Does anybody have VASP working with Centos 5 + OpenMPI + AMD gnu gfortran+ACML + AMD Barcelona?

Questions regarding the compilation of VASP on various platforms: hardware, compilers and libraries, etc.


Moderators: Global Moderator, Moderator

Post Reply
Message
Author
midair77
Newbie
Newbie
Posts: 11
Joined: Mon Apr 02, 2007 11:32 pm

Does anybody have VASP working with Centos 5 + OpenMPI + AMD gnu gfortran+ACML + AMD Barcelona?

#1 Post by midair77 » Fri Nov 07, 2008 6:21 am

Hi, everybody. I have tried to compile VASP and I was able to produce VASP binary but then when I ran test through Torque PBS or manually with mpiexec I would get the same type of errors. Here are what I have:

Environment: Centos 5.2 x86_64/Rocks 5 sp3 on AMD Barcelona, AMD's gnutools-4.2.0-barcelona (gcc/gfortran), AMD's ACML4.1.0, openmpi 1.2.8 (or 1.2.7 or 1.2.6). This is the closest compilable VASP version I could obtain and it crashed as soon as it started. I have tried to compile GNU gcc/g++/gfortran 4.2.4 by hand from GNU source files and that version did not even compile VASP at all with recompiled openmpi.

I looked at the errors and saw the trace that went into /lib64/libpthread.so.0 but this particular file is of glibc-2.5-18.el5_1.1 and I do not think I could update or modify it by anyway.

----------------
ldd /usr/local/bin/vaspmpi
libacml.so => /opt/acml4.1.0/gfortran64/lib/libacml.so (0x00002aaaaaaad000)
libmpi_f90.so.0 => /usr/local/lib/libmpi_f90.so.0 (0x00002aaaad794000)
libmpi_f77.so.0 => /usr/local/lib/libmpi_f77.so.0 (0x00002aaaad997000)
libmpi.so.0 => /usr/local/lib/libmpi.so.0 (0x00002aaaadbc9000)
libopen-rte.so.0 => /usr/local/lib/libopen-rte.so.0 (0x00002aaaadee1000)
libopen-pal.so.0 => /usr/local/lib/libopen-pal.so.0 (0x00002aaaae1b0000)
librt.so.1 => /lib64/librt.so.1 (0x000000355f800000)
libtorque.so.2 => /opt/torque/lib64/libtorque.so.2 (0x00002aaaae41c000)
libdl.so.2 => /lib64/libdl.so.2 (0x000000355e400000)
libnsl.so.1 => /lib64/libnsl.so.1 (0x0000003560800000)
libutil.so.1 => /lib64/libutil.so.1 (0x000000355f000000)
libm.so.6 => /lib64/libm.so.6 (0x000000355ec00000)
libgcc_s.so.1 => /opt/amd/gnutools-4.2.0-barcelona/lib64/libgcc_s.so.1 (0x00002aaaae675000)
libpthread.so.0 => /lib64/libpthread.so.0 (0x000000355e800000)
libc.so.6 => /lib64/libc.so.6 (0x000000355e000000)
libacml_mv.so => /opt/acml4.1.0/gfortran64/lib/libacml_mv.so (0x00002aaaae883000)
libgfortran.so.2 => /opt/amd/gnutools-4.2.0-barcelona/lib64/libgfortran.so.2 (0x00002aaaae9c9000)
/lib64/ld-linux-x86-64.so.2 (0x000000355dc00000)

-------------------------

[test@compute-0-0 8cores]$ /usr/local/bin/mpirun -np 8 --machinefile /mnt/lustre/test//8cores/machinefile /usr/local/bin/vaspmpi
running on 8 nodes
distr: one band on 4 nodes, 2 groups
vasp.4.6.19 08Dec03 complex
POSCAR found : 3 types and 49 ions

-----------------------------------------------------------------------------
| |
| ADVICE TO THIS USER RUNNING 'VASP/VAMP' (HEAR YOUR MASTER'S VOICE ...): |
| |
| You have a (more or less) 'large supercell' and for larger cells |
| it might be more efficient to use real space projection operators |
| So try LREAL=.TRUE. in the INCAR file. |
| Mind: If you want to do an extremely accurate calculations keep the |
| reciprocal projection scheme (i.e. LREAL=.FALSE.) |
| |
-----------------------------------------------------------------------------


-----------------------------------------------------------------------------
| |
| ADVICE TO THIS USER RUNNING 'VASP/VAMP' (HEAR YOUR MASTER'S VOICE ...): |
| |
| You enforced a specific xc-type in the INCAR file, |
| a different type was found on the POTCAR file |
| I HOPE YOU KNOW, WHAT YOU ARE DOING |
| |
-----------------------------------------------------------------------------

LDA part: xc-table for Pade appr. of Perdew
POSCAR, INCAR and KPOINTS ok, starting setup
WARNING: wrap around errors must be expected
FFT: planning ...
[compute-0-0:09959] *** Process received signal ***
[compute-0-0:09959] Signal: Segmentation fault (11)
[compute-0-0:09959] Signal code: (128)
[compute-0-0:09959] Failing at address: (nil)
[compute-0-0:09959] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09959] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09959] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09959] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09959] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09959] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09959] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09959] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09959] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09959] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09959] *** End of error message ***
[compute-0-0:09960] *** Process received signal ***
[compute-0-0:09960] Signal: Segmentation fault (11)
[compute-0-0:09960] Signal code: (128)
[compute-0-0:09960] Failing at address: (nil)
[compute-0-0:09960] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09960] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09960] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09960] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09960] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09960] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09960] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09960] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09960] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09960] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09960] *** End of error message ***
[compute-0-0:09961] *** Process received signal ***
[compute-0-0:09961] Signal: Segmentation fault (11)
[compute-0-0:09961] Signal code: (128)
[compute-0-0:09961] Failing at address: (nil)
[compute-0-0:09961] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09961] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09961] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09961] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09961] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09961] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09961] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09961] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09961] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09961] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09961] *** End of error message ***
[compute-0-0:09962] *** Process received signal ***
[compute-0-0:09962] Signal: Segmentation fault (11)
[compute-0-0:09962] Signal code: (128)
[compute-0-0:09962] Failing at address: (nil)
[compute-0-0:09962] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09962] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09962] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09962] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09962] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09962] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09962] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09962] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09962] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09962] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09962] *** End of error message ***
[compute-0-0:09963] *** Process received signal ***
[compute-0-0:09963] Signal: Segmentation fault (11)
[compute-0-0:09963] Signal code: (128)
[compute-0-0:09963] Failing at address: (nil)
[compute-0-0:09963] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09963] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09963] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09963] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09963] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09963] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09963] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09963] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09963] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09963] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09963] *** End of error message ***
[compute-0-0:09964] *** Process received signal ***
[compute-0-0:09964] Signal: Segmentation fault (11)
[compute-0-0:09964] Signal code: (128)
[compute-0-0:09964] Failing at address: (nil)
[compute-0-0:09964] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09964] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09964] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09964] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09964] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09964] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09964] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09964] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09964] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09964] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09964] *** End of error message ***
[compute-0-0:09965] *** Process received signal ***
[compute-0-0:09965] Signal: Segmentation fault (11)
[compute-0-0:09965] Signal code: (128)
[compute-0-0:09965] Failing at address: (nil)
[compute-0-0:09965] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09965] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09965] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09965] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09965] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09965] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09965] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09965] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09965] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09965] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09965] *** End of error message ***
[compute-0-0:09966] *** Process received signal ***
[compute-0-0:09966] Signal: Segmentation fault (11)
[compute-0-0:09966] Signal code: (128)
[compute-0-0:09966] Failing at address: (nil)
[compute-0-0:09966] [ 0] /lib64/libpthread.so.0 [0x3fd440de70]
[compute-0-0:09966] [ 1] /usr/local/lib/libopen-pal.so.0(free+0x30) [0x2aaaae1dba90]
[compute-0-0:09966] [ 2] /usr/local/bin/vaspmpi(_gfortran_deallocate+0xe) [0x6f2d1e]
[compute-0-0:09966] [ 3] /usr/local/bin/vaspmpi(__smart_allocate__smart_allocate_complex+0x35) [0x446355]
[compute-0-0:09966] [ 4] /usr/local/bin/vaspmpi(fftbas_plan_+0x4d) [0x63800d]
[compute-0-0:09966] [ 5] /usr/local/bin/vaspmpi(fftmakeplan_+0x1e) [0x637f7e]
[compute-0-0:09966] [ 6] /usr/local/bin/vaspmpi(MAIN__+0xf81e) [0x423f96]
[compute-0-0:09966] [ 7] /usr/local/bin/vaspmpi(main+0xe) [0x6f223e]
[compute-0-0:09966] [ 8] /lib64/libc.so.6(__libc_start_main+0xf4) [0x3fd3c1d8a4]
[compute-0-0:09966] [ 9] /usr/local/bin/vaspmpi [0x4146e9]
[compute-0-0:09966] *** End of error message ***
[compute-0-1.local:09623] [0,0,0] ORTE_ERROR_LOG: Timeout in file base/pls_base_orted_cmds.c at line 275
[compute-0-1.local:09623] [0,0,0] ORTE_ERROR_LOG: Timeout in file pls_rsh_module.c at line 1158
[compute-0-1.local:09623] [0,0,0] ORTE_ERROR_LOG: Timeout in file errmgr_hnp.c at line 90
mpirun noticed that job rank 0 with PID 9959 on node compute-0-0 exited on signal 11 (Segmentation fault).
4 additional processes aborted (not shown)
[compute-0-1.local:09623] [0,0,0] ORTE_ERROR_LOG: Timeout in file base/pls_base_orted_cmds.c at line 188
[compute-0-1.local:09623] [0,0,0] ORTE_ERROR_LOG: Timeout in file pls_rsh_module.c at line 1190
--------------------------------------------------------------------------
mpirun was unable to cleanly terminate the daemons for this job. Returned value Timeout instead of ORTE_SUCCESS.

<span class='smallblacktext'>[ Edited ]</span>
Last edited by midair77 on Fri Nov 07, 2008 6:21 am, edited 1 time in total.

admin
Administrator
Administrator
Posts: 2921
Joined: Tue Aug 03, 2004 8:18 am
License Nr.: 458

Does anybody have VASP working with Centos 5 + OpenMPI + AMD gnu gfortran+ACML + AMD Barcelona?

#2 Post by admin » Wed Nov 12, 2008 9:10 am

The crash might be due to FFT-problems, please check if vasp runs if you choose the alternative FFT3D.
Last edited by admin on Wed Nov 12, 2008 9:10 am, edited 1 time in total.

Post Reply