-
Notifications
You must be signed in to change notification settings - Fork 15
Description
I am using the HPC facility of DOST ASTI (https://asti.dost.gov.ph/coare/wiki/Main/using-coare/hpc/basic-hpc/). The COARE team installed genesis v2.1.4 for both gpu & cpu versions in a singularity container. I tried submitting the following submission script:
#!/bin/bash
#SBATCH --partition=batch
#SBATCH --qos=batch_default
#SBATCH --nodes=4
#SBATCH --ntasks=32
#SBATCH --nodelist=saliksik-cpu-07
#SBATCH --job-name="3md_0-100"
#SBATCH --output="3md_0-100.out"
##SBATCH --requeue
##SBATCH --ntasks-per-node=8
module purge
module load anaconda/3-2023.07-2
module load openmpi/4.1.2
#MAIN
export OMP_NUM_THREADS=4
mpirun -np 8 -npernode 4 singularity exec genesis.sif spdyn 3md_0-100.inp > 3md_0-100.out
But got this error:
Program received signal SIGILL: Illegal instruction.
Backtrace for this error:
Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
#0 0x2ac383bfd960 in ???
#1 0x2ac383bfcac5 in ???
#2 0x2ac38414751f in ???
#3 0x5633100a741a in ???
#4 0x56330ff16df8 in ???
#5 0x56331008b542 in ???
#6 0x5633100a2903 in ???
#7 0x56330fbdc1ae in ???
#8 0x2ac38412ed8f in ???
#9 0x2ac38412ee3f in ???
#10 0x56330fbdc1d4 in ???
#11 0xffffffffffffffff in ???
mpirun noticed that process rank 1 with PID 0 on node saliksik-cpu-07 exited on signal 4 (Illegal instruction).