Sample batch job submission scripts on Sapelo2 - Revision history

Shtsai at 02:52, 5 April 2026

2026-04-05T02:52:28Z

← Older revision		Revision as of 22:52, 4 April 2026
Line 1:		Line 1:
	[[Category:Sapelo2]]		[[Category:Sapelo2]]

	====Serial (single-processor) Job====		==Serial (single-processor) Job==

	Sample job submission script (sub.sh) to run an R program called add.R using a single core:		Sample job submission script (sub.sh) to run an R program called add.R using a single core:
Line 27:		Line 27:
	In this sample script, the standard output and error of the job will be saved into a file called testserial.%j.out and testserial.%j.err, where %j will be automatically replaced by the job id of the job and %x by the jobname.		In this sample script, the standard output and error of the job will be saved into a file called testserial.%j.out and testserial.%j.err, where %j will be automatically replaced by the job id of the job and %x by the jobname.

	====Serial (single-processor) Job on an AMD EPYC Milan processor====		==Serial (single-processor) Job on an AMD EPYC Milan processor==

	Sample job submission script (sub.sh) to run an R program called add.R using a single core:		Sample job submission script (sub.sh) to run an R program called add.R using a single core:
Line 54:		Line 54:
	In this sample script, the standard output and error of the job will be saved into a file called testserial.o%j, where %j will be automatically replaced by the job id of the job.		In this sample script, the standard output and error of the job will be saved into a file called testserial.o%j, where %j will be automatically replaced by the job id of the job.

	====MPI Job====		==MPI Job==

	Sample job submission script (sub.sh) to run an OpenMPI application. In this example the job requests 16 cores and further specifies that these 16 cores need to be divided equally on 2 nodes (8 cores per node) and the binary is called mympi.exe:		Sample job submission script (sub.sh) to run an OpenMPI application. In this example the job requests 16 cores and further specifies that these 16 cores need to be divided equally on 2 nodes (8 cores per node) and the binary is called mympi.exe:
Line 83:		Line 83:
	Please note that you need to start the application with '''srun''' and not with '''mpirun''' or '''mpiexec'''.		Please note that you need to start the application with '''srun''' and not with '''mpirun''' or '''mpiexec'''.

	====MPI Job on nodes with the same processor type====		==MPI Job on nodes with the same processor type==

	Sample job submission script (sub.sh) to run an OpenMPI application. In this example the job requests 16 cores and further specifies that these 16 cores need to be divided equally on 2 nodes (8 cores per node) with a Milan processor, and the binary is called mympi.exe:		Sample job submission script (sub.sh) to run an OpenMPI application. In this example the job requests 16 cores and further specifies that these 16 cores need to be divided equally on 2 nodes (8 cores per node) with a Milan processor, and the binary is called mympi.exe:
Line 113:		Line 113:
	Please note that you need to start the application with '''srun''', and not with '''mpirun''' or '''mpiexec'''.		Please note that you need to start the application with '''srun''', and not with '''mpirun''' or '''mpiexec'''.

	====OpenMP (Multi-Thread) Job====		==OpenMP (Multi-Thread) Job==

	Sample job submission script (sub.sh) to run a program that uses OpenMP with 6 threads. Please set '''--ntasks=1''' and set '''--cpus-per-task''' to the number of threads you wish to use. The name of the binary in this example is a.out.		Sample job submission script (sub.sh) to run a program that uses OpenMP with 6 threads. Please set '''--ntasks=1''' and set '''--cpus-per-task''' to the number of threads you wish to use. The name of the binary in this example is a.out.
Line 140:		Line 140:
	</pre>		</pre>

	====High Memory Job====		==High Memory Job==

	Sample job submission script (sub.sh) to run a velvet application that needs to use 200GB of memory and 4 threads:		Sample job submission script (sub.sh) to run a velvet application that needs to use 200GB of memory and 4 threads:
Line 167:		Line 167:
	</pre>		</pre>

	====Hybrid MPI/shared-memory using OpenMPI====		==Hybrid MPI/shared-memory using OpenMPI==

	Sample job submission script (sub.sh) to run a parallel job that uses 4 MPI processes with OpenMPI and each MPI process runs with 3 threads:		Sample job submission script (sub.sh) to run a parallel job that uses 4 MPI processes with OpenMPI and each MPI process runs with 3 threads:
Line 197:		Line 197:
	</pre>		</pre>

	====Array job====		==Array job==

	Sample job submission script (sub.sh) to submit an array job with 10 elements. In this example, each array job element will run the a.out binary using an input file called input_0, input_1, ..., input_9.		Sample job submission script (sub.sh) to submit an array job with 10 elements. In this example, each array job element will run the a.out binary using an input file called input_0, input_1, ..., input_9.
Line 221:		Line 221:
	</pre>		</pre>

	====Singularity job====		==Singularity job==

	Sample job submission script (sub.sh) to run a program (e.g. sortmerna) using a singularity container:		Sample job submission script (sub.sh) to run a program (e.g. sortmerna) using a singularity container:
Line 245:		Line 245:
	For more information about software installed as singularity containers on the cluster, please see [[Software_on_Sapelo2#Singularity_Containers]]		For more information about software installed as singularity containers on the cluster, please see [[Software_on_Sapelo2#Singularity_Containers]]

	====GPU/CUDA====		==GPU/CUDA==

	Sample script to run Amber on a GPU node using one node, 2 CPU cores, and 1 GPU A100 card:		Sample script to run Amber on a GPU node using one node, 2 CPU cores, and 1 GPU A100 card:

Shtsai at 00:03, 1 August 2025

2025-08-01T00:03:55Z

← Older revision		Revision as of 20:03, 31 July 2025
Line 83:		Line 83:
	Please note that you need to start the application with '''srun''' and not with '''mpirun''' or '''mpiexec'''.		Please note that you need to start the application with '''srun''' and not with '''mpirun''' or '''mpiexec'''.

	====MPI Job on nodes ~~connected via~~ the ~~EDR IB fabric~~====		====MPI Job on nodes with the same processor type====

	Sample job submission script (sub.sh) to run an OpenMPI application. In this example the job requests 16 cores and further specifies that these 16 cores need to be divided equally on 2 nodes (8 cores per node) and the binary is called mympi.exe:		Sample job submission script (sub.sh) to run an OpenMPI application. In this example the job requests 16 cores and further specifies that these 16 cores need to be divided equally on 2 nodes (8 cores per node) with a Milan processor, and the binary is called mympi.exe:

	<pre class="gscript">		<pre class="gscript">
Line 91:		Line 91:
	#SBATCH --job-name=mpitest # Job name		#SBATCH --job-name=mpitest # Job name
	#SBATCH --partition=batch # Partition (queue) name		#SBATCH --partition=batch # Partition (queue) name
	#SBATCH --constraint=~~EDR~~ # node feature		#SBATCH --constraint=Milan # node feature
	#SBATCH --nodes=2 # Number of nodes		#SBATCH --nodes=2 # Number of nodes
	#SBATCH --ntasks=16 # Number of MPI ranks		#SBATCH --ntasks=16 # Number of MPI ranks
Line 264:		Line 264:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	ml Amber/22.0-foss-~~2021b~~-AmberTools-22.3-CUDA-11.4.1		ml Amber/24.3-foss-2022a-AmberTools-24.10-CUDA-12.1.1

	srun $AMBERHOME/bin/pmemd.cuda -O -i ./prod.in -o prod.out -p ./dimerFBP_GOL.prmtop -c ./restart.rst -r prod.rst -x prod.mdcrd		srun $AMBERHOME/bin/pmemd.cuda -O -i ./prod.in -o prod.out -p ./dimerFBP_GOL.prmtop -c ./restart.rst -r prod.rst -x prod.mdcrd
	</pre>		</pre>
	You can use the header <code>#SBATCH --gres=gpu:P100:1</code> or <code>#SBATCH --gres=gpu:~~A100~~:1</code> to specify using a P100 or ~~an A100~~ GPU device. The compute mode of the GPU is set to Default.		You can use the header <code>#SBATCH --gres=gpu:P100:1</code>, <code>#SBATCH --gres=gpu:L4:1</code>, <code>#SBATCH --gres=gpu:A100:1</code>, or <code>#SBATCH --gres=gpu:H100:1</code> to specify using a P100, L4, A100, or H100 GPU device. The compute mode of the GPU is set to Default.

	----		----
	[[#top\|Back to Top]]		[[#top\|Back to Top]]

Shtsai at 02:12, 6 September 2023

2023-09-06T02:12:03Z

Shtsai: /* Serial (single-processor) Job */

2023-09-06T02:01:54Z

Serial (single-processor) Job

← Older revision		Revision as of 22:01, 5 September 2023
Line 12:		Line 12:
	#SBATCH --mem=1gb # Job memory request		#SBATCH --mem=1gb # Job memory request
	#SBATCH --time=02:00:00 # Time limit hrs:min:sec		#SBATCH --time=02:00:00 # Time limit hrs:min:sec
	#SBATCH --output=~~testserial~~.%j.out # Standard output log		#SBATCH --output=%x.%j.out # Standard output log
	#SBATCH --error=~~testserial~~.%j.err # Standard error log		#SBATCH --error=%x.%j.err # Standard error log

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
Line 25:		Line 25:
	</pre>		</pre>

	In this sample script, the standard output and error of the job will be saved into a file called testserial.%j.out and testserial.%j.err, where %j will be automatically replaced by the job id of the job.		In this sample script, the standard output and error of the job will be saved into a file called testserial.%j.out and testserial.%j.err, where %j will be automatically replaced by the job id of the job and %x by the jobname.

	====Serial (single-processor) Job on an AMD EPYC Milan processor====		====Serial (single-processor) Job on an AMD EPYC Milan processor====

Shtsai at 02:00, 6 September 2023

2023-09-06T02:00:54Z

← Older revision		Revision as of 22:00, 5 September 2023
Line 43:		Line 43:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 72:		Line 72:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 102:		Line 102:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 129:		Line 129:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 156:		Line 156:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 185:		Line 185:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 210:		Line 210:
	#SBATCH --error=array_%A-%a.err # Standard error log		#SBATCH --error=array_%A-%a.err # Standard error log
	#SBATCH --array=0-9 # Array range		#SBATCH --array=0-9 # Array range
			#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
			#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 234:		Line 236:
	#SBATCH --cpus-per-task=4 # Number of CPU cores per task		#SBATCH --cpus-per-task=4 # Number of CPU cores per task
	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR
Line 259:		Line 261:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

Shtsai: /* Serial (single-processor) Job */

2023-09-06T01:59:10Z

Serial (single-processor) Job

← Older revision		Revision as of 21:59, 5 September 2023
Line 16:		Line 16:

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=~~username~~@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail

	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

Shtsai at 01:58, 6 September 2023

2023-09-06T01:58:01Z

← Older revision		Revision as of 21:58, 5 September 2023
Line 20:		Line 20:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	module load R/3.~~6.2~~-foss-~~2019b~~		module load R/4.3.1-foss-2022a

	R CMD BATCH add.R		R CMD BATCH add.R
	</pre>		</pre>

	In this sample script, the standard output and error of the job will be saved into a file called testserial.o%j, where %j will be automatically replaced by the job id of the job.		In this sample script, the standard output and error of the job will be saved into a file called testserial.%j.out and testserial.%j.err, where %j will be automatically replaced by the job id of the job.

	====Serial (single-processor) Job on an AMD EPYC processor====		====Serial (single-processor) Job on an AMD EPYC Milan processor====

	Sample job submission script (sub.sh) to run an R program called add.R using a single core:		Sample job submission script (sub.sh) to run an R program called add.R using a single core:
Line 35:		Line 35:
	#SBATCH --job-name=testserial # Job name		#SBATCH --job-name=testserial # Job name
	#SBATCH --partition=batch # Partition (queue) name		#SBATCH --partition=batch # Partition (queue) name
	#SBATCH --constraint=~~EPYC~~ # node feature		#SBATCH --constraint=Milan # node feature
	#SBATCH --ntasks=1 # Run on a single CPU		#SBATCH --ntasks=1 # Run on a single CPU
	#SBATCH --mem=1gb # Job memory request		#SBATCH --mem=1gb # Job memory request
Line 47:		Line 47:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	module load R/3.~~6.2~~-foss-~~2019b~~		module load R/4.3.1-foss-2022a

	R CMD BATCH add.R		R CMD BATCH add.R
Line 76:		Line 76:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	module load OpenMPI/3.1.4-GCC-8.3.0		module load OpenMPI/4.1.4-GCC-11.3.0

	srun ./mympi.exe		srun ./mympi.exe
Line 106:		Line 106:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	module load OpenMPI/3.1.4-GCC-8.3.0		module load OpenMPI/4.1.4-GCC-11.3.0

	srun ./mympi.exe		srun ./mympi.exe
Line 135:		Line 135:
	export OMP_NUM_THREADS=6		export OMP_NUM_THREADS=6

	module load foss/~~2019b~~ # load the appropriate module file, e.g. foss/~~2019b~~		module load foss/2022a # load the appropriate module file, e.g. foss/2022a

	time ./a.out		time ./a.out
Line 142:		Line 142:
	====High Memory Job====		====High Memory Job====

	Sample job submission script (sub.sh) to run a velvet application that needs to use ~~50GB~~ of memory and 4 threads:		Sample job submission script (sub.sh) to run a velvet application that needs to use 200GB of memory and 4 threads:

	<pre class="gscript">		<pre class="gscript">
Line 150:		Line 150:
	#SBATCH --ntasks=1 # Run a single task		#SBATCH --ntasks=1 # Run a single task
	#SBATCH --cpus-per-task=4 # Number of CPU cores per task		#SBATCH --cpus-per-task=4 # Number of CPU cores per task
	#SBATCH --mem=~~50gb~~ # Job memory request		#SBATCH --mem=200gb # Job memory request
	#SBATCH --time=02:00:00 # Time limit hrs:min:sec		#SBATCH --time=02:00:00 # Time limit hrs:min:sec
	#SBATCH --output=highmemtest.%j.out # Standard output log		#SBATCH --output=highmemtest.%j.out # Standard output log
Line 189:		Line 189:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	module load OpenMPI/3.1.4-GCC-8.3.0		module load OpenMPI/4.1.4-GCC-11.3.0

	export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK		export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
Line 213:		Line 213:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	module load foss/~~2019b~~ # load any needed module files, e.g. foss/~~2019b~~		module load foss/2022a # load any needed module files, e.g. foss/2022a

	time ./a.out < input_$SLURM_ARRAY_TASK_ID		time ./a.out < input_$SLURM_ARRAY_TASK_ID
Line 245:		Line 245:
	====GPU/CUDA====		====GPU/CUDA====

	Sample script to run Amber on a GPU node using one node, 2 CPU cores, and 1 GPU card:		Sample script to run Amber on a GPU node using one node, 2 CPU cores, and 1 GPU A100 card:
	<pre class="gscript">		<pre class="gscript">
	#!/bin/bash		#!/bin/bash
	#SBATCH --job-name=amber # Job name		#SBATCH --job-name=amber # Job name
	#SBATCH --partition=gpu_p # Partition (queue) name, i.e., gpu_p		#SBATCH --partition=gpu_p # Partition (queue) name, i.e., gpu_p
	#SBATCH --gres=gpu:1 # Requests one GPU device		#SBATCH --gres=gpu:A100:1 # Requests one GPU device
	#SBATCH --ntasks=1 # Run a single task		#SBATCH --ntasks=1 # Run a single task
	#SBATCH --cpus-per-task=2 # Number of CPU cores per task		#SBATCH --cpus-per-task=2 # Number of CPU cores per task
Line 263:		Line 263:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

	ml Amber/18-~~fosscuda~~-~~2018b~~-AmberTools-18-~~patchlevel~~-~~10-8~~		ml Amber/22.0-foss-2021b-AmberTools-22.3-CUDA-11.4.1

	~~mpiexec~~ $AMBERHOME/bin/pmemd.cuda -O -i ./prod.in -o ~~prod_c4-23~~.out -p ./dimerFBP_GOL.prmtop -c ./restart.rst -r prod.rst -x prod.mdcrd		srun $AMBERHOME/bin/pmemd.cuda -O -i ./prod.in -o prod.out -p ./dimerFBP_GOL.prmtop -c ./restart.rst -r prod.rst -x prod.mdcrd
	</pre>		</pre>
	You can use the header <code>#SBATCH --gres=gpu:~~K20~~:1</code>~~, <code>#SBATCH --gres=gpu:K40:1</code>,~~ or <code>#SBATCH --gres=gpu:~~P100~~:1</code> to specify using a ~~K20, K40,~~ or ~~P100~~ GPU ~~node~~. The compute mode of the GPU is set to Default.		You can use the header <code>#SBATCH --gres=gpu:P100:1</code> or <code>#SBATCH --gres=gpu:A100:1</code> to specify using a P100 or an A100 GPU device. The compute mode of the GPU is set to Default.

	----		----
	[[#top\|Back to Top]]		[[#top\|Back to Top]]

Shtsai at 19:28, 27 January 2022

2022-01-27T19:28:22Z

← Older revision		Revision as of 15:28, 27 January 2022
Line 78:		Line 78:
	module load OpenMPI/3.1.4-GCC-8.3.0		module load OpenMPI/3.1.4-GCC-8.3.0

	~~mpirun~~ ./mympi.exe		srun ./mympi.exe
	</pre>		</pre>

	Please note that you need to start the application with '''mpirun''' or '''mpiexec'''~~, and not with srun~~.		Please note that you need to start the application with '''srun''' and not with '''mpirun''' or '''mpiexec'''.

	====MPI Job on nodes connected via the EDR IB fabric====		====MPI Job on nodes connected via the EDR IB fabric====
Line 108:		Line 108:
	module load OpenMPI/3.1.4-GCC-8.3.0		module load OpenMPI/3.1.4-GCC-8.3.0

	~~mpirun~~ ./mympi.exe		srun ./mympi.exe
	</pre>		</pre>

	Please note that you need to start the application with '''mpirun''' or '''mpiexec'''~~, and not with srun~~.		Please note that you need to start the application with '''srun''', and not with '''mpirun''' or '''mpiexec'''.

	====OpenMP (Multi-Thread) Job====		====OpenMP (Multi-Thread) Job====
Line 189:		Line 189:
	cd $SLURM_SUBMIT_DIR		cd $SLURM_SUBMIT_DIR

			module load OpenMPI/3.1.4-GCC-8.3.0

	export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK		export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK

	~~mpirun~~ ./myhybridprog.exe		srun ./myhybridprog.exe

	</pre>		</pre>

Moses at 14:55, 3 December 2020

2020-12-03T14:55:06Z

← Older revision		Revision as of 10:55, 3 December 2020
Line 265:		Line 265:
	mpiexec $AMBERHOME/bin/pmemd.cuda -O -i ./prod.in -o prod_c4-23.out -p ./dimerFBP_GOL.prmtop -c ./restart.rst -r prod.rst -x prod.mdcrd		mpiexec $AMBERHOME/bin/pmemd.cuda -O -i ./prod.in -o prod_c4-23.out -p ./dimerFBP_GOL.prmtop -c ./restart.rst -r prod.rst -x prod.mdcrd
	</pre>		</pre>
	You can use the ~~option~~ <code>#SBATCH --gres=gpu:K40:1</code> or <code>#SBATCH --gres=gpu:P100:1</code> to specify using a K40 or a P100 GPU ~~device, respectively~~. The compute mode of the GPU ~~will be~~ set to Default.		You can use the header <code>#SBATCH --gres=gpu:K20:1</code>, <code>#SBATCH --gres=gpu:K40:1</code>, or <code>#SBATCH --gres=gpu:P100:1</code> to specify using a K20, K40, or P100 GPU node. The compute mode of the GPU is set to Default.

	----		----
	[[#top\|Back to Top]]		[[#top\|Back to Top]]

Shtsai: /* Singularity job */

2020-10-28T13:44:59Z

Singularity job

← Older revision		Revision as of 09:44, 28 October 2020
Line 239:		Line 239:
	--threads 4 --ref db.fasta,db.idx --reads file.fa --aligned base_name_output		--threads 4 --ref db.fasta,db.idx --reads file.fa --aligned base_name_output
	</pre>		</pre>
	For more information about software installed as singularity containers on the cluster, please see [[~~Software_on_sap2test~~#Singularity_Containers]]		For more information about software installed as singularity containers on the cluster, please see [[Software_on_Sapelo2#Singularity_Containers]]

	====GPU/CUDA====		====GPU/CUDA====

← Older revision		Revision as of 22:12, 5 September 2023
Line 35:		Line 35:
	#SBATCH --job-name=testserial # Job name		#SBATCH --job-name=testserial # Job name
	#SBATCH --partition=batch # Partition (queue) name		#SBATCH --partition=batch # Partition (queue) name
	#SBATCH --constraint=Milan # node feature		#SBATCH --constraint=Milan # node feature
	#SBATCH --ntasks=1 # Run on a single CPU		#SBATCH --ntasks=1 # Run on a single CPU
	#SBATCH --mem=1gb # Job memory request		#SBATCH --mem=1gb # Job memory request
Line 150:		Line 150:
	#SBATCH --ntasks=1 # Run a single task		#SBATCH --ntasks=1 # Run a single task
	#SBATCH --cpus-per-task=4 # Number of CPU cores per task		#SBATCH --cpus-per-task=4 # Number of CPU cores per task
	#SBATCH --mem=200gb # Job memory request		#SBATCH --mem=200gb # Job memory request
	#SBATCH --time=02:00:00 # Time limit hrs:min:sec		#SBATCH --time=02:00:00 # Time limit hrs:min:sec
	#SBATCH --output=highmemtest.%j.out # Standard output log		#SBATCH --output=highmemtest.%j.out # Standard output log
Line 202:		Line 202:
	<pre class="gscript">		<pre class="gscript">
	#!/bin/bash		#!/bin/bash
	#SBATCH --job-name=arrayjobtest # Job name		#SBATCH --job-name=arrayjobtest # Job name
	#SBATCH --partition=batch # Partition (queue) name		#SBATCH --partition=batch # Partition (queue) name
	#SBATCH --ntasks=1 # Run a single task		#SBATCH --ntasks=1 # Run a single task
	#SBATCH --mem=1gb # Job Memory		#SBATCH --mem=1gb # Job Memory
	#SBATCH --time=10:00:00 # Time limit hrs:min:sec		#SBATCH --time=10:00:00 # Time limit hrs:min:sec
	#SBATCH --output=array_%A-%a.out # Standard output log		#SBATCH --output=array_%A-%a.out # Standard output log
	#SBATCH --error=array_%A-%a.err # Standard error log		#SBATCH --error=array_%A-%a.err # Standard error log
	#SBATCH --array=0-9 # Array range		#SBATCH --array=0-9 # Array range
	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail
Line 252:		Line 252:
	#SBATCH --job-name=amber # Job name		#SBATCH --job-name=amber # Job name
	#SBATCH --partition=gpu_p # Partition (queue) name, i.e., gpu_p		#SBATCH --partition=gpu_p # Partition (queue) name, i.e., gpu_p
	#SBATCH --gres=gpu:A100:1 # Requests one GPU device		#SBATCH --gres=gpu:A100:1 # Requests one GPU device
	#SBATCH --ntasks=1 # Run a single task		#SBATCH --ntasks=1 # Run a single task
	#SBATCH --cpus-per-task=2 # Number of CPU cores per task		#SBATCH --cpus-per-task=2 # Number of CPU cores per task
Line 259:		Line 259:
	#SBATCH --output=amber.%j.out # Standard output log		#SBATCH --output=amber.%j.out # Standard output log
	#SBATCH --error=amber.%j.err # Standard error log		#SBATCH --error=amber.%j.err # Standard error log

	#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)		#SBATCH --mail-type=END,FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
	#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail		#SBATCH --mail-user=yourMyID@uga.edu # Where to send mail