nvcr.io/nvidia/hpc-benchmarks:21.4-hppl xhpl crash

hpc-benchmarks:21.4-hpl_crash.txt

 .....
 Prog= 85.55%   N_left= 1188288 Time= 870.74    Time_left= 147.12       iGF= 6253382.31 GF= 7603226.15  iGF_per= 12407.50       GF_per= 15085.77 
 Prog= 85.94%   N_left= 1177344 Time= 876.23    Time_left= 143.33       iGF= 5573961.76 GF= 7590502.86  iGF_per= 11059.45       GF_per= 15060.52 
 Prog= 86.35%   N_left= 1165824 Time= 881.27    Time_left= 139.31       iGF= 6271848.56 GF= 7582957.89  iGF_per= 12444.14       GF_per= 15045.55 
 Prog= 86.75%   N_left= 1154304 Time= 886.36    Time_left= 135.37       iGF= 6095663.79 GF= 7574422.65  iGF_per= 12094.57       GF_per= 15028.62 
 Prog= 87.12%   N_left= 1143360 Time= 891.10    Time_left= 131.69       iGF= 6100617.39 GF= 7566590.79  iGF_per= 12104.40       GF_per= 15013.08 
 Prog= 88.60%   N_left= 1097856 Time= 910.53    Time_left= 117.14       iGF= 5880744.58 GF= 7530604.49  iGF_per= 11668.14       GF_per= 14941.68 
 Prog= 89.96%   N_left= 1052352 Time= 929.69    Time_left= 103.75       iGF= 5491677.90 GF= 7488589.51  iGF_per= 10896.19       GF_per= 14858.31 
 Prog= 91.19%   N_left= 1007424 Time= 948.52    Time_left= 91.61        iGF= 5061996.93 GF= 7440414.22  iGF_per= 10043.64       GF_per= 14762.73 
 Prog= 92.33%   N_left= 961920  Time= 966.67    Time_left= 80.27        iGF= 4862198.60 GF= 7392002.82  iGF_per= 9647.22        GF_per= 14666.67 
 Prog= 93.36%   N_left= 916992  Time= 983.82    Time_left= 70.00        iGF= 4624393.64 GF= 7343750.82  iGF_per= 9175.38        GF_per= 14570.93 
 Prog= 94.30%   N_left= 871488  Time= 1001.26   Time_left= 60.54        iGF= 4174093.56 GF= 7288545.19  iGF_per= 8281.93        GF_per= 14461.40 
 Prog= 95.15%   N_left= 825984  Time= 1017.29   Time_left= 51.90        iGF= 4092061.82 GF= 7238193.34  iGF_per= 8119.17        GF_per= 14361.49 
[vla3-7009-hpl-test:65524:0:65651] Caught signal 11 (Segmentation fault: address not mapped to object at address 0x80)
==== backtrace (tid:  65651) ====
 0 0x0000000000026975 ucs_debug_print_backtrace()  /build-result/src/hpcx-v2.8.1-gcc-MLNX_OFED_LINUX-5.1-0.6.6.0-ubuntu16.04-x86_64/ucx-96422ce/src/ucs/debug/debug.c:656
 1 0x0000000000011390 __funlockfile()  ???:0
 2 0x00000000004c4430 __kmpc_omp_task_with_deps()  ???:0
 3 0x00000000004cba51 __kmpc_omp_task_alloc()  ???:0
 4 0x00000000004d109d __kmpc_omp_task_alloc()  ???:0
 5 0x000000000051cab7 __kmp_external___intel_sse2_strspn()  ???:0
 6 0x00000000005212f4 __kmp_external___intel_sse2_strspn()  ???:0
 7 0x0000000000498f40 omp_in_parallel()  ???:0
 8 0x00000000004dba60 __kmp_external___intel_sse2_strspn()  ???:0
 9 0x00000000000076ba start_thread()  ???:0
10 0x000000000010751d clone()  ???:0
=================================
[vla3-7009-hpl-test:65524] *** Process received signal ***
[vla3-7009-hpl-test:65524] Signal: Segmentation fault (11)
[vla3-7009-hpl-test:65524] Signal code:  (-6)
[vla3-7009-hpl-test:65524] Failing at address: 0xfff4
[vla3-7009-hpl-test:65524] [ 0] /lib/x86_64-linux-gnu/libpthread.so.0(+0x11390)[0x7f6d03f8c390]
[vla3-7009-hpl-test:65524] [ 1] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x4c4430]
[vla3-7009-hpl-test:65524] [ 2] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x4cba51]
[vla3-7009-hpl-test:65524] [ 3] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x4d109d]
[vla3-7009-hpl-test:65524] [ 4] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x51cab7]
[vla3-7009-hpl-test:65524] [ 5] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x5212f4]
[vla3-7009-hpl-test:65524] [ 6] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x498f40]
[vla3-7009-hpl-test:65524] [ 7] /opt/hpc-benchmarks/workspace/hpl-linux-x86_64/xhpl[0x4dba60]
[vla3-7009-hpl-test:65524] [ 8] /lib/x86_64-linux-gnu/libpthread.so.0(+0x76ba)[0x7f6d03f826ba]
[vla3-7009-hpl-test:65524] [ 9] /lib/x86_64-linux-gnu/libc.so.6(clone+0x6d)[0x7f6d03cb851d]
[vla3-7009-hpl-test:65524] *** End of error message ***
./hpl.sh: line 321: 65524 Segmentation fault      (core dumped) numactl --physcpubind=${CPU} ${MEMBIND} ${XHPL} ${DAT}
--------------------------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[8832,1],501]
  Exit code:    139
  
 Crash caused by opt/intel/compilers_and_libraries_2020.4.304, use nvcr.io/nvidia/hpc-benchmarks:20.10-hpl docker image instead