HP XC System 3.x Software - Manual (Page 115)

Table 10-3 LSF-HPC Equivalents of SLURM srun Options (continued)
LSF-HPC Equivalent Description srun Option
You can use when launching parallel tasks. Specify how stdin is to be redirected. -i
--input=none,tasked
bsub -e error_file Specify how stderr is to be
redirected. -e
--error=file_name
You can use when launching parallel tasks. Specify how stderr is to be
redirected. -e
--error=none,tasked
You cannot use this option. When creating
allocation. SLURM sets LSF-HPC job id
automatically. Specify a name for the job. -J
--job-name=job_name
You cannot use this option. LSF-HPC uses it to
create allocation. Root attempts to submit or run a job
as normal user. --uid=user
bsub -W runlimit Establish a time limit to terminate the
job after specified number of minutes. -t
--time=minutes
You cannot use this option. LSF-HPC uses this
option to create allocation. Root attempts to submit or run a job
as group. --gid=group
You cannot use this option. LSF-HPC uses this
option to create allocation. Allocate resource and spawn a shell. -A
--allocate
You cannot use this option. LSF-HPC uses this
option to create allocation. Immediately exit after allocating
resources. --no-shell
You cannot use this option. LSF-HPC uses this
option to create allocation. Allocate immediately or fail. -I
--immediate
You cannot use this option. LSF-HPC uses this
option to create allocation. Share nodes with other running jobs.
SHARED=FORCE shares all nodes in
partition.
SHARED=YES shares nodes if and only
if –share is specified.
SHARED=NO means do not share the
node.
-s
--share
Use when launching parallel tasks. Overcommit resources. -O
--overcommit
Meaningless under LSF-HPC integrated with
SLURM. Submit in “batch mode”. -b
--batch
Use as an argument to srun when launching
parallel tasks. Run a job step relative to node n of the
current allocation. It is about placing
tasks within allocation. -r
--relative=n
Job starts in job submission directory by
default. Specify the working directory of the
job. -D
--chdir=path
When creating allocation, LSF-HPC does not
use the –k option. SLURM always terminates
a job if one of allocated nodes fails Do not automatically terminate a job
if one of the nodes it has been allocated
fails. -k
--no-kill
Use as an argument to srun when launching
parallel tasks. The srun command uses nthreads
to initiate and control the parallel job. -T
--threads=nthreads
10.14 LSF-HPC Equivalents of SLURM srun Options 115