version,
      since the human body model they use only runs correctly using R10.2 with
      MPP. Updating the model to a new version is a fairly complex and time
      consuming task. This is not something they can do.

      I've attached an email from one of our HPC support people showing various things they have tried.

      Here is the exact version of LS-DYNA info

      Date: 11/08/2022 Time: 20:58:04



      ___________________________________________________

      | |

      | Livermore Software Technology Corporation |

      | |

      | 7374 Las Positas Road |

      | Livermore, CA 94551 |

      | Tel: (925) 449-2500 Fax: (925) 449-2507 |

      | www.lstc.com |

      |_________________________________________________|

      | |

      | LS-DYNA, A Program for Nonlinear Dynamic |

      | Analysis of Structures in Three Dimensions |

      | Version : mpp s R10.2.0 Date: 03/05/2019 |

      | Revision: 135267 Time: 15:49:10 |

      | |

      | Features enabled in this version: |

      | Distributed Memory Parallel |

      | FFTW (multi-dimensional FFTW Library) |

      | ANSYS License (ans160) |

      | |

      | Licensed to: |

      | |

      | Platform : Intel-MPI 2018 Xeon64 |

      | OS Level : Linux CentOS 6.5 uum |

      | Compiler : Intel Fortran Compiler 16.0 AVX-2 |

      | Hostname : caen-vnc-mi16.engin.umich.edu |

      | Precision : Single precision (I4R4) |

      | SVN Version: 135714 |

      | |

      | Unauthorized use infringes LSTC copyrights |

      |_________________________________________________|





      Is there any support we can get with this issue from LSTC .



      Could we get a special recompile of 10.2 for Red Hat 8.4 ?

       

       

    • Reno Genest
      Ansys Employee

      Hello,

      Do you have more information on the error message?

      Have you tried with a double precision solver? 

      Also, have you tried with a different instruction set like SSE2 instead of AVX2?

      You can download different R10.2 solvers here:

      https://lsdyna.ansys.com/downloader-filter/

      username: user

      password: computer

       

      Reno.

    • Reno Genest
      Ansys Employee

      Hello,

      I checked with a developer and here is his reply:

      "The code needs to be recompiled with ifort 16.4.258 and on RedHat 7.8 or above."

      Let me check if I can get you a recompiled version of R10.2.

       

      Reno.

    • Amadi
      Subscriber

      Yes. We tried 

      1) MPP Ls-dyna 10.2 single precision both  "sse". and "avx2

      2) MPP LS-dyna 10.2 double precision both  "sse" and "avx2

       

      all four versions gave the same error :

       

      *** buffer overflow detected ***: /home/amadi/lsdyna/tmp/am/lsdyna_mpp_s terminated
      forrtl: error (76): Abort trap signal
      Image              PC                Routine            Line        Source
      lsdyna_mpp_s       0000000007E18F15  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007E16B37  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D766D4  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D764E6  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D119F6  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D18308  Unknown               Unknown  Unknown
      libpthread.so.0    000014B6E5C29B20  Unknown               Unknown  Unknown
      libc.so.6          000014B6E371A37F  Unknown               Unknown  Unknown
      libc.so.6          000014B6E3704DB5  Unknown               Unknown  Unknown
      libc.so.6          000014B6E375D4E7  Unknown               Unknown  Unknown
      libc.so.6          000014B6E37F0365  Unknown               Unknown  Unknown
      libc.so.6          000014B6E37F0397  Unknown               Unknown  Unknown
      libc.so.6          000014B6E37EE356  Unknown               Unknown  Unknown
      libc.so.6          000014B6E37ED9BF  Unknown               Unknown  Unknown
      libc.so.6          000014B6E3761611  Unknown               Unknown  Unknown
      libc.so.6          000014B6E3733DC8  Unknown               Unknown  Unknown
      libc.so.6          000014B6E37EDA63  Unknown               Unknown  Unknown
      libc.so.6          000014B6E37ED98E  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D7B823  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D7D5E9  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D2C4FD  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000007D61B39  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000000E45D73  chkenv_                  2154  chkenv.f
      lsdyna_mpp_s       0000000000E5C192  qlink_                   2550  qlink.f
      lsdyna_mpp_s       0000000000439618  MAIN__                   3805  lsdyna.f
      lsdyna_mpp_s       0000000000433C1E  Unknown               Unknown  Unknown
      libc.so.6          000014B6E3706493  Unknown               Unknown  Unknown
      lsdyna_mpp_s       0000000000433B29  Unknown               Unknown  Unknown
       
      ===================================================================================
      =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
      =   RANK 0 PID 3252682 RUNNING AT gl3004
      =   KILLED BY SIGNAL: 6 (Aborted)
      ===================================================================================
       
      ===================================================================================
      =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
      =   RANK 1 PID 3252683 RUNNING AT gl3004
      =   KILLED BY SIGNAL: 9 (Killed)
      ===================================================================================
       
      ===================================================================================
      =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
      =   RANK 2 PID 3252684 RUNNING AT gl3004
      =   KILLED BY SIGNAL: 9 (Killed)
      ==========================================================================
       
       

       

       

       

       

    • Amadi
      Subscriber

       

      Reno,

      Yes. A recompiled 10.2 version very much be appreciated .

    • Reno Genest
      Ansys Employee

      Hello Amadi,

      I will send you a new version via SecureTransfer.

       

      Reno.

    • Amadi
      Subscriber

      Thanks so much.  I've downloaded the file and we will get it to the researchers for testing .

      My initial testing went very well.  It work for my small test model on the Red Hat 8.4 HPC machine.

      Because of the holiday, the researchers  may not get back to me until next week.

    • Reno Genest
      Ansys Employee

      Hello Amadi,

      This is good news that it works on the small model. Let me know how it goes when you hear from the researcher.

       

      Reno.

    • Amadi
      Subscriber

      Reno,

      Here is a question coming from our HPC folks who work with the researchers:

      Can we get recompiled MPP Ls-Dyna 10.2 single precision sse2? 

      Their model is very sensitive, so I do not think avx2 will work for them.

       

       

    • Reno Genest
      Ansys Employee

      Hello Amadi,

      Ok, I will request the R10.2 MPP Intel MPI single precision SSE2.

       

      Reno.

    • Amadi
      Subscriber

      Reno,

       The researchers have got back to us.  They say the newly compiled 10.2 versions are working very well.

      The results are very similar to the results they had when running MPP Ls-DYNA 10.2 under CENTOS 7 .

      I think we can consider this matter closed.  Thanks again for all your help 

       

Viewing 10 reply threads
  • You must be logged in to reply to this topic.