Research Computing Center Wiki - User contributions [en]

Job Submission partitions on Sapelo2

2026-05-15T18:37:45Z

Shtsai:

[[category:sapelo2]]

== Overview ==
This page describes the Slurm partitions available on the Sapelo2 cluster, including job limits and the resources available in each partition.

In Slurm, queues are called ''partitions''. When you submit a job, you must request both:
* the partition to use, and
* the resources your job needs, such as CPU cores, memory, or GPU devices.

Slurm will reject a job submission if no nodes match the resources you request. For background on Slurm, see [[Migrating from Torque to Slurm]].

== How to use this page ==
Use the first table to choose a partition based on job type and time limit.

Use the second table to confirm that your requested resources fit within the hardware available in that partition.

== Partition limits ==
{| class="wikitable unsortable"
|+ Sapelo2 partitions, time limits, and per-user job limits
|-
! scope="col" | Partition name
! scope="col" | Time limit
! scope="col" | Maximum running jobs per user
! scope="col" | Maximum submitted jobs per user
! scope="col" | Intended use and notes
|-
! scope="row" | <code>batch</code>
| 7 days
| 250
| 10,000
| Standard partition for regular compute jobs on general-purpose nodes.
|-
! scope="row" | <code>batch_30d</code>
| 30 days
| 1
| 2
| Standard partition for long-running jobs on regular nodes. A user may have one running job and one pending job, or two pending jobs and no running job. A third submission to this partition will be rejected.
|-
! scope="row" | <code>highmem_p</code>
| 7 days
| 6
| 100
| High-memory partition for jobs that require more memory than standard nodes provide.
|-
! scope="row" | <code>highmem_30d_p</code>
| 30 days
| 1
| 2
| High-memory partition for long-running jobs. A user may have one running job and one pending job, or two pending jobs and no running job. A third submission to this partition will be rejected.
|-
! scope="row" | <code>hugemem_p</code>
| 7 days
| 4
| 4
| Huge-memory partition for jobs needing up to 3 TB of memory.
|-
! scope="row" | <code>hugemem_30d_p</code>
| 30 days
| 4
| 4
| Huge-memory partition for long-running jobs needing up to 3 TB of memory.
|-
! scope="row" | <code>gpu_p</code>
| 7 days
| 8
| 20
| GPU-enabled partition for jobs that require one or more GPUs.
|-
! scope="row" | <code>gpu_30d_p</code>
| 30 days
| 2
| 2
| GPU-enabled partition for long-running jobs. A user may have one running job and one pending job, or two pending jobs and no running job. A third submission to this partition will be rejected.
|-
! scope="row" | <code>inter_p</code>
| 2 days
| 3
| 20
| Interactive partition for interactive jobs on regular nodes.
|-
! scope="row" | <code>''name''_p</code>
| Variable
| Variable
| Variable
| Partition for a specific group's buy-in nodes. Replace <code>''name''</code> with the group-specific partition prefix.
|}

== Resource limits by partition ==
Before submitting a job, make sure your requested memory, CPU cores, and GPU count fit within the limits of the partition you choose.

In the table below, the phrase '''partition maximum''' identifies the largest per-node resource values available within that partition. This replaces color-only emphasis so that the information is available to all users.

{| class="wikitable unsortable"
|+ Node resources available in each Sapelo2 partition
|-
! scope="col" | Partition
! scope="col" | Number of nodes
! scope="col" | Memory per node (GB)
! scope="col" | CPU cores per node
! scope="col" | Processor type
! scope="col" | GPU configuration
! scope="col" | Notes
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 16
| 740
| 128
| AMD EPYC Genoa (4th gen)
| None
| Partition maximum for memory and cores is available on this node type.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 120
| 500
| 128
| AMD EPYC Milan (3rd gen)
| None
| Partition maximum for cores is also available on this node type.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 4
| 250
| 64
| AMD EPYC Milan (3rd gen)
| None
| Standard-capacity general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 2
| 120
| 64
| AMD EPYC Milan (3rd gen)
| None
| Standard-capacity general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 123
| 120
| 64
| AMD EPYC Rome (2nd gen)
| None
| Standard-capacity general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 25
| 120
| 32
| AMD EPYC Naples (1st gen)
| None
| Lower-core-count general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 40
| 180
| 32
| Intel Xeon Skylake
| None
| Lower-core-count general-purpose nodes.
|-
! scope="row" | <code>highmem_p</code>, <code>highmem_30d_p</code>
| 10
| 500
| 32
| AMD EPYC Naples (1st gen)
| None
| High-memory nodes.
|-
! scope="row" | <code>highmem_p</code>, <code>highmem_30d_p</code>
| 2
| 990
| 128
| AMD EPYC Milan (3rd gen)
| None
| Partition maximum for memory and cores is available on this node type.
|-
! scope="row" | <code>highmem_p</code>, <code>highmem_30d_p</code>
| 12
| 990
| 32
| AMD EPYC Milan (3rd gen)
| None
| High-memory nodes with fewer available cores per node.
|-
! scope="row" | <code>hugemem_p</code>, <code>hugemem_30d_p</code>
| 3
| 3000
| 48
| AMD EPYC Genoa (4th gen)
| None
| Partition maximum for memory and cores is available on this node type.
|-
! scope="row" | <code>hugemem_p</code>, <code>hugemem_30d_p</code>
| 2
| 2000
| 32
| AMD EPYC Rome (2nd gen)
| None
| Huge-memory nodes with lower maximums than the partition peak.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 2
| 180
| 32
| Intel Xeon Skylake
| 1 NVIDIA P100
| Older GPU nodes.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 2
| 120
| 64
| AMD EPYC Rome (2nd gen)
| 1 NVIDIA V100S
| Single-GPU nodes with 64 cores.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 14
| 1000
| 64
| AMD EPYC Milan (3rd gen)
| 4 NVIDIA A100
| Partition maximum for memory is available on this node type.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 12
| 1000
| 64
| Intel Xeon Sapphire Rapids
| 4 NVIDIA H100
| Partition maximum for memory is available on this node type.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 12
| 740
| 128
| AMD EPYC Genoa (4th gen)
| 4 NVIDIA L4
| Partition maximum for cores is available on this node type.
|-
! scope="row" | <code>''name''_p</code>
| Variable
| Variable
| Variable
| Variable
| Variable
| Resource limits depend on the group's buy-in nodes.
|}

== Choosing a partition ==
A general rule of thumb is:

* Use <code>batch</code> for most non-GPU jobs.
* Use <code>batch_30d</code> only when your job genuinely needs a longer wall time.
* Use <code>highmem_p</code> or <code>highmem_30d_p</code> when your memory requirements exceed what standard nodes provide.
* Use <code>hugemem_p</code> or <code>hugemem_30d_p</code> for jobs that need very large memory allocations, including jobs approaching 3 TB of memory.
* Use <code>gpu_p</code> or <code>gpu_30d_p</code> for GPU jobs.
* Use <code>inter_p</code> for interactive work.
* Use <code>''name''_p</code> only if your group has access to a buy-in partition with that name.



== Terms used on this page ==
; Partition
: A Slurm queue that determines which nodes your job may run on.
; Time limit
: The maximum wall-clock runtime allowed for a job in that partition.
; Running jobs
: Jobs currently executing for a user in that partition.
; Submitted jobs
: Total jobs a user may have in the partition, including running and pending jobs.
; Buy-in nodes
: Nodes purchased by a specific group and made available through a group-specific partition.

== Related documentation ==
* [[Migrating from Torque to Slurm]]

Nsight-Compute-CLI-Sapelo2

2026-05-14T21:21:23Z

Shtsai:

[[Category:Sapelo2]][[Category:Software]][[Category:Other]]

== Category ==

Other

== Program On ==

Sapelo2

== Version ==

2023.1.1.0, 2024.1.0.0, 2024.3.0.0, 2025.1.0.0, 2025.4.0.0

== Author / Distributor ==

NVIDIA

== Description ==

From https://docs.nvidia.com/nsight-compute/NsightComputeCli/index.html: "NVIDIA Nsight Compute CLI (ncu) provides a non-interactive way to profile applications from the command line. "

== Running Program ==

Also refer to [[Running Jobs on Sapelo2]]

Compute nodes equipped with GPU cards have access to all applications installed in /apps.

* Version 2025.4.0.0 is installed with CUDA v. 13.1.0 in /apps/eb/CUDA/13.1.0

To use it, please first load the module with:
<pre class="gcommand">
module load CUDA/13.1.0
</pre>

* Version 2025.1.0.0 is installed with CUDA v. 12.8.0 in /apps/eb/CUDA/12.8.0

To use it, please first load the module with:
<pre class="gcommand">
module load CUDA/12.8.0
</pre>

* Version 2024.3.0.0 is installed with CUDA v. 12.6.0 in /apps/eb/CUDA/12.6.0

To use it, please first load the module with:
<pre class="gcommand">
module load CUDA/12.6.0
</pre>

* Version 2024.1.0.0 is installed with CUDA v. 12.4.0 in /apps/eb/CUDA/12.4.0

To use it, please first load the module with:
<pre class="gcommand">
module load CUDA/12.4.0
</pre>

* Version 2023.1.1.0 is installed with CUDA v. 12.1.1 in /apps/eb/CUDA/12.1.1

To use it, please first load the module with:
<pre class="gcommand">
module load CUDA/12.1.1
</pre>

'''Please note:'''

'''1.''' Before running ncu to profile an application, please set the environment variable TMPDIR to point to a directory of yours. For example, use
<pre class="gcommand">
export TMPDIR=/scratch/$USER
</pre>

'''2.''' To profile applications on the H100 devices, please use the ncu in CUDA version 12.6.0 or higher. The older versions of ncu do not support the Hopper architecture.

'''3.''' Currently the ncu command only works on the following nodes:

<pre class="gcomment">
A100: ra4-1, ra4-2, b6-1, b6-2, b6-3, b6-4, b7-1, b7-2,b7-4, b8-4

H100: ra5-2, ra5-3, ra7-2, ra8-3, ra8-4
</pre>

More nodes will be added to the list above, as ncu is enabled on them (it requires a node reboot). Please check back, if of interest.

You can request a specific node with the Slurm <code>--nodelist</code> option. For example, <code>--nodelist=ra8-3 </code>.

'''Sample command to request an interactive job on a specific node:'''
<pre class="gcommand">
interact -p gpu_p --gres=gpu:H100:1 --nodelist=ra8-3
</pre>

'''Sample Slurm header line to request a specific node for a batch job:'''
<pre class="gcommand">
#SBATCH --nodelist=ra8-3
</pre>

== Documentation ==

Please see https://docs.nvidia.com/nsight-compute/NsightComputeCli/index.html

== Installation ==

Downloaded from NVIDIA site.

== System ==

64-bit Linux

Trinity-Sapelo2

2026-05-11T19:56:28Z

Shtsai:

[[Category:Sapelo2]][[Category:Software]][[Category:Bioinformatics]]
== Category ==

Bioinformatics

== Program On ==

Sapelo2

== Version ==

2.5.1, 2.8.4, 2.8.5, 2.15.1, 2.15.2

== Author / Distributor ==

Trinity is now published online at [http://www.nature.com/nbt/journal/v29/n7/abs/nbt.1883.html Nature Biotechnology]. The Broad Institute’s [http://www.broadinstitute.org/blog/suite-tools-takes-flight blog] has a story on how the Trinity project came together.

More details at [https://github.com/trinityrnaseq/trinityrnaseq/ Trinity github page]

== Description ==

From https://github.com/trinityrnaseq/trinityrnaseq/wiki:

"Trinity, developed at the [http://www.broadinstitute.org/ Broad Institute], represents a novel method for the efficient and robust de novo reconstruction of transcriptomes from RNA-Seq data. Trinity combines three independent software modules: Inchworm, Chrysalis, and Butterfly, applied sequentially to process large volumes of RNA-Seq reads. Trinity partitions the sequence data into many individual de Bruijn graphs, each representing the transcriptional complexity at at a given gene or locus, and then processes each graph independently to extract full-length splicing isoforms and to tease apart transcripts derived from paralogous genes. Briefly, the process works like so:

Inchworm assembles the RNA-Seq data into the unique sequences of transcripts, often generating full-length transcripts for a dominant isoform, but then reports just the unique portions of alternatively spliced transcripts.

Chrysalis clusters the Inchworm contigs into clusters and constructs complete de Bruijn graphs for each cluster. Each cluster represents the full transcriptonal complexity for a given gene (or sets of genes that share sequences in common). Chrysalis then partitions the full read set among these disjoint graphs.

Butterfly then processes the individual graphs in parallel, tracing the paths that reads and pairs of reads take within the graph, ultimately reporting full-length transcripts for alternatively spliced isoforms, and teasing apart transcripts that corresponds to paralogous genes."

[[#top|Back to Top]]

== Running Program ==

===General Instructions===

Also refer to [[Running Jobs on Sapelo2]]

Trinity versions 2.5.1, 2.8.4, 2.8.5, 2.15.1, and 2.15.2 are installed on Sapelo2.

* Mostly trinity needs to run at large memory queue, namely highmem_p, as in the sample script below.
* '''Trinity is best run utilizing /lscratch, please see [[Trinity-Sapelo2#Utilizing .2Flscratch in Trinity Job Submission Script|Utilizing /lscratch for Trinity Jobs]] or scroll down to see how to configure your job submission script to use /lscratch'''
* To run Trinity in conjunction with HpcGridRunner, please see [[Trinity-HpcGridRunner|our wiki page on Trinity HpcGridRunner]].

* Memory estimates according to an old Trinity documentation: For a 4 billion base mouse, it uses about 50 GB memory at peak.

* Do not ask for more than 24 CPU cores at the command and double the quantity of requesting CPU from queue. e.g. at the following, command ask for 8 CPU cores and at the header, it asks for --cpus-per-task=8.

* Using --normalize_reads could tremendously reduce the needs of memory. For this feature, please ensure there is no space in sequence name and quality score names, and adding "/1", "/2" to sequence name to make each seq name unique for pair reads in fasta /fq header.

* '''Please use the --full_cleanup option to make sure Trinity cleans up after itself.''' This helps a lot in keeping the number of files on Lustre storage under control.

* If previous jobs left dir trinity_out_dir, remove it before start another trinity job.

===Trinity versions 2.5.1, 2.8.4, and 2.8.5 Singularity Container on Sapelo2===

On the Sapelo2 cluster, singularity containers have access to the users home directory ($HOME), scratch directory (/scratch), lscratch directory (/lscratch), /tmp directory (/tmp) inside the container.

All environment variables set before executing singularity command is available inside the container.

To run Trinity v2.5.1, sample command is as below:

<pre class="gcommand">
singularity exec /apps/singularity-images/trinity-2.5.1.simg COMMAND
</pre>

where COMMAND should be replaced by the command you want to use.

To run Trinity v2.8.4, sample command is as below:

<pre class="gcommand">
singularity exec /apps/singularity-images/trinity-2.8.4.simg COMMAND
</pre>

To run Trinity v2.8.5, sample command is as below:

<pre class="gcommand">
singularity exec /apps/singularity-images/trinity-2.8.5.simg COMMAND
</pre>

where COMMAND should be replaced by the command you want to use.

Example of a shell script sub.sh to run Trinity v2.8.4 on the batch partition:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=8 # CPU core count per task
#SBATCH --mem=100G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=log.%j.out # Standard output log
#SBATCH --error=log.%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

singularity exec /apps/singularity-images/trinity-2.8.4.simg Trinity --seqType <string> --max_memory 100G --CPU 8 --no_version_check --full_cleanup --normalize_reads
</pre>

Example to run Trinity script align_and_estimate_abundance.pl:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=1 # CPU core count per task
#SBATCH --mem=20G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=%x_%j.out # Standard output log
#SBATCH --error=%x_%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

singularity exec /apps/singularity-images/trinity-2.8.4.simg /usr/local/bin/trinityrnaseq/util/align_and_estimate_abundance.pl [options]
</pre>

Where [options] need to be added as appropriate. Other parameters of the job, such as the maximum wall clock time, maximum memory, the number cores per node, and the job name need to be modified appropriately as well.

[[#top|Back to Top]]

===Trinity versions 2.15.1 and 2.15.2 Software Module on Sapelo2 ===

*version 2.15.1 running with Python3 is installed at /apps/eb/Trinity/2.15.1-foss-2022a

To run Trinity v2.15.1, please load the module:

<pre class="gcommand">
module load Trinity/2.15.1-foss-2022a
</pre>

*version 2.15.2 running with Python3 is installed at /apps/eb/Trinity/2.15.2-foss-2023a

To run Trinity v2.15.2, please load the module:

<pre class="gcommand">
module load Trinity/2.15.2-foss-2023a
</pre>

Example of a shell script sub.sh to run Trinity v2.15.1 on the batch partition:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=8 # CPU core count per task
#SBATCH --mem=100G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=log.%j.out # Standard output log
#SBATCH --error=log.%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

module load Trinity/2.15.1-foss-2022a

Trinity --seqType <string> --max_memory 100G --CPU 8 --no_version_check --full_cleanup --normalize_reads
</pre>

Example to run Trinity script align_and_estimate_abundance.pl:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=1 # CPU core count per task
#SBATCH --mem=20G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=%x_%j.out # Standard output log
#SBATCH --error=%x_%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

module load Trinity/2.15.1-foss-2022a

${EBROOTTRINITY}/trinityrnaseq-v2.10.0/util/align_and_estimate_abundance.pl [options]
</pre>

Where EBROOTTRINITY is the env variable storing Trinity installation pat, i.e., /apps/eb/Trinity/2.15.1-foss-2022a ; [options] need to be added as appropriate. Other parameters of the job, such as the maximum wall clock time, maximum memory, the number cores per node, and the job name need to be modified appropriately as well.

[[#top|Back to Top]]

==Utilizing /lscratch in Trinity Job Submission Script==
* Utilizing /lscratch allows Trinity jobs to run much faster and smoother and also negates the effects of heavy IO traffic.
* This /lscratch directory resides on the local hard drive of the compute node that your job gets allocated to (which means you cannot access this directory outside the job submission script).
* Below is a sample job submission script including steps so you can see what you need to add to your job submission script in order to make your Trinity job utilize /lscratch.
** As well as adding the 6 steps below, please also add the Slurm header --gres=lscratch:___ which requests space in /lscratch. The default units for this is GB and in the example submission script below, we are requesting 200GB of space with the line '''''#SBATCH --gres=lscratch:200''''' (it is the last Slurm header). Please only request as much space in /lscratch as is needed for your job.

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=36 # CPU core count per task
#SBATCH --mem=128G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=log.%j.out # Standard output log
#SBATCH --error=log.%j.err # Standard error log
#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)
#SBATCH --gres=lscratch:200

cd $SLURM_SUBMIT_DIR

# Step 1: create a directory in /lscratch

mkdir -p /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs

# Step 2: copy over any input files.

cp file1.fastq.gz /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs
cp file2.fastq.gz /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs
cp file3.bam /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs

# Step 3: change directories into /lscratch

cd /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs

# Step 4: your normal job lines (loading Trinity and running Trinity command)

module load Trinity/2.15.1-foss-2022a

Trinity --seqType fq --left 'file1.fastq.gz' --right 'file2.fastq.gz' --CPU 36 --max_memory 120G --output '/lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs/trinity'

Trinity --genome_guided_bam 'file3.bam' --genome_guided_max_intron 10000 --CPU 36 --max_memory 120G --output '/lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs/trinity'

### NOTE: the directory specified in --output is the directory created in step 1 with the addition of /trinity at the end. This is because Trinity writes some files in the --output dir and some right above it.

# Step 5: copy output files back over to a certain location in /scratch which you can change below

cp -r /lscratch/${USER}/* /scratch/${USER}/some/directory

# Step 6: clean up /lscratch directory **VERY IMPORTANT STEP**

rm -rf /lscratch/${USER}/${SLURM_JOB_ID}
</pre>

* Please feel free to submit a ticket to us if you would like further help, explanations of how /lscratch works, or to even look over your submission script to ensure it is correctly utilizing /lscratch!

==Job Submission==

Submit a job submission script (sub.sh) to Sapelo2:

<pre class="gcommand">
sbatch sub.sh
</pre>

[[#top|Back to Top]]

==Documentation ==

More details at [https://github.com/trinityrnaseq/trinityrnaseq/wiki/ Trinity wiki page]

<pre class="gcommand">
[cft07037@b1-24 ~]$ ml Trinity/2.15.1-foss-2022a
To execute picard run: java -jar $EBROOTPICARD/picard.jar
[cft07037@b1-24 ~]$ Trinity --show_full_usage_info

###############################################################################
#

______ ____ ____ ____ ____ ______ __ __
| || \ | || \ | || || | |
| || D ) | | | _ | | | | || | |
|_| |_|| / | | | | | | | |_| |_|| ~ |
| | | \ | | | | | | | | | |___, |
| | | . \ | | | | | | | | | | |
|__| |__|\_||____||__|__||____| |__| |____/

Trinity-v2.15.1

#
#
# Required:
#
# --seqType <string> :type of reads: ('fa' or 'fq')
#
# --max_memory <string> :suggested max memory to use by Trinity where limiting can be enabled. (jellyfish, sorting, etc)
# provided in Gb of RAM, ie. '--max_memory 10G'
#
# If paired reads:
# --left <string> :left reads, one or more file names (separated by commas, no spaces)
# --right <string> :right reads, one or more file names (separated by commas, no spaces)
#
# Or, if unpaired reads:
# --single <string> :single reads, one or more file names, comma-delimited (note, if single file contains pairs, can use flag: --run_as_paired )
#
# Or,
# --samples_file <string> tab-delimited text file indicating biological replicate relationships.
# ex.
# cond_A cond_A_rep1 A_rep1_left.fq A_rep1_right.fq
# cond_A cond_A_rep2 A_rep2_left.fq A_rep2_right.fq
# cond_B cond_B_rep1 B_rep1_left.fq B_rep1_right.fq
# cond_B cond_B_rep2 B_rep2_left.fq B_rep2_right.fq
#
# # if single-end instead of paired-end, then leave the 4th column above empty.
#
####################################
## Misc: #########################
#
# --SS_lib_type <string> :Strand-specific RNA-Seq read orientation.
# if paired: RF or FR,
# if single: F or R. (dUTP method = RF)
# See web documentation.
#
# --CPU <int> :number of CPUs to use, default: 2
# --min_contig_length <int> :minimum assembled contig length to report
# (def=200, must be >= 100)
#
# --long_reads <string> :fasta file containing error-corrected or circular consensus (CCS) pac bio reads
# (** note: experimental parameter **, this functionality continues to be under development)
#
# --genome_guided_bam <string> :genome guided mode, provide path to coordinate-sorted bam file.
# (see genome-guided param section under --show_full_usage_info)
#
# --long_reads_bam <string> :long reads to include for genome-guided Trinity
# (bam file consists of error-corrected or circular consensus (CCS) pac bio read aligned to the genome)
#
# --jaccard_clip :option, set if you have paired reads and
# you expect high gene density with UTR
# overlap (use FASTQ input file format
# for reads).
# (note: jaccard_clip is an expensive
# operation, so avoid using it unless
# necessary due to finding excessive fusion
# transcripts w/o it.)
#
# --trimmomatic :run Trimmomatic to quality trim reads
# see '--quality_trimming_params' under full usage info for tailored settings.
#
# --output <string> :name of directory for output (will be
# created if it doesn't already exist)
# default( your current working directory: "/home/cft07037/trinity_out_dir"
# note: must include 'trinity' in the name as a safety precaution! )
#
# --full_cleanup :only retain the Trinity fasta file, rename as ${output_dir}.Trinity.fasta
#
# --cite :show the Trinity literature citation
#
# --verbose :provide additional job status info during the run.
#
# --version :reports Trinity version (Trinity-v2.15.1) and exits.
#
# --show_full_usage_info :show the many many more options available for running Trinity (expert usage).

#
# --no_super_reads :turn off super-reads mode
#
# --prep :Only prepare files (high I/O usage) and stop before kmer counting.
#
# --no_cleanup :retain all intermediate input files.
#
# --no_version_check :dont run a network check to determine if software updates are available.
#
# --no_symlink :dont symlink, just copy files instead (sets env var NO_SYMLINK=TRUE)
#
# --monitoring :use collectl to monitor all steps of Trinity
# --monitor_sec <int> : number of seconds for each interval of runtime monitoring (default: 60)
#
# --no_distributed_trinity_exec :do not run Trinity phase 2 (assembly of partitioned reads), and stop after generating command list.
#
# --workdir <string> :where Trinity phase-2 assembly computation takes place (defaults to --output setting).
# (can set this to a node-local drive or RAM disk)
#
####################################################
# Inchworm and K-mer counting-related options: #####
#
# --min_kmer_cov <int> :min count for K-mers to be assembled by
# Inchworm (default: 1)
# --inchworm_cpu <int> :number of CPUs to use for Inchworm, default is min(6, --CPU option)
#
# --no_run_inchworm :stop after running jellyfish, before inchworm. (phase 1, read clustering only)
#
###################################
# Chrysalis-related options: ######
#
# --max_reads_per_graph <int> :maximum number of reads to anchor within
# a single graph (default: 200000)
# --min_glue <int> :min number of reads needed to glue two inchworm contigs
# together. (default: 2)
#
# --max_chrysalis_cluster_size <int> :max number of Inchworm contigs to be included in a single Chrysalis cluster. (default: 25)
#
# --no_bowtie :dont run bowtie to use pair info in chrysalis clustering.
#
# --no_run_chrysalis :stop after running inchworm, before chrysalis. (phase 1, read clustering only)
#
#####################################
### Butterfly-related options: ####
#
# --bfly_algorithm <string> : assembly algorithm to use. Options: ORIGINAL PASAFLY
#
# --bfly_opts <string> :additional parameters to pass through to butterfly
# (see butterfly options: java -jar Butterfly.jar ).
# (note: only for expert or experimental use. Commonly used parameters are exposed through this Trinity menu here).
#
#
# Butterfly read-pair grouping settings (used to define 'pair paths'):
#
# --group_pairs_distance <int> :maximum length expected between fragment pairs (default: 500)
# (reads outside this distance are treated as single-end)
#
# ///////////////////////////////////////////////
# Butterfly default reconstruction mode settings.
#
# --path_reinforcement_distance <int> :minimum overlap of reads with growing transcript
# path (default: PE: 25, SE: 25)
# Set to 1 for the most lenient path extension requirements.
#
#
# /////////////////////////////////////////
# Butterfly transcript reduction settings:
#
# --no_path_merging : all final transcript candidates are output (including SNP variations, however, some SNPs may be unphased)
#
# By default, alternative transcript candidates are merged (in reality, discarded) if they are found to be too similar, according to the following logic:
#
# (identity=(numberOfMatches/shorterLen) > 98.0% or if we have <= 2 mismatches) and if we have internal gap lengths <= 10
#
# with parameters as:
#
# --min_per_id_same_path <int> default: 98 min percent identity for two paths to be merged into single paths
# --max_diffs_same_path <int> default: 2 max allowed differences encountered between path sequences to combine them
# --max_internal_gap_same_path <int> default: 10 maximum number of internal consecutive gap characters allowed for paths to be merged into single paths.
#
# If, in a comparison between two alternative transcripts, they are found too similar, the transcript with the greatest cumulative
# compatible read (pair-path) support is retained, and the other is discarded.
#
#
# //////////////////////////////////////////////
# Butterfly Java and parallel execution settings.
#
# --bflyHeapSpaceMax <string> :java max heap space setting for butterfly
# (default: 10G) => yields command
# 'java -Xmx10G -jar Butterfly.jar ... $bfly_opts'
# --bflyHeapSpaceInit <string> :java initial heap space settings for
# butterfly (default: 1G) => yields command
# 'java -Xms1G -jar Butterfly.jar ... $bfly_opts'
# --bflyGCThreads <int> :threads for garbage collection
# (default: 2))
# --bflyCPU <int> :CPUs to use (default will be normal
# number of CPUs; e.g., 2)
# --bflyCalculateCPU :Calculate CPUs based on 80% of max_memory
# divided by maxbflyHeapSpaceMax
#
# --bfly_jar <string> : /path/to/Butterfly.jar, otherwise default
# Trinity-installed version is used.
#
#
################################################################################
#### Quality Trimming Options ####
#
# --quality_trimming_params <string> defaults to: "ILLUMINACLIP:/apps/eb/Trinity/2.15.1-foss-2022a/trinityrnaseq-v2.15.1/trinity-plugins/Trimmomatic/adapters/TruSeq3-PE.fa:2:30:10 SLIDINGWINDOW:4:5 LEADING:5 TRAILING:5 MINLEN:25"
#
################################################################################
#### In silico Read Normalization Options ###
#
# --normalize_max_read_cov <int> defaults to 200
# --normalize_by_read_set run normalization separate for each pair of fastq files,
# then one final normalization that combines the individual normalized reads.
# Consider using this if RAM limitations are a consideration.
#
# --just_normalize_reads stop after performing read normalization
#
# --no_normalize_reads :Do *not* run in silico normalization of reads. Defaults to max. read coverage of 200.
# see '--normalize_max_read_cov' under full usage info for tailored settings.
# (Note, as of Sept 21, 2016, normalization is on by default)
# (*Turning off normalization is not recommended for most applications)
#
# --no_parallel_norm_stats :Do not try to run the high-mem normalization stats generator in parallel for paired-end fastqs.
#
###############################################################################
#### Genome-guided de novo assembly
#
# * required:
#
# --genome_guided_max_intron <int> :maximum allowed intron length (also maximum fragment span on genome)
#
# * optional:
#
# --genome_guided_min_coverage <int> :minimum read coverage for identifying and expressed region of the genome. (default: 1)
#
# --genome_guided_min_reads_per_partition <int> :default min of 10 reads per partition
#
#
#######################################################################
# Trinity phase 2 (parallel assembly of read clusters) Options: #######
#
# --grid_exec <string> :your command-line utility for submitting jobs to the grid.
# This should be a command line tool that accepts a single parameter:
# ${your_submission_tool} /path/to/file/containing/commands.txt
# and this submission tool should exit(0) upon successful
# completion of all commands.
#
# --grid_node_CPU <int> number of threads for each parallel process to leverage. (default: 1)
#
# --grid_node_max_memory <string> max memory targeted for each grid node. (default: 1G)
#
# The --grid_node_CPU and --grid_node_max_memory are applied as
# the --CPU and --max_memory parameters for the Trinity jobs run in
# Trinity Phase 2 (assembly of read clusters)
#
# --FORCE ignore failed commands from earlier run, continue on.
# (Note, this should only be used after you've
# already dealt with these failed commands directly as needed)
#
########################################################################
# Singularity-related options
#
# --singularity_img <string> :path to a Trinity singularity image to use
#
# --singularity_extra_params <string> :additional parameters to include for the singularity command execution
#
#

#
#
###############################################################################
#
# *Note, a typical Trinity command might be:
#
# Trinity --seqType fq --max_memory 50G --left reads_1.fq --right reads_2.fq --CPU 6
#
# (if you have multiple samples, use --samples_file ... see above for details)
#
# and for Genome-guided Trinity, provide a coordinate-sorted bam:
#
# Trinity --genome_guided_bam rnaseq_alignments.csorted.bam --max_memory 50G
# --genome_guided_max_intron 10000 --CPU 6
#
# see: /apps/eb/Trinity/2.15.1-foss-2022a/trinityrnaseq-v2.15.1/sample_data/test_Trinity_Assembly/
# for sample data and 'runMe.sh' for example Trinity execution
#
# For more details, visit: http://trinityrnaseq.github.io
#
###############################################################################
</pre>
[[#top|Back to Top]]

== Installation==

Sources are downloaded from https://github.com/trinityrnaseq/trinityrnaseq

==System==
64-bit Linux

[[#top|Back to Top]]

Trinity-Sapelo2

2026-05-11T19:35:14Z

Shtsai:

[[Category:Sapelo2]][[Category:Software]][[Category:Bioinformatics]]
== Category ==

Bioinformatics

== Program On ==

Sapelo2

== Version ==

2.5.1, 2.8.4, 2.8.5, 2.15.1, 2.15.2

== Author / Distributor ==

Trinity is now published online at [http://www.nature.com/nbt/journal/v29/n7/abs/nbt.1883.html Nature Biotechnology]. The Broad Institute’s [http://www.broadinstitute.org/blog/suite-tools-takes-flight blog] has a story on how the Trinity project came together.

More details at [http://trinityrnaseq.github.io/ Trinity]

== Description ==

From [http://trinityrnaseq.github.io/ Trinity]:

"Trinity, developed at the [http://www.broadinstitute.org/ Broad Institute], represents a novel method for the efficient and robust de novo reconstruction of transcriptomes from RNA-Seq data. Trinity combines three independent software modules: Inchworm, Chrysalis, and Butterfly, applied sequentially to process large volumes of RNA-Seq reads. Trinity partitions the sequence data into many individual de Bruijn graphs, each representing the transcriptional complexity at at a given gene or locus, and then processes each graph independently to extract full-length splicing isoforms and to tease apart transcripts derived from paralogous genes. Briefly, the process works like so:

Inchworm assembles the RNA-Seq data into the unique sequences of transcripts, often generating full-length transcripts for a dominant isoform, but then reports just the unique portions of alternatively spliced transcripts.

Chrysalis clusters the Inchworm contigs into clusters and constructs complete de Bruijn graphs for each cluster. Each cluster represents the full transcriptonal complexity for a given gene (or sets of genes that share sequences in common). Chrysalis then partitions the full read set among these disjoint graphs.

Butterfly then processes the individual graphs in parallel, tracing the paths that reads and pairs of reads take within the graph, ultimately reporting full-length transcripts for alternatively spliced isoforms, and teasing apart transcripts that corresponds to paralogous genes."

[[#top|Back to Top]]

== Running Program ==

===General Instructions===

Also refer to [[Running Jobs on Sapelo2]]

Trinity versions 2.5.1, 2.8.4, 2.8.5, 2.15.1, and 2.15.2 are installed on Sapelo2.

* Mostly trinity needs to run at large memory queue, namely highmem_p, as in the sample script below.
* '''Trinity is best run utilizing /lscratch, please see [[Trinity-Sapelo2#Utilizing .2Flscratch in Trinity Job Submission Script|Utilizing /lscratch for Trinity Jobs]] or scroll down to see how to configure your job submission script to use /lscratch'''
* To run Trinity in conjunction with HpcGridRunner, please see [[Trinity-HpcGridRunner|our wiki page on Trinity HpcGridRunner]].

* Here is a post for memory estimates. For a 4 billion base mouse, it uses about 50 GB memory at peak. [http://trinityrnaseq.github.io/performance/index.html performance]

* Do not ask for more than 24 CPU cores at the command and double the quantity of requesting CPU from queue. e.g. at the following, command ask for 8 CPU cores and at the header, it asks for --cpus-per-task=8.

* Using --normalize_reads could tremendously reduce the needs of memory. For this feature, please ensure there is no space in sequence name and quality score names, and adding "/1", "/2" to sequence name to make each seq name unique for pair reads in fasta /fq header.

* '''Please use the --full_cleanup option to make sure Trinity cleans up after itself.''' This helps a lot in keeping the number of files on Lustre storage under control.

* If previous jobs left dir trinity_out_dir, remove it before start another trinity job.

===Trinity versions 2.5.1, 2.8.4, and 2.8.5 Singularity Container on Sapelo2===

On the Sapelo2 cluster, singularity containers have access to the users home directory ($HOME), scratch directory (/scratch), lscratch directory (/lscratch), /tmp directory (/tmp) inside the container.

All environment variables set before executing singularity command is available inside the container.

To run Trinity v2.5.1, sample command is as below:

<pre class="gcommand">
singularity exec /apps/singularity-images/trinity-2.5.1.simg COMMAND
</pre>

where COMMAND should be replaced by the command you want to use.

To run Trinity v2.8.4, sample command is as below:

<pre class="gcommand">
singularity exec /apps/singularity-images/trinity-2.8.4.simg COMMAND
</pre>

To run Trinity v2.8.5, sample command is as below:

<pre class="gcommand">
singularity exec /apps/singularity-images/trinity-2.8.5.simg COMMAND
</pre>

where COMMAND should be replaced by the command you want to use.

Example of a shell script sub.sh to run Trinity v2.8.4 on the batch partition:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=8 # CPU core count per task
#SBATCH --mem=100G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=log.%j.out # Standard output log
#SBATCH --error=log.%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

singularity exec /apps/singularity-images/trinity-2.8.4.simg Trinity --seqType <string> --max_memory 100G --CPU 8 --no_version_check --full_cleanup --normalize_reads
</pre>

Example to run Trinity script align_and_estimate_abundance.pl:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=1 # CPU core count per task
#SBATCH --mem=20G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=%x_%j.out # Standard output log
#SBATCH --error=%x_%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

singularity exec /apps/singularity-images/trinity-2.8.4.simg /usr/local/bin/trinityrnaseq/util/align_and_estimate_abundance.pl [options]
</pre>

Where [options] need to be added as appropriate. Other parameters of the job, such as the maximum wall clock time, maximum memory, the number cores per node, and the job name need to be modified appropriately as well.

[[#top|Back to Top]]

===Trinity versions 2.15.1 and 2.15.2 Software Module on Sapelo2 ===

*version 2.15.1 running with Python3 is installed at /apps/eb/Trinity/2.15.1-foss-2022a

To run Trinity v2.15.1, please load the module:

<pre class="gcommand">
module load Trinity/2.15.1-foss-2022a
</pre>

*version 2.15.2 running with Python3 is installed at /apps/eb/Trinity/2.15.2-foss-2023a

To run Trinity v2.15.2, please load the module:

<pre class="gcommand">
module load Trinity/2.15.2-foss-2023a
</pre>

Example of a shell script sub.sh to run Trinity v2.15.1 on the batch partition:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=8 # CPU core count per task
#SBATCH --mem=100G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=log.%j.out # Standard output log
#SBATCH --error=log.%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

module load Trinity/2.15.1-foss-2022a

Trinity --seqType <string> --max_memory 100G --CPU 8 --no_version_check --full_cleanup --normalize_reads
</pre>

Example to run Trinity script align_and_estimate_abundance.pl:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=1 # CPU core count per task
#SBATCH --mem=20G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=%x_%j.out # Standard output log
#SBATCH --error=%x_%j.err # Standard error log

#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)

cd $SLURM_SUBMIT_DIR

module load Trinity/2.15.1-foss-2022a

${EBROOTTRINITY}/trinityrnaseq-v2.10.0/util/align_and_estimate_abundance.pl [options]
</pre>

Where EBROOTTRINITY is the env variable storing Trinity installation pat, i.e., /apps/eb/Trinity/2.15.1-foss-2022a ; [options] need to be added as appropriate. Other parameters of the job, such as the maximum wall clock time, maximum memory, the number cores per node, and the job name need to be modified appropriately as well.

[[#top|Back to Top]]

==Utilizing /lscratch in Trinity Job Submission Script==
* Utilizing /lscratch allows Trinity jobs to run much faster and smoother and also negates the effects of heavy IO traffic.
* This /lscratch directory resides on the local hard drive of the compute node that your job gets allocated to (which means you cannot access this directory outside the job submission script).
* Below is a sample job submission script including steps so you can see what you need to add to your job submission script in order to make your Trinity job utilize /lscratch.
** As well as adding the 6 steps below, please also add the Slurm header --gres=lscratch:___ which requests space in /lscratch. The default units for this is GB and in the example submission script below, we are requesting 200GB of space with the line '''''#SBATCH --gres=lscratch:200''''' (it is the last Slurm header). Please only request as much space in /lscratch as is needed for your job.

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=j_Trinity # Job name (j_Trinity)
#SBATCH --partition=batch # Partition name (batch or highmem_p)
#SBATCH --ntasks=1 # Run job in single task
#SBATCH --cpus-per-task=36 # CPU core count per task
#SBATCH --mem=128G # Memory per node (100GB)
#SBATCH --time=48:00:00 # Time limit hrs:min:sec or days-hours:minutes:seconds
#SBATCH --export=NONE # Do not export any user’s explicit environment variables to compute node
#SBATCH --output=log.%j.out # Standard output log
#SBATCH --error=log.%j.err # Standard error log
#SBATCH --mail-user=username@uga.edu # Where to send mail
#SBATCH --mail-type=ALL # Mail events (BEGIN, END, FAIL, ALL)
#SBATCH --gres=lscratch:200

cd $SLURM_SUBMIT_DIR

# Step 1: create a directory in /lscratch

mkdir -p /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs

# Step 2: copy over any input files.

cp file1.fastq.gz /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs
cp file2.fastq.gz /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs
cp file3.bam /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs

# Step 3: change directories into /lscratch

cd /lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs

# Step 4: your normal job lines (loading Trinity and running Trinity command)

module load Trinity/2.15.1-foss-2022a

Trinity --seqType fq --left 'file1.fastq.gz' --right 'file2.fastq.gz' --CPU 36 --max_memory 120G --output '/lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs/trinity'

Trinity --genome_guided_bam 'file3.bam' --genome_guided_max_intron 10000 --CPU 36 --max_memory 120G --output '/lscratch/${USER}/${SLURM_JOB_ID}/trinity_outputs/trinity'

### NOTE: the directory specified in --output is the directory created in step 1 with the addition of /trinity at the end. This is because Trinity writes some files in the --output dir and some right above it.

# Step 5: copy output files back over to a certain location in /scratch which you can change below

cp -r /lscratch/${USER}/* /scratch/${USER}/some/directory

# Step 6: clean up /lscratch directory **VERY IMPORTANT STEP**

rm -rf /lscratch/${USER}/${SLURM_JOB_ID}
</pre>

* Please feel free to submit a ticket to us if you would like further help, explanations of how /lscratch works, or to even look over your submission script to ensure it is correctly utilizing /lscratch!

==Job Submission==

Submit a job submission script (sub.sh) to Sapelo2:

<pre class="gcommand">
sbatch sub.sh
</pre>

[[#top|Back to Top]]

==Documentation ==

More details at [http://trinityrnaseq.github.io/ Trinity]

<pre class="gcommand">
[cft07037@b1-24 ~]$ ml Trinity/2.15.1-foss-2022a
To execute picard run: java -jar $EBROOTPICARD/picard.jar
[cft07037@b1-24 ~]$ Trinity --show_full_usage_info

###############################################################################
#

______ ____ ____ ____ ____ ______ __ __
| || \ | || \ | || || | |
| || D ) | | | _ | | | | || | |
|_| |_|| / | | | | | | | |_| |_|| ~ |
| | | \ | | | | | | | | | |___, |
| | | . \ | | | | | | | | | | |
|__| |__|\_||____||__|__||____| |__| |____/

Trinity-v2.15.1

#
#
# Required:
#
# --seqType <string> :type of reads: ('fa' or 'fq')
#
# --max_memory <string> :suggested max memory to use by Trinity where limiting can be enabled. (jellyfish, sorting, etc)
# provided in Gb of RAM, ie. '--max_memory 10G'
#
# If paired reads:
# --left <string> :left reads, one or more file names (separated by commas, no spaces)
# --right <string> :right reads, one or more file names (separated by commas, no spaces)
#
# Or, if unpaired reads:
# --single <string> :single reads, one or more file names, comma-delimited (note, if single file contains pairs, can use flag: --run_as_paired )
#
# Or,
# --samples_file <string> tab-delimited text file indicating biological replicate relationships.
# ex.
# cond_A cond_A_rep1 A_rep1_left.fq A_rep1_right.fq
# cond_A cond_A_rep2 A_rep2_left.fq A_rep2_right.fq
# cond_B cond_B_rep1 B_rep1_left.fq B_rep1_right.fq
# cond_B cond_B_rep2 B_rep2_left.fq B_rep2_right.fq
#
# # if single-end instead of paired-end, then leave the 4th column above empty.
#
####################################
## Misc: #########################
#
# --SS_lib_type <string> :Strand-specific RNA-Seq read orientation.
# if paired: RF or FR,
# if single: F or R. (dUTP method = RF)
# See web documentation.
#
# --CPU <int> :number of CPUs to use, default: 2
# --min_contig_length <int> :minimum assembled contig length to report
# (def=200, must be >= 100)
#
# --long_reads <string> :fasta file containing error-corrected or circular consensus (CCS) pac bio reads
# (** note: experimental parameter **, this functionality continues to be under development)
#
# --genome_guided_bam <string> :genome guided mode, provide path to coordinate-sorted bam file.
# (see genome-guided param section under --show_full_usage_info)
#
# --long_reads_bam <string> :long reads to include for genome-guided Trinity
# (bam file consists of error-corrected or circular consensus (CCS) pac bio read aligned to the genome)
#
# --jaccard_clip :option, set if you have paired reads and
# you expect high gene density with UTR
# overlap (use FASTQ input file format
# for reads).
# (note: jaccard_clip is an expensive
# operation, so avoid using it unless
# necessary due to finding excessive fusion
# transcripts w/o it.)
#
# --trimmomatic :run Trimmomatic to quality trim reads
# see '--quality_trimming_params' under full usage info for tailored settings.
#
# --output <string> :name of directory for output (will be
# created if it doesn't already exist)
# default( your current working directory: "/home/cft07037/trinity_out_dir"
# note: must include 'trinity' in the name as a safety precaution! )
#
# --full_cleanup :only retain the Trinity fasta file, rename as ${output_dir}.Trinity.fasta
#
# --cite :show the Trinity literature citation
#
# --verbose :provide additional job status info during the run.
#
# --version :reports Trinity version (Trinity-v2.15.1) and exits.
#
# --show_full_usage_info :show the many many more options available for running Trinity (expert usage).

#
# --no_super_reads :turn off super-reads mode
#
# --prep :Only prepare files (high I/O usage) and stop before kmer counting.
#
# --no_cleanup :retain all intermediate input files.
#
# --no_version_check :dont run a network check to determine if software updates are available.
#
# --no_symlink :dont symlink, just copy files instead (sets env var NO_SYMLINK=TRUE)
#
# --monitoring :use collectl to monitor all steps of Trinity
# --monitor_sec <int> : number of seconds for each interval of runtime monitoring (default: 60)
#
# --no_distributed_trinity_exec :do not run Trinity phase 2 (assembly of partitioned reads), and stop after generating command list.
#
# --workdir <string> :where Trinity phase-2 assembly computation takes place (defaults to --output setting).
# (can set this to a node-local drive or RAM disk)
#
####################################################
# Inchworm and K-mer counting-related options: #####
#
# --min_kmer_cov <int> :min count for K-mers to be assembled by
# Inchworm (default: 1)
# --inchworm_cpu <int> :number of CPUs to use for Inchworm, default is min(6, --CPU option)
#
# --no_run_inchworm :stop after running jellyfish, before inchworm. (phase 1, read clustering only)
#
###################################
# Chrysalis-related options: ######
#
# --max_reads_per_graph <int> :maximum number of reads to anchor within
# a single graph (default: 200000)
# --min_glue <int> :min number of reads needed to glue two inchworm contigs
# together. (default: 2)
#
# --max_chrysalis_cluster_size <int> :max number of Inchworm contigs to be included in a single Chrysalis cluster. (default: 25)
#
# --no_bowtie :dont run bowtie to use pair info in chrysalis clustering.
#
# --no_run_chrysalis :stop after running inchworm, before chrysalis. (phase 1, read clustering only)
#
#####################################
### Butterfly-related options: ####
#
# --bfly_algorithm <string> : assembly algorithm to use. Options: ORIGINAL PASAFLY
#
# --bfly_opts <string> :additional parameters to pass through to butterfly
# (see butterfly options: java -jar Butterfly.jar ).
# (note: only for expert or experimental use. Commonly used parameters are exposed through this Trinity menu here).
#
#
# Butterfly read-pair grouping settings (used to define 'pair paths'):
#
# --group_pairs_distance <int> :maximum length expected between fragment pairs (default: 500)
# (reads outside this distance are treated as single-end)
#
# ///////////////////////////////////////////////
# Butterfly default reconstruction mode settings.
#
# --path_reinforcement_distance <int> :minimum overlap of reads with growing transcript
# path (default: PE: 25, SE: 25)
# Set to 1 for the most lenient path extension requirements.
#
#
# /////////////////////////////////////////
# Butterfly transcript reduction settings:
#
# --no_path_merging : all final transcript candidates are output (including SNP variations, however, some SNPs may be unphased)
#
# By default, alternative transcript candidates are merged (in reality, discarded) if they are found to be too similar, according to the following logic:
#
# (identity=(numberOfMatches/shorterLen) > 98.0% or if we have <= 2 mismatches) and if we have internal gap lengths <= 10
#
# with parameters as:
#
# --min_per_id_same_path <int> default: 98 min percent identity for two paths to be merged into single paths
# --max_diffs_same_path <int> default: 2 max allowed differences encountered between path sequences to combine them
# --max_internal_gap_same_path <int> default: 10 maximum number of internal consecutive gap characters allowed for paths to be merged into single paths.
#
# If, in a comparison between two alternative transcripts, they are found too similar, the transcript with the greatest cumulative
# compatible read (pair-path) support is retained, and the other is discarded.
#
#
# //////////////////////////////////////////////
# Butterfly Java and parallel execution settings.
#
# --bflyHeapSpaceMax <string> :java max heap space setting for butterfly
# (default: 10G) => yields command
# 'java -Xmx10G -jar Butterfly.jar ... $bfly_opts'
# --bflyHeapSpaceInit <string> :java initial heap space settings for
# butterfly (default: 1G) => yields command
# 'java -Xms1G -jar Butterfly.jar ... $bfly_opts'
# --bflyGCThreads <int> :threads for garbage collection
# (default: 2))
# --bflyCPU <int> :CPUs to use (default will be normal
# number of CPUs; e.g., 2)
# --bflyCalculateCPU :Calculate CPUs based on 80% of max_memory
# divided by maxbflyHeapSpaceMax
#
# --bfly_jar <string> : /path/to/Butterfly.jar, otherwise default
# Trinity-installed version is used.
#
#
################################################################################
#### Quality Trimming Options ####
#
# --quality_trimming_params <string> defaults to: "ILLUMINACLIP:/apps/eb/Trinity/2.15.1-foss-2022a/trinityrnaseq-v2.15.1/trinity-plugins/Trimmomatic/adapters/TruSeq3-PE.fa:2:30:10 SLIDINGWINDOW:4:5 LEADING:5 TRAILING:5 MINLEN:25"
#
################################################################################
#### In silico Read Normalization Options ###
#
# --normalize_max_read_cov <int> defaults to 200
# --normalize_by_read_set run normalization separate for each pair of fastq files,
# then one final normalization that combines the individual normalized reads.
# Consider using this if RAM limitations are a consideration.
#
# --just_normalize_reads stop after performing read normalization
#
# --no_normalize_reads :Do *not* run in silico normalization of reads. Defaults to max. read coverage of 200.
# see '--normalize_max_read_cov' under full usage info for tailored settings.
# (Note, as of Sept 21, 2016, normalization is on by default)
# (*Turning off normalization is not recommended for most applications)
#
# --no_parallel_norm_stats :Do not try to run the high-mem normalization stats generator in parallel for paired-end fastqs.
#
###############################################################################
#### Genome-guided de novo assembly
#
# * required:
#
# --genome_guided_max_intron <int> :maximum allowed intron length (also maximum fragment span on genome)
#
# * optional:
#
# --genome_guided_min_coverage <int> :minimum read coverage for identifying and expressed region of the genome. (default: 1)
#
# --genome_guided_min_reads_per_partition <int> :default min of 10 reads per partition
#
#
#######################################################################
# Trinity phase 2 (parallel assembly of read clusters) Options: #######
#
# --grid_exec <string> :your command-line utility for submitting jobs to the grid.
# This should be a command line tool that accepts a single parameter:
# ${your_submission_tool} /path/to/file/containing/commands.txt
# and this submission tool should exit(0) upon successful
# completion of all commands.
#
# --grid_node_CPU <int> number of threads for each parallel process to leverage. (default: 1)
#
# --grid_node_max_memory <string> max memory targeted for each grid node. (default: 1G)
#
# The --grid_node_CPU and --grid_node_max_memory are applied as
# the --CPU and --max_memory parameters for the Trinity jobs run in
# Trinity Phase 2 (assembly of read clusters)
#
# --FORCE ignore failed commands from earlier run, continue on.
# (Note, this should only be used after you've
# already dealt with these failed commands directly as needed)
#
########################################################################
# Singularity-related options
#
# --singularity_img <string> :path to a Trinity singularity image to use
#
# --singularity_extra_params <string> :additional parameters to include for the singularity command execution
#
#

#
#
###############################################################################
#
# *Note, a typical Trinity command might be:
#
# Trinity --seqType fq --max_memory 50G --left reads_1.fq --right reads_2.fq --CPU 6
#
# (if you have multiple samples, use --samples_file ... see above for details)
#
# and for Genome-guided Trinity, provide a coordinate-sorted bam:
#
# Trinity --genome_guided_bam rnaseq_alignments.csorted.bam --max_memory 50G
# --genome_guided_max_intron 10000 --CPU 6
#
# see: /apps/eb/Trinity/2.15.1-foss-2022a/trinityrnaseq-v2.15.1/sample_data/test_Trinity_Assembly/
# for sample data and 'runMe.sh' for example Trinity execution
#
# For more details, visit: http://trinityrnaseq.github.io
#
###############################################################################
</pre>
[[#top|Back to Top]]

== Installation==

Sources are downloaded from [https://trinityrnaseq.github.io Trinity]

==System==
64-bit Linux

[[#top|Back to Top]]

Trinity-HpcGridRunner

2026-05-11T19:28:26Z

Shtsai:

==Description==
Instruction on how to modify a Trinity script to run in conjunction with HpcGridRunner
==Running Program==
Step 1: Create normal Trinity script

* Note: normal Trinity jobs should be run utilizing /lscratch, however, this method running with HpcGridRunner does not benefit from /lscratch so this example will not have any /lscratch components in it. For more information on running normal Trinity jobs with /lscratch, please see [[Trinity-Sapelo2#Utilizing /lscratch in Trinity Job Submission Script|Utilizing /lscratch in Trinity Job Submission Script]].
* For more information on creating a Trinity job (without utilizing /lscratch) please see [[Trinity-Sapelo2#Running Program|Running Trinity Jobs]].

Step 2: add a line to load HpcGridRunner module AND add the --grid_exec flag in your Trinity command (see how to format --grid exec below)

* Your grid_exec flag should look exactly like the one below, where the only part you'll change is the '''location to your config.conf''' file after --grid_conf. Note the location of the quotation marks as they are necessary.
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=Trinity_HpcGridRunner
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=8
#SBATCH --mem=200G
#SBATCH --time=48:00:00
#SBATCH --output=log.%j.out
#SBATCH --error=log.%j.err

cd $SLURM_SUBMIT_DIR

ml Trinity/2.15.1-foss-2022a
ml HpcGridRunner/1.0.2

Trinity --seqType <string> --max_memory 100G \
--CPU 8 \
--left reads.left.fq.gz \
--right reads.right.fq.gz \
--output /scratch/cft07037/trinity_tests/testing/${SLURM_JOB_ID}/outputs/trinity/ \
--full_cleanup \
--grid_exec "/apps/eb/HpcGridRunner/1.0.2/hpc_cmds_GridRunner.pl --grid_conf /scratch/path/to/your/configfile/config.conf -c"

</pre>
Step 3: create config.conf file<pre class="gscript">
# grid type:
grid=SLURM

# template for a grid submission:
cmd=sbatch -p batch --mem 80gb -n 1 --cpus-per-task 8 -t 01:00:00

##########################################################################################
# settings below configure the Trinity job submission system, not tied to the grid itself.
##########################################################################################

# number of grid submissions to be maintained at steady state by the Trinity submission system
max_nodes=5

# number of commands that are batched into a single grid submission job. These run sequentially, not concurrently, so you only need to request enough cpus-per-task for the threads of a single command
cmds_per_node=3
</pre>

* The main things to change in your config.conf file are the max_nodes (how many individual grid jobs will be allowed to run at the same time) and the cmds_per_node (number of commands per grid job), which together determine how the grid will run on the cluster. You can also alter the cmd, which is the command that will be used to submit the individual grid jobs.
* The number of grid jobs that will be submitted depends on how many recursive Trinity commands you have and what variables you choose for max_nodes and cmds_per_node.
** Increasing the number of cmds_per_node and max_nodes will lower the total time it takes for all of the recursive Trinity commands to finish running, however it is important to note that though you may put a large number for max_nodes, the amount actually used will be determined by SLURM and ultimately depends on what resources are currently available and how many jobs you already have running. Similarly, setting a large number for the variable cmds_per_node can make the overall job complete more quickly, but then those individual jobs (submitted by the cmd variable) may need more memory.

==Other Resources==

https://github.com/trinityrnaseq/trinityrnaseq/wiki/Running-Trinity#optional-adapting-trinity-to-a-computing-grid-for-massively-parallel-processing-of-embarrassingly-parallel-steps

Trinity-HpcGridRunner

2026-05-11T19:27:06Z

Shtsai:

==Description==
Instruction on how to modify a Trinity script to run in conjunction with HpcGridRunner
==Running Program==
Step 1: Create normal Trinity script

* Note: normal Trinity jobs should be run utilizing /lscratch, however, this method running with HpcGridRunner does not benefit from /lscratch so this example will not have any /lscratch components in it. For more information on running normal Trinity jobs with /lscratch, please see [[Trinity-Sapelo2#Utilizing /lscratch in Trinity Job Submission Script|Utilizing /lscratch in Trinity Job Submission Script]].
* For more information on creating a Trinity job (without utilizing /lscratch) please see [[Trinity-Sapelo2#Trinity v2.15.1 Software Module on Sapelo2|here]].

Step 2: add a line to load HpcGridRunner module AND add the --grid_exec flag in your Trinity command (see how to format --grid exec below)

* Your grid_exec flag should look exactly like the one below, where the only part you'll change is the '''location to your config.conf''' file after --grid_conf. Note the location of the quotation marks as they are necessary.
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=Trinity_HpcGridRunner
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=8
#SBATCH --mem=200G
#SBATCH --time=48:00:00
#SBATCH --output=log.%j.out
#SBATCH --error=log.%j.err

cd $SLURM_SUBMIT_DIR

ml Trinity/2.15.1-foss-2022a
ml HpcGridRunner/1.0.2

Trinity --seqType <string> --max_memory 100G \
--CPU 8 \
--left reads.left.fq.gz \
--right reads.right.fq.gz \
--output /scratch/cft07037/trinity_tests/testing/${SLURM_JOB_ID}/outputs/trinity/ \
--full_cleanup \
--grid_exec "/apps/eb/HpcGridRunner/1.0.2/hpc_cmds_GridRunner.pl --grid_conf /scratch/path/to/your/configfile/config.conf -c"

</pre>
Step 3: create config.conf file<pre class="gscript">
# grid type:
grid=SLURM

# template for a grid submission:
cmd=sbatch -p batch --mem 80gb -n 1 --cpus-per-task 8 -t 01:00:00

##########################################################################################
# settings below configure the Trinity job submission system, not tied to the grid itself.
##########################################################################################

# number of grid submissions to be maintained at steady state by the Trinity submission system
max_nodes=5

# number of commands that are batched into a single grid submission job. These run sequentially, not concurrently, so you only need to request enough cpus-per-task for the threads of a single command
cmds_per_node=3
</pre>

* The main things to change in your config.conf file are the max_nodes (how many individual grid jobs will be allowed to run at the same time) and the cmds_per_node (number of commands per grid job), which together determine how the grid will run on the cluster. You can also alter the cmd, which is the command that will be used to submit the individual grid jobs.
* The number of grid jobs that will be submitted depends on how many recursive Trinity commands you have and what variables you choose for max_nodes and cmds_per_node.
** Increasing the number of cmds_per_node and max_nodes will lower the total time it takes for all of the recursive Trinity commands to finish running, however it is important to note that though you may put a large number for max_nodes, the amount actually used will be determined by SLURM and ultimately depends on what resources are currently available and how many jobs you already have running. Similarly, setting a large number for the variable cmds_per_node can make the overall job complete more quickly, but then those individual jobs (submitted by the cmd variable) may need more memory.

==Other Resources==

https://github.com/trinityrnaseq/trinityrnaseq/wiki/Running-Trinity#optional-adapting-trinity-to-a-computing-grid-for-massively-parallel-processing-of-embarrassingly-parallel-steps

Trinity-HpcGridRunner

2026-05-11T18:59:35Z

Shtsai:

==Description==
Instruction on how to modify a Trinity script to run in conjunction with HpcGridRunner
==Running Program==
Step 1: Create normal Trinity script

* Note: normal Trinity jobs should be run utilizing /lscratch, however, this method running with HpcGridRunner does not benefit from /lscratch so this example will not have any /lscratch components in it. For more information on running normal Trinity jobs with /lscratch, please see [[Trinity-Sapelo2#Utilizing /lscratch in Trinity Job Submission Script|here]].
* For more information on creating a Trinity job (without utilizing /lscratch) please see [[Trinity-Sapelo2#Trinity v2.15.1 Software Module on Sapelo2|here]].

Step 2: add a line to load HpcGridRunner module AND add the --grid_exec flag in your Trinity command (see how to format --grid exec below)

* Your grid_exec flag should look exactly like the one below, where the only part you'll change is the '''location to your config.conf''' file after --grid_conf. Note the location of the quotation marks as they are necessary.
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=Trinity_HpcGridRunner
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=8
#SBATCH --mem=200G
#SBATCH --time=48:00:00
#SBATCH --output=log.%j.out
#SBATCH --error=log.%j.err

cd $SLURM_SUBMIT_DIR

ml Trinity/2.15.1-foss-2022a
ml HpcGridRunner/1.0.2

Trinity --seqType <string> --max_memory 100G \
--CPU 8 \
--left reads.left.fq.gz \
--right reads.right.fq.gz \
--output /scratch/cft07037/trinity_tests/testing/${SLURM_JOB_ID}/outputs/trinity/ \
--full_cleanup \
--grid_exec "/apps/eb/HpcGridRunner/1.0.2/hpc_cmds_GridRunner.pl --grid_conf /scratch/path/to/your/configfile/config.conf -c"

</pre>
Step 3: create config.conf file<pre class="gscript">
# grid type:
grid=SLURM

# template for a grid submission:
cmd=sbatch -p batch --mem 80gb -n 1 --cpus-per-task 8 -t 01:00:00

##########################################################################################
# settings below configure the Trinity job submission system, not tied to the grid itself.
##########################################################################################

# number of grid submissions to be maintained at steady state by the Trinity submission system
max_nodes=5

# number of commands that are batched into a single grid submission job. These run sequentially, not concurrently, so you only need to request enough cpus-per-task for the threads of a single command
cmds_per_node=3
</pre>

* The main things to change in your config.conf file are the max_nodes (how many individual grid jobs will be allowed to run at the same time) and the cmds_per_node (number of commands per grid job), which together determine how the grid will run on the cluster. You can also alter the cmd, which is the command that will be used to submit the individual grid jobs.
* The number of grid jobs that will be submitted depends on how many recursive Trinity commands you have and what variables you choose for max_nodes and cmds_per_node.
** Increasing the number of cmds_per_node and max_nodes will lower the total time it takes for all of the recursive Trinity commands to finish running, however it is important to note that though you may put a large number for max_nodes, the amount actually used will be determined by SLURM and ultimately depends on what resources are currently available and how many jobs you already have running. Similarly, setting a large number for the variable cmds_per_node can make the overall job complete more quickly, but then those individual jobs (submitted by the cmd variable) may need more memory.

==Other Resources==

https://github.com/trinityrnaseq/trinityrnaseq/wiki/Running-Trinity#optional-adapting-trinity-to-a-computing-grid-for-massively-parallel-processing-of-embarrassingly-parallel-steps

Software installed on Rocky 8

2026-05-11T18:57:17Z

Shtsai:

As part of our August 29-31,2023 maintenance window, the GACRC will be upgrading the Sapelo2 cluster operating system from CentOS 7 to Rocky 8.

Because this is a major OS update, we need to recompile all the applications and ensure that they work with the new version of OS.

Below is a list of the modules already installed on the Rocky 8 system. More software packages continue to be installed. If the software you need is not in this list yet, please feel free to let us know, if you would like us to install it centrally on the updated cluster.

All singularity containers available in /apps/singularity-images on the current Sapelo2 (CentOS 7) will continue to be available after the maintenance.

== List of software already installed centrally on the Rocky 8 system (new Sapelo2, available after the maintenance) ==
3-NA/201008-foss-2021b-Python-2.7.18
ABySS/2.3.5-foss-2021b
ACTC/1.1-GCCcore-11.2.0
AMIXTURE/1.3.0
AGAT/0.9.2-GCC-11.2.0
AGAT/1.1.0
AMOS/3.1.0-foss-2021b
ANTLR/2.7.7-GCCcore-11.2.0-Java-11
ANTs/2.4.4-foss-2021b
APR-util/1.6.1-GCCcore-11.2.0
APR/1.7.0-GCCcore-11.2.0
ART/2016.06.05-GCC-11.2.0
ASE/3.22.1-foss-2021b
ASTRAL/5.7.8-Java-1.8.0_241
ATK/2.36.0-GCCcore-11.2.0
ATK/2.38.0-GCCcore-11.3.0
AUGUSTUS/3.4.0-foss-2021b
AUGUSTUS/3.5.0-foss-2022a
AlignGraph/2023-03-02-GCC-8.3.0
AlphaFold/2.3.4-foss-2022a-CUA-11.7.0-ColabFold
Amber/22.0-foss-2021b-AmberTools-22.3-CUA-11.4.1
Anaconda3/2022.10
Archive-Zip/1.68-GCCcore-11.2.0
Armadillo/11.4.3-foss-2021b
Armadillo/11.4.3-foss-2022a
Arrow/8.0.0-foss-2021b
Autoconf/2.69-GCCcore-8.3.0
Autoconf/2.69-GCCcore-10.2.0
Autoconf/2.71-GCCcore-11.2.0
Autoconf/2.71-GCCcore-11.3.0
Autoconf/2.71-GCCcore-12.2.0
Automake/1.16.1-GCCcore-8.3.0
Automake/1.16.2-GCCcore-10.2.0
Automake/1.16.4-GCCcore-11.2.0
Automake/1.16.5-GCCcore-11.3.0
Automake/1.16.5-GCCcore-12.2.0
Autotools/20180311-GCCcore-8.3.0
Autotools/20200321-GCCcore-10.2.0
Autotools/20210726-GCCcore-11.2.0
Autotools/20220317-GCCcore-11.3.0
Autotools/20220317-GCCcore-12.2.0
BBMap/38.98-GCC-11.2.0
BCFtools/1.14-GCC-11.2.0
BCFtools/1.15.1-GCC-11.3.0
BEOPS/2.4.41-foss-2021b
BETools/2.30.0-GCC-11.2.0
BLAST+/2.2.31
BLAST+/2.12.0-gompi-2021b
BLAST+/2.13.0-gompi-2021b
BLAST+/2.13.0-gompi-2022a
BLAST/2.2.26-Linux_x86_64
BLAT/3.5-GCC-11.2.0
BLAT/3.7-GCC-11.3.0
BLIS/0.8.1-GCC-11.2.0
BLIS/0.9.0-GCC-11.3.0
BRAKER/2.1.6-foss-2021b
BRIG/0.95-gompi-2021b-Java-1.8.0_241
BUSCO/5.4.3-foss-2021b
BWA/0.7.17-GCCcore-11.2.0
BamTools/2.5.2-GCC-11.2.0
BamTools/2.5.2-GCC-11.3.0
BamUtil/1.0.15-foss-2021b
Bandage/0.9.0-GCCcore-11.2.0
BayeScan/2.1-foss-2019b
Bazel/3.7.2-GCCcore-11.2.0
Bazel/4.2.2-GCCcore-11.2.0
Bazel/5.1.1-GCCcore-11.3.0
Beagle/5.4.22Jul22.46e-Java-11
Beast/2.7.1-foss-2021b-CUA-11.4.1
BigFT/1.9.1-foss-2021b
Bio-B-HTS/3.01-GCC-11.2.0
BioPerl/1.7.8-GCCcore-11.2.0
BioPerl/1.7.8-GCCcore-11.3.0
Biopython/1.79-foss-2021b
Biopython/1.79-foss-2022a
Biopython/1.81-foss-2021b
Bismark/0.23.1-foss-2021b
Bison/3.3.2-GCCcore-8.3.0
Bison/3.3.2
Bison/3.7.1-GCCcore-10.2.0
Bison/3.7.6-GCCcore-11.2.0
Bison/3.8.2-GCCcore-11.3.0
Bison/3.8.2-GCCcore-12.2.0
Bison/3.8.2
Blosc/1.21.3-GCCcore-11.2.0
Boost.MPI/1.79.0-gompi-2022a
Boost.Python/1.77.0-GCC-11.2.0
Boost/1.75.0-GCC-11.2.0
Boost/1.77.0-GCC-11.2.0
Boost/1.79.0-GCC-11.3.0
Bottleneck/1.3.7-foss-2022a
Bowtie/1.3.1-GCC-11.2.0
Bowtie/1.3.1-GCC-11.3.0
Bowtie2/2.4.1-GCC-8.3.0
Bowtie2/2.4.4-GCC-11.2.0
Bowtie2/2.4.5-GCC-11.2.0
Bowtie2/2.4.5-GCC-11.3.0
Bracken/2.7-GCCcore-11.2.0
Brotli/1.0.9-GCCcore-11.2.0
Brotli/1.0.9-GCCcore-11.3.0
C-HIT/4.8.1-GCC-11.2.0
C-HIT/4.8.1-GCC-11.3.0
CFITSIO/3.49-GCCcore-11.2.0
CGAL/4.14.3-gompi-2021b
CGmapTools/0.1.2-foss-2021b
CMake/3.12.1
CMake/3.21.1-GCCcore-11.2.0
CMake/3.22.1-GCCcore-11.2.0
CMake/3.23.1-GCCcore-11.3.0
CMake/3.24.3-GCCcore-11.3.0
CUA/11.3.1
CUA/11.4.1
CUA/11.7.0
CUA/12.0.0
CapnProto/0.9.1-GCCcore-11.2.0
CellRanger/7.0.0
Centrifuge/1.0.4-gompi-2021b
Cereal/1.3.0
CheMPS2/1.8.11-foss-2021b
Check/0.15.2-GCCcore-11.2.0
CheckM/1.1.3-foss-2021b
Chimera/1.16-linux_x86_64
Circos/0.69-9-GCCcore-11.2.0
Clang/13.0.1-GCCcore-11.2.0
Clustal-Omega/1.2.4-GCC-11.2.0
ClustalW2/2.1-GCC-11.2.0
Consed/29.0-foss-2021b
Consed/29.0-foss-2022a
CoordgenLibs/3.0.1-gompi-2021b
CppUnit/1.15.1-GCCcore-11.2.0
Cufflinks/20190706-GCC-11.2.0
Cython/0.27.3-GCCcore-11.3.0-Python-2.7.18
Cytoscape/3.9.1-Java-11
B/18.1.32-GCCcore-8.3.0
B/18.1.40-GCCcore-10.2.0
B/18.1.40-GCCcore-11.2.0
B/18.1.40-GCCcore-11.3.0
B/18.1.40-GCCcore-12.2.0
B-mysql/4.050-GCC-11.2.0
B_File/1.857-GCCcore-11.2.0
B_File/1.858-GCCcore-11.3.0
Bus/1.13.18-GCCcore-11.2.0
Bus/1.14.0-GCCcore-11.3.0
IAMON/2.0.13-GCC-11.2.0
IAMON/2.0.15-GCC-11.2.0
IAMON/2.1.0-GCC-11.3.0
ataWarrior/5.5.0
endroPy/4.5.2-GCCcore-11.2.0
eve-Size/0.83-GCCcore-11.2.0-Perl-5.34.0
ockQ/1.0-foss-2022a
oxygen/1.9.1-GCCcore-11.2.0
oxygen/1.9.4-GCCcore-11.3.0
ELPA/2021.11.001-foss-2021b
EMBOSS/6.6.0-foss-2021b
ETE/3.1.2-foss-2021b
EasyBuild/4.6.0
Eigen/3.3.9-GCCcore-11.2.0
Eigen/3.4.0-GCCcore-11.2.0
Eigen/3.4.0-GCCcore-11.3.0
EnTAP/0.10.8-beta-foss-2021b
Exonerate/2.4.0-GCC-11.2.0
Exonerate/2.4.0-GCC-11.3.0
FASTX-Toolkit/0.0.14-GCC-11.2.0
FFTW.MPI/3.3.10-gompi-2022a
FFTW/3.3.8-gompi-2019b
FFTW/3.3.10-GCC-11.3.0
FFTW/3.3.10-gompi-2021b
FFmpeg/4.3.2-GCCcore-11.2.0
FLAC/1.3.3-GCCcore-11.2.0
FLAC/1.3.4-GCCcore-11.3.0
FLASH/2.2.00-GCC-11.2.0
FLTK/1.3.7-GCCcore-11.2.0
FSL/6.0.5.1-foss-2021b
FTGL/2.4.0-GCCcore-11.3.0
FastANI/1.33-GCC-11.2.0
FastME/2.1.6.1-GCC-11.2.0
FastQC/0.11.9-Java-11
FastTree/2.1.11-GCCcore-11.2.0
Flask/2.0.2-GCCcore-11.2.0
Flask/2.2.2-GCCcore-11.3.0
FlexiBLAS/3.0.4-GCC-11.2.0
FlexiBLAS/3.2.0-GCC-11.3.0
Flye/2.9.1-GCC-11.2.0
FragGeneScan/1.31-GCCcore-11.2.0
FreeImage/3.18.0-GCCcore-11.2.0
FreeSurfer/7.4.1-foss-2021b
FriBidi/1.0.10-GCCcore-11.2.0
FriBidi/1.0.12-GCCcore-11.3.0
GATK/4.3.0.0-GCCcore-11.2.0-Java-11
GATK/4.3.0.0-GCCcore-11.2.0-Java-13.0.2
GATK/4.3.0.0-GCCcore-11.3.0-Java-11
GCC/8.3.0
GCC/10.2.0
GCC/11.2.0
GCC/11.3.0
GCC/12.2.0
GCCcore/8.3.0
GCCcore/10.2.0
GCCcore/11.2.0
GCCcore/11.3.0
GCCcore/12.2.0
G/2.75-GCCcore-11.2.0
GAL/3.3.2-foss-2021b
GAL/3.5.0-foss-2022a
GRCopy/2.3-GCCcore-11.2.0
GRCopy/2.3-GCCcore-11.3.0
GEM/1.5.1-foss-2022a
GEOS/3.9.1-GCC-11.2.0
GEOS/3.10.3-GCC-11.3.0
GLPK/5.0-GCCcore-11.2.0
GLPK/5.0-GCCcore-11.3.0
GLib/2.69.1-GCCcore-11.2.0
GLib/2.72.1-GCCcore-11.3.0
GLibmm/2.66.4-GCCcore-11.2.0
GMAP-GSNAP/2021-21-17-GCC-11.2.0
GMAP-GSNAP/2023-02-17-GCC-11.3.0
GMP/6.1.2-GCCcore-8.3.0
GMP/6.2.1-GCCcore-11.2.0
GMP/6.2.1-GCCcore-11.3.0
GObject-Introspection/1.68.0-GCCcore-11.2.0
GObject-Introspection/1.72.0-GCCcore-11.3.0
GROMACS/2021.5-foss-2021b-CUA-11.4.1-PLUME-2.8.0
GSL/2.7-GCC-11.2.0
GSL/2.7-GCC-11.3.0
GST-plugins-base/1.18.5-GCC-11.2.0
GStreamer/1.18.5-GCC-11.2.0
GTK+/3.24.23-GCCcore-11.3.0
GTK2/2.24.33-GCCcore-11.3.0
GTK3/3.24.31-GCCcore-11.2.0
GTS/0.7.6-GCCcore-11.2.0
Gdk-Pixbuf/2.42.6-GCCcore-11.2.0
Gdk-Pixbuf/2.42.8-GCCcore-11.3.0
GeneMark-ET/4.71-GCCcore-11.2.0
GeneMark-ET/4.71-GCCcore-11.3.0
GeneMarkS-T/5.1-GCCcore-11.2.0
Genome/05012020-foss-2021b
Genome/05012020-foss-2022a
GenomeThreader/1.7.3-Linux_x86_64-64bit
GenomeTools/1.6.2-GCC-11.2.0
GffCompare/0.12.6-GCC-11.2.0
Ghostscript/9.54.0-GCCcore-11.2.0
Ghostscript/9.56.1-GCCcore-11.3.0
GitPython/3.1.24-GCCcore-11.2.0
GlimmerHMM/3.0.4c-GCC-11.2.0
Globus-CLI/3.6.0-GCCcore-11.2.0
Go/1.17.6
Grace/5.1.25-foss-2021b
Graphviz/2.50.0-GCCcore-11.2.0
Guile/1.8.8-GCCcore-8.3.0
Guile/3.0.7-GCCcore-11.2.0
HF/4.2.15-GCCcore-11.2.0
HF/4.2.15-GCCcore-11.3.0
HF5/1.10.8-gompi-2021b
HF5/1.10.8-gompi-2022a
HF5/1.12.1-gompi-2021b
HF5/1.12.2-gompi-2022a
HEC-RAS/6.10
HH-suite/3.3.0-gompi-2021b
HH-suite/3.3.0-gompi-2022a
HISAT2/2.2.1-gompi-2021b
HISAT2/2.2.1-gompi-2022a
HMMER/3.3.2-gompi-2021b
HMMER/3.3.2-gompi-2022a
HPL/2.3-foss-2021b
HTSeq/2.0.2-foss-2021b
HTSlib/1.9-GCC-11.2.0
HTSlib/1.14-GCC-11.2.0
HTSlib/1.15.1-GCC-11.3.0
HarfBuzz/2.8.2-GCCcore-11.2.0
HarfBuzz/4.2.1-GCCcore-11.3.0
Homer/4.11-foss-2021b
HyPhy/2.5.33-gompi-2021b
HybPiper/2.1.6-conda
ICU/69.1-GCCcore-11.2.0
ICU/71.1-GCCcore-11.3.0
IBA-U/1.1.3-GCC-11.2.0
IGV/2.16.1-Java-11
IPython/7.26.0-GCCcore-11.2.0
IQ-TREE/2.2.1-gompi-2021b
ISA-L/2.30.0-GCCcore-11.2.0
ImageMagick/7.1.0-4-GCCcore-11.2.0
ImageMagick/7.1.0-37-GCCcore-11.3.0
Infernal/1.1.4-foss-2021b
Infernal/1.1.4-foss-2022a
InterProScan/5.62-94.0-foss-2021b
JAGS/4.3.0-foss-2021b
JUnit/4.12-Java-1.8.0_241
JasPer/2.0.33-GCCcore-11.2.0
JasPer/2.0.33-GCCcore-11.3.0
Java/1.7.0_80
Java/1.8.0_241
Java/11.0.16
Java/13.0.2
Java/15.0.1
Java/17.0.6
Jellyfish/2.3.0-GCC-11.2.0
Jellyfish/2.3.0-GCC-11.3.0
JsonCpp/1.9.4-GCCcore-11.2.0
JsonCpp/1.9.5-GCCcore-11.3.0
Judy/1.0.5-GCCcore-11.2.0
Judy/1.0.5-GCCcore-11.3.0
Julia/1.8.2-linux-x86_64
Kalign/3.3.2-GCCcore-11.2.0
Kalign/3.3.5-GCCcore-11.3.0
Kent_tools/422-GCC-11.2.0
KerasTuner/1.3.5-foss-2022a
KronaTools/2.8.1-GCCcore-11.2.0
LAME/3.100-GCCcore-11.2.0
LAME/3.100-GCCcore-11.3.0
LAMMPS/23Jun2022-foss-2021b-kokkos
LAPACK/3.10.1-GCC-11.2.0
LASTZ/1.04.15-foss-2021b
LLVM/12.0.1-GCCcore-11.2.0
LLVM/14.0.3-GCCcore-11.3.0
LMB/0.9.29-GCCcore-11.2.0
LMB/0.9.29-GCCcore-11.3.0
LS2/2.3-GCCcore-11.2.0
LTR_retriever/2.9.0-foss-2021b-RepeatMasker-4.1.4
LTR_retriever/2.9.0-foss-2021b
LZO/2.10-GCCcore-11.2.0
LZO/2.10-GCCcore-11.3.0
LibTIFF/4.3.0-GCCcore-11.2.0
LibTIFF/4.3.0-GCCcore-11.3.0
LightGBM/3.3.5-foss-2021b-CUA-11.4.1
LightGBM/3.3.5-foss-2021b
LittleCMS/2.12-GCCcore-11.2.0
LittleCMS/2.13.1-GCCcore-11.3.0
LoFreq/2.1.3.1-foss-2021b-Python-2.7.18
Lua/5.4.3-GCCcore-11.2.0
M4/1.4.18-GCCcore-8.3.0
M4/1.4.18-GCCcore-10.2.0
M4/1.4.18
M4/1.4.19-GCCcore-11.2.0
M4/1.4.19-GCCcore-11.3.0
M4/1.4.19-GCCcore-12.2.0
M4/1.4.19
MACS2/2.2.7.1-foss-2021b
MAFFT/7.490-GCC-11.2.0-with-extensions
MAFFT/7.490-gompi-2021b-with-extensions
MAKER/3.01.04-foss-2022a
MCL/14.137-GCCcore-11.2.0
MEGAN/6.24.23-Java-17
MEME/5.4.1-gompi-2021b
MEME/5.5.0-gompi-2021b
METIS/5.1.0-GCCcore-11.2.0
METIS/5.1.0-GCCcore-11.3.0
MMseqs2/13-45111-gompi-2021b
MMseqs2/14-7e284-gompi-2021b
MMseqs2/14-7e284-gompi-2022a
MPACK/3.0.0-foss-2021b
MPFR/4.1.0-GCCcore-11.2.0
MPFR/4.1.0-GCCcore-11.3.0
MUMmer/4.0.0beta2-GCCcore-11.2.0
MUMmer/4.0.0rc1-GCCcore-11.2.0
MUSCLE/3.8.31-GCCcore-11.2.0
Make-Lastz-Chains/0.9.1
Mako/1.1.4-GCCcore-11.2.0
Mako/1.2.0-GCCcore-11.3.0
MariaB-connector-c/3.2.2-GCCcore-11.2.0
MariaB/10.6.4-GCC-11.2.0
MariaB/10.9.3-GCC-11.3.0
Mash/2.3-GCC-11.2.0
Medusa/1.6-foss-2021b-Python-3.9.6-Java-1.8.0_241
Mesa/21.1.7-GCCcore-11.2.0
Mesa/22.0.3-GCCcore-11.3.0
Meson/0.55.3-GCCcore-11.2.0
Meson/0.58.2-GCCcore-11.2.0
Meson/0.62.1-GCCcore-11.3.0
MetaEuk/6-GCC-11.2.0
MinCE/0.4.2-GCCcore-8.3.0-Java-11
Miniconda3/4.12.0
Miniconda3/22.11.1-1
Mirage/2.0.0-GCCcore-11.2.0
MuTect/1.1.7-Java-1.7.0_80
MultiQC/1.12-foss-2021b
MySQL/8.0.34-glibc2.28
NASM/2.15.05-GCCcore-11.2.0
NASM/2.15.05-GCCcore-11.3.0
NCCL/2.10.3-GCCcore-11.2.0-CUA-11.4.1
NCCL/2.12.12-GCCcore-11.3.0-CUA-11.7.0
NGS/2.10.9-GCCcore-11.2.0
NGS/2.11.2-GCCcore-11.2.0
NLopt/2.7.0-GCCcore-11.2.0
NLopt/2.7.1-GCCcore-11.3.0
NSPR/4.32-GCCcore-11.2.0
NSS/3.69-GCCcore-11.2.0
NVHPC/22.11-CUA-11.7.0
NVHPC/23.1-CUA-12.0.0
Nextflow/22.10.6
Ninja/1.10.2-GCCcore-11.2.0
Ninja/1.10.2-GCCcore-11.3.0
ORCA/5.0.3-gompi-2021b
OpenBLAS/0.3.7-GCC-8.3.0
OpenBLAS/0.3.18-GCC-11.2.0
OpenBLAS/0.3.20-GCC-11.3.0
OpenBabel/3.1.1-gompi-2021b
OpenCV/4.5.5-foss-2021b-contrib
OpenEXR/3.1.1-GCCcore-11.2.0
OpenJPEG/2.4.0-GCCcore-11.2.0
OpenJPEG/2.5.0-GCCcore-11.3.0
OpenMM/7.5.1-foss-2021b-eepMind-patch
OpenMM/8.0.0-foss-2022a-CUA-11.7.0
OpenMPI/4.1.2-GCC-11.2.0-pmi2
OpenMPI/4.1.2-GCC-11.2.0
OpenMPI/4.1.4-GCC-11.3.0
OpenMPI/4.1.4-GCC-12.2.0
OpenPGM/5.2.122-GCCcore-11.2.0
OpenSSL/1.1
OrthoFinder/2.5.4-foss-2021b
PAML/4.9j-GCCcore-11.2.0
PCRE/8.45-GCCcore-11.2.0
PCRE/8.45-GCCcore-11.3.0
PCRE2/10.37-GCCcore-11.2.0
PCRE2/10.40-GCCcore-11.3.0
PLINK/2.00a4-GCC-11.2.0
PLUME/2.7.3-foss-2021b
PLUME/2.8.0-foss-2021b
PMIx/3.1.5-GCCcore-10.2.0
PMIx/4.1.0-GCCcore-11.2.0
PMIx/4.1.2-GCCcore-11.3.0
PMIx/4.2.2-GCCcore-12.2.0
PROJ/8.1.0-GCCcore-11.2.0
PROJ/9.0.0-GCCcore-11.3.0
PSI4/1.7-foss-2021b
PTarPmiR/0.1-foss-2021b-Python-3.9.6
Pango/1.48.8-GCCcore-11.2.0
Pango/1.50.7-GCCcore-11.3.0
Perl/5.30.0-GCCcore-8.3.0-minimal
Perl/5.30.0-GCCcore-8.3.0
Perl/5.32.0-GCCcore-10.2.0-minimal
Perl/5.32.0-GCCcore-10.2.0
Perl/5.34.0-GCCcore-11.2.0-minimal
Perl/5.34.0-GCCcore-11.2.0
Perl/5.34.1-GCCcore-11.3.0-minimal
Perl/5.34.1-GCCcore-11.3.0
Perl/5.36.0-GCCcore-12.2.0
Phobius/1.01-GCCcore-11.2.0-Perl-5.34.0
Phrap/0.990329-foss-2021b
Phrap/0.990329-foss-2022a
Phred/0.071220.c-foss-2021b
Phred/0.071220.c-foss-2022a
Pillow-SIM/8.3.2-GCCcore-11.2.0
Pillow/8.3.2-GCCcore-11.2.0
Pillow/9.1.1-GCCcore-11.3.0
Pilon/1.23-Java-11
PnetCF/1.12.3-gompi-2021b
PyBioLib/1.1.988-GCCcore-11.3.0
PyQt5/5.15.4-GCCcore-11.2.0
PyRosetta/4.release-339-GCCcore-11.2.0-Python-3.9.6
PyTorch-Lightning/1.5.9-foss-2021b-CUA-11.4.1
PyTorch/1.12.1-foss-2021b-CUA-11.4.1
PyYAML/5.4.1-GCCcore-11.2.0
PyYAML/6.0-GCCcore-11.2.0
PyYAML/6.0-GCCcore-11.3.0
Pysam/0.17.0-GCC-11.2.0
Python/2.7.18-GCCcore-11.2.0-bare
Python/2.7.18-GCCcore-11.2.0
Python/2.7.18-GCCcore-11.3.0
Python/3.7.4-GCCcore-8.3.0
Python/3.9.6-GCCcore-11.2.0-bare
Python/3.9.6-GCCcore-11.2.0
Python/3.10.4-GCCcore-11.3.0-bare
Python/3.10.4-GCCcore-11.3.0
QIIME2/2023.2
QUAST/5.0.2-foss-2021b
Qhull/2020.2-GCCcore-11.2.0
Qhull/2020.2-GCCcore-11.3.0
Qt5/5.15.2-GCCcore-11.2.0
QuantumESPRESSO/7.1-foss-2021b
Qwt/6.2.0-GCCcore-11.2.0
R/4.1.2-foss-2021b
R/4.2.1-foss-2021b
R/4.2.1-foss-2022a
R/4.3.1-foss-2022a
RAxML/8.2.12-gompi-2021b-hybrid-avx2
RKit/2022.03.5-foss-2021b
RE2/2022-02-01-GCCcore-11.2.0
RE2/2022-06-01-GCCcore-11.3.0
RECON/1.08-GCC-11.2.0
RMBlast/2.11.0-gompi-2021b
RMBlast/2.13.0-gompi-2021b
RMBlast/2.13.0-gompi-2022a
RSEM/1.3.3-foss-2021b
RSEM/1.3.3-foss-2022a
Racon/1.5.0-GCCcore-11.2.0
RapidJSON/1.1.0-GCCcore-11.2.0
RapidJSON/1.1.0-GCCcore-11.3.0
RepeatMasker/4.1.2-p1-foss-2021b
RepeatMasker/4.1.4-foss-2021b
RepeatMasker/4.1.4-foss-2022a
RepeatModeler/2.0.2a-foss-2021b
RepeatModeler/2.0.3-foss-2021b
RepeatModeler/2.0.4-foss-2021b
RepeatProfiler/1.1-foss-2021b
RepeatScout/1.0.6-GCC-11.2.0
Rosetta/2022.46.334-intel-2021b
Ruby/3.0.5-GCCcore-11.2.0
Rust/1.54.0-GCCcore-11.2.0
Rust/1.60.0-GCCcore-11.3.0
Rust/1.70.0-GCCcore-11.3.0
SAMtools/0.1.20-GCC-11.2.0
SAMtools/1.6-GCC-11.2.0
SAMtools/1.14-GCC-11.2.0
SAMtools/1.16.1-GCC-11.3.0
SCons/4.2.0-GCCcore-11.2.0
SEPP/4.5.1-foss-2021b
SLATEC/4.1-GCC-11.2.0
SMRT-Link/12.0.0.177059-cli-tools-only
SNAP-HMM/20190603-GCC-11.2.0
SNAP-HMM/20221022-GCC-11.3.0
SNAP/2.0.1-GCC-11.2.0
SNPGenie/1.0-foss-2021b-Perl-5.34.0
SPAdes/3.15.3-GCC-11.2.0
SPAdes/3.15.5-GCC-11.2.0-kmer300
SPAdes/3.15.5-GCC-11.2.0
SQANTI3/5.1.1
SQLAlchemy/1.4.42-foss-2021b-Python-3.9.6
SQLite/3.29.0-GCCcore-8.3.0
SQLite/3.36-GCCcore-11.2.0
SQLite/3.38.3-GCCcore-11.3.0
SRA-Toolkit/3.0.1-centos_linux64
SRA-Toolkit/3.0.3-gompi-2022a
SSW/1.1-GCCcore-11.2.0
STAR/2.7.10b-GCC-11.2.0
STAR/2.7.10b-GCC-11.3.0
SWIG/4.0.2-GCCcore-11.2.0
SWIG/4.0.2-GCCcore-11.3.0
Salmon/0.8.2
Salmon/1.9.0-GCC-11.2.0
Salmon/1.9.0-GCC-11.3.0
ScaFaCoS/1.0.1-foss-2021b
ScaLAPACK/2.0.2-gompi-2019b
ScaLAPACK/2.1.0-gompi-2021b-fb
ScaLAPACK/2.2.0-gompi-2022a-fb
SciPy-bundle/2021.10-foss-2021b-Python-2.7.18
SciPy-bundle/2021.10-foss-2021b
SciPy-bundle/2021.10-foss-2022a-Python-2.7.18
SciPy-bundle/2022.05-foss-2021b
SciPy-bundle/2022.05-foss-2022a
SeqKit/0.16.1
SeqKit/2.3.1
SeqLib/1.2.0-GCC-11.2.0
Serf/1.3.9-GCCcore-11.2.0
Shapely/1.8.2-foss-2021b
ShortStack/4.0.1-foss-2021b-Perl-5.34.0
SignalP/4.1f-GCCcore-11.2.0
SignalP/5.0b-Linux
SignalP/6.0g-GCCcore-11.2.0-slow-sequential
Stacks/2.62-foss-2021b
StringTie/2.2.1-GCC-11.2.0
Structure/2.3.4-GCC-11.2.0
Subread/2.0.3-GCC-11.2.0
Subversion/1.14.1-GCCcore-11.2.0
SuiteSparse/5.10.1-foss-2021b-METIS-5.1.0
SuiteSparse/5.13.0-foss-2022a-METIS-5.1.0
Szip/2.1.1-GCCcore-11.2.0
Szip/2.1.1-GCCcore-11.3.0
TASSEL/5.2.44-Java-1.8.0_241
TMHMM/2.0c-GCCcore-11.2.0-Perl-5.34.0
TRF/4.09.1-GCCcore-11.2.0
TRF/4.09.1-GCCcore-11.3.0
TWL-NINJA/0.97-cluster_only-GCC-11.2.0
TWL-NINJA/0.98-cluster_only-GCC-11.2.0
Tcl/8.6.9-GCCcore-8.3.0
Tcl/8.6.11-GCCcore-11.2.0
Tcl/8.6.12-GCCcore-11.3.0
TensorFlow/2.7.1-foss-2021b-CUA-11.4.1
TensorFlow/2.11.0-foss-2022a-CUA-11.7.0
TensorFlow/2.11.0-foss-2022a
Theano/1.1.2-foss-2021b-PyMC
Tk/8.6.11-GCCcore-11.2.0
Tk/8.6.12-GCCcore-11.3.0
Tkinter/2.7.18-GCCcore-11.2.0
Tkinter/2.7.18-GCCcore-11.3.0
Tkinter/3.9.6-GCCcore-11.2.0
Tkinter/3.10.4-GCCcore-11.3.0
Transecoder/5.5.0-GCC-11.3.0
Transecoder/5.7.0-GCC-11.3.0
Transrate/1.0.3
TreeMix/1.13-GCC-11.2.0
Trim_Galore/0.6.7-GCCcore-11.2.0
Trimmomatic/0.39-Java-13
Trinity/2.15.1-foss-2021b
Trinity/2.15.1-foss-2022a
Trinotate/4.0.1-foss-2022a
UCC/1.0.0-GCCcore-11.3.0
UCC/1.1.0-GCCcore-12.2.0
UCLUST/1.2.22q-i86linux64
UCX-CUA/1.11.2-GCCcore-11.2.0-CUA-11.4.1
UCX-CUA/1.12.1-GCCcore-11.3.0-CUA-11.7.0
UCX/1.9.0-GCCcore-10.2.0
UCX/1.11.2-GCCcore-11.2.0
UCX/1.12.1-GCCcore-11.3.0
UCX/1.13.1-GCCcore-12.2.0
UUNITS/2.2.28-GCCcore-11.2.0
UUNITS/2.2.28-GCCcore-11.3.0
UMI-tools/1.1.2-foss-2021b-Python-3.9.6
USEARCH/11.0.667-i86linux32
UnZip/6.0-GCCcore-11.2.0
UnZip/6.0-GCCcore-11.3.0
Unicycler/0.5.0-gompi-2021b-Python-3.9.6
Unicycler/0.5.0-gompi-2021b
VCFtools/0.1.16-GCC-11.2.0
VEP/105-GCC-11.2.0
VSEARCH/2.22.1-GCC-11.2.0
VTK/9.1.0-foss-2021b
Velvet/1.2.10-GCC-11.2.0-mt-kmer_191
ViennaRNA/2.5.1-foss-2021b
Voro++/0.4.6-GCCcore-11.2.0
WEKA/3.8.6-Java-1.8.0_241
WPS/4.4-foss-2021b-dmpar
WRF-Chem-KPP/4.4.2-foss-2021b-dmpar
WRF-Chem/4.4.2-foss-2021b-dmpar
WRF/4.3-foss-2021b-dmpar
WRF/4.4.2-foss-2021b-dmpar
WU-Blast/2.2.6-GCC-11.2.0
WU-Blast/2.2.6-GCC-11.3.0
X11/20210802-GCCcore-11.2.0
X11/20220504-GCCcore-11.3.0
XML-Compile/1.63-GCCcore-11.2.0
XML-LibXML/2.0207-GCCcore-11.2.0
XML-LibXML/2.0207-GCCcore-11.3.0
XZ/5.2.4-GCCcore-8.3.0
XZ/5.2.5-GCCcore-10.2.0
XZ/5.2.5-GCCcore-11.2.0
XZ/5.2.5-GCCcore-11.3.0
XZ/5.2.7-GCCcore-12.2.0
XlsxWriter/3.0.8-GCCcore-11.3.0
Xvfb/1.20.13-GCCcore-11.2.0
Xvfb/21.1.3-GCCcore-11.3.0
Yasm/1.3.0-GCCcore-11.2.0
Z3/4.8.12-GCCcore-11.2.0
ZeroMQ/4.3.4-GCCcore-11.2.0
Zip/3.0-GCCcore-11.2.0
Zip/3.0-GCCcore-11.3.0
angsd/0.940-GCC-11.2.0
annovar/20200607-GCCcore-11.2.0-Perl-5.34.0
ant/1.10.1-Java-1.8.0_241
ant/1.10.11-Java-11
ant/1.10.12-Java-11
archspec/0.1.3-GCCcore-11.2.0
argtable/2.13-GCCcore-11.2.0
aria2/1.36.0-GCCcore-11.2.0
arpack-ng/3.8.0-foss-2021b
arpack-ng/3.8.0-foss-2022a
at-spi2-atk/2.38.0-GCCcore-11.2.0
at-spi2-atk/2.38.0-GCCcore-11.3.0
at-spi2-core/2.40.3-GCCcore-11.2.0
at-spi2-core/2.44.1-GCCcore-11.3.0
attr/2.5.1-GCCcore-11.2.0
bam-readcount/0.8.0-GCC-11.2.0
barrnap/0.9-gompi-2021b
bcbio-gff/0.7.0-foss-2021b
bcl2fastq2/2.20.0-GCC-11.2.0
beagle-lib/4.0.0-foss-2021b-CUA-11.4.1
binutils/2.32-GCCcore-8.3.0
binutils/2.32
binutils/2.35-GCCcore-10.2.0
binutils/2.35
binutils/2.37-GCCcore-11.2.0
binutils/2.37
binutils/2.38-GCCcore-11.3.0
binutils/2.38
binutils/2.39-GCCcore-12.2.0
binutils/2.39
bioawk/1.0-GCC-11.2.0
biom-format/2.1.14-foss-2021b
bokeh/2.4.2-foss-2021b
bokeh/2.4.3-foss-2021b
boto3/1.20.13-GCCcore-11.2.0
breseq/0.38.1-foss-2021b
bwa-meth/0.2.6-GCC-11.2.0
bx-python/0.8.13-foss-2021b
bzip2/1.0.8-GCCcore-8.3.0
bzip2/1.0.8-GCCcore-11.2.0
bzip2/1.0.8-GCCcore-11.3.0
c-ares/1.18.1-GCCcore-11.2.0
cURL/7.78.0-GCCcore-11.2.0
cURL/7.83.0-GCCcore-11.3.0
cairo/1.16.0-GCCcore-11.2.0
cairo/1.17.4-GCCcore-11.3.0
canu/2.2-GCCcore-11.2.0
ccache/4.6.3-GCCcore-11.2.0
cfour/2.1-intel-2021b-mpi
cfour/2.1-intel-2021b-serial
cppy/1.1.0-GCCcore-11.2.0
cppy/1.2.1-GCCcore-11.3.0
cuNN/8.2.1.32-CUA-11.3.1
cuNN/8.2.2.26-CUA-11.4.1
cuNN/8.4.1.50-CUA-11.7.0
cuNN/8.8.0.121-CUA-12.0.0
cutadapt/3.5-GCCcore-11.2.0
dask/2022.1.0-foss-2021b
deepTools/3.5.1-foss-2021b
dill/0.3.6-GCCcore-11.3.0
dm-tree/0.1.6-GCCcore-11.2.0
dorado/0.3.0-CUA-11.4.1
double-conversion/3.1.5-GCCcore-11.2.0
double-conversion/3.2.0-GCCcore-11.3.0
eggnog-mapper/2.1.9-foss-2022a
einops/0.4.1-GCCcore-11.2.0
elfutils/0.185-GCCcore-11.2.0
expat/2.2.7-GCCcore-8.3.0
expat/2.2.9-GCCcore-10.2.0
expat/2.4.1-GCCcore-11.2.0
expat/2.4.8-GCCcore-11.3.0
expat/2.4.9-GCCcore-12.2.0
expecttest/0.1.3-GCCcore-11.2.0
fastStructure/1.0-foss-2022a-Python-2.7.18
fastahack/1.0.0-GCCcore-11.2.0
fastp/0.23.2-GCC-11.2.0
fermi-lite/20190320-GCCcore-11.2.0
file/5.41-GCCcore-11.2.0
file/5.43-GCCcore-11.3.0
filevercmp/20191210-GCCcore-11.2.0
flatbuffers-python/2.0-GCCcore-11.2.0
flatbuffers-python/2.0-GCCcore-11.3.0
flatbuffers/2.0.0-GCCcore-11.2.0
flatbuffers/2.0.7-GCCcore-11.3.0
flex/2.6.4-GCCcore-8.3.0
flex/2.6.4-GCCcore-10.2.0
flex/2.6.4-GCCcore-11.2.0
flex/2.6.4-GCCcore-11.3.0
flex/2.6.4-GCCcore-12.2.0
flex/2.6.4
fontconfig/2.13.94-GCCcore-11.2.0
fontconfig/2.14.0-GCCcore-11.3.0
foss/2019b
foss/2021b
foss/2022a
freebayes/1.3.6-foss-2021b-R-4.1.2
freeglut/3.2.1-GCCcore-11.2.0
freetype/2.11.0-GCCcore-11.2.0
freetype/2.12.1-GCCcore-11.3.0
fsom/20141119-GCCcore-11.2.0
gaussian/09-AM-SSE4a
gaussian/09-Intel-SSE4_2
gaussian/16-AVX
gaussian/16-AVX2
gaussian/16-SSE4
gc/7.6.12-GCCcore-8.3.0
gc/8.2.0-GCCcore-11.2.0
gettext/0.19.8.1
gettext/0.21-GCCcore-11.2.0
gettext/0.21-GCCcore-11.3.0
gettext/0.21
gettext/0.21.1
gffread/0.12.7-GCCcore-11.2.0
gflags/2.2.2-GCCcore-11.2.0
giflib/5.2.1-GCCcore-11.2.0
giflib/5.2.1-GCCcore-11.3.0
git/2.33.1-GCCcore-11.2.0-nodocs
git/2.36.0-GCCcore-11.3.0-nodocs
glew/2.2.0-GCCcore-11.3.0-egl
gnuplot/5.4.2-GCCcore-11.2.0
gompi/2019b
gompi/2021b
gompi/2022a
googletest/1.11.0-GCCcore-11.3.0
gperf/3.1-GCCcore-11.2.0
gperf/3.1-GCCcore-11.3.0
graphite2/1.3.14-GCCcore-11.2.0
groff/1.22.4-GCCcore-8.3.0
groff/1.22.4-GCCcore-10.2.0
groff/1.22.4-GCCcore-11.2.0
groff/1.22.4-GCCcore-11.3.0
groff/1.22.4-GCCcore-12.2.0
gzip/1.10-GCCcore-11.2.0
gzip/1.12-GCCcore-11.3.0
h5py/3.6.0-foss-2021b
h5py/3.7.0-foss-2022a
help2man/1.47.8-GCCcore-8.3.0
help2man/1.47.16-GCCcore-10.2.0
help2man/1.48.3-GCCcore-11.2.0
help2man/1.49.2-GCCcore-11.3.0
help2man/1.49.2-GCCcore-12.2.0
hiredis/1.0.2-GCCcore-11.2.0
hsi/1.0.0-GCCcore-11.2.0
hwloc/1.11.12-GCCcore-8.3.0
hwloc/2.2.0-GCCcore-10.2.0
hwloc/2.5.0-GCCcore-11.2.0
hwloc/2.7.1-GCCcore-11.3.0
hwloc/2.8.0-GCCcore-12.2.0
hypothesis/4.57.1-GCCcore-11.2.0-Python-2.7.18
hypothesis/4.57.1-GCCcore-11.3.0-Python-2.7.18
hypothesis/6.14.6-GCCcore-11.2.0
hypothesis/6.46.7-GCCcore-11.3.0
iccifort/2019.5.281
igv-reports/1.7.0-GCC-11.2.0-Python-3.9.6
iimpi/2021b
imageio/2.13.5-foss-2021b
imkl-FFTW/2021.4.0-iimpi-2021b
imkl/2021.4.0
impi/2021.4.0-intel-compilers-2021.4.0
intel-compilers/2021.4.0
intel-compilers/2022.2.1
intel/2021b
intervaltree/0.1-GCCcore-11.2.0
intltool/0.51.0-GCCcore-11.2.0
intltool/0.51.0-GCCcore-11.3.0
jax/0.3.23-foss-2021b-CUA-11.4.1
jax/0.3.25-foss-2022a-CUA-11.7.0
jbigkit/2.1-GCCcore-11.2.0
jbigkit/2.1-GCCcore-11.3.0
jemalloc/5.2.1-GCCcore-11.2.0
jemalloc/5.2.1-GCCcore-11.3.0
jemalloc/5.3.0-GCCcore-11.3.0
kallisto/0.48.0-gompi-2021b
kallisto/0.48.0-gompi-2022a
kim-api/2.3.0-GCCcore-11.2.0
kineto/0.4.0-GCC-11.2.0
libGLU/9.0.2-GCCcore-11.2.0
libGLU/9.0.2-GCCcore-11.3.0
libaio/0.3.112-GCCcore-11.2.0
libaio/0.3.112-GCCcore-11.3.0
libarchive/3.5.1-GCCcore-11.2.0
libarchive/3.6.1-GCCcore-11.3.0
libcerf/1.17-GCCcore-11.2.0
libdeflate/1.8-GCCcore-11.2.0
libdeflate/1.10-GCCcore-11.3.0
libdrm/2.4.107-GCCcore-11.2.0
libdrm/2.4.110-GCCcore-11.3.0
libepoxy/1.5.8-GCCcore-11.2.0
libepoxy/1.5.10-GCCcore-11.3.0
libevent/2.1.12-GCCcore-10.2.0
libevent/2.1.12-GCCcore-11.2.0
libevent/2.1.12-GCCcore-11.3.0
libevent/2.1.12-GCCcore-12.2.0
libfabric/1.11.0-GCCcore-10.2.0
libfabric/1.13.2-GCCcore-11.2.0
libfabric/1.15.1-GCCcore-11.3.0
libfabric/1.16.1-GCCcore-12.2.0
libffi/3.2.1-GCCcore-8.3.0
libffi/3.4.2-GCCcore-11.2.0
libffi/3.4.2-GCCcore-11.3.0
libgd/2.3.3-GCCcore-11.2.0
libgeotiff/1.7.0-GCCcore-11.2.0
libgeotiff/1.7.1-GCCcore-11.3.0
libgit2/1.1.1-GCCcore-11.2.0
libgit2/1.4.3-GCCcore-11.3.0
libglvnd/1.3.3-GCCcore-11.2.0
libglvnd/1.4.0-GCCcore-11.3.0
libgtextutils/0.7-GCCcore-11.2.0
libharu/2.3.0-foss-2021b
libiconv/1.16-GCCcore-11.2.0
libiconv/1.17-GCCcore-11.3.0
libidn2/2.3.2-GCCcore-11.3.0
libjpeg-turbo/2.0.6-GCCcore-11.2.0
libjpeg-turbo/2.1.3-GCCcore-11.3.0
libmatheval/1.1.11-GCCcore-8.3.0
libogg/1.3.5-GCCcore-11.2.0
libogg/1.3.5-GCCcore-11.3.0
libopus/1.3.1-GCCcore-11.3.0
libpciaccess/0.14-GCCcore-8.3.0
libpciaccess/0.16-GCCcore-10.2.0
libpciaccess/0.16-GCCcore-11.2.0
libpciaccess/0.16-GCCcore-11.3.0
libpciaccess/0.17-GCCcore-12.2.0
libpng/1.6.37-GCCcore-11.2.0
libpng/1.6.37-GCCcore-11.3.0
libreadline/8.0-GCCcore-8.3.0
libreadline/8.0-GCCcore-10.2.0
libreadline/8.1-GCCcore-11.2.0
libreadline/8.1.2-GCCcore-11.3.0
libreadline/8.2-GCCcore-12.2.0
libsigc++/3.4.0-GCCcore-11.2.0
libsndfile/1.0.31-GCCcore-11.2.0
libsndfile/1.1.0-GCCcore-11.3.0
libsodium/1.0.18-GCCcore-11.2.0
libtirpc/1.3.2-GCCcore-11.2.0
libtirpc/1.3.2-GCCcore-11.3.0
libtool/2.4.6-GCCcore-8.3.0
libtool/2.4.6-GCCcore-10.2.0
libtool/2.4.6-GCCcore-11.2.0
libtool/2.4.7-GCCcore-11.3.0
libtool/2.4.7-GCCcore-12.2.0
libunistring/0.9.10-GCCcore-8.3.0
libunistring/1.0-GCCcore-11.2.0
libunwind/1.5.0-GCCcore-11.2.0
libunwind/1.6.2-GCCcore-11.3.0
libuv/1.37.0-GCCcore-11.3.0
libvorbis/1.3.7-GCCcore-11.2.0
libvorbis/1.3.7-GCCcore-11.3.0
libwebp/1.2.0-GCCcore-11.2.0
libxc/5.1.6-GCC-11.2.0
libxc/5.2.3-GCC-11.2.0
libxml++/2.42.1-GCC-11.2.0
libxml2/2.9.9-GCCcore-8.3.0
libxml2/2.9.10-GCCcore-10.2.0
libxml2/2.9.10-GCCcore-11.2.0
libxml2/2.9.13-GCCcore-11.3.0
libxml2/2.10.3-GCCcore-12.2.0
libxslt/1.1.34-GCCcore-11.2.0
libxslt/1.1.34-GCCcore-11.3.0
libyaml/0.2.5-GCCcore-11.2.0
libyaml/0.2.5-GCCcore-11.3.0
lpsolve/5.5.2.11-GCC-11.2.0
lpsolve/5.5.2.11-GCC-11.3.0
lxml/4.6.3-GCCcore-11.2.0
lz4/1.9.3-GCCcore-11.2.0
lz4/1.9.3-GCCcore-11.3.0
maeparser/1.3.0-gompi-2021b
magma/2.6.2-foss-2021b-CUA-11.4.1
make/4.3-GCCcore-11.2.0
make/4.3-GCCcore-11.3.0
makeinfo/6.7-GCCcore-8.3.0-minimal
makeinfo/6.7-GCCcore-10.2.0-minimal
matlab/R2022b
matlab/R2023a
matplotlib/2.2.5-foss-2021b-Python-2.7.18
matplotlib/2.2.5-foss-2022a-Python-2.7.18
matplotlib/3.4.3-foss-2021b
matplotlib/3.5.2-foss-2021b
matplotlib/3.5.2-foss-2022a
methylpy/1.4.6-foss-2021b
minimap2/2.22-GCCcore-11.2.0
minimap2/2.24-GCCcore-11.2.0
mm-common/1.0.5-GCCcore-11.2.0
molmod/1.4.8-foss-2021b
motif/2.3.8-GCCcore-11.2.0
multichoose/1.0.3-GCCcore-11.2.0
ncbi-vdb/2.10.9-gompi-2021b
ncbi-vdb/2.11.2-gompi-2021b
ncbi-vdb/3.0.2-gompi-2022a
ncurses/6.0
ncurses/6.1-GCCcore-8.3.0
ncurses/6.1
ncurses/6.2-GCCcore-10.2.0
ncurses/6.2-GCCcore-11.2.0
ncurses/6.2
ncurses/6.3-GCCcore-11.3.0
ncurses/6.3-GCCcore-12.2.0
ncurses/6.3
netCF-Fortran/4.5.3-gompi-2021b
netCF/4.8.1-gompi-2021b
netCF/4.9.0-gompi-2022a
netMHCpan/4.1b
nettle/3.7.3-GCCcore-11.2.0
nettle/3.8-GCCcore-11.3.0
networkx/2.6.3-foss-2021b
networkx/2.8.4-foss-2022a
nlohmann_json/3.10.5-GCCcore-11.3.0
nodejs/14.17.6-GCCcore-11.2.0
nodejs/16.15.1-GCCcore-11.3.0
nsync/1.24.0-GCCcore-11.2.0
nsync/1.25.0-GCCcore-11.3.0
numactl/2.0.12-GCCcore-8.3.0
numactl/2.0.13-GCCcore-10.2.0
numactl/2.0.14-GCCcore-11.2.0
numactl/2.0.14-GCCcore-11.3.0
numactl/2.0.16-GCCcore-12.2.0
numexpr/2.8.4-foss-2021b
pandasql/0.7.3-foss-2021b-Python-3.9.6
parallel/20210722-GCCcore-11.2.0
parallel/20221122-GCCcore-11.2.0
pblat/2.5-GCCcore-8.3.0
picard/2.25.1-Java-11
picard/2.27.5-Java-15
pigz/2.6-GCCcore-11.2.0
pixman/0.40.0-GCCcore-11.2.0
pixman/0.40.0-GCCcore-11.3.0
pkg-config/0.29.2-GCCcore-10.2.0
pkg-config/0.29.2-GCCcore-11.2.0
pkg-config/0.29.2-GCCcore-11.3.0
pkgconf/1.8.0-GCCcore-11.2.0
pkgconf/1.8.0-GCCcore-11.3.0
pkgconf/1.8.0
pkgconf/1.9.3-GCCcore-12.2.0
pkgconfig/1.5.5-GCCcore-11.2.0-python
pkgconfig/1.5.5-GCCcore-11.3.0-python
plotly.py/5.4.0-GCCcore-11.2.0
poppler/22.11.0-GCC-11.2.0
pplacer/1.1.alpha19
pretty-yaml/21.10.1-GCCcore-11.2.0
prodigal/2.6.3-GCCcore-11.2.0
prodigal/2.6.3-GCCcore-11.3.0
protobuf-python/3.17.3-GCCcore-11.2.0
protobuf-python/3.19.4-GCCcore-11.3.0
protobuf/3.17.3-GCCcore-11.2.0
protobuf/3.19.4-GCCcore-11.3.0
psutil/5.9.4-GCCcore-11.2.0
purge_dups/1.2.5-foss-2021b
pyBigWig/0.3.18-foss-2021b
pybedtools/0.8.2-GCC-11.2.0
pybind11/2.7.1-GCCcore-11.2.0-Python-2.7.18
pybind11/2.7.1-GCCcore-11.2.0
pybind11/2.7.1-GCCcore-11.3.0-Python-2.7.18
pybind11/2.9.2-GCCcore-11.3.0
pytest-xdist/2.5.0-GCCcore-11.2.0
pytest-xdist/2.5.0-GCCcore-11.3.0
pytest/7.1.3-GCCcore-11.2.0
python-isal/0.11.1-GCCcore-11.2.0
python-isal/1.1.0-GCCcore-11.2.0
re2c/2.2-GCCcore-11.2.0
rjags/4-12-foss-2021b-R-4.2.1
scikit-bio/0.5.7-foss-2021b
scikit-build/0.11.1-GCCcore-11.2.0
scikit-image/0.19.1-foss-2021b
scikit-learn/1.0.1-foss-2021b
scikit-learn/1.1.2-foss-2022a
scikit-optimize/0.9.0-foss-2021b
seqtk/1.3-GCC-11.2.0
smithwaterman/20160702-GCCcore-11.2.0
snappy/1.1.9-GCCcore-11.2.0
snappy/1.1.9-GCCcore-11.3.0
spaln/2.4.12-GCC-11.2.0
sparsehash/2.0.4-GCCcore-11.2.0
spglib-python/1.16.3-foss-2021b
statsmodels/0.13.1-foss-2021b
tRNAscan-SE/2.0.12-foss-2021b
tRNAscan-SE/2.0.12-GCC-11.2.0
tabixpp/1.1.0-GCC-11.2.0
tbb/2019_U9-GCCcore-8.3.0
tbb/2020.3-GCCcore-11.2.0
tbb/2021.5.0-GCCcore-11.3.0
tcsh/6.24.01-GCCcore-11.2.0
tensorboard/2.8.0-foss-2021b
time/1.9-GCCcore-11.2.0
tmux/3.3a-GCCcore-11.3.0
tqdm/4.62.3-GCCcore-11.2.0
typing-extensions/3.10.0.2-GCCcore-11.2.0
ucsc/434
ucsc/443
utf8proc/2.6.1-GCCcore-11.2.0
utf8proc/2.7.0-GCCcore-11.3.0
util-linux/2.37-GCCcore-11.2.0
util-linux/2.38-GCCcore-11.3.0
vcflib/1.0.3-foss-2021b-R-4.1.2
wget/1.21.3-GCCcore-11.3.0
x264/20210613-GCCcore-11.2.0
x265/3.5-GCCcore-11.2.0
xorg-macros/1.19.2-GCCcore-8.3.0
xorg-macros/1.19.2-GCCcore-10.2.0
xorg-macros/1.19.3-GCCcore-11.2.0
xorg-macros/1.19.3-GCCcore-11.3.0
xorg-macros/1.19.3-GCCcore-12.2.0
xprop/1.2.5-GCCcore-11.2.0
xxd/8.2.4220-GCCcore-11.2.0
yaff/1.6.0-foss-2021b
zlib/1.2.11-GCCcore-8.3.0
zlib/1.2.11-GCCcore-10.2.0
zlib/1.2.11-GCCcore-11.2.0
zlib/1.2.11
zlib/1.2.12-GCCcore-11.3.0
zlib/1.2.12-GCCcore-12.2.0
zlib/1.2.12
zstd/1.5.0-GCCcore-11.2.0
zstd/1.5.2-GCCcore-11.3.0

Code Compilation on Sapelo2

2026-05-11T15:59:17Z

Shtsai: Added header for column 1 and table caption

[[Category:Sapelo2]]

==Where should I compile my code?==



Please DO NOT compile source code on the login node. Instead, compile your code in an interactive session started with the <code>interact</code> command.

Code compilation can be done in an interactive session. To start an interactive session, first login into Sapelo2 and from there issue the <code>'''[[Running Jobs on Sapelo2#How to open an interactive session|interact]]'''</code> command
<pre class="gcommand">
interact
</pre>
If you plan to run the code on an AMD node, you can start an interactive session on an AMD node to compile the code. To start an interactive on an AMD node, use the command
<pre class="gcommand">
interact --constraint AMD
</pre>

If you plan to run the code on an Intel node, you can start an interactive session on an Intel node to compile the code. To start an interactive on an Intel node, use the command
<pre class="gcommand">
interact --constraint Intel
</pre>

For detailed information on how to access the compute node interactively for code compilation, please see [[Running Jobs on Sapelo2]].

----

==Compilers==

A number of Fortran and C/C++ compilers, as well as Java and scripting languages such as Perl and Python, are available on Sapelo2.

=== Summary of main Fortran and C/C++ compilers installed ===
{| width="100%" border="1" cellspacing="0" cellpadding="2" align="center" class="wikitable unsortable"
|+Table showing various compilers for a given language
|-
! scope="col" |Language
! scope="col" | NVHPC
! scope="col" | Intel
! scope="col" | GNU
! scope="col" | OpenMPI
! scope="col" | File extension
|-

| Fortran77 || nvfortran
| ifort || gfortran
| mpif77|| .f
|-
| Fortran90 || nvfortran
| ifort || gfortran|| mpif90|| .f90
|-
| Fortran95 || nvfortran
| ifort || gfortran || mpifort || .f95
|-
|Fortran2003
|nvfortran
|ifort
|gfortran
|mpifort
|.f
|-
| C || nvc || icc || gcc || mpicc || .c
|-
| C++ || nvcc || icpc || g++ || mpicxx || .C, .cpp, .cc
|-

|}

The various compiler suites are provided by their environment modules.

=== GNU compiler suites ===
The following command will show all the modules that provide GCC compiler suites:
<pre class="gcommand">
module spider GCC
</pre>

Sample partial output of this command:
<pre class="gcomment">
[shtsai@d2-13 ~]$ module spider GCC
-----------------------------------------------------------------------------------------------------------------
GCC:
-----------------------------------------------------------------------------------------------------------------
Description:
The GNU Compiler Collection includes front ends for C, C++, Objective-C, Fortran, Java, and Ada, as well as libraries for these languages (libstdc++, libgcj,...).

Versions:
GCC/11.2.0
GCC/11.3.0
GCC/12.3.0
GCC/13.2.0
GCC/13.3.0
Other possible modules matches:
GCCcore
-----------------------------------------------------------------------------------------------------------------
</pre>

This output indicates that the following versions of GCC compilers are available:

*Version 11.2.0, with binutils 2.37, provided by the GCC/11.2.0 module, includes C, C++, and Fortran compilers.
*Version 11.3.0, with binutils 2.38, provided by the GCC/11.3.0 module, includes C, C++, and Fortran compilers.
*Version 12.3.0, with binutils 2.40, provided by the GCC/12.3.0 module, includes C, C++, and Fortran compilers.
*Version 13.2.0, with binutils 2.40, provided by the GCC/13.2.0 module, includes C, C++, and Fortran compilers.
*Version 13.3.0, with binutils 2.42, provided by the GCC/13.3.0 module, includes C, C++, and Fortran compilers.

We suggest that you run the<code> module spider GCC</code> command to check an updated list of GCC compilers available on the cluster.

=== Intel compiler suites ===
The following command will show all the modules that provide Intel compiler suites:
<pre class="gcommand">
module spider intel-compilers
</pre>

Sample output of this command
<pre class="gcomment">
[shtsai@d2-13 ~]$ ml spider intel-compilers

-----------------------------------------------------------------------------------------------------------------
intel-compilers:
-----------------------------------------------------------------------------------------------------------------
Description:
Intel C, C++ & Fortran compilers (classic and oneAPI)

Versions:
intel-compilers/2021.4.0
intel-compilers/2022.1.0
intel-compilers/2023.1.0
intel-compilers/2023.2.1
intel-compilers/2024.2.0
-----------------------------------------------------------------------------------------------------------------
</pre>

This output indicates that the following versions of the Intel compiler suites are available:

*Version 2021.4.0, provided by the intel-compilers/2021.4.0 module.
*Version 2022.1.0, provided by the intel-compilers/2022.1.0 module.
*Version 2023.1.0, provided by the intel-compilers/2023.1.0 module.
*Version 2023.2.1, provided by the intel-compilers/2023.2.1 module.
*Version 2024.2.0, provided by the intel-compilers/2024.2.0 module.

We suggest that you run the <code>module spider intel-compilers</code> or <code>module spider iccifort</code> command to check an updated list of Intel compilers available on the cluster.

=== LLVM compiler suites ===
The following command will show all the modules that provide LLVM compilers:
<pre class="gcommand">
module spider LLVM
</pre>
Sample output of this command
<pre class="gcomment">
[shtsai@d2-13 ~]$ module spider LLVM
------------------------------------------------------------------------------------------------------------------------------------
LLVM:
------------------------------------------------------------------------------------------------------------------------------------
Description:
The LLVM Core libraries provide a modern source- and target-independent optimizer, along with code generation support for many popular CPUs (as well as some less common ones!) These libraries are built around a well specified
code representation known as the LLVM intermediate representation ("LLVM IR"). The LLVM Core libraries are well documented, and it is particularly easy to invent your own language (or port an existing compiler) to use LLVM as an
optimizer and code generator.

Versions:
LLVM/14.0.3-GCCcore-11.3.0
LLVM/14.0.6-GCCcore-12.3.0-llvmlite
LLVM/14.0.6-GCCcore-13.3.0-llvmlite
LLVM/16.0.6-GCCcore-12.3.0
LLVM/16.0.6-GCCcore-13.2.0
LLVM/18.1.8-GCCcore-13.3.0-minimal

-----------------------------------------------------------------------------------------------------------------------------------
</pre>

=== How to load a compiler module ===

To use any of the compiler suite, please first load the corresponding module. For example, to use the GNU 12.3.0 compiler suite, load the module with<pre class="gcommand">
module load GCC/12.3.0
</pre>
Once this module is loaded the gcc, g++, and gfortran for GCC v. 12.3.0 will be available in your path.

Please note that you can only have one compiler module loaded at a time.

=== Some commonly used compiler options ===

====Intel compiler suite====
{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Option
! scope="col" |Description
|-

| -O0||Specifies no optimization, recommended for code debugging
|-
| -O2 ||Enables optimizations for speed. This is the generally recommended optimization level.
|-
| -O3||Performs -O2 optimizations and more aggressive loop transformations. Use with care.
|-
| -fast ||Chooses generally good optimization options for the platform. Type pgcc -fast -help to see the equivalent options.
|-
| -Mbounds ||Performs runtime array bound check, recommended for code debugging
|}

====GNU compiler suite====
{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Option
! scope="col" | Description
|-

| -O0||Specifies no optimization, recommended for code debugging
|-
| -O2 ||Enables optimizations for speed. This is the generally recommended optimization level.
|-
| -O3||Performs -O2 optimizations and more aggressive loop transformations. Use with care.
|-
| -std=
|Determine the language standard. This option is currently only supported when compiling C or C++.
|-
| -fopenmp
|Enable handling of OpenMP directives "#pragma omp" in C/C++ and "!$omp" in Fortran.
|-
| -fopenacc
| Enable handling of OpenACC directives "#pragma acc" in C/C++ and "!$acc" in Fortran.
|-
|<nowiki>-Wpedantic</nowiki>
|Issue all the warnings demanded by strict ISO C and ISO C++; reject all programs that use forbidden extensions, and some other programs that do not follow ISO C and ISO C++.
|-
| -Wall
|This enables all the warnings about constructions that some users consider questionable.
|}

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

== Compiler Toolchains==
On Sapelo2 we use the [https://easybuild.readthedocs.io/en/latest/ EasyBuild] framework to install software applications. The EasyBuild toolchains are also available for users to compile their own code. Each toolchain provides a compiler suite and some basic libraries, such as MPI, BLAS, LAPACK, FFTW, etc.

More information about compiler toolchains, please [[Available Toolchains and Toolchain Compatibility]].

===foss toolchains===
Most software applications are installed with the '''foss''' toolchain, where '''foss''' is short for “Free and Open Source Software”.

The foss toolchain consists of:

*binutils (https://www.gnu.org/software/binutils/)
*the GNU Compiler Collection (GCC, https://gcc.gnu.org/), i.e. gcc (C), g++ (C++) and gfortran (Fortran)
*the Open MPI library (https://www.open-mpi.org/)
*the OpenBLAS (http://www.openblas.net/) + LAPACK (http://netlib.org/lapack) libraries
*the ScaLAPACK (http://netlib.org/scalapack) library is also included
*the FFTW library (http://fftw.org/)

You can check the foss toolchain modules that are installed on the cluster with the command
<pre class="gcommand">
module spider foss
</pre>

When you load a foss toolchain, all it components will be loaded. For example:
<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load foss/2023a
[shtsai@d2-13 ~]$ module list

Currently Loaded Modules:
1) GCCcore/12.3.0 7) libxml2/2.11.4-GCCcore-12.3.0 13) libfabric/1.18.0-GCCcore-12.3.0 19) FFTW/3.3.10-GCC-12.3.0
2) zlib/1.2.13-GCCcore-12.3.0 8) libpciaccess/0.17-GCCcore-12.3.0 14) PMIx/4.2.4-GCCcore-12.3.0 20) gompi/2023a
3) binutils/2.40-GCCcore-12.3.0 9) hwloc/2.9.1-GCCcore-12.3.0 15) UCC/1.2.0-GCCcore-12.3.0 21) FFTW.MPI/3.3.10-gompi-2023a
4) GCC/12.3.0 10) OpenSSL/1.1 16) OpenMPI/4.1.5-GCC-12.3.0 22) ScaLAPACK/2.2.0-gompi-2023a-fb
5) numactl/2.0.16-GCCcore-12.3.0 11) libevent/2.1.12-GCCcore-12.3.0 17) OpenBLAS/0.3.23-GCC-12.3.0 23) foss/2023a
6) XZ/5.4.2-GCCcore-12.3.0 12) UCX/1.14.1-GCCcore-12.3.0 18) FlexiBLAS/3.3.1-GCC-12.3.0

</pre>

===intel toolchains===
The intel toolchain consists of

*the Intel compiler suite
*the Intel MPI libraries
*the Intel Math Kernel Libraries (MKL)

You can check the intel toolchain modules that are installed on the cluster with the command
<pre class="gcommand">
module spider intel
</pre>

When you load an intel toolchain, all it components will be loaded. For example:
<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load intel/2023a
[shtsai@d2-13 ~]$ module list

Currently Loaded Modules:
1) GCCcore/12.3.0 4) intel-compilers/2023.1.0 7) impi/2021.9.0-intel-compilers-2023.1.0 10) imkl-FFTW/2023.1.0-iimpi-2023a
2) zlib/1.2.13-GCCcore-12.3.0 5) numactl/2.0.16-GCCcore-12.3.0 8) imkl/2023.1.0 11) intel/2023a
3) binutils/2.40-GCCcore-12.3.0 6) UCX/1.14.1-GCCcore-12.3.0 9) iimpi/2023a

</pre>





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

== Linking with libraries==
Some library packages are installed along with some compiler toolchains. Examples of these are OpenBLAS, MKL, FFTW, etc. Other libraries are installed as a separate module, for example, Boost and GSL.

If you want to compile a code that uses a library that is not included with compiler toolchain, you will have to load a library module that uses a[[Available Toolchains and Toolchain Compatibility | compatible]] toolchain. For example, if you want to compile your code with GCC 12.3.0 (or with the foss/2023a toolchain), and you need to use GSL, you can load the GSL/2.7-GCC-12.3.0 module.

Also note that when you load a module for a library or an application, the full path to its installation directory will be stored in an environment variable called '''EBROOT''NAME''''', where ''NAME'' is the name of the application or library. For example, when you load a GSL module, the directory where the GSL libraries are installed will be in an environment variable called EBROOTGSL.

For example:

<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load GCC/12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGCC
/apps/eb/GCCcore/12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGSL

[shtsai@d2-13 ~]$ module load GSL/2.7-GCC-12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGSL
/apps/eb/GSL/2.7-GCC-12.3.0
[shtsai@d2-13 ~]$
</pre>

As shown in the example above, when you load an GSL module, an environment variable called '''EBROOTGSL''' is defined, and it points to the installation path for GSL.

When you compile your code, you can add the compiler option:

<code> -I${EBROOTGSL}/include </code>

and the linker option

<code> -L${EBROOTGSL}/lib -lgsl -lgslcblas </code>

'''Example of program compilation that uses GCC 12.3.0 and GSL v. 2.7:'''

<pre class="gcommand">
module load GSL/2.7-GCC-12.3.0

gcc -O program.c -I${EBROOTGSL}/include -L${EBROOTGSL}/lib -lgsl -lgslcblas -Wl,-rpath=${EBROOTGSL}/lib
</pre>

Users can include the compilation option e.g. '''-Wl,-rpath=${EBROOTGSL}/lib''' to include the library directory in the '''runtime path'''. If this option is not included, then at runtime the user has to load the GSL module again, in order to define the environment variable LD_LIBRARY_PATH.
----
[[#top|Back to Top]]

Software installed on Rocky 9

2026-05-11T15:09:40Z

Shtsai: changed section heading for WAG.

As part of our July 29-31,2025 maintenance window, the GACRC will be upgrading the Sapelo2 cluster operating system from Rocky 8 to Rocky 9.

Because this is a major OS update, we need to recompile all the applications and ensure that they work with the new version of OS.

Below is a list of the modules already installed on the Rocky 9 system. More software packages continue to be installed. If the software you need is not in this list yet, please feel free to let us know, if you would like us to install it centrally on the updated cluster.

All singularity containers available in /apps/singularity-images on the current Sapelo2 (Rocky 8) will continue to be available after the maintenance.

== List of software already installed centrally on the Rocky 9 system (new Sapelo2, available after the maintenance) ==
ABySS/2.3.7-foss-2023a
ADMIXTURE/1.3.0
AFNI/25.1.01-foss-2024a
AGAT/1.4.0-GCC-12.3.0
AMOS/3.1.0-foss-2023a
ANIcalculator/1.0-GCCcore-11.3.0
ANSYS/2025R1
ANTLR/2.7.7-GCCcore-12.3.0-Java-11
ANTLR/2.7.7-GCCcore-13.3.0-Java-17
APR-util/1.6.3-GCCcore-13.3.0
APR/1.7.4-GCCcore-13.3.0
ASE/3.22.1-foss-2022a
ASE/3.23.0-gfbf-2024a
ASTRAL/5.7.8-Java-1.8.0_241
ATK/2.38.0-GCCcore-11.3.0
ATK/2.38.0-GCCcore-12.3.0
ATK/2.38.0-GCCcore-13.2.0
AUGUSTUS/3.5.0-foss-2022a
AUGUSTUS/3.5.0-foss-2023a
AUGUSTUS/3.5.0-foss-2024a
AUGUSTUS/3.5.0-20240612-foss-2023a
Abseil/20230125.3-GCCcore-12.3.0
Abseil/20240116.1-GCCcore-13.2.0
Abseil/20240722.0-GCCcore-13.3.0
Albumentations/1.3.0-foss-2022a
Albumentations/1.4.0-foss-2023a
AlphaFold/2.3.2-foss-2023a-CUDA-12.1.1
AlphaPulldown/2.0.3-foss-2023a-CUDA-12.1.1
Amber/22.4-foss-2022a-AmberTools-22.5-CUDA-11.7.0
Amber/24.3-foss-2022a-AmberTools-24.10-CUDA-12.1.1
Ancestry_HMM/1.0.2-foss-2024a
Archive-Zip/1.68-GCCcore-12.3.0
Archive-Zip/1.68-GCCcore-13.3.0
Armadillo/11.4.3-foss-2022a
Armadillo/12.6.2-foss-2023a
Armadillo/12.8.0-foss-2023b
Armadillo/14.0.3-foss-2024a
Arrow/14.0.1-gfbf-2023a
Arrow/16.1.0-gfbf-2023b
Arrow/17.0.0-gfbf-2024a
Autoconf/2.71-GCCcore-11.3.0
Autoconf/2.71-GCCcore-12.3.0
Autoconf/2.71-GCCcore-13.2.0
Autoconf/2.71
Autoconf/2.72-GCCcore-13.3.0
Automake/1.16.5-GCCcore-11.3.0
Automake/1.16.5-GCCcore-12.3.0
Automake/1.16.5-GCCcore-13.2.0
Automake/1.16.5-GCCcore-13.3.0
Automake/1.16.5
Autotools/20220317-GCCcore-11.3.0
Autotools/20220317-GCCcore-12.3.0
Autotools/20220317-GCCcore-13.2.0
Autotools/20220317
Autotools/20231222-GCCcore-13.3.0
BBMap/39.01-GCC-11.3.0
BBMap/39.01-GCC-12.3.0
BBMap/39.19-GCC-13.3.0
BCFtools/1.15.1-GCC-11.3.0
BCFtools/1.18-GCC-12.3.0
BCFtools/1.21-GCC-13.3.0
BEDOPS/2.4.41-foss-2023a
BEDTools/2.31.0-GCC-12.3.0
BEDTools/2.31.1-GCC-13.3.0
BLAST+/2.13.0-gompi-2022a
BLAST+/2.14.1-gompi-2023a
BLAST+/2.16.0-gompi-2024a
BLAT/3.7-GCC-11.3.0
BLAT/3.7-GCC-12.3.0
BLIS/0.9.0-GCC-11.3.0
BLIS/0.9.0-GCC-12.3.0
BLIS/0.9.0-GCC-13.2.0
BLIS/1.0-GCC-13.3.0
BRAKER/3.0.8-foss-2023a
BUSCO/5.8.3-foss-2023a
BWA/0.7.17-GCCcore-11.3.0
BWA/0.7.17-GCCcore-12.3.0
BWA/0.7.18-GCCcore-13.2.0
BWA/0.7.18-GCCcore-13.3.0
BamTools/2.5.2-GCC-11.3.0
BamTools/2.5.2-GCC-12.3.0
BamTools/2.5.2-GCC-13.3.0
Bandage/0.9.0-GCCcore-12.3.0
Bazel/6.1.0-GCCcore-12.3.0
Bazel/6.3.1-GCCcore-12.3.0
Beagle/5.4.22Jul22.46e-Java-11
Beast/2.7.7-GCC-12.3.0-CUDA-12.1.1
BeautifulSoup/4.12.2-GCCcore-12.3.0
BeautifulSoup/4.12.2-GCCcore-13.2.0
BeautifulSoup/4.12.3-GCCcore-13.3.0
Bio-DB-HTS/3.01-GCC-12.3.0
Bio-DB-HTS/3.01-GCC-13.3.0
Bio-SearchIO-hmmer/1.7.3-GCC-12.3.0
BioPerl/1.7.2-GCCcore-13.3.0
BioPerl/1.7.8-GCCcore-11.3.0
BioPerl/1.7.8-GCCcore-12.3.0
BioPerl/1.7.8-GCCcore-13.2.0
BioPerl/1.7.8-GCCcore-13.3.0
Biopython/1.79-foss-2022a
Biopython/1.83-foss-2023a
Biopython/1.84-foss-2023b
Biopython/1.84-foss-2024a
Bismark/0.24.2-GCC-12.3.0
Bison/3.8.2-GCCcore-11.3.0
Bison/3.8.2-GCCcore-12.3.0
Bison/3.8.2-GCCcore-13.2.0
Bison/3.8.2-GCCcore-13.3.0
Bison/3.8.2
Blosc/1.21.5-GCCcore-12.3.0
Blosc/1.21.6-GCCcore-13.3.0
Blosc2/2.17.0-GCCcore-13.3.0
Boltz/2.1.1
Boost.MPI/1.79.0-gompi-2022a
Boost.MPI/1.82.0-gompi-2023a
Boost.Python/1.82.0-GCC-12.3.0
Boost.Python/1.85.0-GCC-13.3.0
Boost/1.75.0-GCC-12.3.0
Boost/1.79.0-GCC-11.3.0
Boost/1.82.0-GCC-12.3.0
Boost/1.83.0-GCC-13.2.0
Boost/1.85.0-GCC-13.3.0
Bowtie/1.3.1-GCC-11.3.0
Bowtie/1.3.1-GCC-12.3.0
Bowtie2/2.4.5-GCC-11.3.0
Bowtie2/2.5.1-GCC-12.3.0
Bowtie2/2.5.2-GCC-11.3.0
Bracken/3.1-GCCcore-12.3.0
BrainNetViewer/20191031
Brotli-python/1.1.0-GCCcore-13.3.0
Brotli/1.0.9-GCCcore-11.3.0
Brotli/1.0.9-GCCcore-12.3.0
Brotli/1.1.0-GCCcore-13.2.0
Brotli/1.1.0-GCCcore-13.3.0
Brunsli/0.1-GCCcore-12.3.0
Brunsli/0.1-GCCcore-13.2.0
Brunsli/0.1-GCCcore-13.3.0
CD-HIT/4.8.1-GCC-11.3.0
CD-HIT/4.8.1-GCC-12.3.0
CDBtools/0.99-GCC-12.3.0
CDO/2.4.4-gompi-2024a
CFITSIO/4.3.0-GCCcore-12.3.0
CFITSIO/4.3.1-GCCcore-13.2.0
CFITSIO/4.4.1-GCCcore-13.3.0
CGAL/5.6.1-GCCcore-13.3.0
CMSeq/1.0.4-foss-2024a
CMake/3.18.4
CMake/3.23.1-GCCcore-11.3.0
CMake/3.24.3-GCCcore-11.3.0
CMake/3.26.3-GCCcore-12.3.0
CMake/3.27.6-GCCcore-13.2.0
CMake/3.29.3-GCCcore-13.3.0
CUDA/11.7.0
CUDA/12.1.1
CUDA/12.4.0
CUDA/12.6.0
CUnit/2.1-3-GCCcore-12.3.0
CVXPY/1.4.2-foss-2023a
CapnProto/0.10.2-GCCcore-11.3.0
CapnProto/1.0.1.1-GCCcore-13.2.0
CapnProto/1.1.0-GCCcore-13.3.0
Cartopy/0.22.0-foss-2023a
Catch2/2.13.9-GCCcore-12.3.0
Catch2/2.13.9-GCCcore-13.2.0
Catch2/2.13.10-GCCcore-13.3.0
Cbc/2.10.12-foss-2024a
Cereal/1.3.0
Cereal/1.3.2
Cgl/0.60.8-foss-2024a
CharLS/2.4.2-GCCcore-13.3.0
CheMPS2/1.8.12-foss-2023a
CheMPS2/1.8.12-foss-2023b
CheMPS2/1.8.12-foss-2024a
Check/0.15.2-GCCcore-13.3.0
CheckM-Database/2015_01_16
CheckM/1.2.2-foss-2022a
Circlator/1.5.5-foss-2023a
Clang/13.0.1-GCCcore-11.3.0
Clang/16.0.6-GCCcore-12.3.0-CUDA-12.1.1
Clang/16.0.6-GCCcore-12.3.0
Clang/18.1.8-GCCcore-13.3.0-CUDA-12.6.0
Clang/18.1.8-GCCcore-13.3.0
Clarabel.rs/0.7.1-gfbf-2023a
Clp/1.17.10-foss-2024a
Clustal-Omega/1.2.4-GCC-12.3.0
ClustalW2/2.1-GCC-12.3.0
CodingQuarry/2.0-foss-2023a
CoinUtils/2.11.12-GCC-13.3.0
Compress-Raw-Zlib/2.213-GCCcore-12.3.0
Compress-Raw-Zlib/2.213-GCCcore-13.3.0
Consed/29.0-foss-2022a
CoordgenLibs/3.0.2-gompi-2023a
CoverM/0.4.0
CppUnit/1.15.1-GCCcore-12.3.0
Cufflinks/20190706-GCC-12.3.0
Cython/0.29.37-GCCcore-13.3.0-Python-2.7.18
Cython/3.0.7-GCCcore-12.3.0
Cython/3.0.8-GCCcore-12.3.0
Cython/3.0.10-GCCcore-13.2.0
Cython/3.0.10-GCCcore-13.3.0
DB/18.1.40-GCCcore-11.3.0
DB/18.1.40-GCCcore-12.3.0
DB/18.1.40-GCCcore-13.2.0
DB/18.1.40-GCCcore-13.3.0
DBD-mysql/4.050-GCC-12.3.0
DB_File/1.858-GCCcore-11.3.0
DB_File/1.859-GCCcore-12.3.0
DB_File/1.859-GCCcore-13.2.0
DB_File/1.859-GCCcore-13.3.0
DBus/1.14.0-GCCcore-11.3.0
DBus/1.15.4-GCCcore-12.3.0
DBus/1.15.8-GCCcore-13.2.0
DBus/1.15.8-GCCcore-13.3.0
DIAMOND/2.1.0-GCC-11.3.0
DIAMOND/2.1.8-GCC-12.3.0
DIAMOND/2.1.9-GCC-13.2.0
DIAMOND/2.1.11-GCC-13.3.0
Delly/1.3.3-GCC-13.3.0
DendroPy/4.5.2-GCCcore-11.3.0
DendroPy/4.6.1-GCCcore-12.3.0
Doxygen/1.9.4-GCCcore-11.3.0
Doxygen/1.9.7-GCCcore-12.3.0
Doxygen/1.9.8-GCCcore-13.2.0
Doxygen/1.11.0-GCCcore-13.3.0
ELPA/2024.05.001-foss-2024a
EMBOSS/6.6.0-foss-2023a
ESMF/8.6.0-foss-2023a
ETE/3.1.3-foss-2023a
EVidenceModeler/2.1.0-foss-2023a
EasyBuild/4.7.2
EasyBuild/4.8.0
EasyBuild/4.9.4
Eigen/3.4.0-GCCcore-11.3.0
Eigen/3.4.0-GCCcore-12.3.0
Eigen/3.4.0-GCCcore-13.2.0
Eigen/3.4.0-GCCcore-13.3.0
Exonerate/2.4.0-GCC-12.3.0
Exonerate/2.4.0-GCC-13.3.0
FASTA/36.3.8i-GCC-12.3.0
FASTX-Toolkit/0.0.14-GCC-11.3.0
FFTW.MPI/3.3.10-gompi-2022a
FFTW.MPI/3.3.10-gompi-2023a
FFTW.MPI/3.3.10-gompi-2023b
FFTW.MPI/3.3.10-gompi-2024a
FFTW/3.3.10-GCC-11.3.0
FFTW/3.3.10-GCC-12.3.0
FFTW/3.3.10-GCC-13.2.0
FFTW/3.3.10-GCC-13.3.0
FFmpeg/4.4.2-GCCcore-11.3.0
FFmpeg/6.0-GCCcore-12.3.0
FFmpeg/6.0-GCCcore-13.2.0
FFmpeg/7.0.2-GCCcore-13.3.0
FLAC/1.3.4-GCCcore-11.3.0
FLAC/1.4.2-GCCcore-12.3.0
FLAC/1.4.3-GCCcore-13.2.0
FLAC/1.4.3-GCCcore-13.3.0
FLASH/2.2.00-GCCcore-13.3.0
FastANI/1.33-GCC-11.3.0
FastANI/1.34-GCC-13.2.0
FastK/1.1.0-GCC-12.3.0
FastME/2.1.6.3-GCC-12.3.0
FastQC/0.11.9-Java-11
FastQC/0.12.1-Java-11
FastTree/2.1.11-GCCcore-11.3.0
FastTree/2.1.11-GCCcore-12.3.0
FastTree/2.1.11-GCCcore-13.2.0
Fastaq/3.17.0-GCC-12.3.0
Filtlong/0.2.1-GCC-12.3.0
Fiona/1.8.21-foss-2022a
Fiona/1.9.5-foss-2023a
Fiona/1.10.1-foss-2024a
Flask/2.2.2-GCCcore-11.3.0
Flask/2.3.3-GCCcore-12.3.0
Flask/3.0.3-GCCcore-13.3.0
FlexiBLAS/3.2.0-GCC-11.3.0
FlexiBLAS/3.3.1-GCC-12.3.0
FlexiBLAS/3.3.1-GCC-13.2.0
FlexiBLAS/3.4.4-GCC-13.3.0
Flye/2.9.5-GCC-13.3.0
FreeSurfer/7.4.1-GCCcore-12.3.0
FreeXL/2.0.0-GCCcore-12.3.0
FriBidi/1.0.12-GCCcore-11.3.0
FriBidi/1.0.12-GCCcore-12.3.0
FriBidi/1.0.13-GCCcore-13.2.0
FriBidi/1.0.15-GCCcore-13.3.0
GATK/4.3.0.0-GCCcore-11.3.0-Java-11
GATK/4.3.0.0-GCCcore-12.3.0-Java-11
GATK/4.4.0.0-GCCcore-12.3.0-Java-17
GATK/4.6.0.0-GCCcore-13.2.0-Java-17
GCC/11.3.0
GCC/12.3.0
GCC/13.2.0
GCC/13.3.0
GCCcore/11.3.0
GCCcore/12.3.0
GCCcore/13.2.0
GCCcore/13.3.0
GDAL/3.5.0-foss-2022a
GDAL/3.7.1-foss-2023a
GDAL/3.9.0-foss-2023b
GDAL/3.10.0-foss-2024a
GDGraph/1.56-GCCcore-11.3.0
GDRCopy/2.3-GCCcore-11.3.0
GDRCopy/2.3.1-GCCcore-12.3.0
GDRCopy/2.4-GCCcore-13.2.0
GDRCopy/2.4.1-GCCcore-13.3.0
GEM/1.5.1-foss-2023a
GEMMA/0.98.5-gfbf-2023b
GEOS/3.10.3-GCC-11.3.0
GEOS/3.12.0-GCC-12.3.0
GEOS/3.12.1-GCC-13.2.0
GEOS/3.12.2-GCC-13.3.0
GLM/1.0.1-GCCcore-13.3.0
GLPK/5.0-GCCcore-11.3.0
GLPK/5.0-GCCcore-12.3.0
GLPK/5.0-GCCcore-13.2.0
GLPK/5.0-GCCcore-13.3.0
GLib/2.72.1-GCCcore-11.3.0
GLib/2.77.1-GCCcore-12.3.0
GLib/2.78.1-GCCcore-13.2.0
GLib/2.80.4-GCCcore-13.3.0
GLibmm/2.77.0-GCCcore-12.3.0
GMAP-GSNAP/2023-02-17-GCC-11.3.0
GMAP-GSNAP/2023-04-20-GCC-12.3.0
GMAP-GSNAP/2024-09-18-GCC-13.3.0
GMP/6.2.1-GCCcore-11.3.0
GMP/6.2.1-GCCcore-12.3.0
GMP/6.3.0-GCCcore-13.2.0
GMP/6.3.0-GCCcore-13.3.0
GOATOOLS/1.4.5-foss-2023a
GOATOOLS/1.4.12-foss-2024a
GObject-Introspection/1.72.0-GCCcore-11.3.0
GObject-Introspection/1.76.1-GCCcore-12.3.0
GObject-Introspection/1.78.1-GCCcore-13.2.0
GObject-Introspection/1.80.1-GCCcore-13.3.0
GRASS/8.4.0-foss-2023a
GROMACS/2024.4-foss-2023b-CUDA-12.4.0-PLUMED-2.9.2
GSL/2.7-GCC-11.3.0
GSL/2.7-GCC-12.3.0
GSL/2.7-GCC-13.2.0
GSL/2.8-GCC-13.3.0
GST-plugins-bad/1.20.2-GCC-11.3.0
GST-plugins-bad/1.22.5-GCC-12.3.0
GST-plugins-base/1.20.2-GCC-11.3.0
GST-plugins-base/1.22.5-GCC-12.3.0
GStreamer/1.20.2-GCC-11.3.0
GStreamer/1.22.5-GCC-12.3.0
GStreamer/1.24.8-GCC-13.3.0
GTDB-Tk/2.3.2-foss-2022a
GTK2/2.24.33-GCCcore-11.3.0
GTK3/3.24.37-GCCcore-12.3.0
GTK3/3.24.39-GCCcore-13.2.0
GTK4/4.7.0-GCC-11.3.0
GTK4/4.13.1-GCC-12.3.0
GTS/0.7.6-GCCcore-12.3.0
GTS/0.7.6-GCCcore-13.3.0
Gdk-Pixbuf/2.42.8-GCCcore-11.3.0
Gdk-Pixbuf/2.42.10-GCCcore-12.3.0
Gdk-Pixbuf/2.42.10-GCCcore-13.2.0
Gdk-Pixbuf/2.42.11-GCCcore-13.3.0
GeneMark-ET/4.72-GCCcore-12.3.0
GeneMark-ETP/1.0.0-GCC-12.3.0
Genome/05012020-foss-2022a
GenomeThreader/1.7.3-Linux_x86_64-64bit
GenomeTools/1.6.2-GCC-11.3.0
GetOrganelle/1.7.7.1-foss-2023a
Ghostscript/9.56.1-GCCcore-11.3.0
Ghostscript/10.01.2-GCCcore-12.3.0
Ghostscript/10.02.1-GCCcore-13.2.0
Ghostscript/10.03.1-GCCcore-13.3.0
GitPython/3.1.40-GCCcore-12.3.0
GitPython/3.1.43-GCCcore-13.3.0
Giza/1.4.1-GCCcore-13.2.0
GlimmerHMM/3.0.4c-GCC-12.3.0
GlobalArrays/5.8.2-intel-2023a
GlobalArrays/5.8.2-intel-2024a
GnuTLS/3.7.8-GCCcore-12.3.0
Go/1.22.1
Graphene/1.10.8-GCCcore-11.3.0
Graphene/1.10.8-GCCcore-12.3.0
Graphviz/8.1.0-GCCcore-12.3.0
Graphviz/12.2.0-GCCcore-13.3.0
Greenlet/2.0.2-GCCcore-11.3.0
Greenlet/3.0.3-GCCcore-13.2.0
Greenlet/3.1.1-GCCcore-13.3.0
Guile/3.0.9-GCCcore-12.3.0
Gurobi/11.0.2-GCCcore-12.3.0
HDF/4.2.15-GCCcore-11.3.0
HDF/4.2.16-2-GCCcore-12.3.0
HDF/4.2.16-2-GCCcore-13.2.0
HDF/4.3.0-GCCcore-13.3.0
HDF5/1.12.2-gompi-2022a
HDF5/1.14.0-gompi-2023a
HDF5/1.14.0-iimpi-2023a
HDF5/1.14.3-gompi-2023b
HDF5/1.14.5-gompi-2024a
HH-suite/3.3.0-gompi-2023a
HISAT2/2.2.1-gompi-2022a
HISAT2/2.2.1-gompi-2023a
HMMER/3.3.2-gompi-2022a
HMMER/3.4-gompi-2023a
HMMER/3.4-gompi-2023b
HMMER/3.4-gompi-2024a
HTSeq/2.0.7-foss-2023a
HTSlib/1.15.1-GCC-11.3.0
HTSlib/1.18-GCC-12.3.0
HTSlib/1.19.1-GCC-13.2.0
HTSlib/1.21-GCC-13.3.0
HarfBuzz/4.2.1-GCCcore-11.3.0
HarfBuzz/5.3.1-GCCcore-12.3.0
HarfBuzz/8.2.2-GCCcore-13.2.0
HarfBuzz/9.0.0-GCCcore-13.3.0
Highway/1.0.4-GCCcore-12.3.0
Homer/5.1-foss-2023a-R-4.3.2
Hybpiper/2.3.2-foss-2024a
Hypre/2.29.0-foss-2023a
Hypre/2.32.0-foss-2024a
ICU/71.1-GCCcore-11.3.0
ICU/73.2-GCCcore-12.3.0
ICU/74.1-GCCcore-13.2.0
ICU/75.1-GCCcore-13.3.0
IDBA-UD/1.1.3-GCCcore-12.3.0
IGV/2.19.1-Java-21
IPython/8.14.0-GCCcore-12.3.0
IPython/8.17.2-GCCcore-13.2.0
IPython/8.27.0-GCCcore-13.3.0
IPython/8.28.0-GCCcore-13.3.0
IQ-TREE/2.3.6-gompi-2023a
IRkernel/1.3.2-gfbf-2023a-R-4.3.2
ISA-L/2.30.0-GCCcore-12.3.0
ISA-L/2.31.0-GCCcore-13.2.0
ISA-L/2.31.0-GCCcore-13.3.0
ImageMagick/7.1.0-37-GCCcore-11.3.0
ImageMagick/7.1.1-15-GCCcore-12.3.0
ImageMagick/7.1.1-34-GCCcore-13.2.0
ImageMagick/7.1.1-38-GCCcore-13.3.0
Imath/3.1.5-GCCcore-11.3.0
Imath/3.1.7-GCCcore-12.3.0
Imath/3.1.9-GCCcore-13.2.0
Imath/3.1.11-GCCcore-13.3.0
Infernal/1.1.4-gompi-2022a
Infernal/1.1.5-foss-2023a
Infernal/1.1.5-gompi-2023a
InterProScan/5.73-104.0-GCC-13.3.0
IsoQuant/3.5.0-foss-2023a
IsoQuant/3.7.0-foss-2023a
IsoSeq/4.3.0
JAGS/4.3.2-foss-2023a
JAGS/4.3.2-foss-2024a
Jansson/2.14-GCC-12.3.0
JasPer/2.0.33-GCCcore-11.3.0
JasPer/4.0.0-GCCcore-12.3.0
JasPer/4.0.0-GCCcore-13.2.0
JasPer/4.2.4-GCCcore-13.3.0
Java/1.8.0_241
Java/1.8.0_311 (1.8)
Java/11.0.20 (11)
Java/17.0.6 (17)
Java/21.0.2
Java/21.0.5 (D:21)
Jellyfish/2.3.0-GCC-11.3.0
Jellyfish/2.3.1-GCC-12.3.0
JsonCpp/1.9.5-GCCcore-12.3.0
JsonCpp/1.9.5-GCCcore-13.3.0
Judy/1.0.5-GCCcore-11.3.0
Judy/1.0.5-GCCcore-12.3.0
Judy/1.0.5-GCCcore-13.3.0
Juicebox/2.20.00
Juicer/1.6-foss-2022a-CUDA-11.7.0-juicebox-1.9.9
Julia/1.11.3-linux-x86_64
JupyterLab/4.0.5-GCCcore-12.3.0
JupyterLab/4.2.0-GCCcore-13.2.0
JupyterLab/4.2.5-GCCcore-13.3.0
JupyterNotebook/7.0.2-GCCcore-12.3.0
JupyterNotebook/7.2.0-GCCcore-13.2.0
JupyterNotebook/7.2.3-GCCcore-13.3.0
KMC/3.2.4-GCC-13.3.0
Kaleido/0.2.1-GCCcore-12.3.0
Kaleido/0.2.1-GCCcore-13.3.0
Kalign/3.4.0-GCCcore-12.3.0
Kent_tools/442-GCC-11.3.0
Kent_tools/468-GCC-12.3.0
Kraken2/2.1.3-gompi-2023a
LAME/3.100-GCCcore-11.3.0
LAME/3.100-GCCcore-12.3.0
LAME/3.100-GCCcore-13.2.0
LAME/3.100-GCCcore-13.3.0
LAMMPS/29Aug2024-foss-2023b-kokkos
LASTZ/1.04.22-GCC-12.3.0
LDC/1.24.0-x86_64
LDC/1.30.0-GCCcore-11.3.0
LERC/4.0.0-GCCcore-12.3.0
LERC/4.0.0-GCCcore-13.2.0
LERC/4.0.0-GCCcore-13.3.0
LLVM/14.0.3-GCCcore-11.3.0
LLVM/14.0.6-GCCcore-12.3.0-llvmlite
LLVM/14.0.6-GCCcore-13.3.0-llvmlite
LLVM/16.0.6-GCCcore-12.3.0
LLVM/16.0.6-GCCcore-13.2.0
LLVM/18.1.8-GCCcore-13.3.0-minimal
LMDB/0.9.29-GCCcore-11.3.0
LMDB/0.9.31-GCCcore-12.3.0
LMDB/0.9.31-GCCcore-13.2.0
LMDB/0.9.31-GCCcore-13.3.0
LSD2/2.4.1-GCCcore-12.3.0
LTR_retriever/2.9.0-foss-2022a
LZO/2.10-GCCcore-11.3.0
LZO/2.10-GCCcore-12.3.0
LZO/2.10-GCCcore-13.3.0
Leptonica/1.85.0-GCCcore-13.3.0
LevelDB/1.22-GCCcore-12.3.0
LibSoup/3.6.1-GCC-12.3.0
LibTIFF/4.3.0-GCCcore-11.3.0
LibTIFF/4.5.0-GCCcore-12.3.0
LibTIFF/4.6.0-GCCcore-13.2.0
LibTIFF/4.6.0-GCCcore-13.3.0
Libint/2.7.2-GCC-12.3.0-lmax-6-cp2k
LiftOn/1.0.5-foss-2023a
LightGBM/4.5.0-foss-2023a-CUDA-12.1.1
LittleCMS/2.13.1-GCCcore-11.3.0
LittleCMS/2.15-GCCcore-12.3.0
LittleCMS/2.15-GCCcore-13.2.0
LittleCMS/2.16-GCCcore-13.3.0
Lua/5.4.4-GCCcore-11.3.0
Lua/5.4.6-GCCcore-12.3.0
Lua/5.4.7-GCCcore-13.3.0
M4/1.4.18
M4/1.4.19-GCCcore-11.3.0
M4/1.4.19-GCCcore-12.3.0
M4/1.4.19-GCCcore-13.2.0
M4/1.4.19-GCCcore-13.3.0
M4/1.4.19
MACS2/2.2.9.1-foss-2023a
MACS3/3.0.1-gfbf-2023a
MAFFT/7.505-GCC-11.3.0-with-extensions
MAFFT/7.520-GCC-12.3.0-with-extensions
MAFFT/7.526-GCC-13.2.0-with-extensions
MAFFT/7.526-GCC-13.3.0-with-extensions
MCL/22.282-GCCcore-12.3.0
MCR/R2018a
MCR/R2023a
MCR/R2023b.9
MDI/1.4.29-gompi-2023b
MDTraj/1.9.7-foss-2022a
MDTraj/1.9.9-gfbf-2023a
MEGA/10.0.5
MEGA/11.0.13
MEGAHIT/1.2.9-GCCcore-13.3.0
MEME/5.5.7-gompi-2023b
METABOLIC/4.0-foss-2022a
METIS/5.1.0-GCCcore-11.3.0
METIS/5.1.0-GCCcore-12.3.0
METIS/5.1.0-GCCcore-13.2.0
METIS/5.1.0-GCCcore-13.3.0
MMseqs2/14-7e284-gompi-2022a
MMseqs2/14-7e284-gompi-2023a
MPC/1.3.1-GCCcore-12.3.0
MPC/1.3.1-GCCcore-13.2.0
MPC/1.3.1-GCCcore-13.3.0
MPFR/4.1.0-GCCcore-11.3.0
MPFR/4.2.0-GCCcore-12.3.0
MPFR/4.2.1-GCCcore-13.2.0
MPFR/4.2.1-GCCcore-13.3.0
MSTmap/20240122-GCC-12.3.0
MUMPS/5.6.1-foss-2023a-metis
MUMPS/5.7.2-foss-2024a-metis
MUMmer/4.0.0rc1-GCCcore-11.3.0
MUMmer/4.0.0rc1-GCCcore-12.3.0
MUSCLE/5.1.0-GCCcore-12.3.0
Mako/1.2.0-GCCcore-11.3.0
Mako/1.2.4-GCCcore-12.3.0
Mako/1.2.4-GCCcore-13.2.0
Mako/1.3.5-GCCcore-13.3.0
Mamba/23.11.0-0
MariaDB/10.9.3-GCC-11.3.0
MariaDB/11.6.0-GCC-12.3.0
Markdown/3.6-GCCcore-13.2.0
Mash/2.3-GCC-11.3.0
Mash/2.3-GCC-13.2.0
Mash/2.3-GCC-13.3.0
Maven/3.6.3
Maven/3.9.7
Medusa/1.6-foss-2023a-Python-3.11.3-Java-11
Mesa/22.0.3-GCCcore-11.3.0
Mesa/23.1.4-GCCcore-12.3.0
Mesa/23.1.9-GCCcore-13.2.0
Mesa/24.1.3-GCCcore-13.3.0
Meson/0.58.2-GCCcore-12.3.0
Meson/0.62.1-GCCcore-11.3.0
Meson/0.64.0-GCCcore-12.3.0
Meson/1.1.1-GCCcore-12.3.0
Meson/1.2.3-GCCcore-13.2.0
Meson/1.3.1-GCCcore-12.3.0
Meson/1.4.0-GCCcore-13.3.0
MetaBAT/2.17-GCC-13.3.0
MetaEuk/6-GCC-11.3.0
MetaEuk/6-GCC-12.3.0
Micromamba/2.3.0
Miniconda3/23.5.2-0
Miniforge3/24.11.3-0
MitoFinder/1.4.2-foss-2023a-Python-2.7.18
Molden/7.3-GCCcore-13.3.0
Monocle3/1.3.1-foss-2023a-R-4.3.2
MrBayes/3.2.7-gompi-2023a
MultiQC/1.28-foss-2024a
NAMD/2.14-foss-2023a-mpi
NASM/2.15.05-GCCcore-11.3.0
NASM/2.16.01-GCCcore-12.3.0
NASM/2.16.01-GCCcore-13.2.0
NASM/2.16.03-GCCcore-13.3.0
NCCL/2.12.12-GCCcore-11.3.0-CUDA-11.7.0
NCCL/2.18.3-GCCcore-11.3.0-CUDA-12.1.1
NCCL/2.18.3-GCCcore-12.3.0-CUDA-12.1.1
NCCL/2.20.5-GCCcore-13.2.0-CUDA-12.4.0
NCCL/2.22.3-GCCcore-13.3.0-CUDA-12.6.0
NCO/5.1.9-foss-2023a
NGS/3.0.1-GCCcore-12.3.0-Java-11
NLTK/3.8.1-foss-2023a
NLopt/2.7.1-GCCcore-11.3.0
NLopt/2.7.1-GCCcore-12.3.0
NLopt/2.7.1-GCCcore-13.2.0
NLopt/2.7.1-GCCcore-13.3.0
NSPR/4.34-GCCcore-11.3.0
NSPR/4.35-GCCcore-12.3.0
NSPR/4.35-GCCcore-13.2.0
NSPR/4.35-GCCcore-13.3.0
NSS/3.79-GCCcore-11.3.0
NSS/3.89.1-GCCcore-12.3.0
NSS/3.94-GCCcore-13.2.0
NSS/3.104-GCCcore-13.3.0
NanoPlot/1.43.0-foss-2023a
NextDenovo/2.5.2-20240510-GCCcore-12.3.0
Nextflow/24.10.2
Nextflow/25.04.2
Nextflow/25.04.4
NiBabel/4.0.2-foss-2022a
NiBabel/5.2.0-gfbf-2023a
NiBabel/5.3.2-gfbf-2023b
Ninja/1.10.2-GCCcore-11.3.0
Ninja/1.10.2-GCCcore-12.3.0
Ninja/1.11.1-GCCcore-12.3.0
Ninja/1.11.1-GCCcore-13.2.0
Ninja/1.12.1-GCCcore-13.3.0
ONNX/1.15.0-gfbf-2023a
ONNX/1.17.0-gfbf-2023b
ORCA/6.0.1-gompi-2023b-avx2
OpenBLAS/0.3.20-GCC-11.3.0
OpenBLAS/0.3.23-GCC-12.3.0
OpenBLAS/0.3.24-GCC-13.2.0
OpenBLAS/0.3.27-GCC-13.3.0
OpenBabel/3.1.1-gompi-2023a
OpenCV/4.6.0-foss-2022a-contrib
OpenCV/4.8.1-foss-2023a-contrib
OpenCV/4.8.1-foss-2023a-CUDA-12.1.1-contrib
OpenEXR/3.1.5-GCCcore-11.3.0
OpenEXR/3.1.7-GCCcore-12.3.0
OpenEXR/3.2.0-GCCcore-13.2.0
OpenEXR/3.2.4-GCCcore-13.3.0
OpenJPEG/2.5.0-GCCcore-11.3.0
OpenJPEG/2.5.0-GCCcore-12.3.0
OpenJPEG/2.5.0-GCCcore-13.2.0
OpenJPEG/2.5.2-GCCcore-13.3.0
OpenMM/8.0.0-foss-2023a-CUDA-12.1.1
OpenMM/8.0.0-foss-2023a
OpenMMTools/0.23.1-foss-2023a
OpenMPI/4.1.4-GCC-11.3.0
OpenMPI/4.1.5-GCC-12.3.0
OpenMPI/4.1.6-GCC-13.2.0
OpenMPI/5.0.3-GCC-13.3.0
OpenMolcas/23.06-intel-2023a
OpenPGM/5.2.122-GCCcore-12.3.0
OpenPGM/5.2.122-GCCcore-13.2.0
OpenPGM/5.2.122-GCCcore-13.3.0
OpenSSL/1.1
OpenSSL/3
Optax/0.2.2-gfbf-2023a-CUDA-12.1.1
Optax/0.2.2-gfbf-2023a
Optuna/3.1.0-foss-2022a
Optuna/3.5.0-foss-2023a
Optuna/3.6.1-foss-2023b
OrthoFinder/2.5.5-foss-2023a
Osi/0.108.11-GCC-13.3.0
PAML/4.9j-GCCcore-11.3.0
PAML/4.10.5-GCCcore-11.3.0
PASA/2.5.3-foss-2023a
PCAngsd/1.2-gfbf-2023a
PCRE/8.45-GCCcore-11.3.0
PCRE/8.45-GCCcore-12.3.0
PCRE/8.45-GCCcore-13.2.0
PCRE/8.45-GCCcore-13.3.0
PCRE2/10.40-GCCcore-11.3.0
PCRE2/10.42-GCCcore-12.3.0
PCRE2/10.42-GCCcore-13.2.0
PCRE2/10.43-GCCcore-13.3.0
PDAL/2.8.2-foss-2023a
PDM/2.12.4-GCCcore-12.3.0
PETSc/3.20.3-foss-2023a
PHYLIP/3.697-GCC-12.3.0
PICRUSt2/2.6.2-foss-2023a
PLUMED/2.9.2-foss-2023b
PLY/3.11-GCCcore-12.3.0
PLY/3.11-GCCcore-13.3.0
PMIx/4.1.2-GCCcore-11.3.0
PMIx/4.2.4-GCCcore-12.3.0
PMIx/4.2.6-GCCcore-13.2.0
PMIx/5.0.2-GCCcore-13.3.0
PRANK/170427-GCC-12.3.0
PROJ/9.0.0-GCCcore-11.3.0
PROJ/9.2.0-GCCcore-12.3.0
PROJ/9.3.1-GCCcore-13.2.0
PROJ/9.4.1-GCCcore-13.3.0
PRRTE/3.0.5-GCCcore-13.3.0
PSI4/1.9.1-foss-2023a
Pandoc/3.6.2
Pango/1.50.7-GCCcore-11.3.0
Pango/1.50.14-GCCcore-12.3.0
Pango/1.51.0-GCCcore-13.2.0
Pango/1.54.0-GCCcore-13.3.0
ParMETIS/4.0.3-gompi-2023a
ParaView/5.11.2-foss-2023a
Parallel-Hashmap/1.3.12-GCCcore-12.3.0
Parsnp/2.1.1-foss-2023b
Perl-bundle-CPAN/5.36.1-GCCcore-12.3.0
Perl-bundle-CPAN/5.38.0-GCCcore-13.2.0
Perl-bundle-CPAN/5.38.2-GCCcore-13.3.0
Perl/5.34.1-GCCcore-11.3.0-minimal
Perl/5.34.1-GCCcore-11.3.0
Perl/5.36.1-GCCcore-12.3.0
Perl/5.38.0-GCCcore-13.2.0
Perl/5.38.0
Perl/5.38.2-GCCcore-13.3.0
PhiPack/2016.06.14-GCC-13.2.0
Phobius/1.01-GCCcore-12.3.0-Perl-5.36.1
Phobius/1.01-GCCcore-13.2.0-Perl-5.38.0
Phobius/1.01-GCCcore-13.3.0-Perl-5.38.2
Phrap/0.990329-foss-2022a
Phred/0.071220.c-foss-2022a
PhyloNet/3.8.3-Java-1.8.0_241
Pillow-SIMD/9.5.0-GCCcore-12.3.0
Pillow-SIMD/10.4.0-GCCcore-13.3.0
Pillow/9.1.1-GCCcore-11.3.0
Pillow/10.0.0-GCCcore-12.3.0
Pillow/10.2.0-GCCcore-13.2.0
Pillow/10.4.0-GCCcore-13.3.0
Pint/0.23-GCCcore-12.3.0
Pint/0.24-GCCcore-13.2.0
Pint/0.24.4-GCCcore-13.3.0
PnetCDF/1.12.3-gompi-2022a
Porechop/0.2.4-20240119-GCCcore-12.3.0
PostgreSQL/16.1-GCCcore-12.3.0
PostgreSQL/16.1-GCCcore-13.2.0
PostgreSQL/16.4-GCCcore-13.3.0
ProtHint/2.6.0-foss-2023a
Proteinortho/6.3.2-gompi-2023a
PuLP/2.8.0-foss-2024a
PyBioLib/1.1.988-GCCcore-11.3.0
PyBioLib/1.1.2250-GCCcore-12.3.0
PyCairo/1.21.0-GCCcore-11.3.0
PyCairo/1.25.0-GCCcore-12.3.0
PyCairo/1.25.1-GCCcore-13.2.0
PyGObject/3.42.1-GCCcore-11.3.0
PyGObject/3.46.0-GCCcore-12.3.0
PyHMMER/0.10.6-gompi-2023a
PyHMMER/0.10.15-gompi-2023b
PyOpenCL/2023.1.4-foss-2023a-CUDA-12.1.1
PyQt-builder/1.15.4-GCCcore-12.3.0
PyQt-builder/1.18.1-GCCcore-13.3.0
PyQt5/5.15.10-GCCcore-12.3.0
PyQt5/5.15.11-GCCcore-13.3.0
PyRosetta/4.release-384-gompi-2022a
PyRosetta/4.release-387-gompi-2023a
PyTables/3.10.2-foss-2024a
PyTorch-Geometric/2.1.0-foss-2022a-PyTorch-1.12.0
PyTorch-Lightning/2.2.1-foss-2023a-CUDA-12.1.1
PyTorch/1.12.0-foss-2022a
PyTorch/2.1.2-foss-2023a-CUDA-12.1.1
PyTorch/2.1.2-foss-2023a
PyTorch/2.1.2-foss-2023b
PyWavelets/1.8.0-foss-2024a
PyYAML/6.0-GCCcore-11.3.0
PyYAML/6.0-GCCcore-12.3.0
PyYAML/6.0.1-GCCcore-13.2.0
PyYAML/6.0.2-GCCcore-13.3.0
PyZMQ/25.1.1-GCCcore-12.3.0
PyZMQ/25.1.2-GCCcore-13.2.0
PyZMQ/26.2.0-GCCcore-13.3.0
Pysam/0.8.4-GCC-13.3.0-Python-2.7.18
Pysam/0.19.1-GCC-11.3.0
Pysam/0.22.0-GCC-12.3.0
Pysam/0.22.1-GCC-13.3.0
Python-bundle-PyPI/2023.06-GCCcore-12.3.0
Python-bundle-PyPI/2023.10-GCCcore-13.2.0
Python-bundle-PyPI/2024.06-GCCcore-13.3.0
Python/2.7.18-GCCcore-11.3.0-bare
Python/2.7.18-GCCcore-12.3.0
Python/2.7.18-GCCcore-13.3.0
Python/3.10.4-GCCcore-11.3.0-bare
Python/3.10.4-GCCcore-11.3.0
Python/3.11.3-GCCcore-12.3.0
Python/3.11.5-GCCcore-13.2.0
Python/3.12.3-GCCcore-13.3.0
QCA/2.3.9-GCCcore-12.3.0
QGIS/3.40.2-foss-2023a
QIIME2/2025.4-amplicon
QScintilla/2.14.1-GCCcore-12.3.0
QUAST/5.2.0-gfbf-2023b
Qhull/2020.2-GCCcore-11.3.0
Qhull/2020.2-GCCcore-12.3.0
Qhull/2020.2-GCCcore-13.2.0
Qhull/2020.2-GCCcore-13.3.0
Qt5/5.15.5-GCCcore-11.3.0
Qt5/5.15.10-GCCcore-12.3.0
Qt5/5.15.13-GCCcore-13.2.0
Qt5/5.15.16-GCCcore-13.3.0
Qt5Webkit/5.212.0-alpha4-GCCcore-12.3.0
Qt6/6.7.2-GCCcore-13.3.0
QtKeychain/0.14.3-GCCcore-12.3.0
Qualimap/2.3-foss-2023a-R-4.3.2
QuantumESPRESSO/7.4-foss-2024a
Qwt/6.3.0-GCCcore-12.3.0
R-bundle-Bioconductor/3.18-foss-2023a-R-4.3.2
R-bundle-Bioconductor/3.19-foss-2023b-R-4.4.1
R-bundle-Bioconductor/3.20-foss-2024a-R-4.4.2
R-bundle-CRAN/2023.12-foss-2023a
R-bundle-CRAN/2024.06-foss-2023b
R-bundle-CRAN/2024.11-foss-2024a
R/4.2.1-foss-2022a
R/4.3.1-foss-2022a
R/4.3.2-gfbf-2023a
R/4.4.1-gfbf-2023b
R/4.4.2-gfbf-2024a
RAxML-NG/1.2.2-GCC-13.2.0
RAxML/8.2.13-gompi-2023b-avx2
RDFlib/6.2.0-GCCcore-11.3.0
RDFlib/7.0.0-GCCcore-12.3.0
RDKit/2024.03.3-foss-2023a
RE2/2023-08-01-GCCcore-12.3.0
RE2/2024-03-01-GCCcore-13.2.0
RE2/2024-07-02-GCCcore-13.3.0
RECON/1.08-GCC-11.3.0
RMBlast/2.13.0-gompi-2022a
RMBlast/2.14.1-gompi-2023a
RSEM/1.3.3-foss-2022a
RSEM/1.3.3-foss-2023a
RSeQC/5.0.1-foss-2023a
RSeQC/5.0.4-foss-2023a
Racon/1.5.0-GCCcore-12.3.0
Racon/1.5.0-GCCcore-13.3.0
RagTag/2.1.0-foss-2022a
RapidJSON/1.1.0-20230928-GCCcore-12.3.0
RapidJSON/1.1.0-20240409-GCCcore-13.2.0
RapidJSON/1.1.0-20240815-GCCcore-13.3.0
Redis/7.0.8-GCC-11.3.0
Redis/7.2.3-GCCcore-12.3.0
Redis/7.2.4-GCCcore-13.2.0
Redis/7.4.1-GCCcore-13.3.0
RepeatMasker/4.1.4-foss-2022a
RepeatMasker/4.1.5-foss-2022a
RepeatMasker/4.1.7-p1-foss-2023a
RepeatMasker/4.1.9-foss-2023a
RepeatModeler/2.0.4-foss-2022a
RepeatScout/1.0.6-GCC-11.3.0
Rosetta/3.14-intel-2022a-release371
Ruby/3.0.3-GCCcore-12.3.0
Ruby/3.3.0-GCCcore-12.3.0
Rust/1.60.0-GCCcore-11.3.0
Rust/1.70.0-GCCcore-12.3.0
Rust/1.73.0-GCCcore-13.2.0
Rust/1.75.0-GCCcore-12.3.0
Rust/1.76.0-GCCcore-13.2.0
Rust/1.78.0-GCCcore-13.3.0
SAMtools/1.16.1-GCC-11.3.0
SAMtools/1.18-GCC-12.3.0
SAMtools/1.21-GCC-13.3.0
SCOTCH/7.0.3-gompi-2023a
SCOTCH/7.0.6-gompi-2024a
SCons/4.4.0-GCCcore-11.3.0
SCons/4.4.0-GCCcore-12.3.0
SCons/4.5.2-GCCcore-12.3.0
SCons/4.6.0-GCCcore-13.2.0
SCons/4.9.0-GCCcore-13.3.0
SDL2/2.28.2-GCCcore-12.3.0
SDL2/2.28.5-GCCcore-13.2.0
SDL2/2.30.6-GCCcore-13.3.0
SEPP/4.5.5-foss-2023a
SHAP/0.43.0-foss-2023a
SIP/6.8.1-GCCcore-12.3.0
SIP/6.10.0-GCCcore-13.3.0
SNAP-HMM/20221022-GCC-12.3.0
SPAdes/3.15.4-GCC-12.3.0
SPAdes/4.1.0-GCC-13.3.0
SQLAlchemy/2.0.25-GCCcore-12.3.0
SQLAlchemy/2.0.29-GCCcore-13.2.0
SQLAlchemy/2.0.36-GCCcore-13.3.0
SQLite/3.38.3-GCCcore-11.3.0
SQLite/3.42.0-GCCcore-12.3.0
SQLite/3.43.1-GCCcore-13.2.0
SQLite/3.45.3-GCCcore-13.3.0
SRA-Toolkit/3.0.3-gompi-2022a
SRA-Toolkit/3.0.10-gompi-2023a
SRA-Toolkit/3.2.0-gompi-2024a
SSW/1.1-GCCcore-12.3.0
SSW/1.1-GCCcore-13.3.0
STAR/2.7.10b-GCC-11.3.0
STAR/2.7.11a-GCC-12.3.0
STAR/2.7.11b-GCC-13.3.0
SWIG/4.1.1-GCCcore-12.3.0
SWIG/4.1.1-GCCcore-13.2.0
SWIG/4.2.1-GCCcore-13.3.0
Sabre/2013-09-28-GCC-13.3.0
Safetensors/0.4.3-gfbf-2023a
Safetensors/0.4.4-gfbf-2023b
Salmon/1.9.0-GCC-11.3.0
Salmon/1.10.3-GCC-12.3.0
Sambamba/0.8.2-GCC-11.3.0
ScaFaCoS/1.0.4-foss-2023a
ScaFaCoS/1.0.4-foss-2023b
ScaLAPACK/2.2.0-gompi-2022a-fb
ScaLAPACK/2.2.0-gompi-2023a-fb
ScaLAPACK/2.2.0-gompi-2023b-fb
ScaLAPACK/2.2.0-gompi-2024a-fb
Scalene/1.5.26-GCCcore-12.3.0
Scalene/1.5.35-GCCcore-13.2.0
SciPy-bundle/2022.05-foss-2022a
SciPy-bundle/2023.07-gfbf-2023a
SciPy-bundle/2023.11-gfbf-2023b
SciPy-bundle/2024.05-gfbf-2024a
Seaborn/0.12.1-foss-2022a
Seaborn/0.13.2-gfbf-2023a
Seaborn/0.13.2-gfbf-2024a
SentencePiece/0.2.0-GCC-13.2.0
SeqKit/2.8.2
SeqLib/1.2.0-GCC-12.3.0
SeqLib/1.2.0-GCC-13.3.0
Seurat/5.1.0-foss-2023a-R-4.3.2
Shapely/1.8.2-foss-2022a
Shapely/2.0.1-gfbf-2023a
Shapely/2.0.6-gfbf-2024a
SignalP/6.0h-foss-2023a-fast
Sniffles/2.4-GCC-13.3.0
SoX/14.4.2-GCCcore-13.3.0
SortMeRNA/4.3.6
Stacks/2.68-foss-2023a
Statistics-R/0.34-foss-2023a
StringTie/2.2.3-GCC-12.3.0
StringTie/3.0.0-GCC-13.3.0
Structure/2.3.4-GCC-12.3.0
Structure_threader/1.3.10-foss-2023a
Subread/2.0.6-GCC-12.3.0
SuiteSparse/5.13.0-foss-2022a-METIS-5.1.0
SuiteSparse/7.1.0-foss-2023a
SuiteSparse/7.10.1-foss-2024a
SuperLU/5.3.0-foss-2022a
SuperLU/6.0.1-foss-2023b
SuperLU_DIST/8.1.2-foss-2023a
Szip/2.1.1-GCCcore-11.3.0
Szip/2.1.1-GCCcore-12.3.0
Szip/2.1.1-GCCcore-13.2.0
Szip/2.1.1-GCCcore-13.3.0
TRF/4.09.1-GCCcore-11.3.0
TRF/4.09.1-GCCcore-12.3.0
TSEBRA/1.1.2.5-gfbf-2023a
TWL-NINJA/0.98-cluster_only-GCC-11.3.0
Tcl/8.6.12-GCCcore-11.3.0
Tcl/8.6.13-GCCcore-12.3.0
Tcl/8.6.13-GCCcore-13.2.0
Tcl/8.6.14-GCCcore-13.3.0
TensorFlow/2.13.0-foss-2023a
TensorFlow/2.15.1-foss-2023a-CUDA-12.1.1
Tk/8.6.12-GCCcore-11.3.0
Tk/8.6.13-GCCcore-12.3.0
Tk/8.6.13-GCCcore-13.2.0
Tk/8.6.14-GCCcore-13.3.0
Tkinter/3.10.4-GCCcore-11.3.0
Tkinter/3.11.3-GCCcore-12.3.0
Tkinter/3.11.5-GCCcore-13.2.0
Tkinter/3.12.3-GCCcore-13.3.0
TransDecoder/5.5.0-GCC-11.3.0
TransDecoder/5.7.1-GCC-12.3.0
Transformers/4.39.3-gfbf-2023a
Transformers/4.44.0-gfbf-2023b
TreeMix/1.13-GCC-12.3.0
Trim_Galore/0.6.10-GCCcore-12.3.0
Trimmomatic/0.39-Java-11
Trinity/2.15.1-foss-2022a
Trinity/2.15.2-foss-2023a
Trinotate/4.0.1-foss-2022a
Trinotate/4.0.2-foss-2023a
UCC/1.0.0-GCCcore-11.3.0
UCC/1.2.0-GCCcore-12.3.0
UCC/1.2.0-GCCcore-13.2.0
UCC/1.3.0-GCCcore-13.3.0
UCX-CUDA/1.12.1-GCCcore-11.3.0-CUDA-11.7.0
UCX-CUDA/1.14.1-GCCcore-11.3.0-CUDA-12.1.1
UCX-CUDA/1.14.1-GCCcore-12.3.0-CUDA-12.1.1
UCX-CUDA/1.15.0-GCCcore-13.2.0-CUDA-12.4.0
UCX-CUDA/1.16.0-GCCcore-13.3.0-CUDA-12.6.0
UCX/1.12.1-GCCcore-11.3.0
UCX/1.14.1-GCCcore-11.3.0
UCX/1.14.1-GCCcore-12.3.0
UCX/1.15.0-GCCcore-13.2.0
UCX/1.16.0-GCCcore-13.3.0
UDUNITS/2.2.28-GCCcore-11.3.0
UDUNITS/2.2.28-GCCcore-12.3.0
UDUNITS/2.2.28-GCCcore-13.2.0
UDUNITS/2.2.28-GCCcore-13.3.0
UMI-tools/1.1.4-foss-2023a
USEARCH/11.0.667-i86linux32
UnZip/6.0-GCCcore-11.3.0
UnZip/6.0-GCCcore-12.3.0
UnZip/6.0-GCCcore-13.2.0
UnZip/6.0-GCCcore-13.3.0
Unicycler/0.5.1-gompi-2024a
Unidecode/1.3.6-GCCcore-11.3.0
VCFtools/0.1.16-GCC-12.3.0
VCFtools/0.1.16-GCC-13.2.0
VCFtools/0.1.16-GCC-13.3.0
VEP/113.0-GCC-12.3.0
VSEARCH/2.25.0-GCC-12.3.0
VSEARCH/2.30.0-GCC-13.3.0
VTK/9.3.0-foss-2023b
Velvet/1.2.10-GCC-13.3.0-mt-kmer_191
Voro++/0.4.6-GCCcore-13.2.0
WFA2/2.3.4-GCCcore-12.3.0
WFA2/2.3.4-GCCcore-13.3.0
WPS/4.5-foss-2022a-dmpar
WPS/4.6.0-foss-2024a-dmpar
WRF-Chem-KPP/4.5.2-foss-2022a-dmpar
WRF-Chem-KPP/4.6.1-foss-2024a-dmpar
WRF/4.5.2-foss-2022a-dmpar
WRF/4.6.1-foss-2024a-dmpar
WU-Blast/2.2.6-GCC-11.3.0
Wayland/1.20.0-GCCcore-11.3.0
Wayland/1.22.0-GCCcore-12.3.0
Wayland/1.22.0-GCCcore-13.2.0
Wayland/1.23.0-GCCcore-13.3.0
Waylandpp/1.0.0-GCCcore-12.3.0
WebKitGTK+/2.41.4-foss-2023a
WhatsHap/2.2-foss-2023a
X11/20220504-GCCcore-11.3.0
X11/20230603-GCCcore-12.3.0
X11/20231019-GCCcore-13.2.0
X11/20240607-GCCcore-13.3.0
XML-Compile/1.63-GCCcore-13.2.0
XML-LibXML/2.0207-GCCcore-11.3.0
XML-LibXML/2.0209-GCCcore-12.3.0
XML-LibXML/2.0210-GCCcore-13.2.0
XML-LibXML/2.0210-GCCcore-13.3.0
XZ/5.2.5-GCCcore-11.3.0
XZ/5.4.2-GCCcore-12.3.0
XZ/5.4.4-GCCcore-13.2.0
XZ/5.4.5-GCCcore-13.3.0
Xerces-C++/3.2.4-GCCcore-12.3.0
Xerces-C++/3.2.5-GCCcore-13.2.0
Xerces-C++/3.2.5-GCCcore-13.3.0
XlsxWriter/3.0.8-GCCcore-11.3.0
XlsxWriter/3.1.3-GCCcore-12.3.0
XlsxWriter/3.2.0-GCCcore-13.3.0
Xvfb/21.1.3-GCCcore-11.3.0
Xvfb/21.1.8-GCCcore-12.3.0
Xvfb/21.1.9-GCCcore-13.2.0
Xvfb/21.1.14-GCCcore-13.3.0
YACS/0.1.8-GCCcore-11.3.0
YACS/0.1.8-GCCcore-12.3.0
YaHS/1.2.2-foss-2024a
Yasm/1.3.0-GCCcore-11.3.0
Yasm/1.3.0-GCCcore-12.3.0
Yasm/1.3.0-GCCcore-13.2.0
Yasm/1.3.0-GCCcore-13.3.0
Z3/4.10.2-GCCcore-11.3.0
Z3/4.12.2-GCCcore-12.3.0
Z3/4.13.0-GCCcore-13.2.0
Z3/4.13.0-GCCcore-13.3.0
ZeroMQ/4.3.4-GCCcore-12.3.0
ZeroMQ/4.3.5-GCCcore-13.2.0
ZeroMQ/4.3.5-GCCcore-13.3.0
Zip/3.0-GCCcore-12.3.0
Zip/3.0-GCCcore-13.3.0
absl-py/2.1.0-GCCcore-12.3.0
accelerate/1.0.1-foss-2023b
aiohttp/3.8.5-GCCcore-12.3.0
aiohttp/3.10.10-GCCcore-13.3.0
alsa-lib/1.2.11-GCCcore-13.3.0
ancestryinfer/20230111-foss-2024a-Python-2.7.18
angsd/0.940-GCC-12.3.0
anndata/0.10.5.post1-foss-2023a
ant/1.10.12-Java-11
ant/1.10.14-Java-11
any2fasta/0.4.2-GCCcore-12.3.0
archspec/0.2.2-GCCcore-13.2.0
argtable/2.13-GCCcore-12.3.0
aria2/1.36.0-GCCcore-12.3.0
arpack-ng/3.8.0-foss-2022a
arpack-ng/3.9.0-foss-2023a
arpack-ng/3.9.0-foss-2023b
arpack-ng/3.9.1-foss-2024a
arrow-R/14.0.1-foss-2023a-R-4.3.2
arrow-R/16.1.0-foss-2023b-R-4.4.1
arrow-R/17.0.0.1-foss-2024a-R-4.4.2
assimp/5.4.3-GCCcore-13.3.0
at-spi2-atk/2.38.0-GCCcore-11.3.0
at-spi2-atk/2.38.0-GCCcore-12.3.0
at-spi2-atk/2.38.0-GCCcore-13.2.0
at-spi2-core/2.44.1-GCCcore-11.3.0
at-spi2-core/2.49.91-GCCcore-12.3.0
at-spi2-core/2.50.0-GCCcore-13.2.0
attr/2.5.2-GCCcore-13.3.0
attrdict3/2.0.2-GCCcore-12.3.0
awscli/2.17.54-GCCcore-13.2.0
bakta/1.11
barrnap/0.9-gompi-2023a
bcbio-gff/0.7.1-foss-2024a
bcl2fastq2/2.20.0-GCC-12.3.0
beagle-lib/4.0.1-GCC-12.3.0-CUDA-12.1.1
binutils/2.35
binutils/2.38-GCCcore-11.3.0
binutils/2.38
binutils/2.39
binutils/2.40-GCCcore-12.3.0
binutils/2.40-GCCcore-13.2.0
binutils/2.40
binutils/2.42-GCCcore-13.3.0
binutils/2.42
bioawk/1.0-GCC-12.3.0
biom-format/2.1.15-foss-2023a
biom-format/2.1.16-foss-2024a
bitsandbytes/0.43.3-foss-2023a
bokeh/2.4.3-foss-2022a
bokeh/3.2.2-foss-2023a
bokeh/3.6.0-gfbf-2024a
boto3/1.28.70-GCCcore-12.3.0
boto3/1.35.36-GCCcore-13.3.0
breseq/0.38.1-foss-2023a
btllib/1.7.0-GCC-12.3.0
bwidget/1.10.1-GCCcore-13.3.0
bx-python/0.10.0-foss-2023a
bzip2/1.0.8-GCCcore-11.3.0
bzip2/1.0.8-GCCcore-12.3.0
bzip2/1.0.8-GCCcore-13.2.0
bzip2/1.0.8-GCCcore-13.3.0
c-ares/1.19.1-GCCcore-12.3.0
cURL/7.83.0-GCCcore-11.3.0
cURL/8.0.1-GCCcore-12.3.0
cURL/8.3.0-GCCcore-13.2.0
cURL/8.7.1-GCCcore-13.3.0
cairo/1.17.4-GCCcore-11.3.0
cairo/1.17.8-GCCcore-12.3.0
cairo/1.18.0-GCCcore-13.2.0
cairo/1.18.0-GCCcore-13.3.0
canu/2.3-GCCcore-13.3.0-Java-11
ccache/4.9-GCCcore-12.3.0
ccache/4.10.2-GCCcore-13.3.0
cffi/1.15.1-GCCcore-12.3.0
cffi/1.15.1-GCCcore-13.2.0
cffi/1.16.0-GCCcore-13.3.0
cfour/2.1-intel-2023a-serial
cimfomfa/22.273-GCCcore-12.3.0
cloudpickle/3.0.0-GCCcore-12.3.0
compleasm/0.2.6-foss-2023a
coverage/5.5-GCCcore-13.3.0-Python-2.7.18
coverage/7.4.4-GCCcore-13.2.0
cpio/2.14-GCCcore-11.3.0
cpio/2.15-GCCcore-12.3.0
cpio/2.15-GCCcore-13.3.0
cppy/1.2.1-GCCcore-11.3.0
cppy/1.2.1-GCCcore-12.3.0
cppy/1.2.1-GCCcore-13.2.0
cppy/1.2.1-GCCcore-13.3.0
crb-blast/0.6.9-GCC-12.3.0
cryptography/41.0.1-GCCcore-12.3.0
cryptography/41.0.5-GCCcore-13.2.0
cryptography/42.0.8-GCCcore-13.3.0
cuDNN/8.4.1.50-CUDA-11.7.0
cuDNN/8.9.2.26-CUDA-12.1.1
cuDNN/9.5.0.50-CUDA-12.6.0
cutadapt/4.9-GCCcore-12.3.0
cutadapt/4.9-GCCcore-13.3.0
dRep/3.4.2-foss-2022a
dask/2022.10.0-foss-2022a
dask/2023.9.2-foss-2023a
dask/2024.9.1-gfbf-2024a
dcm2niix/1.0.20241211-GCCcore-13.3.0
deepTools/3.5.5-gfbf-2023a
deepdiff/6.7.1-GCCcore-12.3.0
dill/0.3.7-GCCcore-12.3.0
dm-haiku/0.0.12-foss-2023a-CUDA-12.1.1
dm-tree/0.1.8-GCCcore-12.3.0
double-conversion/3.2.0-GCCcore-11.3.0
double-conversion/3.3.0-GCCcore-12.3.0
double-conversion/3.3.0-GCCcore-13.2.0
double-conversion/3.3.0-GCCcore-13.3.0
draco/1.5.7-foss-2023a
ecBuild/3.8.5-GCCcore-13.3.0
ecCodes/2.38.3-gompi-2024a
edlib/1.3.9-GCC-12.3.0
edlib/1.3.9.post1-GCC-13.3.0
eggnog-mapper/2.1.9-foss-2022a
eggnog-mapper/2.1.12-foss-2023a
einops/0.7.0-GCCcore-12.3.0
elfutils/0.187-GCCcore-11.3.0
elfutils/0.189-GCCcore-12.3.0
elfutils/0.191-GCCcore-13.3.0
enchant-2/2.6.5-GCCcore-12.3.0
eta/0.9.7-GCCcore-13.3.0-Python-2.7.18
exiv2/0.28.0-GCCcore-12.3.0
expat/2.4.8-GCCcore-11.3.0
expat/2.5.0-GCCcore-12.3.0
expat/2.5.0-GCCcore-13.2.0
expat/2.6.2-GCCcore-13.3.0
expecttest/0.1.3-GCCcore-11.3.0
expecttest/0.1.5-GCCcore-12.3.0
expecttest/0.2.1-GCCcore-13.2.0
fastahack/1.0.0-GCCcore-12.3.0
fastahack/1.0.0-GCCcore-13.3.0
fastp/0.23.4-GCC-13.2.0
fermi-lite/20190320-GCCcore-12.3.0
fermi-lite/20190320-GCCcore-13.3.0
ffnvcodec/11.1.5.2
ffnvcodec/12.0.16.0
ffnvcodec/12.1.14.0
ffnvcodec/12.2.72.0
file/5.43-GCCcore-11.3.0
file/5.43-GCCcore-12.3.0
file/5.46-GCCcore-13.3.0
filevercmp/20191210-GCCcore-12.3.0
filevercmp/20191210-GCCcore-13.3.0
flair/2.0.0-foss-2023a-Python-3.11.3
flatbuffers-python/23.5.26-GCCcore-12.3.0
flatbuffers/23.5.26-GCCcore-12.3.0
flex/2.6.4-GCCcore-11.3.0
flex/2.6.4-GCCcore-12.3.0
flex/2.6.4-GCCcore-13.2.0
flex/2.6.4-GCCcore-13.3.0
flex/2.6.4
flit/3.9.0-GCCcore-12.3.0
flit/3.9.0-GCCcore-13.2.0
flit/3.9.0-GCCcore-13.3.0
fontconfig/2.14.0-GCCcore-11.3.0
fontconfig/2.14.2-GCCcore-12.3.0
fontconfig/2.14.2-GCCcore-13.2.0
fontconfig/2.15.0-GCCcore-13.3.0
fonttools/4.53.1-GCCcore-13.3.0
foss/2022a
foss/2023a
foss/2023b
foss/2024a
freebayes/1.3.7-gfbf-2023a-R-4.3.2
freebayes/1.3.7-gfbf-2024a-R-4.4.2
freeglut/3.4.0-GCCcore-12.3.0
freeglut/3.6.0-GCCcore-13.3.0
freetype/2.12.1-GCCcore-11.3.0
freetype/2.13.0-GCCcore-12.3.0
freetype/2.13.2-GCCcore-13.2.0
freetype/2.13.2-GCCcore-13.3.0
fsom/20151117-GCCcore-12.3.0
fsom/20151117-GCCcore-13.3.0
funannotate/1.8.17-foss-2023a
g2clib/1.7.0-GCCcore-11.3.0
g2lib/3.2.0-GCCcore-11.3.0
gaussian/09-AMD-SSE4a
gaussian/16-AVX2
gc/8.2.4-GCCcore-12.3.0
genomepy/0.16.1-foss-2023a
geopandas/0.12.2-foss-2022a
geopandas/0.14.2-foss-2023a
geopandas/1.0.1-foss-2024a
gettext/0.21-GCCcore-11.3.0
gettext/0.21
gettext/0.21.1-GCCcore-12.3.0
gettext/0.21.1
gettext/0.22-GCCcore-13.2.0
gettext/0.22
gettext/0.22.5-GCCcore-13.3.0
gettext/0.22.5
gfbf/2023a
gfbf/2023b
gfbf/2024a
gffread/0.12.7-GCCcore-12.3.0
gffutils/0.13-foss-2023a
gflags/2.2.2-GCCcore-12.3.0
gflags/2.2.2-GCCcore-13.3.0
giflib/5.2.1-GCCcore-11.3.0
giflib/5.2.1-GCCcore-12.3.0
giflib/5.2.1-GCCcore-13.2.0
giflib/5.2.1-GCCcore-13.3.0
git-lfs/3.5.1
git/2.36.0-GCCcore-11.3.0-nodocs
git/2.41.0-GCCcore-12.3.0-nodocs
git/2.42.0-GCCcore-13.2.0
git/2.45.1-GCCcore-13.3.0
glew/2.2.0-GCCcore-12.3.0-osmesa
glib-networking/2.72.1-GCCcore-12.3.0
glog/0.6.0-GCCcore-12.3.0
gmpy2/2.1.5-GCC-12.3.0
gmpy2/2.1.5-GCC-13.2.0
gmpy2/2.2.0-GCCcore-13.3.0
gnuplot/5.4.4-GCCcore-11.3.0
gnuplot/5.4.8-GCCcore-12.3.0
gnuplot/6.0.1-GCCcore-13.3.0
gompi/2022a
gompi/2023a
gompi/2023b
gompi/2024a
googletest/1.11.0-GCCcore-11.3.0
googletest/1.13.0-GCCcore-12.3.0
googletest/1.14.0-GCCcore-13.2.0
googletest/1.15.2-GCCcore-13.3.0
gperf/3.1-GCCcore-11.3.0
gperf/3.1-GCCcore-12.3.0
gperf/3.1-GCCcore-13.2.0
gperf/3.1-GCCcore-13.3.0
gperftools/2.13-GCCcore-13.2.0
gperftools/2.16-GCCcore-13.3.0
graphite2/1.3.14-GCCcore-11.3.0
graphite2/1.3.14-GCCcore-12.3.0
graphite2/1.3.14-GCCcore-13.2.0
graphite2/1.3.14-GCCcore-13.3.0
graphviz-python/0.20.1-GCCcore-12.3.0
groff/1.22.4-GCCcore-11.3.0
groff/1.22.4-GCCcore-12.3.0
groff/1.23.0-GCCcore-13.2.0
groff/1.23.0-GCCcore-13.3.0
grpcio/1.57.0-GCCcore-12.3.0
grpcio/1.67.1-GCCcore-13.2.0
gzip/1.12-GCCcore-11.3.0
gzip/1.12-GCCcore-12.3.0
gzip/1.13-GCCcore-13.2.0
gzip/1.13-GCCcore-13.3.0
h5py/3.7.0-foss-2022a
h5py/3.9.0-foss-2023a
h5py/3.12.1-foss-2024a
harvest-tools/1.3-GCCcore-13.2.0
hatch-jupyter-builder/0.9.1-GCCcore-13.2.0
hatch-jupyter-builder/0.9.1-GCCcore-13.3.0
hatchling/1.18.0-GCCcore-12.3.0
hatchling/1.18.0-GCCcore-13.2.0
hatchling/1.24.2-GCCcore-13.3.0
help2man/1.49.2-GCCcore-11.3.0
help2man/1.49.3-GCCcore-12.3.0
help2man/1.49.3-GCCcore-13.2.0
help2man/1.49.3-GCCcore-13.3.0
hifiasm/0.24.0-GCCcore-12.3.0
hiredis/1.2.0-GCCcore-12.3.0
hiredis/1.2.0-GCCcore-13.3.0
hmmlearn/0.3.0-gfbf-2023a
hunspell/1.7.2-GCCcore-12.3.0
hwloc/2.7.1-GCCcore-11.3.0
hwloc/2.9.1-GCCcore-12.3.0
hwloc/2.9.2-GCCcore-13.2.0
hwloc/2.10.0-GCCcore-13.3.0
hypothesis/6.46.7-GCCcore-11.3.0
hypothesis/6.82.0-GCCcore-12.3.0
hypothesis/6.90.0-GCCcore-13.2.0
hypothesis/6.103.1-GCCcore-13.3.0
igraph/0.10.10-foss-2023a
iimpi/2022a
iimpi/2023a
iimpi/2023b
iimpi/2024a
imageio/2.22.2-foss-2022a
imageio/2.33.1-gfbf-2023a
imageio/2.36.1-gfbf-2024a
imgaug/0.4.0-foss-2022a
imgaug/0.4.1-foss-2023a
imkl-FFTW/2022.1.0-iimpi-2022a
imkl-FFTW/2023.1.0-iimpi-2023a
imkl-FFTW/2023.2.0-iimpi-2023b
imkl-FFTW/2024.2.0-iimpi-2024a
imkl/2022.1.0
imkl/2023.1.0
imkl/2023.2.0
imkl/2024.2.0
impi/2021.6.0-intel-compilers-2022.1.0
impi/2021.9.0-intel-compilers-2023.1.0
impi/2021.10.0-intel-compilers-2023.2.1
impi/2021.13.0-intel-compilers-2024.2.0
inih/57-GCCcore-12.3.0
intel-compilers/2022.1.0
intel-compilers/2023.1.0
intel-compilers/2023.2.1
intel-compilers/2024.2.0
intel/2022a
intel/2023a
intel/2023b
intel/2024a
intervaltree-python/3.1.0-GCCcore-12.3.0
intervaltree/0.1-GCCcore-12.3.0
intervaltree/0.1-GCCcore-13.3.0
intltool/0.51.0-GCCcore-11.3.0
intltool/0.51.0-GCCcore-12.3.0
intltool/0.51.0-GCCcore-13.2.0
intltool/0.51.0-GCCcore-13.3.0
jax/0.4.25-gfbf-2023a-CUDA-12.1.1
jax/0.4.25-gfbf-2023a
jbigkit/2.1-GCCcore-11.3.0
jbigkit/2.1-GCCcore-12.3.0
jbigkit/2.1-GCCcore-13.2.0
jbigkit/2.1-GCCcore-13.3.0
jedi/0.19.0-GCCcore-12.3.0
jedi/0.19.1-GCCcore-13.2.0
jedi/0.19.1-GCCcore-13.3.0
jemalloc/5.2.1-GCCcore-11.3.0
jemalloc/5.3.0-GCCcore-11.3.0
jemalloc/5.3.0-GCCcore-12.3.0
jemalloc/5.3.0-GCCcore-13.3.0
jq/1.6-GCCcore-12.3.0
json-c/0.16-GCCcore-12.3.0
json-c/0.17-GCCcore-13.2.0
json-c/0.17-GCCcore-13.3.0
jupyter-server/2.7.2-GCCcore-12.3.0
jupyter-server/2.14.0-GCCcore-13.2.0
jupyter-server/2.14.2-GCCcore-13.3.0
kallisto/0.48.0-gompi-2022a
kallisto/0.51.1-gompi-2023a
kallisto/0.51.1-gompi-2023b
kim-api/2.3.0-GCC-13.2.0
kineto/0.4.0-GCC-12.3.0
libGLU/9.0.2-GCCcore-11.3.0
libGLU/9.0.3-GCCcore-12.3.0
libGLU/9.0.3-GCCcore-13.2.0
libGLU/9.0.3-GCCcore-13.3.0
libaec/1.1.3-GCCcore-13.3.0
libaio/0.3.112-GCCcore-11.3.0
libaio/0.3.113-GCCcore-12.3.0
libaio/0.3.113-GCCcore-13.3.0
libarchive/3.6.1-GCCcore-11.3.0
libarchive/3.6.2-GCCcore-12.3.0
libarchive/3.7.2-GCCcore-13.2.0
libarchive/3.7.4-GCCcore-13.3.0
libavif/1.0.4-GCCcore-12.3.0
libcerf/2.1-GCCcore-11.3.0
libcerf/2.3-GCCcore-12.3.0
libcerf/2.4-GCCcore-13.3.0
libdap/3.20.11-GCCcore-12.3.0
libdap/3.21.0-27-GCCcore-13.3.0
libdeflate/1.10-GCCcore-11.3.0
libdeflate/1.18-GCCcore-12.3.0
libdeflate/1.19-GCCcore-13.2.0
libdeflate/1.20-GCCcore-13.3.0
libdrm/2.4.110-GCCcore-11.3.0
libdrm/2.4.115-GCCcore-12.3.0
libdrm/2.4.117-GCCcore-13.2.0
libdrm/2.4.122-GCCcore-13.3.0
libepoxy/1.5.10-GCCcore-11.3.0
libepoxy/1.5.10-GCCcore-12.3.0
libepoxy/1.5.10-GCCcore-13.2.0
libev/4.33-GCC-12.3.0
libevent/2.1.12-GCCcore-11.3.0
libevent/2.1.12-GCCcore-12.3.0
libevent/2.1.12-GCCcore-13.2.0
libevent/2.1.12-GCCcore-13.3.0
libfabric/1.15.1-GCCcore-11.3.0
libfabric/1.18.0-GCCcore-12.3.0
libfabric/1.19.0-GCCcore-13.2.0
libfabric/1.21.0-GCCcore-13.3.0
libffi/3.4.2-GCCcore-11.3.0
libffi/3.4.4-GCCcore-12.3.0
libffi/3.4.4-GCCcore-13.2.0
libffi/3.4.5-GCCcore-13.3.0
libgcrypt/1.10.3-GCCcore-12.3.0
libgd/2.3.3-GCCcore-11.3.0
libgd/2.3.3-GCCcore-12.3.0
libgd/2.3.3-GCCcore-13.3.0
libgeotiff/1.7.1-GCCcore-11.3.0
libgeotiff/1.7.1-GCCcore-12.3.0
libgeotiff/1.7.3-GCCcore-13.2.0
libgeotiff/1.7.3-GCCcore-13.3.0
libgit2/1.4.3-GCCcore-11.3.0
libgit2/1.7.1-GCCcore-12.3.0
libgit2/1.7.2-GCCcore-13.2.0
libgit2/1.8.1-GCCcore-13.3.0
libglvnd/1.4.0-GCCcore-11.3.0
libglvnd/1.6.0-GCCcore-12.3.0
libglvnd/1.7.0-GCCcore-13.2.0
libglvnd/1.7.0-GCCcore-13.3.0
libgpg-error/1.48-GCCcore-12.3.0
libharu/2.3.0-GCCcore-11.3.0
libharu/2.3.0-GCCcore-12.3.0
libiconv/1.17-GCCcore-11.3.0
libiconv/1.17-GCCcore-12.3.0
libiconv/1.17-GCCcore-13.2.0
libiconv/1.17-GCCcore-13.3.0
libidn2/2.3.2-GCCcore-11.3.0
libidn2/2.3.7-GCCcore-12.3.0
libidn2/2.3.8-GCCcore-13.3.0
libjpeg-turbo/2.1.3-GCCcore-11.3.0
libjpeg-turbo/2.1.5.1-GCCcore-12.3.0
libjpeg-turbo/3.0.1-GCCcore-13.2.0
libjpeg-turbo/3.0.1-GCCcore-13.3.0
libmad/0.15.1b-GCCcore-13.3.0
libnsl/2.0.0-GCCcore-11.3.0
libnsl/2.0.1-GCCcore-12.3.0
libnsl/2.0.1-GCCcore-13.3.0
libogg/1.3.5-GCCcore-11.3.0
libogg/1.3.5-GCCcore-12.3.0
libogg/1.3.5-GCCcore-13.2.0
libogg/1.3.5-GCCcore-13.3.0
libopus/1.3.1-GCCcore-11.3.0
libopus/1.4-GCCcore-12.3.0
libopus/1.5.2-GCCcore-13.2.0
libopus/1.5.2-GCCcore-13.3.0
libpciaccess/0.16-GCCcore-11.3.0
libpciaccess/0.17-GCCcore-12.3.0
libpciaccess/0.17-GCCcore-13.2.0
libpciaccess/0.18.1-GCCcore-13.3.0
libpng/1.6.37-GCCcore-11.3.0
libpng/1.6.39-GCCcore-12.3.0
libpng/1.6.40-GCCcore-13.2.0
libpng/1.6.43-GCCcore-13.3.0
libpsl/0.21.5-GCCcore-12.3.0
libreadline/8.1.2-GCCcore-11.3.0
libreadline/8.2-GCCcore-12.3.0
libreadline/8.2-GCCcore-13.2.0
libreadline/8.2-GCCcore-13.3.0
librttopo/1.1.0-GCC-12.3.0
libsigc++/3.6.0-GCCcore-12.3.0
libsndfile/1.1.0-GCCcore-11.3.0
libsndfile/1.2.2-GCCcore-12.3.0
libsndfile/1.2.2-GCCcore-13.2.0
libsndfile/1.2.2-GCCcore-13.3.0
libsodium/1.0.18-GCCcore-12.3.0
libsodium/1.0.19-GCCcore-13.2.0
libsodium/1.0.20-GCCcore-13.3.0
libspatialindex/1.9.3-GCCcore-12.3.0
libspatialite/5.1.0-GCC-12.3.0
libtasn1/4.19.0-GCCcore-12.3.0
libtirpc/1.3.2-GCCcore-11.3.0
libtirpc/1.3.3-GCCcore-12.3.0
libtirpc/1.3.4-GCCcore-13.2.0
libtirpc/1.3.5-GCCcore-13.3.0
libtool/2.4.7-GCCcore-11.3.0
libtool/2.4.7-GCCcore-12.3.0
libtool/2.4.7-GCCcore-13.2.0
libtool/2.4.7-GCCcore-13.3.0
libtool/2.4.7
libunistring/1.1-GCCcore-12.3.0
libunwind/1.6.2-GCCcore-11.3.0
libunwind/1.6.2-GCCcore-12.3.0
libunwind/1.6.2-GCCcore-13.2.0
libunwind/1.8.1-GCCcore-13.3.0
libvorbis/1.3.7-GCCcore-11.3.0
libvorbis/1.3.7-GCCcore-12.3.0
libvorbis/1.3.7-GCCcore-13.2.0
libvorbis/1.3.7-GCCcore-13.3.0
libwebp/1.2.4-GCCcore-11.3.0
libwebp/1.3.1-GCCcore-12.3.0
libwebp/1.3.2-GCCcore-13.2.0
libwebp/1.4.0-GCCcore-13.3.0
libwpe/1.16.0-GCCcore-12.3.0
libxc/6.2.2-GCC-12.3.0
libxc/6.2.2-GCC-13.2.0
libxc/6.2.2-GCC-13.3.0
libxml2/2.9.13-GCCcore-11.3.0
libxml2/2.11.4-GCCcore-12.3.0
libxml2/2.11.5-GCCcore-13.2.0
libxml2/2.12.7-GCCcore-13.3.0
libxslt/1.1.34-GCCcore-11.3.0
libxslt/1.1.38-GCCcore-12.3.0
libxslt/1.1.38-GCCcore-13.2.0
libxslt/1.1.42-GCCcore-13.3.0
libyaml/0.2.5-GCCcore-11.3.0
libyaml/0.2.5-GCCcore-12.3.0
libyaml/0.2.5-GCCcore-13.2.0
libyaml/0.2.5-GCCcore-13.3.0
libzip/1.10.1-GCCcore-12.3.0
lima/2.13.0
lit/18.1.2-GCCcore-12.3.0
lit/18.1.7-GCCcore-11.3.0
lit/18.1.7-GCCcore-13.2.0
lit/18.1.8-GCCcore-13.3.0
lpsolve/5.5.2.11-GCC-11.3.0
lpsolve/5.5.2.11-GCC-12.3.0
lpsolve/5.5.2.11-GCC-13.3.0
lxml/4.9.2-GCCcore-12.3.0
lxml/4.9.3-GCCcore-13.2.0
lxml/5.3.0-GCCcore-13.3.0
lz4/1.9.3-GCCcore-11.3.0
lz4/1.9.4-GCCcore-12.3.0
lz4/1.9.4-GCCcore-13.2.0
lz4/1.9.4-GCCcore-13.3.0
maeparser/1.3.1-gompi-2023a
magma/2.7.2-foss-2023a-CUDA-12.1.1
make/4.3-GCCcore-11.3.0
make/4.4.1-GCCcore-12.3.0
make/4.4.1-GCCcore-13.2.0
make/4.4.1-GCCcore-13.3.0
makedepend/1.0.6-GCCcore-11.3.0
makedepend/1.0.7-GCCcore-11.3.0
makedepend/1.0.9-GCCcore-13.3.0
makeinfo/6.8-GCCcore-11.3.0
makeinfo/7.0.3-GCCcore-12.3.0
makeinfo/7.1-GCCcore-13.3.0
manta/1.6.0
matlab/2023b
matlab/2024a
matplotlib/3.5.2-foss-2022a
matplotlib/3.7.2-gfbf-2023a
matplotlib/3.8.2-gfbf-2023b
matplotlib/3.9.2-gfbf-2024a
maturin/1.1.0-GCCcore-12.3.0
maturin/1.3.1-GCCcore-13.2.0
maturin/1.4.0-GCCcore-12.3.0-Rust-1.75.0
maturin/1.5.0-GCCcore-13.2.0-Rust-1.76.0
maturin/1.6.0-GCCcore-13.3.0
medaka/1.12.1-foss-2023a
meson-python/0.13.2-GCCcore-12.3.0
meson-python/0.15.0-GCCcore-12.3.0
meson-python/0.15.0-GCCcore-13.2.0
meson-python/0.16.0-GCCcore-13.3.0
methlypy/1.4.7-foss-2023a
mgltools/1.5.7
miniasm/0.3-20191007-GCCcore-12.3.0
minimap2/2.24-GCCcore-11.3.0
minimap2/2.26-GCCcore-12.3.0
minimap2/2.28-GCCcore-13.2.0
miniprot/0.13-GCCcore-12.3.0
minizip/1.1-GCCcore-12.3.0
ml_dtypes/0.3.2-gfbf-2023a
mm-common/1.0.6-GCCcore-12.3.0
modkit/0.3.3-GCCcore-12.3.0
modkit/0.4.1-GCCcore-13.3.0
motif/2.3.8-GCCcore-12.3.0
motif/2.3.8-GCCcore-13.3.0
mpi4py/3.1.4-gompi-2023a
mpi4py/3.1.5-gompi-2023b
mpi4py/4.0.1-gompi-2024a
mrcfile/1.5.4-gfbf-2024a
multichoose/1.0.3-GCCcore-12.3.0
multichoose/1.0.3-GCCcore-13.3.0
mygene/3.2.2-foss-2023a
nanoget/1.19.3-foss-2023a
nanomath/1.4.0-foss-2023a
ncbi-FCS/0.5.5-GCCcore-13.3.0
ncbi-genome-download/0.3.3-GCCcore-12.3.0
ncbi-vdb/3.0.2-gompi-2022a
ncbi-vdb/3.0.10-gompi-2023a
ncbi-vdb/3.2.0-gompi-2024a
ncurses/6.2
ncurses/6.3-GCCcore-11.3.0
ncurses/6.3
ncurses/6.4-GCCcore-12.3.0
ncurses/6.4-GCCcore-13.2.0
ncurses/6.4
ncurses/6.5-GCCcore-13.3.0
ncurses/6.5
ncview/2.1.11-gompi-2024a
netCDF-C++4/4.3.1-gompi-2022a
netCDF-C++4/4.3.1-gompi-2023a
netCDF-C++4/4.3.1-gompi-2023b
netCDF-Fortran/4.6.0-gompi-2022a
netCDF-Fortran/4.6.1-gompi-2023a
netCDF-Fortran/4.6.1-gompi-2024a
netCDF/4.9.0-gompi-2022a
netCDF/4.9.2-gompi-2023a
netCDF/4.9.2-gompi-2023b
netCDF/4.9.2-gompi-2024a
netcdf4-python/1.6.4-foss-2023a
netcdf4-python/1.7.1.post2-foss-2024a
nettle/3.8-GCCcore-11.3.0
nettle/3.9.1-GCCcore-12.3.0
nettle/3.9.1-GCCcore-13.2.0
nettle/3.10-GCCcore-13.3.0
networkx/2.6.3-foss-2023a
networkx/2.8.4-foss-2022a
networkx/3.1-gfbf-2023a
networkx/3.2.1-gfbf-2023b
networkx/3.4.2-gfbf-2024a
newick_utils/1.6
nghttp2/1.58.0-GCC-12.3.0
nghttp3/1.3.0-GCCcore-12.3.0
ngsutils/0.5.9-GCC-13.3.0-Python-2.7.18
ngtcp2/1.2.0-GCC-12.3.0
nlohmann_json/3.10.5-GCCcore-11.3.0
nlohmann_json/3.11.2-GCCcore-12.3.0
nlohmann_json/3.11.3-GCCcore-13.2.0
nlohmann_json/3.11.3-GCCcore-13.3.0
nodejs/16.15.1-GCCcore-11.3.0
nodejs/18.17.1-GCCcore-12.3.0
nodejs/20.9.0-GCCcore-13.2.0
nodejs/20.13.1-GCCcore-13.3.0
nsync/1.26.0-GCCcore-12.3.0
numactl/2.0.14-GCCcore-11.3.0
numactl/2.0.16-GCCcore-12.3.0
numactl/2.0.16-GCCcore-13.2.0
numactl/2.0.18-GCCcore-13.3.0
numba/0.56.4-foss-2022a
numba/0.58.1-foss-2023a
numba/0.60.0-foss-2024a
numexpr/2.9.0-foss-2023a
numpy/1.16.6-foss-2023a-Python-2.7.18
nvtop/2.0.2-GCCcore-11.3.0
ont-fast5-api/4.1.2-foss-2023a
openpyxl/3.1.2-GCCcore-12.3.0
openpyxl/3.1.5-GCCcore-13.3.0
orfipy/0.0.4
p11-kit/0.25.3-GCCcore-12.3.0
p7zip/17.05-GCCcore-13.3.0
pairtools/1.1.2-gfbf-2024a
parallel-fastq-dump/0.6.7-gompi-2022a
parallel-fastq-dump/0.6.7-gompi-2023a
parallel/20230722-GCCcore-12.3.0
parallel/20240322-GCCcore-13.2.0
parallel/20240722-GCCcore-13.3.0
parasail/2.6.2-GCC-12.3.0
patchelf/0.15.0-GCCcore-11.3.0
patchelf/0.18.0-GCCcore-12.3.0
patchelf/0.18.0-GCCcore-13.2.0
patchelf/0.18.0-GCCcore-13.3.0
pblat/2.5.1-foss-2023a
phyx/1.3-foss-2022a
picard/2.25.1-Java-11
picard/3.3.0-Java-17
pigz/2.8-GCCcore-12.3.0
pigz/2.8-GCCcore-13.3.0
pixman/0.40.0-GCCcore-11.3.0
pixman/0.42.2-GCCcore-12.3.0
pixman/0.42.2-GCCcore-13.2.0
pixman/0.43.4-GCCcore-13.3.0
pkg-config/0.29.2-GCCcore-11.3.0
pkg-config/0.29.2-GCCcore-12.3.0
pkgconf/1.8.0-GCCcore-11.3.0
pkgconf/1.8.0
pkgconf/1.9.5-GCCcore-12.3.0
pkgconf/2.0.3-GCCcore-13.2.0
pkgconf/2.2.0-GCCcore-13.3.0
pkgconfig/1.5.5-GCCcore-11.3.0-python
pkgconfig/1.5.5-GCCcore-12.3.0-python
plotly.py/5.12.0-GCCcore-11.3.0
plotly.py/5.16.0-GCCcore-12.3.0
plotly.py/5.18.0-GCCcore-13.2.0
plotly.py/5.24.1-GCCcore-13.3.0
pocl/1.8-GCC-11.3.0
pocl/4.0-GCC-12.3.0-CUDA-12.1.1
pocl/4.0-GCC-12.3.0
poetry/1.5.1-GCCcore-12.3.0
poetry/1.6.1-GCCcore-13.2.0
poetry/1.7.1-GCCcore-12.3.0
poetry/1.8.3-GCCcore-13.3.0
poppler/23.09.0-GCC-12.3.0
pplacer/1.1.alpha19
pretty-yaml/24.7.0-GCCcore-12.3.0
prodigal/2.6.3-GCCcore-11.3.0
prodigal/2.6.3-GCCcore-12.3.0
prokka/1.14.5-gompi-2023a
protobuf-python/3.19.4-GCCcore-11.3.0
protobuf-python/4.24.0-GCCcore-12.3.0
protobuf-python/4.25.3-GCCcore-13.2.0
protobuf/3.19.4-GCCcore-11.3.0
protobuf/24.0-GCCcore-12.3.0
protobuf/25.3-GCCcore-13.2.0
psutil/5.9.8-GCCcore-12.3.0
psutil/6.0.0-GCCcore-13.3.0
psutil/6.1.0-GCCcore-13.2.0
psycopg/3.1.18-GCCcore-13.2.0
psycopg/3.2.3-GCCcore-13.3.0
psycopg2/2.9.9-GCCcore-12.3.0
pugixml/1.14-GCCcore-12.3.0
py-cpuinfo/9.0.0-GCCcore-12.3.0
py-cpuinfo/9.0.0-GCCcore-13.2.0
py-cpuinfo/9.0.0-GCCcore-13.3.0
pyBigWig/0.3.22-gfbf-2023a
pybedtools/0.9.1-foss-2023a
pybind11/2.9.2-GCCcore-11.3.0
pybind11/2.11.1-GCCcore-12.3.0
pybind11/2.11.1-GCCcore-13.2.0
pybind11/2.12.0-GCC-13.3.0
pydantic/1.10.4-GCCcore-11.3.0
pydantic/2.5.3-GCCcore-12.3.0
pydantic/2.6.4-GCCcore-13.2.0
pydantic/2.9.1-GCCcore-13.3.0
pydicom/2.3.0-GCCcore-11.3.0
pydicom/2.4.4-GCCcore-12.3.0
pydicom/3.0.1-GCCcore-13.2.0
pydot/2.0.0-GCCcore-12.3.0
pydot/3.0.3-GCCcore-13.3.0
pyfaidx/0.8.1.1-GCCcore-12.3.0
pyfaidx/0.8.1.2-GCCcore-13.3.0
pyproj/3.4.0-GCCcore-11.3.0
pyproj/3.6.0-GCCcore-12.3.0
pyproj/3.7.0-GCCcore-13.3.0
pyspoa/0.2.1-GCC-12.3.0
pyspoa/0.2.1-GCC-13.2.0
pytest-flakefinder/1.1.0-GCCcore-12.3.0
pytest-flakefinder/1.1.0-GCCcore-13.2.0
pytest-rerunfailures/12.0-GCCcore-12.3.0
pytest-rerunfailures/14.0-GCCcore-13.2.0
pytest-shard/0.1.2-GCCcore-12.3.0
pytest-shard/0.1.2-GCCcore-13.2.0
pytest-xdist/3.3.1-GCCcore-12.3.0
pytest/4.6.11-GCCcore-12.3.0-Python-2.7.18
pytest/7.4.2-GCCcore-12.3.0
pytest/7.4.2-GCCcore-13.2.0
pytest/8.3.3-GCCcore-13.3.0
python-isal/1.1.0-GCCcore-12.3.0
python-isal/1.7.0-GCCcore-13.3.0
python-parasail/1.3.4-foss-2023a
python-xxhash/3.4.1-GCCcore-12.3.0
rasterio/1.4.3-foss-2024a
re2c/2.2-GCCcore-11.3.0
re2c/3.1-GCCcore-12.3.0
re2c/3.1-GCCcore-13.2.0
re2c/3.1-GCCcore-13.3.0
redis-py/4.5.1-foss-2022a
redis-py/5.0.1-GCCcore-12.3.0
redis-py/5.0.9-GCCcore-13.2.0
redis-py/5.1.1-GCCcore-13.3.0
rjags/4-15-foss-2023a-R-4.3.2
ruamel.yaml/0.17.32-GCCcore-12.3.0
ruamel.yaml/0.18.6-GCCcore-13.2.0
ruamel.yaml/0.18.6-GCCcore-13.3.0
samclip/0.4.0-GCCcore-13.3.0
scanpy/1.9.8-foss-2023a
schrodinger/2025-1
scikit-build-core/0.5.0-GCCcore-12.3.0
scikit-build-core/0.9.3-GCCcore-12.3.0
scikit-build-core/0.9.3-GCCcore-13.2.0
scikit-build-core/0.10.6-GCCcore-13.3.0
scikit-build/0.17.6-GCCcore-12.3.0
scikit-build/0.17.6-GCCcore-13.2.0
scikit-build/0.17.6-GCCcore-13.3.0
scikit-image/0.19.3-foss-2022a
scikit-image/0.22.0-foss-2023a
scikit-image/0.25.0-foss-2024a
scikit-learn/1.1.2-foss-2022a
scikit-learn/1.3.1-gfbf-2023a
scikit-learn/1.3.2-gfbf-2023b
scikit-learn/1.4.0-gfbf-2023b
scikit-learn/1.4.2-gfbf-2023a
scikit-learn/1.5.2-gfbf-2024a
scikit-optimize/0.10.2-foss-2023a
seqtk/1.4-GCC-13.3.0
setuptools-rust/1.6.0-GCCcore-12.3.0
setuptools-rust/1.8.0-GCCcore-13.2.0
setuptools-rust/1.9.0-GCCcore-13.3.0
smithwaterman/20160702-GCCcore-12.3.0
smithwaterman/20160702-GCCcore-13.3.0
snakemake/8.27.0-foss-2024a
snappy/1.1.9-GCCcore-11.3.0
snappy/1.1.10-GCCcore-12.3.0
snappy/1.1.10-GCCcore-13.2.0
snappy/1.2.1-GCCcore-13.3.0
snpEff/5.2c-GCCcore-12.3.0-Java-11
spaln/2.4.13f-GCC-12.3.0
spaln/3.0.6b-GCC-12.3.0
sparsehash/2.0.4-GCCcore-12.3.0
spglib-python/2.0.0-foss-2022a
spglib-python/2.5.0-gfbf-2024a
spglib/2.5.0-GCCcore-12.3.0
spoa/4.1.0-GCC-12.3.0
spoa/4.1.0-GCC-13.2.0
statsmodels/0.14.1-gfbf-2023a
statsmodels/0.14.4-gfbf-2024a
swalign/0.2-GCCcore-13.3.0-Python-2.7.18
sympy/1.12-gfbf-2023a
sympy/1.12-gfbf-2023b
sympy/1.13.3-gfbf-2024a
tRNAscan-SE/2.0.12-foss-2023a
tabix/0.2.6-GCCcore-12.3.0
tabix/0.2.6-GCCcore-13.3.0
tabixpp/1.1.2-GCC-12.3.0
tabixpp/1.1.2-GCC-13.3.0
tantan/50-GCC-12.3.0
tbb/2021.5.0-GCCcore-11.3.0
tbb/2021.11.0-GCCcore-12.3.0
tbb/2021.13.0-GCCcore-13.2.0
tbl2asn/20230713-GCCcore-12.3.0
tcsh/6.24.01-GCCcore-11.3.0
tcsh/6.24.10-GCCcore-12.3.0
tcsh/6.24.13-GCCcore-13.3.0
tensorboard/2.15.1-gfbf-2023a
tensorboard/2.18.0-gfbf-2023b
tensorboardX/2.6.2.2-foss-2023a
tensorstore/0.1.65-foss-2023a
tesseract/5.5.0-GCCcore-13.3.0
texlive/20230313-GCC-12.3.0
tiktoken/0.9.0-GCCcore-13.3.0
time/1.9-GCCcore-11.3.0
time/1.9-GCCcore-13.3.0
tmux/3.4-GCCcore-13.3.0
tokenizers/0.15.2-GCCcore-12.3.0
tokenizers/0.19.1-GCCcore-13.2.0
torchvision/0.16.0-foss-2023a-CUDA-12.1.1
tornado/6.3.2-GCCcore-12.3.0
tornado/6.4-GCCcore-13.2.0
tornado/6.4.1-GCCcore-13.3.0
tqdm/4.64.0-GCCcore-11.3.0
tqdm/4.66.1-GCCcore-12.3.0
tqdm/4.66.2-GCCcore-13.2.0
tqdm/4.66.5-GCCcore-13.3.0
trimAl/1.4.1-GCCcore-12.3.0
trimAl/1.5.0-GCCcore-13.3.0
typing-extensions/4.3.0-GCCcore-11.3.0
typing-extensions/4.9.0-GCCcore-12.3.0
typing-extensions/4.10.0-GCCcore-13.2.0
typing-extensions/4.11.0-GCCcore-13.3.0
ucsc/443
umap-learn/0.5.5-foss-2023a
unifdef/2.12-GCCcore-12.3.0
unimap/0.1-GCCcore-11.3.0
utf8proc/2.8.0-GCCcore-12.3.0
utf8proc/2.9.0-GCCcore-13.2.0
utf8proc/2.9.0-GCCcore-13.3.0
util-linux/2.38-GCCcore-11.3.0
util-linux/2.39-GCCcore-12.3.0
util-linux/2.39-GCCcore-13.2.0
util-linux/2.40-GCCcore-13.3.0
vcflib/1.0.9-gfbf-2023a-R-4.3.2
vcflib/1.0.9-gfbf-2024a-R-4.4.2
versioningit/3.1.2-GCCcore-13.3.0
vg/1.65.0
virtualenv/20.23.1-GCCcore-12.3.0
virtualenv/20.24.6-GCCcore-13.2.0
virtualenv/20.26.2-GCCcore-13.3.0
wandb/0.16.1-GCC-12.3.0
wget/1.21.3-GCCcore-11.3.0
wget/1.24.5-GCCcore-12.3.0
wpebackend-fdo/1.15.90-GCCcore-12.3.0
wrapt/1.16.0-gfbf-2024a
wxPython/4.2.1-foss-2023a
wxWidgets/3.2.2.1-GCC-12.3.0
x264/20220620-GCCcore-11.3.0
x264/20230226-GCCcore-12.3.0
x264/20231019-GCCcore-13.2.0
x264/20240513-GCCcore-13.3.0
x265/3.5-GCCcore-11.3.0
x265/3.5-GCCcore-12.3.0
x265/3.5-GCCcore-13.2.0
x265/3.6-GCCcore-13.3.0
xarray/2024.11.0-gfbf-2024a
xorg-macros/1.19.3-GCCcore-11.3.0
xorg-macros/1.20.0-GCCcore-12.3.0
xorg-macros/1.20.0-GCCcore-13.2.0
xorg-macros/1.20.1-GCCcore-13.3.0
xprop/1.2.8-GCCcore-13.3.0
xproto/7.0.31-GCCcore-11.3.0
xproto/7.0.31-GCCcore-13.3.0
xxHash/0.8.2-GCCcore-12.3.0
xxd/9.0.2112-GCCcore-12.3.0
xxd/9.1.0307-GCCcore-13.2.0
xxd/9.1.1275-GCCcore-13.3.0
zarr/2.18.4-foss-2024a
zlib/1.2.11
zlib/1.2.12-GCCcore-11.3.0
zlib/1.2.12
zlib/1.2.13-GCCcore-12.3.0
zlib/1.2.13-GCCcore-13.2.0
zlib/1.2.13
zlib/1.3.1-GCCcore-13.3.0
zlib/1.3.1
zstd/1.5.2-GCCcore-11.3.0
zstd/1.5.5-GCCcore-12.3.0
zstd/1.5.5-GCCcore-13.2.0
zstd/1.5.6-GCCcore-13.3.0

Software installed on Rocky 8

2026-05-11T15:02:23Z

Shtsai: Changed the heading type

Consulting

2026-05-06T18:51:47Z

Shtsai:

==Perl and UNIX-shell scripting==

Automating and simplifying tasks with command-scripts is a routine procedure in the Unix/Linux environment. We regularly help users develop scripts to suit their specific needs.

==Code Development==

We provide assistance with code compilation and debugging in serial and parallel environments.

==Computational Physics==

Computational physics methods are sometimes useful and applicable to problems in other fields. We provide some
consultation for computational physics algorithm selection and implementation.

==Bioinformatics==

From the installation of programs and data (e.g., genetic databases), to helping users get started, bioinformatics support is a key support area.

==General Usage==

GACRC staff are available to provide consultation in order to facilitate and optimize the use of GACRC’s resources. We are available to meet with small groups of users, and to provide guest lectures for courses that use GACRC resources.

==People==

===Administrators===

*'''Guy Cormier, Ph.D.''' Director, UGA Georgia Advanced Computing Resource Center Associate Research Scientist, Institute of Bioinformatics

===GACRC Consultants===





*'''Isaiah Davis''' Software Support Associate
*'''Zhuofei Hou, Ph.D.''' High Performance Computing Facilitator
*'''Chelsea Ware''' Software Support Associate
*'''Shan-Ho Tsai, Ph.D.''' Consulting Group Lead and High Performance Computing Consultant
*'''Jordan Utley, M.S.''' Bioinformatics Support Specialist



===GACRC IT Staff===

*'''Paul Brunk''' Principal Unix System Administrator
*'''Bruce Carpenter''' Linux System Administrator
*'''Jonathan "Jon" Gibson''' Linux System Administrator
*'''Keyton Stanier''' Linux System Administrator
*'''Kris Lamoureux''' Linux System Administrator


===Emeritus===
*'''Greg Derda, Ph.D.''' Operations Manager Extraordinaire

==Office Hours==
GACRC staff are located in the Computing Services Building (formerly called Statistics Building), rooms 101 to 108. Our office is open Monday through Friday from 9am until 5pm. You are welcome to stop by and ask questions, or you can schedule an appointment using the [https://uga.teamdynamix.com/TDClient/Requests/ServiceDet?ID=25844 GACRC General Support].

==Directions==
The Computing Services Building is located at 101 Cedar Street, Athens, GA 30602, on the corner of Cedar Street and East Campus Rd. As you enter the building from the entrance on Cedar Street, on the East Campus Rd. end of the building, there are stairs leading down to the first floor. Our offices are on your left, as you come down those stairs.

Policies

2026-05-06T18:43:16Z

Shtsai:

==Introduction to GACRC Policies==

The following policies are subject to revision, especially as the GACRC grows in scope and services. Your comments and questions will be useful to our policy formulation and refinement and are actively solicited by the GACRC Advisory Committee.

The GACRC computational infrastructure, including its servers, clusters, data stores, and other related devices are for the exclusive use of authorized users only.

Anyone using these systems expressly consents to abide by the policies of the University of Georgia and the Georgia Advanced Computing Resource Center and, accordingly, is subject to account termination and/or immediate disconnection from GACRC resources.

==GACRC Resource Usage==

The computational resources of the Georgia Advanced Computing Resource Center are to be used in direct support of research programs at the University of Georgia. Support is also provided for classes that teach computational methods, and provide training for high performance computing. The GACRC reserves the right to restrict access to its resources for course work if such work is deemed to present a negative impact to authorized research activities.

GACRC policies supplement UGA’s Policies on the Use of Computers, found at: [https://policy.uga.edu/policies#/programs/BJWfhwRra?group=Information%20Technology%20&bc=true&bcCurrent=Information%20Technology%20&bcItemType=programs&bc=true&bcCurrent=Acceptable%20Use%20Policy&bcGroup=Information%20Technology%20&bcItemType=programs UGA’s Policies on the Use of Computers]

==GACRC Eligibility and Access ==

Access to and use of the computing facilities managed by the Georgia Advanced Computing Resource Center are limited to persons affiliated with the University of Georgia or associated with research projects sponsored by UGA.

Affiliation in this context means faculty, research staff and supervised students of the University of Georgia. Faculty includes persons holding permanent or temporary appointments as well as adjunct faculty, instructors and visiting faculty while in residence at the University. It also includes those persons with faculty status such as research associates, research scientists, post-doctoral researchers and academic and service professionals. Staff includes all those non-faculty persons employed directly by the University in a research-support role. Graduate and undergraduate students who are members of faculty research labs are eligible for accounts as well. For directly affiliated users, accounts on the GACRC computers will remain active as long as the individuals hold the above status.

Access by non-UGA researchers and their students, affiliated to higher-education institutions or non-profit research organizations, for work on research projects conducted in collaboration with UGA Faculty is possible under the guidelines established by the Office of the Vice President for Research and the Office of International Education. A request for access can be forwarded to the GACRC by the UGA Faculty, providing details of the collaboration on a joint research project. Such Affiliate users will be considered part of the UGA Faculty’s group and will be under the Faculty’s responsibility. Affiliate users’ access will be granted for a fixed period of time, according to the expected length of the collaborative project. Renewal of affiliate accounts will be required annually.

All accounts will remain active no more than 30 days following a status change (i.e., leaving the university). Graduate instructional accounts will only remain active for the duration of the semester in which they are actually needed. HOME and PROJECT directories will be archived for at least 90 days, but no longer than 180 days after an account becomes inactive.

Requests for access by individuals other than those listed above should be directed to the Director of the Center for consideration with the GACRC Advisory Committee.

Access will be granted to a specific GACRC resource after appropriate training is undertaken with GACRC staff. Existing access to other GACRC resources is not a sufficient criteria for access to a new resource. No exceptions will be given to the training requirement.

==GACRC Identity Management==

Below are described the procedures for validating the identity of account users.

===UGA Users and Faculty Lab Groups===

*A UGA Faculty must first establish a GACRC group account using the instructions provided on the GACRC website (http://gacrc.uga.edu/accounts). The UGA Faculty can choose or not to obtain a GACRC user account affiliated with his/her group account.

*User accounts will only be created at the request of a UGA Faculty member, using the instructions provided on the GACRC website (http://gacrc.uga.edu/accounts).

*Upon acceptance of the application, the user will be notified via e-mail. The applicant’s UGA MyID and password will be used to log into the requested GACRC resources.

===Affiliate Users===

*A recognized Affiliate user must be sponsored by a UGA Faculty member through an established GACRC group account. The UGA Faculty involved in an established collaboration with the Affiliate user, must apply on behalf of the applicant by contacting the GACRC staff.

*A request will be made by the GACRC to EITS to allocate to the Affiliate a UGA MyID.

*Upon acceptance of the Affiliate user application, the Affiliate will be notified via e-mail. The Affiliate’s UGA MyID and password will be used to log into the requested GACRC resources.

===Protection of Passwords===

As described in UGA’s Password Policy, an account holder must never divulge their MyID and password to a third party. Only authorized account holders may access the resources of the GACRC. If a third party is found to be using an account holder’s login with or without the permission of the account holder, the account holder’s access privileges may be revoked at the sole discretion of the GACRC Manager or Director. Enforcement of this policy is under the responsibility of the Office of the Vice President for Information Technology’s Division of Information Security.

More information is found at the following EITS website:

[https://policy.uga.edu/policies#/programs/HJe8T3sH6?group=Information%20Technology%20&bc=true&bcCurrent=Information%20Technology%20&bcItemType=programs&bc=true&bcCurrent=Password%20Policy&bcGroup=Information%20Technology%20&bcItemType=programs UGA Policy Website]

==GACRC Storage Usage ==

===Some working definitions===

'''Snapshot''' - Copies of files that are stored on the same storage system as the original files. Snapshots are primarily used to recover files that have been accidentally deleted or corrupted within the recent past. Users are able to manage the file recovery tasks. Snapshots are not maintained beyond a defined rotation schedule, i.e., some number of hourly, daily, weekly, and monthly snapshots are kept on the storage system.

'''Backup''' - Copies of files and/or snapshots kept on a storage system (disk/tape) other than the one that the original files reside on. Backups are primarily used to recover files following a catastrophic failure of the original file or storage system. Backups require administrators to perform file system recovery tasks. Like snapshots, backups have a defined rotation schedule.

'''Archive''' - Copies of files that are not currently being accessed, on a resilient storage system dedicated to reliable long-term storage. Archives can be tape-based or disk-based, and typically part of a disaster recovery plan. The files may be copies of original data which is stored elsewhere (individual groups having their own copies), or the archive storage system may be fed by a dedicated "backup" storage system.

'''Active Projects''' – Projects that have on-going computational work being performed with files that are regularly created, accessed or modified.

===Policy Statement for SCRATCH File System===

The SCRATCH file system resides on a high-performance storage device and is to be used uniquely for temporary storage of files in use by actively running compute jobs. Files are to be removed from SCRATCH when a job completes, e.g. can be copied to the PROJECT file system. The SCRATCH file system is not backed up in any way and no snapshots are taken. The SCRATCH filesystem is mounted under /scratch on all the compute nodes, login nodes and data transfer nodes.

Any file that is not accessed or modified by a compute job in a time period of at least 30 days will be automatically deleted off the SCRATCH file system. Measures circumventing this policy will be monitored and actively discouraged.

There is no storage size quota for SCRATCH usage. Space is only limited by the physical size of the scratch space being used. If usage across the entire file system is more than 80% of total capacity, the GACRC will take additional measures to reduce usage to a more suitable level. Amongst possible actions, the GACRC may request/force users to clean up their SCRATCH directories or reduce temporarily the 30 day limit to a lower limit.

===Policy Statement for WORK File System===

The WORK file system resides on a high-performance storage device and is to be used for storing files that are frequently used by the group for computation. The WORK file system is '''NOT''' subject to the 30-day purge policy. The filesystem usage is controlled using a quota on the size and number of files that can be stored in a lab group's WORK area. Initially each group is given a 500GB and 100,000-file quota. The WORK file system is not backed up in any way and no snapshots are taken. The WORK filesystem is mounted under /work on all the compute nodes, login nodes and data transfer nodes. Each lab group has a directory under the /work directory.

The WORK file system is '''NOT''' subject to the 30-day purge policy. But if there is sufficient space consumption on the storage appliance, we reserve the right to ask users to clean up their WORK area. If the users do not respond in a timely fashion we will purge files beginning with the oldest ones. Please do not use the WORK area to store files long term.

===Policy Statement for HOME File System===

The HOME file system resides on a high-performance storage device and is used for long-term storage of files, typically programs and scripts, needed for analysis on the GACRC computing cluster.

All users have 200GB allocated for their HOME usage.

HOME directories will have daily, weekly and up to 3 monthly snapshots kept on the same storage unit to protect against accidental file deletion. HOME directories will also be backed-up on a different storage unit to protect against filesystem or hardware issues.

Users are strongly encouraged to make their own copies of critical files, while accepting any risks associated with HOME usage.

Snapshot retention, data purge and quota allocation policies are subject to change based on available storage capacity, users’ demand, equipment condition and availability, as well as any other conditions that might affect the provision of the HOME service.

===Policy Statement for PROJECT File System===

The PROJECT filesystem resides on lower-performance/higher-capacity storage devices.

This filesystem is accessible only from the GACRC’s transfer (xfer) nodes. PROJECT will not be accessible on Sapelo2's compute nodes.

This filesystem is to be used by groups for storage of active projects using Sapelo2. PROJECT should not be seen as a long-term repository, as it is not designed as such. Once a project is completed, data should be moved from the PROJECT space to user-managed storage, freeing up capacity for the next active project.

This filesystem is not for backing-up non-GACRC-related material, such as personal files (music, photos), office documents, and the like. If found, this material is subject to immediate deletion.

Access to the PROJECT filesystem is not supported through NFS to a destination outside of the Boyd Data Center, or through the use of the Samba or CIFS protocols. Transfer protocols available through the data transfer nodes are secure ftp, scp, rsync, GridFTP, amongst others.

Each group can request a PROJECT volume with an initial 1TB allocation, accessible by all users ascribed to the group, where the sharing of files will be enabled. Users are encouraged to consider their PROJECT space as the primary area to transfer compute job outputs. Additional space can be requested by a Faculty on behalf of his/her group.

The GACRC reserves the right to establish a cost-recovery rate for PROJECT storage beyond the initial 1TB allocation. Appropriate communications will take place in such an event.

PROJECT directories will have daily, weekly and monthly snapshots kept on the same storage unit to protect against accidental file deletion. PROJECT directories will also be backed-up on a different storage unit to protect against filesystem or hardware issues.

Users are strongly encouraged to make their own copies of critical files, while accepting any risks associated with PROJECT usage.

Snapshot retention, data purge and quota allocation policies are subject to change based on available storage capacity, users’ demand, equipment condition and availability, as well as any other conditions that might affect the provision of the PROJECT service.

==GACRC Software Policy==

The GACRC maintains a collection of program libraries and software packages to support research computing activities across diverse research domains. While a user can install a software package in their own environment, for the sake of general access across groups, and an appropriate deployment with current libraries, compilers and other dependencies, we strongly recommend that GACRC staff be asked to perform the installation or upgrade.

Any software that requires a signed license or contract, even if it is a click-through agreement, must absolutely be reviewed and handled by the Office of Legal Affairs before being signed by an appropriate signature authority. After the license or contract is accepted and the software is made available, GACRC users must fully comply and use the software in a way that does not violate any terms of the license or contract. Further information on licensing issues can be found at the following EITS website:


As a matter of policy, the GACRC will not purchase any commercial software for the use of a single group or a small number of groups. Commercial software currently purchased and maintained by the GACRC are of general interest and applicability to the whole UGA research community. The GACRC will however install and maintain a group-purchased commercial software, which complies with the above comments on licenses and contracts.

==Security==

To minimize disruption of service, protect data integrity, conserve facility resources and maximize the effectiveness of staff support, the GACRC maintains strict security requirements for access to GACRC resources. Over time, the enforcement of these requirements will become increasingly strict, with the goal of preventing any access to the GACRC resources by any person or any device that is not in strict compliance with these requirements.

===Operating Systems===

Any computer accessing the GACRC for any purpose must run a currently supported operating system, updated to the latest version and update (patch) levels.

===Anti-Virus Software===

Any computer accessing the GACRC for any purpose must meet minimum levels of anti-virus protection. Any computer used by an account holder must have anti-virus software from a source approved by UGA’s Office of Information Security must have that virus protection activated, and must have automatic updates activated.

More information can be found at the following EITS website:

[https://policy.uga.edu/policies#/programs/BySr6vy8a?q=%20Minimum%20Security%20Standards%20Policy&&limit=20&skip=0&bc=true&bcCurrent=Minimum%20Security%20Standards%20Policy&bcItemType=programs Minimum Security Standards Policy]

===Suspiciously Behaving Software===

Any software that behaves in a suspicious manner may at any time be terminated and/or deleted from GACRC resources at the sole discretion of the GACRC’s systems administrator(s), manager, Director, or EITS information security staff.

===Suspiciously Behaving Networks and Devices===

Any connection from any device to the GACRC may be terminated at any time, if the device or the connection or a network to which the device is attached appears to be not in compliance with UGA’s security requirements, is behaving suspiciously, or if a threat emerges requiring termination for intrusion prevention at the sole discretion of the GACRC’s systems administrator(s), manager, Director, or EITS information security staff.

===Account Holder Responsibility===

The account holder is responsible for diligently monitoring their account and compliance with the GACRC’s operating system, intrusion and virus protection standards. The account holder will be duly notified if GACRC personnel determine that minimum security requirements are not met. Specific actions will be requested of the account holder and compliance to these will be expected in a timely fashion. An account holder’s privileges to use GACRC facilities may be terminated by the GACRC Manager or Director at any time, without notice if, in the opinion of either, the account holder is reluctant or averse to practicing diligence in meeting the GACRC’s minimum requirements for intrusion and/or anti-viral protection.

==Resolving Disagreements about Revocation of Privileges or Provisioning Resources==

The Director of the Georgia Advanced Computing Resource Center has full authority to revoke a user's privileges or deny the request of a new resource allocation. The decision to revoke a user's privileges will be based on, but not limited to, abuses of the UGA Policies on the Use of Computers and/or abuses of the UGA Password Policy.

If an account holder is denied a request for provisioning of GACRC resources or resource privileges are revoked, the account holder’s Department Head may appeal to the Vice President for Research and the Vice President for Information Technology. Their decision will be informed by the Director of the GACRC, the Chief Technology Officer as well as the Associate Chief Information Officer for Information Security. The decision of the Vice President for Research and Vice President for Information Technology is final.

==System Maintenance and Downtime==

===Planned Maintenance===

The GACRC instituted monthly maintenance windows in order to perform maintenance operations requiring system operations to be reduced or interrupted.

The schedule will be as follows:

*The last Wednesday of each month from 10AM to 4PM will be reserved for partial cluster maintenance.

*Twice a year, a two-day shut-down of GACRC services will be scheduled for more complex maintenance operations. These will occur on the last Tuesday and Wednesday of the months of January and July.

These maintenance windows represent periods when the GACRC may choose to drain the queues of running jobs and suspend access to the Sapelo2 cluster, as well as storage devices for maintenance purposes. Interruptions will be kept as brief as possible.

The GACRC will notify all users at least 10 days in advance that a maintenance window will be in effect. The notification will describe the nature and extent (partial or full) of the interruptions of cluster and or storage services. In case a maintenance window has to be extended due to unavoidable technical reasons, adequate communications will be made to all users.

The impact of the outages will vary, and the GACRC will do its best to preserve pending and running jobs, which is often very doable. Nevertheless, users will need to plan their job submissions around the maintenance windows.

===Unplanned Maintenance and System Outage===

From time to time, hardware, software, and/or environmental factors may cause a system or subsystem to malfunction, causing disruption to service. Also, there may be circumstances or events related to possible security issues or intrusions which will cause GACRC staff to take systems offline while the nature of the apparent breach is analyzed and appropriate action is taken.

Whenever possible, account holders will be notified by e-mail of these outages in advance, but that may not always be possible. Account holders will be notified by e-mail if the disruption should last more than 30 minutes.

GACRC staff will strive to preserve the work and/or prevent disruption of jobs in process during such outages. However, there may be circumstances which cause disruption of jobs and loss of data. Users are encouraged to implement methods in their code which minimize the effect of unplanned interruption of a job’s execution, such as checkpoints. Users are also strongly encouraged to maintain copies of files of importance.

==Regulatory Compliance==

The GACRC as an infrastructure and service provider does NOT currently warrant that its practices or facilities meet government-mandated requirements for the storage and protection of sensitive, private or classified information. Users may not store such information on GACRC facilities. In other words, data that falls under HIPAA, FERPA, FISMA or similar regulatory requirements, may not be stored, computed against or otherwise transacted through, or with, GACRC infrastructure.

The GACRC and its users must comply with all existing Federal export control regulations for services and infrastructure. Research groups must agree to NOT install or use any software or data that falls under Export Control regulations. More information on the subject of Export Control is available at the following OVPR website:

http://research.uga.edu/export-control/

Copyrighted materials are prohibited without proper authorization. Additionally, illegal content is prohibited.

Non-compliance with any such Federal requirements might impact GACRC operations or delivery of services and could place the GACRC and UGA at risk. If a research group is found to be in non-compliance, then account access will be immediately suspended, while an investigation by EITS’s Information Security division is instigated.

===Disclosure===

Research groups that are involved in activities that store protected data on GACRC infrastructure must contact immediately the GACRC Director in order to address the issue. Depending on circumstances, accommodations might be possible for such activities.

===Research Data Compliance===

Research Data Management is a critical factor in both obtaining federal funding from the NSF, NIH, DoD and other federal agencies, and in the conduct of funded research. Responsibility in maintaining and preserving research data, as detailed in data management plans submitted to Federal funding agencies, is entirely placed upon the research faculty, post docs, and graduate students conducting the research. The GACRC will help by providing information and assistance, but will not be responsible to ensure compliance with a project’s data management plan.

During the phase of proposal writing, arrangements can be discussed and agreed upon as to the GACRC playing an active role, and ensuring the provision of specific services towards the compliance of a data management plan. Depending on the complexity or the nature of the proposed services, the GACRC might require the purchase of specific hardware/software and/or the availability of a %FTE salary and benefits.

More information on data management plans can be found [http://guides.libs.uga.edu/c.php?g=349946&p=2363161 here].

Maker-Sapelo2

2026-05-06T18:34:30Z

Shtsai:

[[Category:Sapelo2]][[Category:Software]][[Category:Bioinformatics]]
== Category ==
Bioinformatics

== Program On ==

Sapelo2

== Version ==

3.01.04

== Author / Distributor ==

[https://github.com/Yandell-Lab/maker Yandell-lab]

== Description ==

More details from http://gmod.org/wiki/MAKER_Tutorial#What_does_MAKER_do.3F

MAKER is an easy-to-use genome annotation pipeline designed to be usable by small research groups with little bioinformatics experience; however, MAKER is also designed to be scalable and is appropriate for projects of any size even including use by large sequence centers. MAKER can be used for de novo annotation of newly sequenced genomes, for updating existing annotations to reflect new evidence, or just to combine annotations, evidence, and quality control statistics for use in other GMOD programs.

== Running Program ==

Also refer to [[Running Jobs on Sapelo2]]

Version 3.01.04 is installed at /apps/eb/Maker/3.01.04-foss-2022a

Example to prepare the configuration files.
<pre class="gscript">
module load MAKER/3.01.04-foss-2022a
maker -CTL
</pre>

Command "maker -CTL" will generate the configuration files '''maker_bopts.ctl''', '''maker_evm.ctl''', '''maker_exe.ctl''', and '''maker_opts.ctl''' in your working folder. You need to configure those configuration files before you run maker. Examples can be found at [http://weatherby.genetics.utah.edu/MAKER/wiki/index.php/MAKER_Tutorial_for_WGS_Assembly_and_Annotation_Winter_School_2018#Running_MAKER_with_example_data Running_MAKER_with_example_data].

To use an MPI-enabled version:
<pre class="gscript">
module load MAKER/3.01.04-foss-2022a-MPI
</pre>

=== Running maker in a MPI job ===

Here is an example of submission script (sub.sh) for running maker in a MPI job of 60 MPI processes running on 5 nodes:

<pre class="gscript">
#!/bin/bash
#SBATCH --partition=batch
#SBATCH --job-name=maker-mpi
#SBATCH --nodes=1
#SBATCH --ntasks=16
#SBATCH --cpus-per-task=1
#SBATCH --mem-per-cpu=1G
#SBATCH --time=24:00:00
#SBATCH --output=log.o%j
#SBATCH --export=NONE

export OMPI_MCA_mpi_warn_on_fork=0
unset SLURM_EXPORT_ENV

cd $SLURM_SUBMIT_DIR

ml MAKER/3.01.04-foss-2022a-MPI

srun $EBROOTMAKER/bin/maker
</pre>

=== Running maker in a memory-sharing threaded job ===

The maker command provides the -cpus option to specify how many threads to use for BLAST+.

Here is an example of submission script (sub.sh) for running maker in a threaded job of 16 threads running on 1 node:

<pre class="gscript">
#!/bin/bash
#SBATCH --partition=batch
#SBATCH --job-name=Maker
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=16
#SBATCH --mem=20G
#SBATCH --time=8:00:00
#SBATCH --output=log.o%j
#SBATCH --export=NONE

cd $SLURM_SUBMIT_DIR

ml MAKER/3.01.04-foss-2022a

maker -cpus 16
</pre>

=== Running maker in a single-core job ===

Here is an example of submission script (sub.sh) for running maker in a single-core job:

<pre class="gscript">
#!/bin/bash
#SBATCH --partition=batch
#SBATCH --job-name=Maker
#SBATCH --ntasks=1
#SBATCH --mem=10G
#SBATCH --time=8:00:00
#SBATCH --output=log.o%j
#SBATCH --export=NONE

cd $SLURM_SUBMIT_DIR

ml MAKER/3.01.04-foss-2022a

maker
</pre>

Then submit the job by:
<pre class="gcommand">
sbatch ./sub.sh
</pre>

== Documentation ==

Maker wiki site is at https://weatherby.genetics.utah.edu/MAKER/wiki/index.php/Main_Page

<pre class="gcommand">
ml MAKER/3.01.04-foss-2022a
maker -h

MAKER version 3.01.04

Usage:

maker [options] <maker_opts> <maker_bopts> <maker_exe>

Description:

MAKER is a program that produces gene annotations in GFF3 format using
evidence such as EST alignments and protein homology. MAKER can be used to
produce gene annotations for new genomes as well as update annotations
from existing genome databases.

The three input arguments are control files that specify how MAKER should
behave. All options for MAKER should be set in the control files, but a
few can also be set on the command line. Command line options provide a
convenient machanism to override commonly altered control file values.
MAKER will automatically search for the control files in the current
working directory if they are not specified on the command line.

Input files listed in the control options files must be in fasta format
unless otherwise specified. Please see MAKER documentation to learn more
about control file configuration. MAKER will automatically try and
locate the user control files in the current working directory if these
arguments are not supplied when initializing MAKER.

It is important to note that MAKER does not try and recalculated data that
it has already calculated. For example, if you run an analysis twice on
the same dataset you will notice that MAKER does not rerun any of the
BLAST analyses, but instead uses the blast analyses stored from the
previous run. To force MAKER to rerun all analyses, use the -f flag.

MAKER also supports parallelization via MPI on computer clusters. Just
launch MAKER via mpiexec (i.e. mpiexec -n 40 maker). MPI support must be
configured during the MAKER installation process for this to work though

Options:

-genome|g <file> Overrides the genome file path in the control files

-RM_off|R Turns all repeat masking options off.

-datastore/ Forcably turn on/off MAKER's two deep directory
nodatastore structure for output. Always on by default.

-old_struct Use the old directory styles (MAKER 2.26 and lower)

-base <string> Set the base name MAKER uses to save output files.
MAKER uses the input genome file name by default.

-tries|t <integer> Run contigs up to the specified number of tries.

-cpus|c <integer> Tells how many cpus to use for BLAST analysis.
Note: this is for BLAST and not for MPI!

-force|f Forces MAKER to delete old files before running again.
This will require all blast analyses to be rerun.

-again|a recaculate all annotations and output files even if no
settings have changed. Does not delete old analyses.

-quiet|q Regular quiet. Only a handlful of status messages.

-qq Even more quiet. There are no status messages.

-dsindex Quickly generate datastore index file. Note that this
will not check if run settings have changed on contigs

-nolock Turn off file locks. May be usful on some file systems,
but can cause race conditions if running in parallel.

-TMP Specify temporary directory to use.

-CTL Generate empty control files in the current directory.

-OPTS Generates just the maker_opts.ctl file.

-BOPTS Generates just the maker_bopts.ctl file.

-EXE Generates just the maker_exe.ctl file.

-MWAS <option> Easy way to control mwas_server for web-based GUI

options: STOP
START
RESTART

-version Prints the MAKER version.

-help|? Prints this usage statement.

</pre>

[[#top|Back to Top]]
== Installation ==

Source download from https://github.com/Yandell-Lab/maker

== System ==
64-bit Linux

Software Template

2026-05-06T17:26:18Z

Shtsai:

<pre>
[[Category:Sapelo2]][[Category:Software]][[Category:Bioinformatics]]
== Category ==
Bioinformatics
== Program On ==
Sapelo2
== Version ==

== Author / Distributor ==

== Description ==

== Running Program ==

Also refer to [[Running Jobs on zcluster]]

== Documentation ==
== Installation ==
== System ==
64-bit Linux
</pre>

MPI

2026-05-06T16:55:26Z

Shtsai:

[[Category:Sapelo2]][[Category:Teaching]]

==MPI Libraries for parallel jobs on Sapelo2==

All compute nodes on Sapelo2 have Infiniband (IB) interconnect via '''EDR''' Infiniband network (100Gbps). Various IB-enabled MPI libraries are available and users can set the environment variables for the MPI library of choice by loading the corresponding module file.


For more information on Environment Modules, please see the [[Lmod]] page.

The following MPI libraries are available:

===OpenMPI===

You can find all OpenMPI modules available on Sapelo2 by running the following command on a Sapelo2 node:
<pre class="gcommand">
module spider OpenMPI
</pre>

The module names have the format OpenMPI/''Version''-''CompilerToolchain''-''ToolchainVersion''.

For example, these are some of the modules available:

<pre class="gcomment">
[shtsai@b1-24 ~]$ module spider OpenMPI

-----------------------------------------------------------------------------------------------------------------------------------------------
OpenMPI:
-----------------------------------------------------------------------------------------------------------------------------------------------
Description:
The Open MPI Project is an open source MPI-3 implementation.

Versions:
OpenMPI/4.1.1-GCC-11.2.0
OpenMPI/4.1.4-GCC-11.3.0
OpenMPI/4.1.5-GCC-12.3.0
OpenMPI/4.1.6-GCC-13.2.0
OpenMPI/5.0.3-GCC-13.3.0

------------------------------------------------------------------------------------------------------------------------------------------------
For detailed information about a specific "OpenMPI" package (including how to load the modules) use the module's full name.
Note that names that have a trailing (E) are extensions provided by other modules.
For example:

$ module spider OpenMPI/5.0.3-GCC-13.3.0
-----------------------------------------------------------------------------------------------------------------------------------------------
</pre>

Once the appropriate module is loaded, you can compile code with '''mpicc, mpiCC, mpicxx,''' '''mpic++,''' '''mpifort,''' '''mpif90,''' '''mpif77,''' etc. and you can run applications that were linked to the '''MPI libraries''' loaded by the module.

=== Intel MPI ===
You can find all Intel MPI modules available on Sapelo2 by running the following command on a Sapelo2 node:<pre class="gcommand">
module spider impi
</pre>The module names have the format impi/''Version''-''CompilerToolchain''-''ToolchainVersion.''

For example, these are some of the modules available:<pre class="gcomment">
[shtsai@ss-sub1 ~]$ module spider impi

------------------------------------------------------------------------------------------------------------------------------------
impi:
------------------------------------------------------------------------------------------------------------------------------------
Description:
Intel MPI Library, compatible with MPICH ABI

Versions:
impi/2021.6.0-intel-compilers-2022.1.0
impi/2021.9.0-intel-compilers-2023.1.0
impi/2021.10.0-intel-compilers-2023.2.1
impi/2021.13.0-intel-compilers-2024.2.0

Other possible modules matches:
iimpi

------------------------------------------------------------------------------------------------------------------------------------
To find other possible module matches execute:

$ module -r spider '.*impi.*'

------------------------------------------------------------------------------------------------------------------------------------
For detailed information about a specific "impi" package (including how to load the modules) use the module's full name.
Note that names that have a trailing (E) are extensions provided by other modules.
For example:

$ module spider impi/2021.13.0-intel-compilers-2024.2.0
------------------------------------------------------------------------------------------------------------------------------------
</pre>

Once the appropriate module is loaded, you can compile code with '''mpicc, mpiicc, mpicxx, mpiicpc,''' '''mpiifort,''' '''mpif90,''' '''mpif77,''' etc. and you can run applications that were linked to the '''MPI libraries''' loaded by the module.

===MPI commands and how to launch MPI programs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="center" class="wikitable unsortable"
|-
! scope="col" | MPI library
! scope="col" | Version
! scope="col" | Base toolchain
! scope="col" | Toolchain
! scope="col" | Fortran
! scope="col" | C
! scope="col" | C++
! scope="col" | How to launch with Slurm
|-

| OpenMPI || 4.1.1-GCC-11.2.0 || GCCcore-11.2.0 || foss/2021b || mpif90 || mpicc || mpicxx || srun
|-
| OpenMPI || 4.1.4-GCC-11.3.0 || GCCcore-11.3.0 || foss/2022a || mpif90 || mpicc || mpicxx || srun
|-
| OpenMPI || 4.1.5-GCC-12.3.0 || GCCcore-12.3.0 || foss/2023a || mpif90 || mpicc || mpicxx || srun
|-
| OpenMPI || 4.1.6-GCC-13.2.0 || GCCcore-13.2.0 || foss/2023b || mpif90 || mpicc || mpicxx || srun
|-
| OpenMPI || 5.0.3-GCC-13.3.0 || GCCcore-13.3.0 || foss/2024a || mpif90 || mpicc || mpicxx || srun
|-
| Intel MPI || 2021.6.0-intel-compilers-2022.1.0 || GCCcore-11.3.0 || intel/2022a || mpiifort || mpiicc || mpiicpc || srun
|-
| Intel MPI || 2021.9.0-intel-compilers-2023.1.0 || GCCcore-12.3.0 || intel/2023a || mpiifort || mpiicc || mpiicpc || srun
|-
| Intel MPI || 2021.10.0-intel-compilers-2023.2.1 || GCCcore-13.2.0 || intel/2023b || mpiifort || mpiicc || mpiicpc || srun
|-
| Intel MPI || 2021.13.0-intel-compilers-2024.2.0 || GCCcore-13.3.0 || intel/2024a || mpiifort || mpiicc || mpiicpc || srun
|-
|}

====Note====

If your MPI job receives any of the following or similar errors:
*PMIX ERROR: OUT-OF-RESOURCE in file base/bfrop_base_unpack.c at line 750
*PMIX ERROR: UNPACK-PAST-END in file base/bfrop_base_unpack.c at line 750
*PMIX ERROR: UNPACK-INADEQUATE-SPACE in file base/gds_base_fns.c at line 138
*UNPACK-PMIX-VALUE: UNSUPPORTED TYPE 126
then please use <code>srun --mpi=pmi2</code> to start the MPI application.

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

==MPI Libraries for parallel jobs on the teaching cluster==

All compute nodes on Sapelo2 have Infiniband (IB) interconnect via '''EDR''' Infiniband network (100Gbps). Various IB-enabled MPI libraries are available and users can set the environment variables for the MPI library of choice by loading the corresponding module file.

For more information on Environment Modules, please see the [[Lmod]] page.

The following MPI libraries are available:

===OpenMPI===

You can find all OpenMPI modules available on the teaching cluster by running the following command:
<pre class="gcommand">
module spider OpenMPI
</pre>

The module names have the format OpenMPI/''Version''-''CompilerToolchain''-''ToolchainVersion''.

For example, these are some of the modules available:

<pre class="gcomment">
zhuofei@teach-sub1 ~$ ml spider OpenMPI

------------------------------------------------------------------------------------------------------------------------------------
OpenMPI:
------------------------------------------------------------------------------------------------------------------------------------
Description:
The Open MPI Project is an open source MPI-3 implementation.

Versions:
OpenMPI/3.1.4-GCC-8.3.0
OpenMPI/4.1.1-GCC-11.2.0
OpenMPI/4.1.2-GCC-11.2.0
OpenMPI/4.1.4-GCC-11.3.0
OpenMPI/4.1.4-GCC-12.2.0

--------------------------------------------------------------------------------------------------------------------------------------
For detailed information about a specific "OpenMPI" package (including how to load the modules) use the module's full name.
Note that names that have a trailing (E) are extensions provided by other modules.
For example:

$ module spider OpenMPI/4.1.4-GCC-12.2.0
------------------------------------------------------------------------------------------------------------------------------------
</pre>

Once the appropriate module is loaded, you can compile code with '''mpicc, mpiCC, mpicxx,''' '''mpic++,''' '''mpifort,''' '''mpif90,''' '''mpif77,''' etc. and you can run applications that were linked to the '''MPI libraries''' loaded by the module.

=== Intel MPI ===
You can find all Intel MPI modules available on the teaching cluster by running the following command:<pre class="gcommand">
module spider impi
</pre>The module names have the format impi/''Version''-''CompilerToolchain''-''ToolchainVersion''.

For example, these are some of the modules available:<pre class="gcomment">
zhuofei@teach-sub1 ~$ ml spider impi

------------------------------------------------------------------------------------------------------------------------------------
impi: impi/2018.5.288-iccifort-2019.5.281
------------------------------------------------------------------------------------------------------------------------------------
Description:
Intel MPI Library, compatible with MPICH ABI

Versions:
impi/2021.4.0-intel-compilers-2021.4.0
impi/2021.6.0-intel-compilers-2022.1.0
impi/2021.9.0-intel-compilers-2023.1.0
Other possible modules matches:
iimpi

------------------------------------------------------------------------------------------------------------------------------------
To find other possible module matches execute:

$ module -r spider '.*impi.*'

------------------------------------------------------------------------------------------------------------------------------------
For detailed information about a specific "impi" package (including how to load the modules) use the module's full name.
Note that names that have a trailing (E) are extensions provided by other modules.
For example:

$ module spider impi/2021.9.0-intel-compilers-2023.1.0
------------------------------------------------------------------------------------------------------------------------------------
</pre>Once the appropriate module is loaded, you can compile code with '''mpicc, mpiicc, mpicxx, mpiicpc,''' '''mpiifort,''' '''mpif90,''' '''mpif77,''' etc. and you can run applications that were linked to the '''MPI libraries''' loaded by the module.

[[#top|Back to Top]]

Training

2026-05-06T16:48:12Z

Shtsai:

==GACRC Training==

The GACRC regularly hosts training sessions on a number of subjects relevant to the use of our computational and storage resources. Scheduled trainings will be announced through the GACRC mailing list.

'''NOTE: New users are required to attend a Sapelo2 cluster introductory training session and information about that will be sent once an account is requested.'''

==Regular Training Announcement==

In '''April 2026''', the GACRC is hosting 9 training sessions listed below. These training workshops will be offered remotely via Zoom Meeting. Detailed instructions for joining the Zoom meeting will be sent to your UGA email account before each training session you register for.

We will offer:

1. Linux training for Linux-inexperienced cluster new users (3 sessions)

2. Sapelo2 cluster new user training (3 sessions)

3. Sapelo2 Part II (1 session)

4. Job Parallelization with GNU Parallel and Slurm Arrays (1 session)

5. Installing Software Packages in Virtual Environments on Sapelo2 (1 session)

In '''May 2026''', the GACRC is hosting 9 training sessions listed below. These training workshops will be offered remotely via Zoom Meeting. Detailed instructions for joining the Zoom meeting will be sent to your UGA email account before each training session you register for.

We will offer:

1. Linux training for Linux-inexperienced cluster new users (3 sessions)

2. Sapelo2 cluster new user training (3 sessions)

==Event Schedule==

This section describes the training workshops that we offer, along with the sessions that are currently scheduled.

===Sapelo2 Cluster New User Training===

This mandatory training consists of an overview of the structure of Sapelo2 as well as hands-on practice submitting a job along with guidance and best practices when using the Sapelo2 cluster.

'''Prerequisites:'''

*Linux basics. A Linux-inexperienced user must complete a prerequisite Linux training for Linux-inexperienced cluster new users.

'''Workshop Training Goals:'''

*Understand the layout of Sapelo2

*Understand the Sapelo2 file systems

*Understand the Sapelo2 partitions

*Understand the Sapelo2 software environment

*Understand how to request computing resources and submit a computational batch job following the Sapelo2 cluster general workflow

*Understand how to initiate an interactive job

*Understand how to transfer files to and from the cluster

*Understand how to get support from GACRC support team when you have any issues on cluster

'''Scheduled Sessions:'''

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Title
! scope="col" |Date/Time
|-
|Using Sapelo2 Cluster at the GACRC
|May 8th, Friday, 2:00 PM - 4:00 PM
|-
|Using Sapelo2 Cluster at the GACRC
|May 14th, Thursday, 2:00 PM - 4:00 PM
|-
|Using Sapelo2 Cluster at the GACRC
|May 20th, Wednesday, 2:00 PM - 4:00 PM
|}

===Linux Training for Linux-inexperienced Cluster New Users===
The Sapelo2 High Performance Computing (HPC) cluster runs a headless Linux distribution as the operating system on each of its constituent nodes. The term headless refers to the fact that these nodes do not have a desktop graphical user interface (GUI) installed by default. Graphical desktop environments consume resources that analyses could otherwise use, so users employ a command-line interface (CLI) instead. To interact with these resources, users connect to a remote terminal via SSH and execute commands.

The Linux Training workshop provides hands-on practice of the fundamental Linux commands necessary to interact with HPC resources.

'''Prerequisite:'''

Please watch the introductory videos on Linux, basic Linux terms, and Linux Paths and Directories (total ~17 minutes) '''before attending the training workshop'''.

*[https://kaltura.uga.edu/media/t/1_81u2kfi2/176125031 Linux]
*[https://kaltura.uga.edu/media/t/1_ol51cuyn/176125031 basic Linux terms]
*[https://kaltura.uga.edu/media/t/1_wdyxhgdg/176125031 Linux Paths and Directories]

'''Training Goals:'''

1. Understand fundamental concepts of Linux working environment (filesystem hierarchy, path, PATH, etc.)

2. Know how to use Linux common commands (ls, cd, pwd, cat, more, nano, mkdir, rm, cp, mv, etc.)

3. Understand what is Linux bash shell and know how to make a simple Linux script and run it in Linux environment

'''Scheduled Sessions:'''

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" | Title
! scope="col" |Date/Time
|-
|Use Linux on Cluster
|May 6th, Wednesday, 1:00 PM - 3:00 PM
|-
|Use Linux on Cluster
|May 12th, Tuesday, 1:00 PM - 3:00 PM
|-
|Use Linux on Cluster
|May 18th, Monday, 1:00 PM - 3:00 PM
|}

===Using Sapelo2 Cluster at the GACRC, Part II ===
This workshop will cover high-performance computing on Sapelo2, including job scheduling, resource requests (CPU, memory, GPU), and techniques for optimizing job performance.

'''Prerequisites:'''
*Linux basics. A Linux-inexperienced user must complete a prerequisite Linux training for Linux-inexperienced cluster new users.
*Sapelo2 cluster new user training. Fundamental HPC and Sapelo2 knowledge is required for this advanced Sapelo2 workshop.

'''Training Goals:'''

1. Learn about high-performance computing framework

2. Why is my job pending? How can I get my job to start sooner? How to find available computing resources on Sapelo2?

3. How to request computing resources such as nodes, CPU cores, memory, GPU device, etc. to run serial, threaded, MPI, and GPU jobs on Sapelo2?

4. How can I make my job run more efficiently (through the correct use of software and hardware)?

5. A quick intro to MPI library and how to compile/run MPI jobs on Sapelo2

'''Scheduled Sessions:'''

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Title
! scope="col" |Date/Time
|-
|Using Sapelo2 Cluster at the GACRC, Part II
|April 17th, Friday, 1:00 - 3:00 PM
|}

===Installing Software Packages in Virtual Environments on Sapelo2 ===
This workshop will cover the basics of virtual environments as well as provide practical guidance and best practices for using virtual environments on the Sapelo2 cluster. Participants will learn the basics of creating and configuring virtual environments, how to install software packages in both a Conda virtual environment and a Python virtual environment, and manage dependencies in their environments.

'''Prerequisite:'''

Must already have strong understanding of the Linux environment and Sapelo2.

'''Training Goals:'''

1. Learn how to create a virtual environment on Sapelo2

2. Be able to install software packages into both Conda and Python virtual environments

3. Understand how to manage dependencies of their virtual environments

'''Scheduled Sessions:'''

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Title
! scope="col" |Date/Time
|-
|Installing Software Packages in Virtual Environments on Sapelo2
|April 23rd, Thursday, 2:00 - 3:00 PM
|}

===Job Parallelization with GNU Parallel and Slurm Arrays ===
Learn how to run multiple commands in parallel using GNU Parallel and Slurm Arrays. These tools greatly reduce the runtime of certain types of jobs by running multiple instances of the same command in parallel. The workshop focuses on problems that involve executing the same command on multiple different inputs. This workshop is intended for users comfortable writing job submission scripts and using a command line. Concurrent and parallel programming techniques are not covered in this workshop.

'''Prerequisite:'''

Must already have strong understanding of the Linux environment and Sapelo2.

'''Training Goals:'''

1. Understand which jobs benefit from GNU Parallel and Slurm Arrays

2. Use GNU Parallel and Slurm Arrays to parallelize jobs

3. Understand the differences and similarities between GNU Parallel and Slurm Arrays

'''Scheduled Sessions:'''

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Title
! scope="col" |Date/Time
|-
|Job Parallelization with GNU Parallel and Slurm Arrays
|April 30th, Thursday, 1:00 - 2:30 PM
|}



==How to Register==

The training workshops '''Using Sapelo2 Cluster at the GACRC''' and '''Use Linux on Cluster''' are '''ONLY''' offered to '''new users''' who need user accounts on the GACRC Sapelo2 cluster or current Sapelo2 users seeking a refresher. If you would like to use the cluster, please ask your group PI/UGA faculty member to send us an account creation request for you, using the [https://uga.teamdynamix.com/TDClient/Requests/ServiceDet?ID=25839 GACRC User Account Request Form].

If you would like to attend the '''Using Sapelo2 Cluster at the GACRC, Part II''', the '''Installing Software Packages in Virtual Environments on Sapelo2''', and/or the '''Job Parallelization with GNU Parallel and Slurm Arrays''' training workshops, please send us a request using the [https://uga.teamdynamix.com/TDClient/Requests/ServiceDet?ID=25852 GACRC Training Request Form]. In your request, please tell us which session(s) you would like to attend.



== Download==

This section provides the slides that we use for our current workshops and material used for several of our past training events and presentations.

===Sapelo2 Cluster Training===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|[[Media:GACRC_Sapelo2_cluster_new_user_training_workshop_v10.8.pdf]]
|-
|}

===Teaching Cluster Training===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
|[[Media:GACRC-Teaching-cluster-new-user-training-workshop-Spring2026.pdf]]
|-
|}

===Linux Training for New Cluster Users===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
|[[Media:Linux_Training_For_New_Users_Of_Cluster_Suchi_04252019.pdf]]
|-
|}

===Installing Software Packages in Virtual Environments on Sapelo2===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
|[[Media:GACRC_virtual_environments_training_v1.2.pdf]]
|}

===Job Parallelization with GNU Parallel and Slurm Arrays===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
|[[Media:GNU_Parallel_and_SLURM_Arrays_v1.1.pdf]]
|}



===Topical Sessions===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|
|-
|[[Media:AI_Resources_on_the_GACRC_Sapelo2_Cluster.pdf]]
|-
|[[Media:Using_Sapelo2_Cluster_at_the_GACRC_Part_II_Rocky8.pdf]]

|}

===Out-Reach/In-Class Talk===

{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Dept./Center/Institute
! scope="col" |Type
! scope="col" |Workshop PDF
|-
|GEOG - Spring2026 || In-Class || [[Media:GACRC-Teaching-cluster-new-user-training-workshop-python-Spring2026.pdf]]
|-
|BCMB8330 - Spring2026 || In-Class || [[Media:GACRC-Teaching-cluster-new-user-training-workshop_bcmb8330_Spring2026.pdf]]
|-
|PHYS8601 - Spring2026 || In-Class || [[Media:GACRC_Teaching_cluster_new_user_training_workshop-phys8601-Spring2026.pdf]] ; [[Media:Gacrc_handout2026_phys8601.pdf]]
|-
|Anthropology Department || Out-Reach || [[Media:GACRC_overview_20251117_Anthropology.pdf]]
|-
|CSP seminar - Fall 2025|| Out-Reach || [[Media:GACRC_overview_20250819-CSP.pdf]]

|}

'''NOTE:''' The slides may become outdated and you should always check GACRC Wiki for up to date information.

Sapelo2 and Sapelo2 (old) comparison

2026-05-06T16:23:29Z

Shtsai:

[[Category:Sapelo2]]

Side-by-side comparison of Sapelo2 (old) and Sapelo2, where Sapelo2 (old) refers to the Sapelo2 cluter before the Oct. 24th, 2020 maintenance.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="center" class="wikitable sortable"
|+ Cluster comparison before and after update
|-
! scope="col" class="unsortable" width="200px"| Features
! scope="col" class="unsortable" width="240px"| Sapelo2 (old)
! scope="col" class="unsortable" width="240px"| Sapelo2
! scope="col" width="20px"|
|-

! scope="row"| Operating system
|| Centos 7.5 || Centos 7.8 || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Queueing system
|| Torque 6.1.2, Moab 9.1.2 || Slurm 20.02.3 || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Deployment system
|| Foreman || xCAT || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Node and system configuration
|| Puppet || Puppet || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Login node RAM
|| 128GB and 32GB || 32GB || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Login node cores
|| one 24-core Intel, one 16-core Intel VM || four 16-core Intel VMs || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Home directory
|| /home/MyID, NFS exported || same as on Sapelo2 || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Scratch directory
|| /scratch/MyID, DDN Lustre || same as on Sapelo2 || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Shared application path
|| /usr/local/apps || /apps || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Environment modules
|| LMOD 7.4.17 || LMOD 8.3.13 || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| Containers
|| Singularity || Singularity || [[File:Up20.png|20px|link=#top]]
|-
! scope="row"| User ssh access to job-running nodes
|| Enabled || Enabled || [[File:Up20.png|20px|link=#top]]

|-
|}
[[#top|Back To Top]] [[File:Up20.png|20px|link=#top]]

Changes implemented during November 16-22, 2018 maintenance

2026-05-06T16:06:25Z

Shtsai: /* /lustre1 decommissioned */

==Sapelo decommissioned==

The original Sapelo cluster (sapelo1.gacrc.uga.edu) is now fully decommissioned and the nodes that were originally part of Sapelo were migrated into Sapelo2.

==File transfer nodes (xfer) require Archpass Duo==

The file transfer nodes (xfer) now require two-factor authentication using Archpass Duo. When connecting to an xfer node from off-campus, please first connect to the UGA VPN and then connect to xfer.gacrc.uga.edu. Some documentation on changes needed in the configuration of FileZilla and WinSCP to accommodate using Archpass Duo is available at [[Transferring Files]].

==New hardware added into Sapelo2==

In addition to the nodes that were originally part of Sapelo, we have added the following new hardware into Sapelo2:

*42 compute nodes with Intel Xeon Skylake processors (32 cores and 187GB of RAM per node)
*4 compute nodes with Intel Xeon Skylake processors (32 cores and 187GB of RAM) and 1 NVIDIA P100 GPU card per node
*DDN SFA14KX Lustre appliance (1.26PB), serving /scratch and /work areas
*An EDR Infiniband network that provides internodal communication among a subset of compute nodes and between these nodes and the storage devices serving the users home directories and the scratch and work directories. The subset of nodes that are connected to the EDR IB fabric comprises the new Intel Skylake nodes and the Intel Broadwell nodes that were already on Sapelo2.

==Changes in the storage systems on Sapelo2==

===/lustre1 decommissioned===
The Seagate (Xyratex) ClusterStor1500 Lustre appliance that served /lustre1 has been decommissioned. The new scratch file system is called /scratch and resides in the new DDN SFA14KX Lustre appliance. All files that were in /lustre1 at the start of the maintenance window (5PM Nov. 16th, 2018) were copied into the new /scratch file system.

Jobs that have already been submitted from the /lustre1 directory (i.e. jobs that were pending during the maintenance) will not be affected by the decommissioning of /lustre1, as a link is provided that points /lustre1 to /scratch.

Any new jobs using the scratch file system should be accessed from /scratch and not from /lustre1. The /lustre1 link will be removed after the jobs that were submitted before the maintenance window complete.

'''Please do not submit any new jobs from /lustre1'''

If your job submission scripts or other programs have the /lustre1 path hardcoded in them, please change these files to replace /lustre1 by /scratch.

Some applications experienced issues on Sapelo2 when using /lustre1, because /lustre1 did not have the file locking feature enabled on Sapelo2. These issues should not occur on Sapelo2 when using /scratch, as /scratch does have the file locking feature enabled.

===/scratch file system and file retention policy===

'''Coming soon:''' "30-day purge" policy for files in /scratch

===/work file system===

Each group now has a /work directory (e.g. for abclab group, this directory is called /work/abclab), with a per group quota of 500GB and a maximum number of files limited to 100,000, that can be used to store input files that are often needed for repeated jobs, possibly by multiple users within a group, such as reference data and model data. For more information, please see [[Disk Storage]].

Please also see [[Best Practices on Sapelo2]] for some suggestions on data management workflow.

==Software Upgrade==

The following software updates were performed:

*The compute nodes' operating system was upgraded from 64-bit Linux CentOS 7.1 to 64-bit Linux CentOS 7.5. Code compiled on the older version of OS should continue to work (no need to recompile).
*The queueing system was updated from Torque 6.1.1 to 6.1.3 and Moab 9.1.2 to 9.1.3 to address some bugs in the older versions.

==How parallel jobs using MPI are affected==

Because the Intel nodes on Sapelo2 are now connected via a new EDR Infiniband network, some changes in the MPI jobs will be necessary.

*Applications that use OpenMPI will continue to work on both AMD and Intel nodes. However, applications compiled with older versions of OpenMPI (e.g. v. 1.10.3 in the foss/2016b toolchain) will display a warning at runtime, similar to this:

<pre class="gcomment">
[n249.ecompute:220879] 3 more processes have sent help message help-mpi-btl-openib.txt / no device params found
[n249.ecompute:220879] Set MCA parameter "orte_base_help_aggregate" to 0 to see all help / error messages
</pre>

or a warning similar to this:

<pre class="gcomment">
--------------------------------------------------------------------------
WARNING: No preset parameters were found for the device that Open MPI
detected:

Local host: n275
Device name: mlx5_0
Device vendor ID: 0x02c9
Device vendor part ID: 4119

Default device parameters will be used, which may result in lower
performance. You can edit any of the files specified by the
btl_openib_device_param_files MCA parameter to set values for your
device.

NOTE: You can turn off this warning by setting the MCA parameter
btl_openib_warn_no_device_params_found to 0.
--------------------------------------------------------------------------

</pre>

These warnings are harmless and the application should continue to work.

*Applications that use newer versions of OpenMPI will not display this warning at runtime.

*Applications compiled with MVAPICH2 will continue to work on the AMD nodes, but they will not work on the Intel nodes (EDR IB network). If you use MVAPICH2 to compile your code and want to run your jobs on the Intel nodes that are part of the "batch" queue, please recompile them using an MVAPICH2 module with an -EDR suffix. The following MVAPICH2 modules are available for the EDR IB fabric:

<pre class="gcomment">
MVAPICH2/2.3-GCC-5.4.0-2.26-EDR
MVAPICH2/2.3-GCC-6.4.0-2.28-EDR
MVAPICH2/2.3-iccifort-2013_sp1.0.080-EDR
MVAPICH2/2.3-iccifort-2015.2.164-GCC-4.8.5-EDR
MVAPICH2/2.3-iccifort-2018.1.163-GCC-6.4.0-2.28-EDR
</pre>

Note that code compiled with an MVAPICH2 module that has an -EDR suffix will not work on the AMD nodes (QDR IB network). Please continue to use the MVAPICH2 modules that do not have an -EDR suffix if you want to run the jobs on the AMD nodes.

Code Compilation on Sapelo2

2026-05-06T16:05:14Z

Shtsai: /* Where should I compile my code? */

[[Category:Sapelo2]]

==Where should I compile my code?==



Please DO NOT compile source code on the login node. Instead, compile your code in an interactive session started with the <code>interact</code> command.

Code compilation can be done in an interactive session. To start an interactive session, first login into Sapelo2 and from there issue the <code>'''[[Running Jobs on Sapelo2#How to open an interactive session|interact]]'''</code> command
<pre class="gcommand">
interact
</pre>
If you plan to run the code on an AMD node, you can start an interactive session on an AMD node to compile the code. To start an interactive on an AMD node, use the command
<pre class="gcommand">
interact --constraint AMD
</pre>

If you plan to run the code on an Intel node, you can start an interactive session on an Intel node to compile the code. To start an interactive on an Intel node, use the command
<pre class="gcommand">
interact --constraint Intel
</pre>

For detailed information on how to access the compute node interactively for code compilation, please see [[Running Jobs on Sapelo2]].

----

==Compilers==

A number of Fortran and C/C++ compilers, as well as Java and scripting languages such as Perl and Python, are available on Sapelo2.

=== Summary of main Fortran and C/C++ compilers installed ===
{| width="100%" border="1" cellspacing="0" cellpadding="2" align="center" class="wikitable unsortable"
|-
! scope="col" |
! scope="col" | NVHPC
! scope="col" | Intel
! scope="col" | GNU
! scope="col" | OpenMPI
! scope="col" | File extension
|-

| Fortran77 || nvfortran
| ifort || gfortran
| mpif77|| .f
|-
| Fortran90 || nvfortran
| ifort || gfortran|| mpif90|| .f90
|-
| Fortran95 || nvfortran
| ifort || gfortran || mpifort || .f95
|-
|Fortran2003
|nvfortran
|ifort
|gfortran
|mpifort
|.f
|-
| C || nvc || icc || gcc || mpicc || .c
|-
| C++ || nvcc || icpc || g++ || mpicxx || .C, .cpp, .cc
|-

|}

The various compiler suites are provided by their environment modules.

=== GNU compiler suites ===
The following command will show all the modules that provide GCC compiler suites:
<pre class="gcommand">
module spider GCC
</pre>

Sample partial output of this command:
<pre class="gcomment">
[shtsai@d2-13 ~]$ module spider GCC
-----------------------------------------------------------------------------------------------------------------
GCC:
-----------------------------------------------------------------------------------------------------------------
Description:
The GNU Compiler Collection includes front ends for C, C++, Objective-C, Fortran, Java, and Ada, as well as libraries for these languages (libstdc++, libgcj,...).

Versions:
GCC/11.2.0
GCC/11.3.0
GCC/12.3.0
GCC/13.2.0
GCC/13.3.0
Other possible modules matches:
GCCcore
-----------------------------------------------------------------------------------------------------------------
</pre>

This output indicates that the following versions of GCC compilers are available:

*Version 11.2.0, with binutils 2.37, provided by the GCC/11.2.0 module, includes C, C++, and Fortran compilers.
*Version 11.3.0, with binutils 2.38, provided by the GCC/11.3.0 module, includes C, C++, and Fortran compilers.
*Version 12.3.0, with binutils 2.40, provided by the GCC/12.3.0 module, includes C, C++, and Fortran compilers.
*Version 13.2.0, with binutils 2.40, provided by the GCC/13.2.0 module, includes C, C++, and Fortran compilers.
*Version 13.3.0, with binutils 2.42, provided by the GCC/13.3.0 module, includes C, C++, and Fortran compilers.

We suggest that you run the<code> module spider GCC</code> command to check an updated list of GCC compilers available on the cluster.

=== Intel compiler suites ===
The following command will show all the modules that provide Intel compiler suites:
<pre class="gcommand">
module spider intel-compilers
</pre>

Sample output of this command
<pre class="gcomment">
[shtsai@d2-13 ~]$ ml spider intel-compilers

-----------------------------------------------------------------------------------------------------------------
intel-compilers:
-----------------------------------------------------------------------------------------------------------------
Description:
Intel C, C++ & Fortran compilers (classic and oneAPI)

Versions:
intel-compilers/2021.4.0
intel-compilers/2022.1.0
intel-compilers/2023.1.0
intel-compilers/2023.2.1
intel-compilers/2024.2.0
-----------------------------------------------------------------------------------------------------------------
</pre>

This output indicates that the following versions of the Intel compiler suites are available:

*Version 2021.4.0, provided by the intel-compilers/2021.4.0 module.
*Version 2022.1.0, provided by the intel-compilers/2022.1.0 module.
*Version 2023.1.0, provided by the intel-compilers/2023.1.0 module.
*Version 2023.2.1, provided by the intel-compilers/2023.2.1 module.
*Version 2024.2.0, provided by the intel-compilers/2024.2.0 module.

We suggest that you run the <code>module spider intel-compilers</code> or <code>module spider iccifort</code> command to check an updated list of Intel compilers available on the cluster.

=== LLVM compiler suites ===
The following command will show all the modules that provide LLVM compilers:
<pre class="gcommand">
module spider LLVM
</pre>
Sample output of this command
<pre class="gcomment">
[shtsai@d2-13 ~]$ module spider LLVM
------------------------------------------------------------------------------------------------------------------------------------
LLVM:
------------------------------------------------------------------------------------------------------------------------------------
Description:
The LLVM Core libraries provide a modern source- and target-independent optimizer, along with code generation support for many popular CPUs (as well as some less common ones!) These libraries are built around a well specified
code representation known as the LLVM intermediate representation ("LLVM IR"). The LLVM Core libraries are well documented, and it is particularly easy to invent your own language (or port an existing compiler) to use LLVM as an
optimizer and code generator.

Versions:
LLVM/14.0.3-GCCcore-11.3.0
LLVM/14.0.6-GCCcore-12.3.0-llvmlite
LLVM/14.0.6-GCCcore-13.3.0-llvmlite
LLVM/16.0.6-GCCcore-12.3.0
LLVM/16.0.6-GCCcore-13.2.0
LLVM/18.1.8-GCCcore-13.3.0-minimal

-----------------------------------------------------------------------------------------------------------------------------------
</pre>

=== How to load a compiler module ===

To use any of the compiler suite, please first load the corresponding module. For example, to use the GNU 12.3.0 compiler suite, load the module with<pre class="gcommand">
module load GCC/12.3.0
</pre>
Once this module is loaded the gcc, g++, and gfortran for GCC v. 12.3.0 will be available in your path.

Please note that you can only have one compiler module loaded at a time.

=== Some commonly used compiler options ===

====Intel compiler suite====
{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Option
! scope="col" |Description
|-

| -O0||Specifies no optimization, recommended for code debugging
|-
| -O2 ||Enables optimizations for speed. This is the generally recommended optimization level.
|-
| -O3||Performs -O2 optimizations and more aggressive loop transformations. Use with care.
|-
| -fast ||Chooses generally good optimization options for the platform. Type pgcc -fast -help to see the equivalent options.
|-
| -Mbounds ||Performs runtime array bound check, recommended for code debugging
|}

====GNU compiler suite====
{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Option
! scope="col" | Description
|-

| -O0||Specifies no optimization, recommended for code debugging
|-
| -O2 ||Enables optimizations for speed. This is the generally recommended optimization level.
|-
| -O3||Performs -O2 optimizations and more aggressive loop transformations. Use with care.
|-
| -std=
|Determine the language standard. This option is currently only supported when compiling C or C++.
|-
| -fopenmp
|Enable handling of OpenMP directives "#pragma omp" in C/C++ and "!$omp" in Fortran.
|-
| -fopenacc
| Enable handling of OpenACC directives "#pragma acc" in C/C++ and "!$acc" in Fortran.
|-
|<nowiki>-Wpedantic</nowiki>
|Issue all the warnings demanded by strict ISO C and ISO C++; reject all programs that use forbidden extensions, and some other programs that do not follow ISO C and ISO C++.
|-
| -Wall
|This enables all the warnings about constructions that some users consider questionable.
|}

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

== Compiler Toolchains==
On Sapelo2 we use the [https://easybuild.readthedocs.io/en/latest/ EasyBuild] framework to install software applications. The EasyBuild toolchains are also available for users to compile their own code. Each toolchain provides a compiler suite and some basic libraries, such as MPI, BLAS, LAPACK, FFTW, etc.

More information about compiler toolchains, please [[Available Toolchains and Toolchain Compatibility]].

===foss toolchains===
Most software applications are installed with the '''foss''' toolchain, where '''foss''' is short for “Free and Open Source Software”.

The foss toolchain consists of:

*binutils (https://www.gnu.org/software/binutils/)
*the GNU Compiler Collection (GCC, https://gcc.gnu.org/), i.e. gcc (C), g++ (C++) and gfortran (Fortran)
*the Open MPI library (https://www.open-mpi.org/)
*the OpenBLAS (http://www.openblas.net/) + LAPACK (http://netlib.org/lapack) libraries
*the ScaLAPACK (http://netlib.org/scalapack) library is also included
*the FFTW library (http://fftw.org/)

You can check the foss toolchain modules that are installed on the cluster with the command
<pre class="gcommand">
module spider foss
</pre>

When you load a foss toolchain, all it components will be loaded. For example:
<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load foss/2023a
[shtsai@d2-13 ~]$ module list

Currently Loaded Modules:
1) GCCcore/12.3.0 7) libxml2/2.11.4-GCCcore-12.3.0 13) libfabric/1.18.0-GCCcore-12.3.0 19) FFTW/3.3.10-GCC-12.3.0
2) zlib/1.2.13-GCCcore-12.3.0 8) libpciaccess/0.17-GCCcore-12.3.0 14) PMIx/4.2.4-GCCcore-12.3.0 20) gompi/2023a
3) binutils/2.40-GCCcore-12.3.0 9) hwloc/2.9.1-GCCcore-12.3.0 15) UCC/1.2.0-GCCcore-12.3.0 21) FFTW.MPI/3.3.10-gompi-2023a
4) GCC/12.3.0 10) OpenSSL/1.1 16) OpenMPI/4.1.5-GCC-12.3.0 22) ScaLAPACK/2.2.0-gompi-2023a-fb
5) numactl/2.0.16-GCCcore-12.3.0 11) libevent/2.1.12-GCCcore-12.3.0 17) OpenBLAS/0.3.23-GCC-12.3.0 23) foss/2023a
6) XZ/5.4.2-GCCcore-12.3.0 12) UCX/1.14.1-GCCcore-12.3.0 18) FlexiBLAS/3.3.1-GCC-12.3.0

</pre>

===intel toolchains===
The intel toolchain consists of

*the Intel compiler suite
*the Intel MPI libraries
*the Intel Math Kernel Libraries (MKL)

You can check the intel toolchain modules that are installed on the cluster with the command
<pre class="gcommand">
module spider intel
</pre>

When you load an intel toolchain, all it components will be loaded. For example:
<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load intel/2023a
[shtsai@d2-13 ~]$ module list

Currently Loaded Modules:
1) GCCcore/12.3.0 4) intel-compilers/2023.1.0 7) impi/2021.9.0-intel-compilers-2023.1.0 10) imkl-FFTW/2023.1.0-iimpi-2023a
2) zlib/1.2.13-GCCcore-12.3.0 5) numactl/2.0.16-GCCcore-12.3.0 8) imkl/2023.1.0 11) intel/2023a
3) binutils/2.40-GCCcore-12.3.0 6) UCX/1.14.1-GCCcore-12.3.0 9) iimpi/2023a

</pre>





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

== Linking with libraries==
Some library packages are installed along with some compiler toolchains. Examples of these are OpenBLAS, MKL, FFTW, etc. Other libraries are installed as a separate module, for example, Boost and GSL.

If you want to compile a code that uses a library that is not included with compiler toolchain, you will have to load a library module that uses a[[Available Toolchains and Toolchain Compatibility | compatible]] toolchain. For example, if you want to compile your code with GCC 12.3.0 (or with the foss/2023a toolchain), and you need to use GSL, you can load the GSL/2.7-GCC-12.3.0 module.

Also note that when you load a module for a library or an application, the full path to its installation directory will be stored in an environment variable called '''EBROOT''NAME''''', where ''NAME'' is the name of the application or library. For example, when you load a GSL module, the directory where the GSL libraries are installed will be in an environment variable called EBROOTGSL.

For example:

<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load GCC/12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGCC
/apps/eb/GCCcore/12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGSL

[shtsai@d2-13 ~]$ module load GSL/2.7-GCC-12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGSL
/apps/eb/GSL/2.7-GCC-12.3.0
[shtsai@d2-13 ~]$
</pre>

As shown in the example above, when you load an GSL module, an environment variable called '''EBROOTGSL''' is defined, and it points to the installation path for GSL.

When you compile your code, you can add the compiler option:

<code> -I${EBROOTGSL}/include </code>

and the linker option

<code> -L${EBROOTGSL}/lib -lgsl -lgslcblas </code>

'''Example of program compilation that uses GCC 12.3.0 and GSL v. 2.7:'''

<pre class="gcommand">
module load GSL/2.7-GCC-12.3.0

gcc -O program.c -I${EBROOTGSL}/include -L${EBROOTGSL}/lib -lgsl -lgslcblas -Wl,-rpath=${EBROOTGSL}/lib
</pre>

Users can include the compilation option e.g. '''-Wl,-rpath=${EBROOTGSL}/lib''' to include the library directory in the '''runtime path'''. If this option is not included, then at runtime the user has to load the GSL module again, in order to define the environment variable LD_LIBRARY_PATH.
----
[[#top|Back to Top]]

Code Compilation on Sapelo2

2026-05-06T16:03:17Z

Shtsai: /* Where should I compile my code? */

[[Category:Sapelo2]]

==Where should I compile my code?==

====<big>IMPORTANT: Please DO NOT compile source code on the login node. Instead, compile your code in an interactive session started with the interact command.</big>====

Code compilation can be done in an interactive session. To start an interactive session, first login into Sapelo2 and from there issue the <code>'''[[Running Jobs on Sapelo2#How to open an interactive session|interact]]'''</code> command
<pre class="gcommand">
interact
</pre>
If you plan to run the code on an AMD node, you can start an interactive session on an AMD node to compile the code. To start an interactive on an AMD node, use the command
<pre class="gcommand">
interact --constraint AMD
</pre>

If you plan to run the code on an Intel node, you can start an interactive session on an Intel node to compile the code. To start an interactive on an Intel node, use the command
<pre class="gcommand">
interact --constraint Intel
</pre>

For detailed information on how to access the compute node interactively for code compilation, please see [[Running Jobs on Sapelo2]].

----

==Compilers==

A number of Fortran and C/C++ compilers, as well as Java and scripting languages such as Perl and Python, are available on Sapelo2.

=== Summary of main Fortran and C/C++ compilers installed ===
{| width="100%" border="1" cellspacing="0" cellpadding="2" align="center" class="wikitable unsortable"
|-
! scope="col" |
! scope="col" | NVHPC
! scope="col" | Intel
! scope="col" | GNU
! scope="col" | OpenMPI
! scope="col" | File extension
|-

| Fortran77 || nvfortran
| ifort || gfortran
| mpif77|| .f
|-
| Fortran90 || nvfortran
| ifort || gfortran|| mpif90|| .f90
|-
| Fortran95 || nvfortran
| ifort || gfortran || mpifort || .f95
|-
|Fortran2003
|nvfortran
|ifort
|gfortran
|mpifort
|.f
|-
| C || nvc || icc || gcc || mpicc || .c
|-
| C++ || nvcc || icpc || g++ || mpicxx || .C, .cpp, .cc
|-

|}

The various compiler suites are provided by their environment modules.

=== GNU compiler suites ===
The following command will show all the modules that provide GCC compiler suites:
<pre class="gcommand">
module spider GCC
</pre>

Sample partial output of this command:
<pre class="gcomment">
[shtsai@d2-13 ~]$ module spider GCC
-----------------------------------------------------------------------------------------------------------------
GCC:
-----------------------------------------------------------------------------------------------------------------
Description:
The GNU Compiler Collection includes front ends for C, C++, Objective-C, Fortran, Java, and Ada, as well as libraries for these languages (libstdc++, libgcj,...).

Versions:
GCC/11.2.0
GCC/11.3.0
GCC/12.3.0
GCC/13.2.0
GCC/13.3.0
Other possible modules matches:
GCCcore
-----------------------------------------------------------------------------------------------------------------
</pre>

This output indicates that the following versions of GCC compilers are available:

*Version 11.2.0, with binutils 2.37, provided by the GCC/11.2.0 module, includes C, C++, and Fortran compilers.
*Version 11.3.0, with binutils 2.38, provided by the GCC/11.3.0 module, includes C, C++, and Fortran compilers.
*Version 12.3.0, with binutils 2.40, provided by the GCC/12.3.0 module, includes C, C++, and Fortran compilers.
*Version 13.2.0, with binutils 2.40, provided by the GCC/13.2.0 module, includes C, C++, and Fortran compilers.
*Version 13.3.0, with binutils 2.42, provided by the GCC/13.3.0 module, includes C, C++, and Fortran compilers.

We suggest that you run the<code> module spider GCC</code> command to check an updated list of GCC compilers available on the cluster.

=== Intel compiler suites ===
The following command will show all the modules that provide Intel compiler suites:
<pre class="gcommand">
module spider intel-compilers
</pre>

Sample output of this command
<pre class="gcomment">
[shtsai@d2-13 ~]$ ml spider intel-compilers

-----------------------------------------------------------------------------------------------------------------
intel-compilers:
-----------------------------------------------------------------------------------------------------------------
Description:
Intel C, C++ & Fortran compilers (classic and oneAPI)

Versions:
intel-compilers/2021.4.0
intel-compilers/2022.1.0
intel-compilers/2023.1.0
intel-compilers/2023.2.1
intel-compilers/2024.2.0
-----------------------------------------------------------------------------------------------------------------
</pre>

This output indicates that the following versions of the Intel compiler suites are available:

*Version 2021.4.0, provided by the intel-compilers/2021.4.0 module.
*Version 2022.1.0, provided by the intel-compilers/2022.1.0 module.
*Version 2023.1.0, provided by the intel-compilers/2023.1.0 module.
*Version 2023.2.1, provided by the intel-compilers/2023.2.1 module.
*Version 2024.2.0, provided by the intel-compilers/2024.2.0 module.

We suggest that you run the <code>module spider intel-compilers</code> or <code>module spider iccifort</code> command to check an updated list of Intel compilers available on the cluster.

=== LLVM compiler suites ===
The following command will show all the modules that provide LLVM compilers:
<pre class="gcommand">
module spider LLVM
</pre>
Sample output of this command
<pre class="gcomment">
[shtsai@d2-13 ~]$ module spider LLVM
------------------------------------------------------------------------------------------------------------------------------------
LLVM:
------------------------------------------------------------------------------------------------------------------------------------
Description:
The LLVM Core libraries provide a modern source- and target-independent optimizer, along with code generation support for many popular CPUs (as well as some less common ones!) These libraries are built around a well specified
code representation known as the LLVM intermediate representation ("LLVM IR"). The LLVM Core libraries are well documented, and it is particularly easy to invent your own language (or port an existing compiler) to use LLVM as an
optimizer and code generator.

Versions:
LLVM/14.0.3-GCCcore-11.3.0
LLVM/14.0.6-GCCcore-12.3.0-llvmlite
LLVM/14.0.6-GCCcore-13.3.0-llvmlite
LLVM/16.0.6-GCCcore-12.3.0
LLVM/16.0.6-GCCcore-13.2.0
LLVM/18.1.8-GCCcore-13.3.0-minimal

-----------------------------------------------------------------------------------------------------------------------------------
</pre>

=== How to load a compiler module ===

To use any of the compiler suite, please first load the corresponding module. For example, to use the GNU 12.3.0 compiler suite, load the module with<pre class="gcommand">
module load GCC/12.3.0
</pre>
Once this module is loaded the gcc, g++, and gfortran for GCC v. 12.3.0 will be available in your path.

Please note that you can only have one compiler module loaded at a time.

=== Some commonly used compiler options ===

====Intel compiler suite====
{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Option
! scope="col" |Description
|-

| -O0||Specifies no optimization, recommended for code debugging
|-
| -O2 ||Enables optimizations for speed. This is the generally recommended optimization level.
|-
| -O3||Performs -O2 optimizations and more aggressive loop transformations. Use with care.
|-
| -fast ||Chooses generally good optimization options for the platform. Type pgcc -fast -help to see the equivalent options.
|-
| -Mbounds ||Performs runtime array bound check, recommended for code debugging
|}

====GNU compiler suite====
{| class="wikitable unsortable" width="100%" border="1" cellspacing="0" cellpadding="2" align="center"
|-
! scope="col" |Option
! scope="col" | Description
|-

| -O0||Specifies no optimization, recommended for code debugging
|-
| -O2 ||Enables optimizations for speed. This is the generally recommended optimization level.
|-
| -O3||Performs -O2 optimizations and more aggressive loop transformations. Use with care.
|-
| -std=
|Determine the language standard. This option is currently only supported when compiling C or C++.
|-
| -fopenmp
|Enable handling of OpenMP directives "#pragma omp" in C/C++ and "!$omp" in Fortran.
|-
| -fopenacc
| Enable handling of OpenACC directives "#pragma acc" in C/C++ and "!$acc" in Fortran.
|-
|<nowiki>-Wpedantic</nowiki>
|Issue all the warnings demanded by strict ISO C and ISO C++; reject all programs that use forbidden extensions, and some other programs that do not follow ISO C and ISO C++.
|-
| -Wall
|This enables all the warnings about constructions that some users consider questionable.
|}

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

== Compiler Toolchains==
On Sapelo2 we use the [https://easybuild.readthedocs.io/en/latest/ EasyBuild] framework to install software applications. The EasyBuild toolchains are also available for users to compile their own code. Each toolchain provides a compiler suite and some basic libraries, such as MPI, BLAS, LAPACK, FFTW, etc.

More information about compiler toolchains, please [[Available Toolchains and Toolchain Compatibility]].

===foss toolchains===
Most software applications are installed with the '''foss''' toolchain, where '''foss''' is short for “Free and Open Source Software”.

The foss toolchain consists of:

*binutils (https://www.gnu.org/software/binutils/)
*the GNU Compiler Collection (GCC, https://gcc.gnu.org/), i.e. gcc (C), g++ (C++) and gfortran (Fortran)
*the Open MPI library (https://www.open-mpi.org/)
*the OpenBLAS (http://www.openblas.net/) + LAPACK (http://netlib.org/lapack) libraries
*the ScaLAPACK (http://netlib.org/scalapack) library is also included
*the FFTW library (http://fftw.org/)

You can check the foss toolchain modules that are installed on the cluster with the command
<pre class="gcommand">
module spider foss
</pre>

When you load a foss toolchain, all it components will be loaded. For example:
<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load foss/2023a
[shtsai@d2-13 ~]$ module list

Currently Loaded Modules:
1) GCCcore/12.3.0 7) libxml2/2.11.4-GCCcore-12.3.0 13) libfabric/1.18.0-GCCcore-12.3.0 19) FFTW/3.3.10-GCC-12.3.0
2) zlib/1.2.13-GCCcore-12.3.0 8) libpciaccess/0.17-GCCcore-12.3.0 14) PMIx/4.2.4-GCCcore-12.3.0 20) gompi/2023a
3) binutils/2.40-GCCcore-12.3.0 9) hwloc/2.9.1-GCCcore-12.3.0 15) UCC/1.2.0-GCCcore-12.3.0 21) FFTW.MPI/3.3.10-gompi-2023a
4) GCC/12.3.0 10) OpenSSL/1.1 16) OpenMPI/4.1.5-GCC-12.3.0 22) ScaLAPACK/2.2.0-gompi-2023a-fb
5) numactl/2.0.16-GCCcore-12.3.0 11) libevent/2.1.12-GCCcore-12.3.0 17) OpenBLAS/0.3.23-GCC-12.3.0 23) foss/2023a
6) XZ/5.4.2-GCCcore-12.3.0 12) UCX/1.14.1-GCCcore-12.3.0 18) FlexiBLAS/3.3.1-GCC-12.3.0

</pre>

===intel toolchains===
The intel toolchain consists of

*the Intel compiler suite
*the Intel MPI libraries
*the Intel Math Kernel Libraries (MKL)

You can check the intel toolchain modules that are installed on the cluster with the command
<pre class="gcommand">
module spider intel
</pre>

When you load an intel toolchain, all it components will be loaded. For example:
<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load intel/2023a
[shtsai@d2-13 ~]$ module list

Currently Loaded Modules:
1) GCCcore/12.3.0 4) intel-compilers/2023.1.0 7) impi/2021.9.0-intel-compilers-2023.1.0 10) imkl-FFTW/2023.1.0-iimpi-2023a
2) zlib/1.2.13-GCCcore-12.3.0 5) numactl/2.0.16-GCCcore-12.3.0 8) imkl/2023.1.0 11) intel/2023a
3) binutils/2.40-GCCcore-12.3.0 6) UCX/1.14.1-GCCcore-12.3.0 9) iimpi/2023a

</pre>





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

== Linking with libraries==
Some library packages are installed along with some compiler toolchains. Examples of these are OpenBLAS, MKL, FFTW, etc. Other libraries are installed as a separate module, for example, Boost and GSL.

If you want to compile a code that uses a library that is not included with compiler toolchain, you will have to load a library module that uses a[[Available Toolchains and Toolchain Compatibility | compatible]] toolchain. For example, if you want to compile your code with GCC 12.3.0 (or with the foss/2023a toolchain), and you need to use GSL, you can load the GSL/2.7-GCC-12.3.0 module.

Also note that when you load a module for a library or an application, the full path to its installation directory will be stored in an environment variable called '''EBROOT''NAME''''', where ''NAME'' is the name of the application or library. For example, when you load a GSL module, the directory where the GSL libraries are installed will be in an environment variable called EBROOTGSL.

For example:

<pre class="gcommand">
[shtsai@d2-13 ~]$ module list
No modules loaded
[shtsai@d2-13 ~]$ module load GCC/12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGCC
/apps/eb/GCCcore/12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGSL

[shtsai@d2-13 ~]$ module load GSL/2.7-GCC-12.3.0
[shtsai@d2-13 ~]$ echo $EBROOTGSL
/apps/eb/GSL/2.7-GCC-12.3.0
[shtsai@d2-13 ~]$
</pre>

As shown in the example above, when you load an GSL module, an environment variable called '''EBROOTGSL''' is defined, and it points to the installation path for GSL.

When you compile your code, you can add the compiler option:

<code> -I${EBROOTGSL}/include </code>

and the linker option

<code> -L${EBROOTGSL}/lib -lgsl -lgslcblas </code>

'''Example of program compilation that uses GCC 12.3.0 and GSL v. 2.7:'''

<pre class="gcommand">
module load GSL/2.7-GCC-12.3.0

gcc -O program.c -I${EBROOTGSL}/include -L${EBROOTGSL}/lib -lgsl -lgslcblas -Wl,-rpath=${EBROOTGSL}/lib
</pre>

Users can include the compilation option e.g. '''-Wl,-rpath=${EBROOTGSL}/lib''' to include the library directory in the '''runtime path'''. If this option is not included, then at runtime the user has to load the GSL module again, in order to define the environment variable LD_LIBRARY_PATH.
----
[[#top|Back to Top]]

Job Submission partitions on Sapelo2

2026-05-06T15:55:19Z

Shtsai:

[[category:sapelo2]]

== Overview ==
This page describes the Slurm partitions available on the Sapelo2 cluster, including job limits and the resources available in each partition.

In Slurm, queues are called ''partitions''. When you submit a job, you must request both:
* the partition to use, and
* the resources your job needs, such as CPU cores, memory, or GPU devices.

Slurm will reject a job submission if no nodes match the resources you request. For background on Slurm, see [[Migrating from Torque to Slurm]].

== How to use this page ==
Use the first table to choose a partition based on job type and time limit.

Use the second table to confirm that your requested resources fit within the hardware available in that partition.

== Partition limits ==
{| class="wikitable unsortable"
|+ Sapelo2 partitions, time limits, and per-user job limits
|-
! scope="col" | Partition name
! scope="col" | Time limit
! scope="col" | Maximum running jobs per user
! scope="col" | Maximum submitted jobs per user
! scope="col" | Intended use and notes
|-
! scope="row" | <code>batch</code>
| 7 days
| 250
| 10,000
| Standard partition for regular compute jobs on general-purpose nodes.
|-
! scope="row" | <code>batch_30d</code>
| 30 days
| 1
| 2
| Standard partition for long-running jobs on regular nodes. A user may have one running job and one pending job, or two pending jobs and no running job. A third submission to this partition will be rejected.
|-
! scope="row" | <code>highmem_p</code>
| 7 days
| 6
| 100
| High-memory partition for jobs that require more memory than standard nodes provide.
|-
! scope="row" | <code>highmem_30d_p</code>
| 30 days
| 1
| 2
| High-memory partition for long-running jobs. A user may have one running job and one pending job, or two pending jobs and no running job. A third submission to this partition will be rejected.
|-
! scope="row" | <code>hugemem_p</code>
| 7 days
| 4
| 4
| Huge-memory partition for jobs needing up to 3 TB of memory.
|-
! scope="row" | <code>hugemem_30d_p</code>
| 30 days
| 4
| 4
| Huge-memory partition for long-running jobs needing up to 3 TB of memory.
|-
! scope="row" | <code>gpu_p</code>
| 7 days
| 6
| 20
| GPU-enabled partition for jobs that require one or more GPUs.
|-
! scope="row" | <code>gpu_30d_p</code>
| 30 days
| 2
| 2
| GPU-enabled partition for long-running jobs. A user may have one running job and one pending job, or two pending jobs and no running job. A third submission to this partition will be rejected.
|-
! scope="row" | <code>inter_p</code>
| 2 days
| 3
| 20
| Interactive partition for interactive jobs on regular nodes.
|-
! scope="row" | <code>''name''_p</code>
| Variable
| Variable
| Variable
| Partition for a specific group's buy-in nodes. Replace <code>''name''</code> with the group-specific partition prefix.
|}

== Resource limits by partition ==
Before submitting a job, make sure your requested memory, CPU cores, and GPU count fit within the limits of the partition you choose.

In the table below, the phrase '''partition maximum''' identifies the largest per-node resource values available within that partition. This replaces color-only emphasis so that the information is available to all users.

{| class="wikitable unsortable"
|+ Node resources available in each Sapelo2 partition
|-
! scope="col" | Partition
! scope="col" | Number of nodes
! scope="col" | Memory per node (GB)
! scope="col" | CPU cores per node
! scope="col" | Processor type
! scope="col" | GPU configuration
! scope="col" | Notes
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 16
| 740
| 128
| AMD EPYC Genoa (4th gen)
| None
| Partition maximum for memory and cores is available on this node type.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 120
| 500
| 128
| AMD EPYC Milan (3rd gen)
| None
| Partition maximum for cores is also available on this node type.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 4
| 250
| 64
| AMD EPYC Milan (3rd gen)
| None
| Standard-capacity general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 2
| 120
| 64
| AMD EPYC Milan (3rd gen)
| None
| Standard-capacity general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 123
| 120
| 64
| AMD EPYC Rome (2nd gen)
| None
| Standard-capacity general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 25
| 120
| 32
| AMD EPYC Naples (1st gen)
| None
| Lower-core-count general-purpose nodes.
|-
! scope="row" | <code>batch</code>, <code>batch_30d</code>
| 40
| 180
| 32
| Intel Xeon Skylake
| None
| Lower-core-count general-purpose nodes.
|-
! scope="row" | <code>highmem_p</code>, <code>highmem_30d_p</code>
| 10
| 500
| 32
| AMD EPYC Naples (1st gen)
| None
| High-memory nodes.
|-
! scope="row" | <code>highmem_p</code>, <code>highmem_30d_p</code>
| 2
| 990
| 128
| AMD EPYC Milan (3rd gen)
| None
| Partition maximum for memory and cores is available on this node type.
|-
! scope="row" | <code>highmem_p</code>, <code>highmem_30d_p</code>
| 12
| 990
| 32
| AMD EPYC Milan (3rd gen)
| None
| High-memory nodes with fewer available cores per node.
|-
! scope="row" | <code>hugemem_p</code>, <code>hugemem_30d_p</code>
| 3
| 3000
| 48
| AMD EPYC Genoa (4th gen)
| None
| Partition maximum for memory and cores is available on this node type.
|-
! scope="row" | <code>hugemem_p</code>, <code>hugemem_30d_p</code>
| 2
| 2000
| 32
| AMD EPYC Rome (2nd gen)
| None
| Huge-memory nodes with lower maximums than the partition peak.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 2
| 180
| 32
| Intel Xeon Skylake
| 1 NVIDIA P100
| Older GPU nodes.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 2
| 120
| 64
| AMD EPYC Rome (2nd gen)
| 1 NVIDIA V100S
| Single-GPU nodes with 64 cores.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 14
| 1000
| 64
| AMD EPYC Milan (3rd gen)
| 4 NVIDIA A100
| Partition maximum for memory is available on this node type.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 12
| 1000
| 64
| Intel Xeon Sapphire Rapids
| 4 NVIDIA H100
| Partition maximum for memory is available on this node type.
|-
! scope="row" | <code>gpu_p</code>, <code>gpu_30d_p</code>
| 12
| 740
| 128
| AMD EPYC Genoa (4th gen)
| 4 NVIDIA L4
| Partition maximum for cores is available on this node type.
|-
! scope="row" | <code>''name''_p</code>
| Variable
| Variable
| Variable
| Variable
| Variable
| Resource limits depend on the group's buy-in nodes.
|}

== Choosing a partition ==
A general rule of thumb is:

* Use <code>batch</code> for most non-GPU jobs.
* Use <code>batch_30d</code> only when your job genuinely needs a longer wall time.
* Use <code>highmem_p</code> or <code>highmem_30d_p</code> when your memory requirements exceed what standard nodes provide.
* Use <code>hugemem_p</code> or <code>hugemem_30d_p</code> for jobs that need very large memory allocations, including jobs approaching 3 TB of memory.
* Use <code>gpu_p</code> or <code>gpu_30d_p</code> for GPU jobs.
* Use <code>inter_p</code> for interactive work.
* Use <code>''name''_p</code> only if your group has access to a buy-in partition with that name.



== Terms used on this page ==
; Partition
: A Slurm queue that determines which nodes your job may run on.
; Time limit
: The maximum wall-clock runtime allowed for a job in that partition.
; Running jobs
: Jobs currently executing for a user in that partition.
; Submitted jobs
: Total jobs a user may have in the partition, including running and pending jobs.
; Buy-in nodes
: Nodes purchased by a specific group and made available through a group-specific partition.

== Related documentation ==
* [[Migrating from Torque to Slurm]]

Software

2026-04-30T17:10:20Z

Shtsai: /* Partial List of Installed Software */

On Sapelo2 and on the Teaching cluster users have the option to install their own software or use software installed centrally by the GACRC staff. Detailed information on how to find and access software packages installed on Sapelo2 are available at the [[Software on Sapelo2]] page and on the teaching cluster at the [[Software on Teaching Cluster]] page.

Below is a very limited list of software packages installed on Sapelo2 and on the Teaching cluster. We only intend to make an application page for software packages that requires extra documentation not covered in [[Software on Sapelo2]] or [[Software on Teaching Cluster]].

To view a list of all modules installed on Sapelo2/Teaching, along with a short description of each module, please run the following command on Sapelo2/Teaching:
<pre class="gcommand">
module spider
</pre>
You can also use the command above to search for a specific application. For more information, please see [[Lmod]].

The '''file transfer''' nodes ('''xfer''' nodes) do not have environment modules installed. File transfer utilities are installed centrally on the xfer nodes and available on the users' default PATH. Such utilities include bs (basespace-cli), fpsync, rclone, rsync, etc.
https://wiki.gacrc.uga.edu/wiki/Main_Page

'''Note:''' Although we have not made individual software pages for the applications installed on Sapelo2, there are currently over 1300 software packages installed there. For more information, please see [[Software on Sapelo2]].

==Partial List of Installed Software==
Last updated '''{{REVISIONYEAR}}-{{REVISIONMONTH}}-{{REVISIONDAY2}}'''. This is a partial list of installed software so there may be software or versions of software available on Sapelo2 which are not included in this table.
'''Note:''' Click on the icons to the right of the column headings to sort the table.
[[#0|0-9]] [[#A|A]] [[#B|B]] [[#C|C]] [[#D|D]] [[#E|E]] [[#F|F]] [[#G|G]] [[#H|H]] [[#I|I]] [[#J|J]] [[#K|K]] [[#L|L]] [[#M|M]] [[#N|N]] [[#O|O]] [[#P|P]] [[#Q|Q]] [[#R|R]] [[#S|S]] [[#T|T]] [[#U|U]] [[#V|V]] [[#W|W]] [[#X|X]] [[#Y|Y]] [[#Z|Z]]
{| width="100%" border="1" cellspacing="0" cellpadding="2" align="center" class="wikitable sortable"
|-
! scope="col" width="200px"| Name
! scope="col" class="unsortable" width="240px"| Version
! scope="col" width="160px"| Category
! scope="col" width="60px"| Cluster
! scope="col" width="20px"| Top
|-













| [[AlphaFold-Sapelo2|AlphaFold 2]] || 2.3.1, 2.3.2 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-
|- -->
| [[AlphaFold3-Sapelo2|AlphaFold 3]] || 3.0.0, 3.0.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-





| [[AMBER-Sapelo2|AMBER]] || 22.4, 24.3 || [[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->








| [[anvi'o-Sapelo2|anvi'o]] || 4, 5.1, 5.3, 5.4, 6.1, 7, 7.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:sapelo2|sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->














| | [[Bactopia-Sapelo2|Bactopia]] || 3.2.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->


| [[basespace-cli-Sapelo2|basespace-cli]] || 1.2.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->










|[[Beast-Sapelo2|Beast]] || 1.10.4, 2.5.1, 2.6.3, 2.7.3, 2.7.5 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->










| [[BioPython-Sapelo2|BioPython]] || 1.76, 1.79, 1.80, 1.83, 1.84 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
|[[Biopython-Teaching|Biopython]] || 1.76, 1.79, 1.80, 1.83, 1.84 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-




| [[BLAST+-Sapelo2|BLAST+]] || 2.13.0, 2.14.1, 2.16.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] ||[[File:Up20.png|20px|link=#top]]
|- -->
| [[BLAST+-Teaching|BLAST+]] || 2.13.0, 2.14.1, 2.16.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-








| [[Bowtie2-Sapelo2|Bowtie2]] || 2.4.4, 2.4.5, 2.5.1, 2.5.2, 2.5.4 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[Bowtie2-Teaching|Bowtie2]] || 2.4.4, 2.4.5, 2.5.1, 2.5.2, 2.5.4 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-

| [[Bracken-Sapelo2|Bracken]] || 3.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[BRAKER-Sapelo2|BRAKER]] || 2.1.6, 3.0.3, 3.0.8 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-



| [[BUSCO-Sapelo2|BUSCO]] || 2.0, 4.0.5, 5.4.7, 5.5.0, 5.8.2 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-




| [[Cactus-Sapelo2|Cactus]] || 1.2.3, 2.0.3, 2.4.3, 2.4.4, 2.5.0, 2.6.0, 2.6.7, 2.6.9, 2.7.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-

| [[Canu-Sapelo2|Canu]] || 2.2||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-









| [[CellRanger-ATAC-Sapelo2|CellRanger-ATAC]] || 2.1.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->








| [[Chimera-Teaching|Chimera]] || 1.16 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-























| [[cryoSPARC-Sapelo2|CryoSPARC]] || 3.3.1 || [[:Category:Engineering|Engineering]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-
| [[Cromwell-Sapelo2|Cromwell]] || 56 || [[:Category:Tools|Tools]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-
|[[CUDA-Sapelo2|CUDA]] || 11.7.0, 11.8.0, 12.1.1, 12.4.0, 12.6.0, 12.8.0 ||[[:Category:Programming|Programming]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-







| [[Cytoscape-Sapelo2|Cytoscape]] || 3.9.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[Cytoscape-Teaching|Cytoscape]] || 3.9.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-



























|-->
| [[dMRIharmonization-Sapelo2|dMRIharmonization]] || 20240227 || [[:Category:Engineering|Engineering]]|| [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-->





| [[EGAPx-Sapelo2|EGAPx]] || N/A || [[:Category:Bioinformatics|Bioinformatics]] || N/A || [[File:Up20.png|20px|link=#top]]
|- -->


| [[EIGENSOFT-Sapelo2|EIGENSOFT]] || 7.2.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[EIGENSOFT-Teaching|EIGENSOFT]] || 7.2.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-
| [[Flankophile-Sapelo2|Flankophile]] || 0.2.10 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-






































|-
| [[Funannotate-Sapelo2|Funannotate]] || 1.8.17 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-
|- -->













| [[GAUSSIAN-Sapelo2|GAUSSIAN]] || 09, 16 || [[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
|[[GAUSSIAN-Teaching|GAUSSIAN]] || 09, 16 || [[:Category:Chemistry|Chemistry]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-
| [[GaussView-Sapelo2|GaussView]] || 5, 6.1 || [[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[GaussView-Teaching|GaussView]] || 6.1 || [[:Category:Chemistry|Chemistry]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-







| [[GEM-Sapelo2|GEM]] || 1.5.1 ||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->


| [[GeneMarkES-Sapelo2|GeneMarkET]] || 4.71 ||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->





























|[[gocryptfs-Sapelo2|gocryptfs]] || 2.5.2 || [[:Category:Other|Other]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-





| [[GROMACS-Sapelo2 |GROMACS]] || 2023.4, 2024.4 ||[[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->


















| [[HISAT2-Sapelo2|HISAT2]] || 2.2.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[HISAT2-Teaching|HISAT2]] || 2.2.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->



| [[HpcGridRunner-Sapelo2|HPCGridRunner]] || 1.0.2 || [[:Category:Tools|Tools]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-










|-
| [[iCommands-Sapelo2|iCommands]] || 4.2.8 || [[:Category:Tools|Tools]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-










| [[InterProScan-Sapelo2|InterProScan]] || 5.63-95.0, 5.64-96.0, 5.66-98.0 ||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->



| [[IQ-Tree-Sapelo2|IQ-Tree]] || 2.2.2.7, 2.3.5, 2.3.6, 3.0.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[IQ-Tree-Teaching|IQ-Tree]] || 2.2.2.7, 2.3.5, 2.3.6, 3.0.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-








| [[Java-Teaching|Java]] || 1.8.0_241, 1.8.0_311, 11.0.20, 17.0.6, 21.0.2, 21.0.5 || [[:Category:Programming|Programming]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-






| [[Jupyter-Sapelo2|Jupyter]] || 6.5.6, 7.0.2, 7.2.0, 7.2.3 || [[:Category:Programming|Programming]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-
| [[Jupyter-Teaching|Jupyter]] || 6.4.12 || [[:Category:Programming|Programming]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-
|- -->













| [[LAMMPS-Sapelo2|LAMMPS]] || 23Jun2022 || [[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-



































| [[Magma-Sapelo2|Magma]] || 2.27-1, 2.28-27 || [[:Category:Other|Other]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-


| [[Maker-Sapelo2|Maker]] || 3.01.04 ||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-









| [[MATLAB-Sapelo2|MATLAB]] || R2023a, R2023b || [[:Category:Programming|Programming]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-









| [[Medusa-Sapelo2 |Medusa]] || 1.6 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-













| [[MetaPhlAn4-Sapelo2|MetaPhlAn4]] || 4.0.3.1, 4.0.6, 4.1.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-









































| [[Nsight-Compute-CLI-Sapelo2|Nsight Compute CLI]] || 2024.3.0.0, 2025.1.0.0, 2025.4.0.0 || [[:Category:Other|Other]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-




































| [[Ont-Guppy-Sapelo2|Ont-Guppy]] || 6.5.7 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-





| [[ORCA-Sapelo2 |ORCA]] || 4.2.1, 5.0.4 || [[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-




|[[ORP-Sapelo2|ORP]] || 2.2.6, 2.2.8 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[OrthoFinder-Sapelo2|OrthoFinder]] || 2.5.4, 2.5.5 ||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->








| [[PAML-Teaching|PAML]] || 4.9j, 4.10.5 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->









| [[PASA-Sapelo2|PASA]] || 2.5.3 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->













| [[Perl-Teaching|Perl]] || 5.34.0, 5.34.1, 5.36.0, 5.36.1, 5.38.0, 5.38.2, 5.40.0, 5.40.2 || [[:Category:Programming|Programming]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->







| [[Phenix-Sapelo2|Phenix]] || 1.21.2-5419 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-

























































|-
| [[Python-Sapelo2 |Python]] || 2.7.18, 3.9.6, 3.10.4, 3.10.8, 3.11.3, 3.11.5, 3.12.3, 3.13.1, 3.13.5 || [[:Category:Programming|Programming]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[Python-Teaching|Python]] || 2.7.18, 3.9.6, 3.10.4, 3.10.8, 3.11.3, 3.11.5, 3.12.3, 3.13.1, 3.13.5 || [[:Category:Programming|Programming]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->






| [[QIIME2-Sapelo2|QIIME2]] || 2020.6, 2023.2, 2023.5.1, 2023.7, 2023.9, 2024.2 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->







| [[R-Sapelo2 |R]] || 4.2.1, 4.3.1, 4.3.2, 4.4.1, 4.4.2, 4.5.1 ||[[:Category:Statistics|Statistics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-
| [[R-Teaching|R]] || 4.2.1, 4.3.1, 4.3.2, 4.4.1, 4.4.2, 4.5.1 || [[:Category:Statistics|Statistics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[racon-Sapelo2 |Racon]] || 1.5.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-




| [[RAxML-NG-Sapelo2 |RAxML-NG]] || 1.2.2 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[RAxML-Sapelo2 |RAxML]] || 8.2.13 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[RAxML-Teaching|RAxML]] || 8.2.13 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->

















| [[RevBayes-Teaching|RevBayes]] || 1.1.0, 1.2.1 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-







| [[Rosetta-Sapelo2 |Rosetta]] || 2021.16.61629, 2022.46.334 ||[[:Category:Chemistry|Chemistry]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->


| [[Rstudio-Sapelo2|Rstudio]] || 2023.06.1-524 || [[:Category:Other|Other]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-










| [[SAMtools-Teaching|SAMtools]] || 0.1.20, 1.6, 1.13, 1.14, 1.16.1, 1.18, 1.21 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|- -->

| [[SequenceTubeMap-Sapelo2|sequenceTubeMap]] || 20230906 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:sapelo2|sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->









































| [[snpEff-Sapelo2|snpEff]] || 5.0e || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->





















| [[SRAToolKit-Sapelo2 |SRAToolKit]] || 3.0.1, 3.0.3 ||[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->













| [[StringTie-Teaching|StringTie]] || 2.2.3, 3.0.0 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-
| [[Structure-Sapelo2|Structure]] || 2.3.4 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->
| [[Structure-Teaching|Structure]] || 2.3.4 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Teaching|Teaching]] || [[File:Up20.png|20px|link=#top]]
|-


































| [[Trinity-Sapelo2|Trinity]] || 2.5.1, 2.8.4, 2.8.5, 2.15.1, 2.15.2 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->



| [[UBCG-Sapelo2|UBCG]] || 3.0
|[[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|-














| [[Velvet-Sapelo2|Velvet]] || 1.2.10 || [[:Category:Bioinformatics|Bioinformatics]] || [[:Category:Sapelo2|Sapelo2]] || [[File:Up20.png|20px|link=#top]]
|- -->






















|}
[[#top|Back To Top]] [[File:Up20.png|20px|link=#top]]

[[Category:Sapelo2]][[Category:Teaching]][[Category:Software]]

MATLAB-Sapelo2

2026-04-14T16:10:22Z

Shtsai: /* Running Program */

[[Category:Sapelo2]][[Category:Software]][[Category:Other]][[Category:Programming]][[Category:Graphics]]
== Category ==

Other, Programming, Graphics

== Program On ==

Sapelo2

== Version ==

R2023b

== Author / Distributor ==

The MathWorks (see http://www.mathworks.com)

== Description ==

MATLAB is a high-level technical computing language and interactive environment for algorithm development, data visualization, data analysis, and numeric computation.

== Running Program ==

Also refer to [[Running Jobs on Sapelo2]]

For more information on Environment Modules on Sapelo2 please see the [[Lmod]] page.

* Version R2023b is installed in /apps/gb/MATLAB/R2023b. In order to use this version of MATLAB, please first load the matlab/R2023b module with
<pre class="gcommand">
ml matlab/R2023b
</pre>

===Running MATLAB interactively===

Please do not run MATLAB interactively on the Sapelo2 login node, instead please run it using the [[Running_Jobs_on_Sapelo2#How_to_open_an_interactive_session | interactive partition]] (without GUI) or using [[OnDemand]] (with GUI).

The best way to run MATLAB interactively with a graphical front-end (GUI) is to run the MATLAB interactive application in the [[OnDemand]] interface to Sapelo2.

To run MATLAB interactively without a GUI, please first start an interactive job with the '''interact''' command.

For example:



1. To run without the graphical front-end on a regular compute node:
<pre class="gcommand">
interact

ml matlab/R2023b

matlab -nodisplay
</pre>

2. To run without the graphical front-end on a node in a different partition, e.g. in abc_p, or to request more resources (cores or memory), use for example
<pre class="gcommand">
interact -p abc_p -c 4 --mem 20gb

ml matlab/R2023b

matlab -nodisplay
</pre>

For more information on how to run interactive jobs, please see [[Running_Jobs_on_Sapelo2#How_to_open_an_interactive_session | interactive partition]]

===Running MATLAB as a batch job===

MATLAB can also be run as a batch job, for example in the batch partition. To do this, first create a MATLAB M-file with the MATLAB commands. Then use a job submission file to submit this job to the batch partition.

Below is sample MATLAB M-file (matrixinv.m), which is a MATLAB script:
<pre class="gscript">
n = 500;
Q = orth(randn(n,n));
d = logspace(0,-10,n);
A = Q*diag(d)*Q';
x = randn(n,1);
b = A*x;
tic, z = A\b, toc
err = norm(z-x)
res = norm(A*z-b)
</pre>

Sample job submission script file (sub.sh) to run a serial (single-core) matrixinv.m:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=1
#SBATCH --mem=5gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023b

matlab -nodisplay < matrixinv.m
</pre>

The parameters of the job, such as the maximum wall clock time, maximum memory, email address, the number of cores per task, and the job name need to be modified appropriately.

If you are calling a main function defined in a MATLAB M-file, for example, functionname.m, you might have to use a sample script like this:
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=1
#SBATCH --mem=5gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023b

echo 'functionname(arg1,arg2)' | matlab -nodisplay -nosplash
</pre>

To submit either of the two sample files sub.sh to the queue:
<pre class="gcommand">
sbatch sub.sh
</pre>

===Parallel Computing - Using multiple CPU cores on a single compute node ===

The Parallel Computing toolbox allows a user to use many CPU cores. If you want to use cores on the same node for the job you can use the <code>defaultProfile</code>. Here is a simple example using the '''parfor''' loop with 24 MATLAB workers.

Sample code psine.m
<pre class="gscript">
p=parcluster('local');
p.NumWorkers=25;
ppool=parpool(p,24);

parfor i=1:1024
A(i) = sin(i*2*pi/1024);
end
p = gcp;
delete(p)
</pre>

Sample job submission script sub.sh
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=25
#SBATCH --mem=50gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023b

matlab -nodisplay < psine.m
</pre>
Note that the number that follows '''--cpus-per-tasks''' needs to match the number of MATLAB workers defined with <code>NumWorkers</code> in the MATLAB code .

Sample job submission command
<pre class="gcommand">
sbatch sub.sh
</pre>



===Parallel Computing - Using cores from one or more compute nodes ===

In order to use the Parallel Computing toolbox to run MATLAB using either cores on a single node, or to use cores on multiple nodes, you need to configure MATLAB and create a new cluster profile. To do this, please login to Sapelo2, start an interactive session with <code>interact</code>, load the matlab module you want to use and start matlab. For example, to configure this for matlab/R2023b:
<pre class="gcommand">
interact

ml matlab/R2023b

matlab -nodisplay
</pre>

In MATLAB, call the <code>configCluster</code> function:
<pre class="gscript">
>> configCluster
</pre>

This function only needs to be called '''once''' per version of MATLAB. Please be aware that running <code>configCluster</code> more than once per version will reset your cluster profile back to default settings and erase any saved modifications to the profile. If calling the <code>configCluster</code> function returns the error '''Unrecognized function or variable 'configCluster' ''', then run the following command in an interactive MATLAB session:
<pre class="gscript">
>>rehash toolboxcache
</pre>

Sample MATLAB code that can be run in a Slurm batch partition and use more than one node (psine.m)
<pre class="gscript">
c = parcluster;
c.AdditionalProperties.QueueName = 'batch';
c.AdditionalProperties.WallTime = '24:00:00';
c.AdditionalProperties.MemUsage = '5G';
c.saveProfile

p = c.parpool(5);

parfor i=1:1024
A(i) = sin(i*2*pi/1024);
end
p.delete
</pre>
Note that the resources you want this parallel job to use (e.g. partition name, the walltime limit and the memory per CPU need to be specified in this MATLAB code. This parallel job will automatically request as many cores as needed for the parpool defined in the code, and the cores can be allocated on more than one node, if needed. For more details on how to request resources in the MATLAB code, please see the [https://wiki.gacrc.uga.edu/wiki/MatLab-Sapelo2#Configuring_Jobs_from_within_MATLAB_on_the_cluster_or_on_your_local_machine Configuring Jobs from within MATLAB] session below.

Sample job submission script sub.sh:
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=1
#SBATCH --mem-per-cpu=5gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023b

matlab -nodisplay < psine.m
</pre>
Note that this job only needs to request one core. When this job runs, MATLAB will submit another parallel job using the resources specified in the psine.m code. It is important that this script (sub.sh) uses the '''--mem-per-cpu''' option to request memory per cpu and '''not''' the total memory with '''--mem'''.

Sample job submission command
<pre class="gcommand">
sbatch sub.sh
</pre>

===Using a MATLAB client installed on your local machine to run jobs on the cluster===

In order to use a MATLAB client installed on your local machine and have it offload work onto the cluster (Sapelo2), you will need to first install some cluster integration files on your local machine. Please note that you need to have the same version of MATLAB client installed on your local machine, as the MATLAB version you will use on the cluster.

The Sapelo2 MATLAB support package can be found on Sapelo2, at the following location:

'''For R2023a'''

Windows: /apps/gb/MATLAB/UGA.nonshared.R2023a.zip

Linux/macOS: /apps/gb/MATLAB/UGA.nonshared.R2023a.tar.gz

Download the appropriate archive file to your local machine and start MATLAB on your local machine. The archive file should be untarred/unzipped in the location returned by calling
<pre class="gscript">
>> userpath
</pre>

Configure MATLAB to run parallel jobs on your cluster by calling <code>configCluster</code>, which only needs to be called once per version of MATLAB.
<pre class="gscript">
>> configCluster
</pre>

Submission to the remote cluster (Sapelo2) requires SSH credentials and you will need to configure key-based SSH. For information on how to set key-based ssh, please see https://www.ssh.com/academy/ssh/keygen. If your local machine is a Mac, please generate the ssh key with <code>ssh-keygen -t rsa -m PEM</code>. Once you have the key-based ssh set up, you can submit jobs to the cluster from within the MATLAB client on your local machine. You will be prompted for your ssh username and your identity file (private key). The username and location of the private key will be stored in MATLAB for future sessions.

Jobs will now default to the cluster rather than submit to the local machine.

NOTE: If you would like to submit to the local machine then run the following command:
<pre class="gscript">
>> % Get a handle to the local resources
>> c = parcluster('local');
</pre>

===Configuring Jobs from within MATLAB on the cluster or on your local machine===
Prior to having MATLAB submit a job to the cluster, we can specify various parameters to pass to our jobs, such as partition, e-mail, walltime, etc. The WallTime, MemUsage, and QueueName (partition name) fields are mandatory in order to submit a job.

<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

[REQUIRED]

>> % Specify memory to use for MATLAB jobs, per core
>> c.AdditionalProperties.MemUsage = '5G';

>> % Specify a queue to use for MATLAB jobs
>> c.AdditionalProperties.QueueName = 'partition-name';

>> % Specify the walltime (e.g. 5 hours)
>> c.AdditionalProperties.WallTime = '05:00:00';

[OPTIONAL]

>> % Specify an account to use for MATLAB jobs
>> c.AdditionalProperties.AccountName = 'account-name';

>> % Specify e-mail address to receive notifications about your job
>> c.AdditionalProperties.EmailAddress = 'user-id@uga.edu';

>> % Specify constraint for you job
>> c.AdditionalProperties.Constraint = 'Intel';

>> % Specify number of GPUs
>> c.AdditionalProperties.GpusPerNode = 1;

>> % Specify GPU type
>> c.AdditionalProperties.GpuType = 'K40';
</pre>

Save changes after modifying AdditionalProperties for the above changes to persist between MATLAB sessions.
<pre class="gscript">
>> c.saveProfile
</pre>

To see the values of the current configuration options, display AdditionalProperties.
<pre class="gscript">
>> % To view current properties
>> c.AdditionalProperties
</pre>

Unset a value when no longer needed.
<pre class="gscript">
>> % Turn off email notifications
>> c.AdditionalProperties.EmailAddress = '';
>> c.saveProfile
</pre>

===Submitting Independent Batch Jobs from within locally installed MATLAB===
Use the <code>batch</code> command to submit asynchronous jobs to the cluster. Users can either run a single function or a Matlab script as a batch job. You must make sure the script is in the MATLAB path. If running MATLAB locally, the command <code>userpath</code> displays the location you can save your .m scripts. See the MATLAB documentation for <code>userpath</code> if you would like to add directories to that path. Since your local file system is different from the worker file system(Sapelo2), if you are submitting jobs to Sapelo 2 from local MATLAB you also have to set the 'AutoAddClientPath' option to false. The <code>batch</code> command will return a job object which is used to access the output of the submitted job. See the MATLAB documentation for more help on <code>batch</code>.

Shown below is an example submitting a batch job from local MATLAB which runs the script testscript.m. Notice that the .m extension is left off.

<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit job to query where MATLAB is running on the cluster
>> j = batch(testscript,'AutoAddClientPath',false);

>> % Query job for state
>> j.State

>> % If state is finished, fetch the results
>> load(j)

>> % Delete the job after results are no longer needed
>> j.delete
</pre>

You can also run functions with multiple arguments using the <code>batch</code> command. For a function to be available it must be in your MATLAB path. Built in functions will automatically be included, but your own functions you will have to save in your userpath. When running functions, you must specify that you are using the worker established with the <code>parcluster</code> command, so use <code>c.batch</code> instead of <code>batch</code>. The example below shows a job which prints the working directory. When retrieving the data, use the command <code>fetchOutputs</code> instead of <code>load</code>.<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit job to query where MATLAB is running on the cluster
>> j = c.batch(@pwd, 1,'AutoAddClientPath',false);

>> % Query job for state
>> j.State

>> j.fetchOutputs{:}

ans =

'/home/keekov'
</pre>

To retrieve a list of currently running or completed jobs, call <code>parcluster</code> to retrieve the cluster object. The cluster object stores an array of jobs that were run, are running, or are queued to run. This allows us to fetch the results of completed jobs. Retrieve and view the list of jobs as shown below. The <code>Jobs</code> command also allows you to see the job id and status of previously submitted jobs.
<pre class="gscript">
>> c = parcluster;
>> jobs = c.Jobs;
</pre>

Data that has been written to files on the cluster needs be retrieved directly from the file system (e.g. via ftp).

To fetch the outputs of a previously completed job use the <code>fetchOutputs</code> or <code>load</code>command. This job used the function method and so data is retrieved with <code>fetchOutputs</code> instead of <code>load.</code>
<pre class="gscript">
>> % Get a handle to the job with ID 2
>> j2 = c.Jobs(2);
>> % Fetch results for job with ID 2
>> j2.fetchOutputs{:}

</pre>

===Submitting Parallel Batch Jobs from within locally installed MATLAB===
Users can also submit parallel workflows with the <code>batch</code> command. Let’s use the following example for a parallel job, which is saved as ''parallel_example.m''.

<pre class="gscript">
function t = parallel_example(iter)

if nargin==0, iter = 8; end

disp('Start sim')

t0 = tic;
parfor idx = 1:iter
A(idx) = idx;
pause(2)
end
t = toc(t0);

disp('Sim Completed')
</pre>

This time when we use the <code>c.batch</code> command, to run a parallel job, we will also specify a MATLAB Pool.
<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit a batch pool job using 4 workers for 16 simulations
>> j = c.batch(@parallel_example, 1, {16}, 'Pool',4, …
'CurrentFolder','.', 'AutoAddClientPath',false);

>> % View current job status
>> j.State

>> % Fetch the results after a finished state is retrieved
>> j.fetchOutputs{:}
ans =
8.8872
</pre>

The job ran in 8.89 seconds using four workers. Note that these jobs will always request N+1 CPU cores, since one worker is required to manage the batch job and pool of workers. For example, a job that needs eight workers will consume nine CPU cores.

We will run the same simulation but increase the Pool size. This time, to retrieve the results later, we will keep track of the job ID.

NOTE: For some applications, there will be a diminishing return when allocating too many workers, as the overhead may exceed computation time.
<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit a batch pool job using 8 workers for 16 simulations
>> j = c.batch(@parallel_example, 1, {16}, 'Pool', 8, …
'CurrentFolder','.', 'AutoAddClientPath',false);

>> % Get the job ID
>> id = j.ID
id =
4

>> % Clear j from workspace (as though we quit MATLAB)
>> clear j
</pre>

Once we have a handle to the cluster, we will call the <code>findJob</code> method to search for the job with the specified job ID.
<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Find the old job
>> j = c.findJob('ID', 4);

>> % Retrieve the state of the job
>> j.State
ans =
finished

>> % Fetch the results
>> j.fetchOutputs{:};
ans =
4.7270
</pre>

The job now runs in 4.73 seconds using eight workers. Run code with different number of workers to determine the ideal number to use.

=== Parallel Interactive Jobs using MATLAB on the cluster ===
To run an interactive pool job on the cluster, continue to use parpool as you’ve done before. Start an interactive session with qlogin (or with srun), load the matlab module and start MATLAB with <code>matlab -nodislay</code>. In Matlab, run

<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Open a pool of 64 workers on the cluster
>> p = c.parpool(64);
</pre>
Rather than running local on the local machine, the pool can now run across multiple nodes on the cluster.

<pre class="gscript">
>> % Run a parfor over 1000 iterations
>> parfor idx = 1:1000
a(idx) = …
end
</pre>
Once we are done with the pool, delete it.
<pre class="gscript">
>> % Delete the pool
>> p.delete
</pre>

===Debugging a MATLAB job===
If a serial job produces an error, call the <code>getDebugLog</code> method to view the error log file. When submitting independent jobs, with multiple tasks, specify the task number.

<pre class="gscript">
>> c.getDebugLog(j.Tasks(3))
</pre>

For Pool jobs, only specify the job object.
<pre class="gscript">
>> c.getDebugLog(j)
</pre>

When troubleshooting a job, the cluster admin may request the scheduler ID of the job. This can be derived by calling <code>schedID</code>
<pre class="gscript">
>> schedID(j)
ans =
25539
</pre>

== Documentation ==

MATLAB documentation is available at https://www.mathworks.com/help/matlab/

Some documentation and sample files are available on Sapelo2, in /apps/gb/MATLAB/R2023a/help

To learn more about the MATLAB Parallel Computing Toolbox, check out these resources:

*[http://www.mathworks.com/help/parallel-computing/examples.html Parallel Computing Coding Examples]
*[http://www.mathworks.com/help/distcomp/index.html Parallel Computing Documentation]
*[http://www.mathworks.com/products/parallel-computing/index.html Parallel Computing Overview]
*[http://www.mathworks.com/products/parallel-computing/tutorials.html Parallel Computing Tutorials]
*[http://www.mathworks.com/products/parallel-computing/videos.html Parallel Computing Videos]
*[http://www.mathworks.com/products/parallel-computing/webinars.html Parallel Computing Webinars]

== Installation ==

'''Version 2023a'''

Installed in /apps/gb/MATLAB/R2023a.

Available toolboxes: Almost all toolboxes for which UGA has a license. For details, see the directories in /apps/gb/MATLAB/R2023a/toolbox

== System ==
64-bit Linux

MATLAB-Sapelo2

2026-04-14T16:06:14Z

Shtsai: /* Version */

[[Category:Sapelo2]][[Category:Software]][[Category:Other]][[Category:Programming]][[Category:Graphics]]
== Category ==

Other, Programming, Graphics

== Program On ==

Sapelo2

== Version ==

R2023b

== Author / Distributor ==

The MathWorks (see http://www.mathworks.com)

== Description ==

MATLAB is a high-level technical computing language and interactive environment for algorithm development, data visualization, data analysis, and numeric computation.

== Running Program ==

Also refer to [[Running Jobs on Sapelo2]]

For more information on Environment Modules on Sapelo2 please see the [[Lmod]] page.

* Version R2023a is installed in /apps/gb/MATLAB/R2023a. In order to use this version of MATLAB, please first load the matlab/R2023a module with
<pre class="gcommand">
ml matlab/R2023a
</pre>

===Running MATLAB interactively===

Please do not run MATLAB interactively on the Sapelo2 login node, instead please run it using the [[Running_Jobs_on_Sapelo2#How_to_open_an_interactive_session | interactive partition]] (without GUI) or using [[OnDemand]] (with GUI).

The best way to run MATLAB interactively with a graphical front-end (GUI) is to run the MATLAB interactive application in the [[OnDemand]] interface to Sapelo2.

To run MATLAB interactively without a GUI, please first start an interactive job with the '''interact''' command.

For example:



1. To run without the graphical front-end on a regular compute node:
<pre class="gcommand">
interact

ml matlab/R2023a

matlab -nodisplay
</pre>

2. To run without the graphical front-end on a node in a different partition, e.g. in abc_p, or to request more resources (cores or memory), use for example
<pre class="gcommand">
interact -p abc_p -c 4 --mem 20gb

ml matlab/R2023a

matlab -nodisplay
</pre>

For more information on how to run interactive jobs, please see [[Running_Jobs_on_Sapelo2#How_to_open_an_interactive_session | interactive partition]]

===Running MATLAB as a batch job===

MATLAB can also be run as a batch job, for example in the batch partition. To do this, first create a MATLAB M-file with the MATLAB commands. Then use a job submission file to submit this job to the batch partition.

Below is sample MATLAB M-file (matrixinv.m), which is a MATLAB script:
<pre class="gscript">
n = 500;
Q = orth(randn(n,n));
d = logspace(0,-10,n);
A = Q*diag(d)*Q';
x = randn(n,1);
b = A*x;
tic, z = A\b, toc
err = norm(z-x)
res = norm(A*z-b)
</pre>

Sample job submission script file (sub.sh) to run a serial (single-core) matrixinv.m:

<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=1
#SBATCH --mem=5gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023a

matlab -nodisplay < matrixinv.m
</pre>

The parameters of the job, such as the maximum wall clock time, maximum memory, email address, the number of cores per task, and the job name need to be modified appropriately.

If you are calling a main function defined in a MATLAB M-file, for example, functionname.m, you might have to use a sample script like this:
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=1
#SBATCH --mem=5gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023a

echo 'functionname(arg1,arg2)' | matlab -nodisplay -nosplash
</pre>

To submit either of the two sample files sub.sh to the queue:
<pre class="gcommand">
sbatch sub.sh
</pre>

===Parallel Computing - Using multiple CPU cores on a single compute node ===

The Parallel Computing toolbox allows a user to use many CPU cores. If you want to use cores on the same node for the job you can use the <code>defaultProfile</code>. Here is a simple example using the '''parfor''' loop with 24 MATLAB workers.

Sample code psine.m
<pre class="gscript">
p=parcluster('local');
p.NumWorkers=25;
ppool=parpool(p,24);

parfor i=1:1024
A(i) = sin(i*2*pi/1024);
end
p = gcp;
delete(p)
</pre>

Sample job submission script sub.sh
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=25
#SBATCH --mem=50gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023a

matlab -nodisplay < psine.m
</pre>
Note that the number that follows '''--cpus-per-tasks''' needs to match the number of MATLAB workers defined with <code>NumWorkers</code> in the MATLAB code .

Sample job submission command
<pre class="gcommand">
sbatch sub.sh
</pre>



===Parallel Computing - Using cores from one or more compute nodes ===

In order to use the Parallel Computing toolbox to run MATLAB using either cores on a single node, or to use cores on multiple nodes, you need to configure MATLAB and create a new cluster profile. To do this, please login to Sapelo2, start an interactive session with <code>interact</code>, load the matlab module you want to use and start matlab. For example, to configure this for matlab/R2023a:
<pre class="gcommand">
interact

ml matlab/R2021a

matlab -nodisplay
</pre>

In MATLAB, call the <code>configCluster</code> function:
<pre class="gscript">
>> configCluster
</pre>

This function only needs to be called '''once''' per version of MATLAB. Please be aware that running <code>configCluster</code> more than once per version will reset your cluster profile back to default settings and erase any saved modifications to the profile. If calling the <code>configCluster</code> function returns the error '''Unrecognized function or variable 'configCluster' ''', then run the following command in an interactive MATLAB session:
<pre class="gscript">
>>rehash toolboxcache
</pre>

Sample MATLAB code that can be run in a Slurm batch partition and use more than one node (psine.m)
<pre class="gscript">
c = parcluster;
c.AdditionalProperties.QueueName = 'batch';
c.AdditionalProperties.WallTime = '24:00:00';
c.AdditionalProperties.MemUsage = '5G';
c.saveProfile

p = c.parpool(5);

parfor i=1:1024
A(i) = sin(i*2*pi/1024);
end
p.delete
</pre>
Note that the resources you want this parallel job to use (e.g. partition name, the walltime limit and the memory per CPU need to be specified in this MATLAB code. This parallel job will automatically request as many cores as needed for the parpool defined in the code, and the cores can be allocated on more than one node, if needed. For more details on how to request resources in the MATLAB code, please see the [https://wiki.gacrc.uga.edu/wiki/MatLab-Sapelo2#Configuring_Jobs_from_within_MATLAB_on_the_cluster_or_on_your_local_machine Configuring Jobs from within MATLAB] session below.

Sample job submission script sub.sh:
<pre class="gscript">
#!/bin/bash
#SBATCH --job-name=myjobname
#SBATCH --partition=batch
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=1
#SBATCH --mem-per-cpu=5gb
#SBATCH --time=48:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
cd $SLURM_SUBMIT_DIR

ml matlab/R2023a

matlab -nodisplay < psine.m
</pre>
Note that this job only needs to request one core. When this job runs, MATLAB will submit another parallel job using the resources specified in the psine.m code. It is important that this script (sub.sh) uses the '''--mem-per-cpu''' option to request memory per cpu and '''not''' the total memory with '''--mem'''.

Sample job submission command
<pre class="gcommand">
sbatch sub.sh
</pre>

===Using a MATLAB client installed on your local machine to run jobs on the cluster===

In order to use a MATLAB client installed on your local machine and have it offload work onto the cluster (Sapelo2), you will need to first install some cluster integration files on your local machine. Please note that you need to have the same version of MATLAB client installed on your local machine, as the MATLAB version you will use on the cluster.

The Sapelo2 MATLAB support package can be found on Sapelo2, at the following location:

'''For R2023a'''

Windows: /apps/gb/MATLAB/UGA.nonshared.R2023a.zip

Linux/macOS: /apps/gb/MATLAB/UGA.nonshared.R2023a.tar.gz

Download the appropriate archive file to your local machine and start MATLAB on your local machine. The archive file should be untarred/unzipped in the location returned by calling
<pre class="gscript">
>> userpath
</pre>

Configure MATLAB to run parallel jobs on your cluster by calling <code>configCluster</code>, which only needs to be called once per version of MATLAB.
<pre class="gscript">
>> configCluster
</pre>

Submission to the remote cluster (Sapelo2) requires SSH credentials and you will need to configure key-based SSH. For information on how to set key-based ssh, please see https://www.ssh.com/academy/ssh/keygen. If your local machine is a Mac, please generate the ssh key with <code>ssh-keygen -t rsa -m PEM</code>. Once you have the key-based ssh set up, you can submit jobs to the cluster from within the MATLAB client on your local machine. You will be prompted for your ssh username and your identity file (private key). The username and location of the private key will be stored in MATLAB for future sessions.

Jobs will now default to the cluster rather than submit to the local machine.

NOTE: If you would like to submit to the local machine then run the following command:
<pre class="gscript">
>> % Get a handle to the local resources
>> c = parcluster('local');
</pre>

===Configuring Jobs from within MATLAB on the cluster or on your local machine===
Prior to having MATLAB submit a job to the cluster, we can specify various parameters to pass to our jobs, such as partition, e-mail, walltime, etc. The WallTime, MemUsage, and QueueName (partition name) fields are mandatory in order to submit a job.

<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

[REQUIRED]

>> % Specify memory to use for MATLAB jobs, per core
>> c.AdditionalProperties.MemUsage = '5G';

>> % Specify a queue to use for MATLAB jobs
>> c.AdditionalProperties.QueueName = 'partition-name';

>> % Specify the walltime (e.g. 5 hours)
>> c.AdditionalProperties.WallTime = '05:00:00';

[OPTIONAL]

>> % Specify an account to use for MATLAB jobs
>> c.AdditionalProperties.AccountName = 'account-name';

>> % Specify e-mail address to receive notifications about your job
>> c.AdditionalProperties.EmailAddress = 'user-id@uga.edu';

>> % Specify constraint for you job
>> c.AdditionalProperties.Constraint = 'Intel';

>> % Specify number of GPUs
>> c.AdditionalProperties.GpusPerNode = 1;

>> % Specify GPU type
>> c.AdditionalProperties.GpuType = 'K40';
</pre>

Save changes after modifying AdditionalProperties for the above changes to persist between MATLAB sessions.
<pre class="gscript">
>> c.saveProfile
</pre>

To see the values of the current configuration options, display AdditionalProperties.
<pre class="gscript">
>> % To view current properties
>> c.AdditionalProperties
</pre>

Unset a value when no longer needed.
<pre class="gscript">
>> % Turn off email notifications
>> c.AdditionalProperties.EmailAddress = '';
>> c.saveProfile
</pre>

===Submitting Independent Batch Jobs from within locally installed MATLAB===
Use the <code>batch</code> command to submit asynchronous jobs to the cluster. Users can either run a single function or a Matlab script as a batch job. You must make sure the script is in the MATLAB path. If running MATLAB locally, the command <code>userpath</code> displays the location you can save your .m scripts. See the MATLAB documentation for <code>userpath</code> if you would like to add directories to that path. Since your local file system is different from the worker file system(Sapelo2), if you are submitting jobs to Sapelo 2 from local MATLAB you also have to set the 'AutoAddClientPath' option to false. The <code>batch</code> command will return a job object which is used to access the output of the submitted job. See the MATLAB documentation for more help on <code>batch</code>.

Shown below is an example submitting a batch job from local MATLAB which runs the script testscript.m. Notice that the .m extension is left off.

<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit job to query where MATLAB is running on the cluster
>> j = batch(testscript,'AutoAddClientPath',false);

>> % Query job for state
>> j.State

>> % If state is finished, fetch the results
>> load(j)

>> % Delete the job after results are no longer needed
>> j.delete
</pre>

You can also run functions with multiple arguments using the <code>batch</code> command. For a function to be available it must be in your MATLAB path. Built in functions will automatically be included, but your own functions you will have to save in your userpath. When running functions, you must specify that you are using the worker established with the <code>parcluster</code> command, so use <code>c.batch</code> instead of <code>batch</code>. The example below shows a job which prints the working directory. When retrieving the data, use the command <code>fetchOutputs</code> instead of <code>load</code>.<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit job to query where MATLAB is running on the cluster
>> j = c.batch(@pwd, 1,'AutoAddClientPath',false);

>> % Query job for state
>> j.State

>> j.fetchOutputs{:}

ans =

'/home/keekov'
</pre>

To retrieve a list of currently running or completed jobs, call <code>parcluster</code> to retrieve the cluster object. The cluster object stores an array of jobs that were run, are running, or are queued to run. This allows us to fetch the results of completed jobs. Retrieve and view the list of jobs as shown below. The <code>Jobs</code> command also allows you to see the job id and status of previously submitted jobs.
<pre class="gscript">
>> c = parcluster;
>> jobs = c.Jobs;
</pre>

Data that has been written to files on the cluster needs be retrieved directly from the file system (e.g. via ftp).

To fetch the outputs of a previously completed job use the <code>fetchOutputs</code> or <code>load</code>command. This job used the function method and so data is retrieved with <code>fetchOutputs</code> instead of <code>load.</code>
<pre class="gscript">
>> % Get a handle to the job with ID 2
>> j2 = c.Jobs(2);
>> % Fetch results for job with ID 2
>> j2.fetchOutputs{:}

</pre>

===Submitting Parallel Batch Jobs from within locally installed MATLAB===
Users can also submit parallel workflows with the <code>batch</code> command. Let’s use the following example for a parallel job, which is saved as ''parallel_example.m''.

<pre class="gscript">
function t = parallel_example(iter)

if nargin==0, iter = 8; end

disp('Start sim')

t0 = tic;
parfor idx = 1:iter
A(idx) = idx;
pause(2)
end
t = toc(t0);

disp('Sim Completed')
</pre>

This time when we use the <code>c.batch</code> command, to run a parallel job, we will also specify a MATLAB Pool.
<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit a batch pool job using 4 workers for 16 simulations
>> j = c.batch(@parallel_example, 1, {16}, 'Pool',4, …
'CurrentFolder','.', 'AutoAddClientPath',false);

>> % View current job status
>> j.State

>> % Fetch the results after a finished state is retrieved
>> j.fetchOutputs{:}
ans =
8.8872
</pre>

The job ran in 8.89 seconds using four workers. Note that these jobs will always request N+1 CPU cores, since one worker is required to manage the batch job and pool of workers. For example, a job that needs eight workers will consume nine CPU cores.

We will run the same simulation but increase the Pool size. This time, to retrieve the results later, we will keep track of the job ID.

NOTE: For some applications, there will be a diminishing return when allocating too many workers, as the overhead may exceed computation time.
<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Submit a batch pool job using 8 workers for 16 simulations
>> j = c.batch(@parallel_example, 1, {16}, 'Pool', 8, …
'CurrentFolder','.', 'AutoAddClientPath',false);

>> % Get the job ID
>> id = j.ID
id =
4

>> % Clear j from workspace (as though we quit MATLAB)
>> clear j
</pre>

Once we have a handle to the cluster, we will call the <code>findJob</code> method to search for the job with the specified job ID.
<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Find the old job
>> j = c.findJob('ID', 4);

>> % Retrieve the state of the job
>> j.State
ans =
finished

>> % Fetch the results
>> j.fetchOutputs{:};
ans =
4.7270
</pre>

The job now runs in 4.73 seconds using eight workers. Run code with different number of workers to determine the ideal number to use.

=== Parallel Interactive Jobs using MATLAB on the cluster ===
To run an interactive pool job on the cluster, continue to use parpool as you’ve done before. Start an interactive session with qlogin (or with srun), load the matlab module and start MATLAB with <code>matlab -nodislay</code>. In Matlab, run

<pre class="gscript">
>> % Get a handle to the cluster
>> c = parcluster;

>> % Open a pool of 64 workers on the cluster
>> p = c.parpool(64);
</pre>
Rather than running local on the local machine, the pool can now run across multiple nodes on the cluster.

<pre class="gscript">
>> % Run a parfor over 1000 iterations
>> parfor idx = 1:1000
a(idx) = …
end
</pre>
Once we are done with the pool, delete it.
<pre class="gscript">
>> % Delete the pool
>> p.delete
</pre>

===Debugging a MATLAB job===
If a serial job produces an error, call the <code>getDebugLog</code> method to view the error log file. When submitting independent jobs, with multiple tasks, specify the task number.

<pre class="gscript">
>> c.getDebugLog(j.Tasks(3))
</pre>

For Pool jobs, only specify the job object.
<pre class="gscript">
>> c.getDebugLog(j)
</pre>

When troubleshooting a job, the cluster admin may request the scheduler ID of the job. This can be derived by calling <code>schedID</code>
<pre class="gscript">
>> schedID(j)
ans =
25539
</pre>

== Documentation ==

MATLAB documentation is available at https://www.mathworks.com/help/matlab/

Some documentation and sample files are available on Sapelo2, in /apps/gb/MATLAB/R2023a/help

To learn more about the MATLAB Parallel Computing Toolbox, check out these resources:

*[http://www.mathworks.com/help/parallel-computing/examples.html Parallel Computing Coding Examples]
*[http://www.mathworks.com/help/distcomp/index.html Parallel Computing Documentation]
*[http://www.mathworks.com/products/parallel-computing/index.html Parallel Computing Overview]
*[http://www.mathworks.com/products/parallel-computing/tutorials.html Parallel Computing Tutorials]
*[http://www.mathworks.com/products/parallel-computing/videos.html Parallel Computing Videos]
*[http://www.mathworks.com/products/parallel-computing/webinars.html Parallel Computing Webinars]

== Installation ==

'''Version 2023a'''

Installed in /apps/gb/MATLAB/R2023a.

Available toolboxes: Almost all toolboxes for which UGA has a license. For details, see the directories in /apps/gb/MATLAB/R2023a/toolbox

== System ==
64-bit Linux

OnDemand

2026-04-05T15:48:49Z

Shtsai:

== Open OnDemand (OOD) ==

Open OnDemand ("OOD") is a web-based service provided by GACRC which provides users an alternative and/or complementary method to access the HPC clusters. It helps computational researchers and students efficiently utilize remote computing resources by making them easy to access from any device, via a convenient web interface. Through Open OnDemand, graphical applications can be utilized on the cluster far more easily and smoothly than using X11 forwarding. It also helps computer center staff support a wide range of clients by simplifying the user interface and experience. A video introduction to Open OnDemand at UGA can be found at GACRC's '''[https://kaltura.uga.edu/media/t/1_u9d1xrpp/176125031 Kaltura video introduction to Open OnDemand]'''.

OOD Features:

* Job submission and monitoring
* File transfer and management
* File editing
* Shell access
* Graphical Desktop on the cluster
* Interactive Applications

{| class="wikitable"
|+Open OnDemand Integration with GACRC Clusters
!Availability
!Cluster
!URL
|-
|Production
|Sapelo2
|https://ondemand.gacrc.uga.edu
|-
|Development Testing
|Sapelo2
|https://oodev.gacrc.uga.edu
|-
|Production
|Teaching
|https://teach-openond.gacrc.uga.edu
|}

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

== How to access Open OnDemand ==

'''In order to access the GACRC OOD login page, You must be connected to the UGA Network, either directly or by [https://eits.uga.edu/access_and_security/infosec/tools/vpn/ VPN].'''

'''Logging in requires a [https://wiki.gacrc.uga.edu/wiki/User_Accounts GACRC Cluster Account].'''

'''GACRC OOD uses UGA Single Sign-On Service (SSO) for authentication.'''

# Open a web browser to the cluster's Open OnDemand URL: https://ondemand.gacrc.uga.edu
# Login with your UGA MyID credentials
===Browser Requirements/Notes===
To have the best experience using OnDemand, GACRC recommends using the latest version of '''Google Chrome, Mozilla Firefox,''' or '''Microsoft Edge'''. Any modern browser that supports ECMAScript 2016 ''should'' work, but GACRC will not support it.

'''Individual browser notes'''

* Google Chrome is currently the ''only'' web browser that natively supports the copy and paste functionality in <code>noVNC</code>. Other browsers can do copy and pasting manually through the <code>noVNC</code> tool drawer.

* Safari users '''''may''''' have issues when using the Shell App or <code>noVNC</code>. If you have issues, make sure your application is up-to-date.
* Internet Explorer 11 is '''NOT''' supported.

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

== Using Open OnDemand ==

Upon logging into Open OnDemand, all of its tools can be accessed via the links in the top menu bar.

[[File: Oodheader.png|alt="image of top menu bar in Open OnDemand"| OOD Menu Bar]]



=== Files ===

Clicking "Files" in the top menu bar will open a drop menu that displays yours and your lab's directories on the cluster. Clicking any of those displayed directories will take you to a new page that allows you to manage the directories contents, as well as navigate to other directories on the cluster to which you have access. In this file browsing interface, there is a menu above the file browsing area that allows you to:

*Open an interactive shell in the current directory
*Create a new file
*Create a new directory
*Upload files
*Download files
*Copy/move files
*Delete files

[[File:Oodfiles2.png|alt="Image displaying the directories on the cluster" |900px]]

Clicking on a directory will navigate the OOD file browser to that directory. Clicking on a text file will open a new read-only window, displaying the file. If you would like to edit a file from within OOD, click the three-vertical-dots button to the right of a file name, and then click "Edit". This will open a new tab that allows you to edit and save changes to a file. The OOD file editor has a plethora of different syntax highlighting options. If the file you're editing has a file extension in its name for which OOD has syntax highlighting, it will pre-select that option, however you can change the syntax highlighting by selecting a different option from the "Mode" drop down menu at the top. Additionally in the top menu of the OOD file editor, you can change the font size, as well as select a different display theme.

==== File Transfer Limitations ====

'''Copy and Moving files'''
When it comes to copying and moving files within the cluster, it is recommended that you only use OOD for smaller files. For anything else, please use the [[Transferring Files|transfer nodes]]. This is due to the OOD server acting as a "man-in-the-middle" for transferring files between the different file systems. For example, if you move something from /home to /scratch, in the background the file first has to be transferred to a temporary storage on the OOD server, before it is then transferred to the destination.

'''Uploading files'''
GACRC '''highly''' recommends using the [[Transferring Files|transfer nodes]] or [[Globus]] for larger file transfers. If you must use OOD for large file transfers, please be aware there is a hard-limit in place of ~10.0 Gib. GACRC reserves the right to lower this limit in the future.

[[#top|Back to Top]]

=== Jobs ===

Clicking "Jobs" will open a drop down menu allowing you to navigate to "Active Jobs" or "Job Composer".

==== Active Jobs ====

In the Active Jobs interface, you're able to view information about your currently running jobs. Clicking the arrow on the left will expand this interface displaying further information about the job, as seen below.

[[File:oodjobs2.png|alt="Image of a list of active jobs" | 1200px]] [[File:Oodjobs.png|alt="Image of the details of a give job" | 1200px]]

[[#top|Back to Top]]

=== Clusters ===

Clicking "Clusters" will open a drop down menu giving you an option to open a shell for the cluster in your browser, on one of the login nodes. This functions just as if you had connected to a Sapelo2 login node via PuTTY (Windows) or Terminal (Mac/Linux). In the top right of this interface you are able to select a different theme for your shell. Please see [[#Browser | Browser Requirements/Notes]] for possible limitations.

[[File:Oodcli1.png|alt="Image of a command line window in Open OnDemand" | 600 px]]

[[#top|Back to Top]]

=== Interactive Apps ===

One of the best features of Open OnDemand is the ability to directly launch interactive graphical applications. "Interactive Applications" or "Apps" are wrappers that will schedule a Slurm job with a particular application, and give you direct web based access into the interface.

These apps can be accessed near the bottom of the Open OnDemand main page called "Pinned Apps" or from the "Interactive Apps" in the top menu bar. ''Note that the image below is only an example, as the list of interactive applications will grow over time.''

[[File:Screen Shot 2024-05-30 at 10.37.57 AM.png|alt="Image of the interactive apps available in Open OnDemand"|1000px]]

'''Notes on Rstudio:'''

1. If you are using the Rstudio application with a version of R that uses the foss/2020b (or newer) toolchain, please request an EDR constraint on the resources page.

2. If the Rstudio application fails to open, please edit the following file in your Sapelo2 home directory ~/.config/RStudio/desktop.ini (create this file if it does not exist) to add the following 2 lines:

<pre class="script">
[General]
desktop.renderingEngine=software
</pre>

Note that .config is a hidden directory in your Sapelo2 home directory. Then try the Rstudio app again.

===Launching an application===
Clicking the icon of the interactive application that you would like to use will take you to a new page in which you define the resources allocated to interactive application.

If the GUI application you want to use has its own interactive app in Open OnDemand, you should use that launcher. If the GUI application you want to use does not have a launcher yet you have two options; You an open a ticket with GACRC and request the application be added to OnDemand (Link TBD), or you can use the "[[#X_Desktop |X Desktop Session]]".

====Configuring the resources====
Resources must be defined like this because an Open OnDemand interactive app is happening within the context of a Slurm job. Each application may allow for the customization of different resources, while some may have static defined resources that cannot be changed. Almost all of the resources available to be configured should be familiar to a user who has submitted a job before.

'''Please note''' that the <code>Number of hours</code> option is equivalent to "wall time". If you do not terminate the job before this limit is reached, Slurm will terminate the job for you.

Once you have defined the resources for your job, click "Launch" to be taken to a new page ([[#Inter |My Interactive Sessions]]). After a small delay, the page will refresh showing the status of the job that your app has scheduled. See [[#Inter |My Interactive Sessions]] section of the wiki for more information.

===X Desktop Session (A.K.A. The Interactive X login app)===
The "X Desktop Session on Sapelo2" is an interactive app that will start an X Desktop GUI session as a job. Launching the VNC session will connect you to an actual X desktop running on a Sapelo2 compute node, in your browser. This desktop is currently configured to run the XFCE lightweight graphical manager.

The Sapelo2 X desktop can be used for graphical applications that do not have a dedicated Open OnDemand interactive app. Please be aware that while it is possible within a Sapelo2 Desktop session to open a terminal, load a module, and run a graphical application, for example grace or gnuplot, some of the computing resources requested for this job would be used by the desktop itself. If you find that you have an application that you do this with regularly, please consider opening a ticket with GACRC requesting an interactive app.

====Copy/Paste in VNC====
If launching an interactive session in the portal, there are a few extra steps that need to be taken. Please reference the media below, or the summary of steps below that for more information.

#Open the toolbar on the left of the screen and select "Clipboard".
#If you want to paste text from your host computer to the remote session, paste the text in the clipboard box. You can then use the middle-mouse button (MMB) to paste it in your terminal.
#If you want to copy text from the remote session to your host computer's clipboard, simply highlight the text in the terminal. It will appear in the Clipboard toolbar pop-out where you can copy it to your host clipboard.

[[#top|Back to Top]]

==My Interactive Sessions==

The last item in Open OnDemand top menu bar is "My Interactive Sessions". This interface will list your current and recent interactive app sessions.

[[File:Interactive Session Example.png|alt="Image of the interactive sessions window"|frameless|693x693px]]

'''Notable items:'''

*'''Host''': Click the name of the host to open a shell to the compute node that is running this job.
*'''Time Remaining''': This is how long the job will remain running before terminating. (Can be thought of as remaining wall time.)
*'''Session ID''': The unique ID of this session. Clicking the link will open a file app window to this Ondemand sessions working directory. (Useful for troubleshooting issues with application launch)
*'''Compression/Image Quality''': These sliders allow you to change the amount of graphical compression and quality of the VNC session. If you are on a particularly slow connection, or find that the 'redraw' time is slow, try lowering the Image Quality, increasing the Compression, or both, and relaunch the VNC window.
*'''Launch Button''': This button will open a new tab with the web based VNC viewer application. Closing the VNC window will NOT terminate the job, only the VNC connection to it. You may return at any time (as long as the job has time remaining) and click the Launch button to reconnect to your session.
*'''View Only''': This will open a new web based VNC viewer application just like the Launch button, with the caveat that no user input is allowed. You can then copy the URL for this window and send it to others, who will be able to view the VNC session, but not interact with it. (e.g. move the mouse, etc) (This is a great function if you want to show multiple people something in a controlled session!)
*'''Delete''': This button will terminate the job, and delete the session.

[[#top|Back to Top]]

==Additional Notes==

===Interactive applications and GPUs (Hardware accelerated rendering)===
Sapelo2 is currently not configured for applications to use hardware GPU for accelerated graphical rendering. This is currently on our "To Do" list.

Requesting a GPU for an interactive application will assign a GPU to the job just as it would requesting one from a normal command line submit script, but the Xserver will not use this GPU for graphical acceleration. (e.g. you can still use the GPU for computation, but it will not accelerate your frame rate.)

===Per-User Experience===
OnDemand will spawn a Per User Nginx session upon successful login. This means that each connection on the OOD server is running as that particular user. Each session is completely separated from other users sessions.

===Troubleshooting===

For any assistance with Open OnDemand, please reach out to us in via the "General Support" form of the "For Users" section at help.gacrc.uga.edu.

[[#top|Back to Top]]

OnDemand

2026-04-05T15:27:33Z

Shtsai:

== Open OnDemand (OOD) ==

Open OnDemand ("OOD") is a web-based service provided by GACRC which provides users an alternative and/or complementary method to access the HPC clusters. It helps computational researchers and students efficiently utilize remote computing resources by making them easy to access from any device, via a convenient web interface. Through Open OnDemand, graphical applications can be utilized on the cluster far more easily and smoothly than using X11 forwarding. It also helps computer center staff support a wide range of clients by simplifying the user interface and experience. A video introduction to Kaltura at UGA can be found '''[https://kaltura.uga.edu/media/t/1_u9d1xrpp/176125031 here]'''.

OOD Features:

* Job submission and monitoring
* File transfer and management
* File editing
* Shell access
* Graphical Desktop on the cluster
* Interactive Applications

{| class="wikitable"
|+Open OnDemand Integration with GACRC Clusters
!Availability
!Cluster
!URL
|-
|Production
|Sapelo2
|https://ondemand.gacrc.uga.edu
|-
|Development Testing
|Sapelo2
|https://oodev.gacrc.uga.edu
|-
|Production
|Teaching
|https://teach-openond.gacrc.uga.edu
|}

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

== How to access Open OnDemand ==

'''In order to access the GACRC OOD login page, You must be connected to the UGA Network, either directly or by [https://eits.uga.edu/access_and_security/infosec/tools/vpn/ VPN].'''

'''Logging in requires a [https://wiki.gacrc.uga.edu/wiki/User_Accounts GACRC Cluster Account].'''

'''GACRC OOD uses UGA Single Sign-On Service (SSO) for authentication.'''

# Open a web browser to the cluster's Open OnDemand URL: https://ondemand.gacrc.uga.edu
# Login with your UGA MyID credentials
===Browser Requirements/Notes===
To have the best experience using OnDemand, GACRC recommends using the latest version of '''Google Chrome, Mozilla Firefox,''' or '''Microsoft Edge'''. Any modern browser that supports ECMAScript 2016 ''should'' work, but GACRC will not support it.

'''Individual browser notes'''

* Google Chrome is currently the ''only'' web browser that natively supports the copy and paste functionality in <code>noVNC</code>. Other browsers can do copy and pasting manually through the <code>noVNC</code> tool drawer.

* Safari users '''''may''''' have issues when using the Shell App or <code>noVNC</code>. If you have issues, make sure your application is up-to-date.
* Internet Explorer 11 is '''NOT''' supported.

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

== Using Open OnDemand ==

Upon logging into Open OnDemand, all of its tools can be accessed via the links in the top menu bar.

[[File: Oodheader.png|alt="image of top menu bar in Open OnDemand"| OOD Menu Bar]]



=== Files ===

Clicking "Files" in the top menu bar will open a drop menu that displays yours and your lab's directories on the cluster. Clicking any of those displayed directories will take you to a new page that allows you to manage the directories contents, as well as navigate to other directories on the cluster to which you have access. In this file browsing interface, there is a menu above the file browsing area that allows you to:

*Open an interactive shell in the current directory
*Create a new file
*Create a new directory
*Upload files
*Download files
*Copy/move files
*Delete files

[[File:Oodfiles2.png|alt="Image displaying the directories on the cluster" |900px]]

Clicking on a directory will navigate the OOD file browser to that directory. Clicking on a text file will open a new read-only window, displaying the file. If you would like to edit a file from within OOD, click the three-vertical-dots button to the right of a file name, and then click "Edit". This will open a new tab that allows you to edit and save changes to a file. The OOD file editor has a plethora of different syntax highlighting options. If the file you're editing has a file extension in its name for which OOD has syntax highlighting, it will pre-select that option, however you can change the syntax highlighting by selecting a different option from the "Mode" drop down menu at the top. Additionally in the top menu of the OOD file editor, you can change the font size, as well as select a different display theme.

==== File Transfer Limitations ====

'''Copy and Moving files'''
When it comes to copying and moving files within the cluster, it is recommended that you only use OOD for smaller files. For anything else, please use the [[Transferring Files|transfer nodes]]. This is due to the OOD server acting as a "man-in-the-middle" for transferring files between the different file systems. For example, if you move something from /home to /scratch, in the background the file first has to be transferred to a temporary storage on the OOD server, before it is then transferred to the destination.

'''Uploading files'''
GACRC '''highly''' recommends using the [[Transferring Files|transfer nodes]] or [[Globus]] for larger file transfers. If you must use OOD for large file transfers, please be aware there is a hard-limit in place of ~10.0 Gib. GACRC reserves the right to lower this limit in the future.

[[#top|Back to Top]]

=== Jobs ===

Clicking "Jobs" will open a drop down menu allowing you to navigate to "Active Jobs" or "Job Composer".

==== Active Jobs ====

In the Active Jobs interface, you're able to view information about your currently running jobs. Clicking the arrow on the left will expand this interface displaying further information about the job, as seen below.

[[File:oodjobs2.png|alt="Image of a list of active jobs" | 1200px]] [[File:Oodjobs.png|alt="Image of the details of a give job" | 1200px]]

[[#top|Back to Top]]

=== Clusters ===

Clicking "Clusters" will open a drop down menu giving you an option to open a shell for the cluster in your browser, on one of the login nodes. This functions just as if you had connected to a Sapelo2 login node via PuTTY (Windows) or Terminal (Mac/Linux). In the top right of this interface you are able to select a different theme for your shell. Please see [[#Browser | Browser Requirements/Notes]] for possible limitations.

[[File:Oodcli1.png|alt="Image of a command line window in Open OnDemand" | 600 px]]

[[#top|Back to Top]]

=== Interactive Apps ===

One of the best features of Open OnDemand is the ability to directly launch interactive graphical applications. "Interactive Applications" or "Apps" are wrappers that will schedule a Slurm job with a particular application, and give you direct web based access into the interface.

These apps can be accessed near the bottom of the Open OnDemand main page called "Pinned Apps" or from the "Interactive Apps" in the top menu bar. ''Note that the image below is only an example, as the list of interactive applications will grow over time.''

[[File:Screen Shot 2024-05-30 at 10.37.57 AM.png|alt="Image of the interactive apps available in Open OnDemand"|1000px]]

'''Notes on Rstudio:'''

1. If you are using the Rstudio application with a version of R that uses the foss/2020b (or newer) toolchain, please request an EDR constraint on the resources page.

2. If the Rstudio application fails to open, please edit the following file in your Sapelo2 home directory ~/.config/RStudio/desktop.ini (create this file if it does not exist) to add the following 2 lines:

<pre class="script">
[General]
desktop.renderingEngine=software
</pre>

Note that .config is a hidden directory in your Sapelo2 home directory. Then try the Rstudio app again.

===Launching an application===
Clicking the icon of the interactive application that you would like to use will take you to a new page in which you define the resources allocated to interactive application.

If the GUI application you want to use has its own interactive app in Open OnDemand, you should use that launcher. If the GUI application you want to use does not have a launcher yet you have two options; You an open a ticket with GACRC and request the application be added to OnDemand (Link TBD), or you can use the "[[#X_Desktop |X Desktop Session]]".

====Configuring the resources====
Resources must be defined like this because an Open OnDemand interactive app is happening within the context of a Slurm job. Each application may allow for the customization of different resources, while some may have static defined resources that cannot be changed. Almost all of the resources available to be configured should be familiar to a user who has submitted a job before.

'''Please note''' that the <code>Number of hours</code> option is equivalent to "wall time". If you do not terminate the job before this limit is reached, Slurm will terminate the job for you.

Once you have defined the resources for your job, click "Launch" to be taken to a new page ([[#Inter |My Interactive Sessions]]). After a small delay, the page will refresh showing the status of the job that your app has scheduled. See [[#Inter |My Interactive Sessions]] section of the wiki for more information.

===X Desktop Session (A.K.A. The Interactive X login app)===
The "X Desktop Session on Sapelo2" is an interactive app that will start an X Desktop GUI session as a job. Launching the VNC session will connect you to an actual X desktop running on a Sapelo2 compute node, in your browser. This desktop is currently configured to run the XFCE lightweight graphical manager.

The Sapelo2 X desktop can be used for graphical applications that do not have a dedicated Open OnDemand interactive app. Please be aware that while it is possible within a Sapelo2 Desktop session to open a terminal, load a module, and run a graphical application, for example grace or gnuplot, some of the computing resources requested for this job would be used by the desktop itself. If you find that you have an application that you do this with regularly, please consider opening a ticket with GACRC requesting an interactive app.

====Copy/Paste in VNC====
If launching an interactive session in the portal, there are a few extra steps that need to be taken. Please reference the media below, or the summary of steps below that for more information.

#Open the toolbar on the left of the screen and select "Clipboard".
#If you want to paste text from your host computer to the remote session, paste the text in the clipboard box. You can then use the middle-mouse button (MMB) to paste it in your terminal.
#If you want to copy text from the remote session to your host computer's clipboard, simply highlight the text in the terminal. It will appear in the Clipboard toolbar pop-out where you can copy it to your host clipboard.

[[#top|Back to Top]]

==My Interactive Sessions==

The last item in Open OnDemand top menu bar is "My Interactive Sessions". This interface will list your current and recent interactive app sessions.

[[File:Interactive Session Example.png|alt="Image of the interactive sessions window"|frameless|693x693px]]

'''Notable items:'''

*'''Host''': Click the name of the host to open a shell to the compute node that is running this job.
*'''Time Remaining''': This is how long the job will remain running before terminating. (Can be thought of as remaining wall time.)
*'''Session ID''': The unique ID of this session. Clicking the link will open a file app window to this Ondemand sessions working directory. (Useful for troubleshooting issues with application launch)
*'''Compression/Image Quality''': These sliders allow you to change the amount of graphical compression and quality of the VNC session. If you are on a particularly slow connection, or find that the 'redraw' time is slow, try lowering the Image Quality, increasing the Compression, or both, and relaunch the VNC window.
*'''Launch Button''': This button will open a new tab with the web based VNC viewer application. Closing the VNC window will NOT terminate the job, only the VNC connection to it. You may return at any time (as long as the job has time remaining) and click the Launch button to reconnect to your session.
*'''View Only''': This will open a new web based VNC viewer application just like the Launch button, with the caveat that no user input is allowed. You can then copy the URL for this window and send it to others, who will be able to view the VNC session, but not interact with it. (e.g. move the mouse, etc) (This is a great function if you want to show multiple people something in a controlled session!)
*'''Delete''': This button will terminate the job, and delete the session.

[[#top|Back to Top]]

==Additional Notes==

===Interactive applications and GPUs (Hardware accelerated rendering)===
Sapelo2 is currently not configured for applications to use hardware GPU for accelerated graphical rendering. This is currently on our "To Do" list.

Requesting a GPU for an interactive application will assign a GPU to the job just as it would requesting one from a normal command line submit script, but the Xserver will not use this GPU for graphical acceleration. (e.g. you can still use the GPU for computation, but it will not accelerate your frame rate.)

===Per-User Experience===
OnDemand will spawn a Per User Nginx session upon successful login. This means that each connection on the OOD server is running as that particular user. Each session is completely separated from other users sessions.

===Troubleshooting===

For any assistance with Open OnDemand, please reach out to us in via the "General Support" form of the "For Users" section at help.gacrc.uga.edu.

[[#top|Back to Top]]

OnDemand

2026-04-05T15:22:58Z

Shtsai: /* Files */

== Open OnDemand (OOD) ==

Open OnDemand ("OOD") is a web-based service provided by GACRC which provides users an alternative and/or complementary method to access the HPC clusters. It helps computational researchers and students efficiently utilize remote computing resources by making them easy to access from any device, via a convenient web interface. Through Open OnDemand, graphical applications can be utilized on the cluster far more easily and smoothly than using X11 forwarding. It also helps computer center staff support a wide range of clients by simplifying the user interface and experience. A video introduction to Kaltura at UGA can be found '''[https://kaltura.uga.edu/media/t/1_u9d1xrpp/176125031 here]'''.

OOD Features:

* Job submission and monitoring
* File transfer and management
* File editing
* Shell access
* Graphical Desktop on the cluster
* Interactive Applications

{| class="wikitable"
|+Open OnDemand Integration with GACRC Clusters
!Availability
!Cluster
!URL
|-
|Production
|Sapelo2
|https://ondemand.gacrc.uga.edu
|-
|Development Testing
|Sapelo2
|https://oodev.gacrc.uga.edu
|-
|Production
|Teaching
|https://teach-openond.gacrc.uga.edu
|}

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

== How to access Open OnDemand ==

'''In order to access the GACRC OOD login page, You must be connected to the UGA Network, either directly or by [https://eits.uga.edu/access_and_security/infosec/tools/vpn/ VPN].'''

'''Logging in requires a [https://wiki.gacrc.uga.edu/wiki/User_Accounts GACRC Cluster Account].'''

'''GACRC OOD uses UGA Single Sign-On Service (SSO) for authentication.'''

# Open a web browser to the cluster's Open OnDemand URL: https://ondemand.gacrc.uga.edu
# Login with your UGA MyID credentials
===Browser Requirements/Notes===
To have the best experience using OnDemand, GACRC recommends using the latest version of '''Google Chrome, Mozilla Firefox,''' or '''Microsoft Edge'''. Any modern browser that supports ECMAScript 2016 ''should'' work, but GACRC will not support it.

'''Individual browser notes'''

* Google Chrome is currently the ''only'' web browser that natively supports the copy and paste functionality in <code>noVNC</code>. Other browsers can do copy and pasting manually through the <code>noVNC</code> tool drawer.

* Safari users '''''may''''' have issues when using the Shell App or <code>noVNC</code>. If you have issues, make sure your application is up-to-date.
* Internet Explorer 11 is '''NOT''' supported.

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

== Using Open OnDemand ==

Upon logging into Open OnDemand, all of its tools can be accessed via the links in the top menu bar.

[[File: Oodheader.png|alt="image of top menu bar in Open OnDemand"| OOD Menu Bar]]



=== Files ===

Clicking "Files" in the top menu bar will open a drop menu that displays yours and your lab's directories on the cluster. Clicking any of those displayed directories will take you to a new page that allows you to manage the directories contents, as well as navigate to other directories on the cluster to which you have access. In this file browsing interface, there is a menu above the file browsing area that allows you to:

*Open an interactive shell in the current directory
*Create a new file
*Create a new directory
*Upload files
*Download files
*Copy/move files
*Delete files

[[File:Oodfiles2.png|alt="Image displaying the directories on the cluster" |900px]]

Clicking on a directory will navigate the OOD file browser to that directory. Clicking on a text file will open a new read-only window, displaying the file. If you would like to edit a file from within OOD, click the three-vertical-dots button to the right of a file name, and then click "Edit". This will open a new tab that allows you to edit and save changes to a file. The OOD file editor has a plethora of different syntax highlighting options. If the file you're editing has a file extension in its name for which OOD has syntax highlighting, it will pre-select that option, however you can change the syntax highlighting by selecting a different option from the "Mode" drop down menu at the top. Additionally in the top menu of the OOD file editor, you can change the font size, as well as select a different display theme.

==== File Transfer Limitations ====

'''Copy and Moving files'''
When it comes to copying and moving files within the cluster, it is recommended that you only use OOD for smaller files. For anything else, please use the [[Transferring Files|transfer nodes]]. This is due to the OOD server acting as a "man-in-the-middle" for transferring files between the different file systems. For example, if you move something from /home to /scratch, in the background the file first has to be transferred to a temporary storage on the OOD server, before it is then transferred to the destination.

'''Uploading files'''
GACRC '''highly''' recommends using the [[Transferring Files|transfer nodes]] or [[Globus]] for larger file transfers. If you must use OOD for large file transfers, please be aware there is a hard-limit in place of ~10.0 Gib. GACRC reserves the right to lower this limit in the future.

[[#top|Back to Top]]

=== Jobs ===

Clicking "Jobs" will open a drop down menu allowing you to navigate to "Active Jobs" or "Job Composer".

==== Active Jobs ====

In the Active Jobs interface, you're able to view information about your currently running jobs. Clicking the arrow on the left will expand this interface displaying further information about the job, as seen below.

[[File:oodjobs2.png | 1200px]] [[File:Oodjobs.png | 1200px]]

[[#top|Back to Top]]

=== Clusters ===

Clicking "Clusters" will open a drop down menu giving you an option to open a shell for the cluster in your browser, on one of the login nodes. This functions just as if you had connected to a Sapelo2 login node via PuTTY (Windows) or Terminal (Mac/Linux). In the top right of this interface you are able to select a different theme for your shell. Please see [[#Browser | Browser Requirements/Notes]] for possible limitations.

[[File:Oodcli1.png | 600 px]]

[[#top|Back to Top]]

=== Interactive Apps ===

One of the best features of Open OnDemand is the ability to directly launch interactive graphical applications. "Interactive Applications" or "Apps" are wrappers that will schedule a Slurm job with a particular application, and give you direct web based access into the interface.

These apps can be accessed near the bottom of the Open OnDemand main page called "Pinned Apps" or from the "Interactive Apps" in the top menu bar. ''Note that the image below is only an example, as the list of interactive applications will grow over time.''

[[File:Screen Shot 2024-05-30 at 10.37.57 AM.png|1000px]]

'''Notes on Rstudio:'''

1. If you are using the Rstudio application with a version of R that uses the foss/2020b (or newer) toolchain, please request an EDR constraint on the resources page.

2. If the Rstudio application fails to open, please edit the following file in your Sapelo2 home directory ~/.config/RStudio/desktop.ini (create this file if it does not exist) to add the following 2 lines:

<pre class="script">
[General]
desktop.renderingEngine=software
</pre>

Note that .config is a hidden directory in your Sapelo2 home directory. Then try the Rstudio app again.

===Launching an application===
Clicking the icon of the interactive application that you would like to use will take you to a new page in which you define the resources allocated to interactive application.

If the GUI application you want to use has its own interactive app in Open OnDemand, you should use that launcher. If the GUI application you want to use does not have a launcher yet you have two options; You an open a ticket with GACRC and request the application be added to OnDemand (Link TBD), or you can use the "[[#X_Desktop |X Desktop Session]]".

====Configuring the resources====
Resources must be defined like this because an Open OnDemand interactive app is happening within the context of a Slurm job. Each application may allow for the customization of different resources, while some may have static defined resources that cannot be changed. Almost all of the resources available to be configured should be familiar to a user who has submitted a job before.

'''Please note''' that the <code>Number of hours</code> option is equivalent to "wall time". If you do not terminate the job before this limit is reached, Slurm will terminate the job for you.

Once you have defined the resources for your job, click "Launch" to be taken to a new page ([[#Inter |My Interactive Sessions]]). After a small delay, the page will refresh showing the status of the job that your app has scheduled. See [[#Inter |My Interactive Sessions]] section of the wiki for more information.

===X Desktop Session (A.K.A. The Interactive X login app)===
The "X Desktop Session on Sapelo2" is an interactive app that will start an X Desktop GUI session as a job. Launching the VNC session will connect you to an actual X desktop running on a Sapelo2 compute node, in your browser. This desktop is currently configured to run the XFCE lightweight graphical manager.

The Sapelo2 X desktop can be used for graphical applications that do not have a dedicated Open OnDemand interactive app. Please be aware that while it is possible within a Sapelo2 Desktop session to open a terminal, load a module, and run a graphical application, for example grace or gnuplot, some of the computing resources requested for this job would be used by the desktop itself. If you find that you have an application that you do this with regularly, please consider opening a ticket with GACRC requesting an interactive app.

====Copy/Paste in VNC====
If launching an interactive session in the portal, there are a few extra steps that need to be taken. Please reference the media below, or the summary of steps below that for more information.

#Open the toolbar on the left of the screen and select "Clipboard".
#If you want to paste text from your host computer to the remote session, paste the text in the clipboard box. You can then use the middle-mouse button (MMB) to paste it in your terminal.
#If you want to copy text from the remote session to your host computer's clipboard, simply highlight the text in the terminal. It will appear in the Clipboard toolbar pop-out where you can copy it to your host clipboard.

[[#top|Back to Top]]

==My Interactive Sessions==

The last item in Open OnDemand top menu bar is "My Interactive Sessions". This interface will list your current and recent interactive app sessions.

[[File:Interactive Session Example.png|frameless|693x693px]]

'''Notable items:'''

*'''Host''': Click the name of the host to open a shell to the compute node that is running this job.
*'''Time Remaining''': This is how long the job will remain running before terminating. (Can be thought of as remaining wall time.)
*'''Session ID''': The unique ID of this session. Clicking the link will open a file app window to this Ondemand sessions working directory. (Useful for troubleshooting issues with application launch)
*'''Compression/Image Quality''': These sliders allow you to change the amount of graphical compression and quality of the VNC session. If you are on a particularly slow connection, or find that the 'redraw' time is slow, try lowering the Image Quality, increasing the Compression, or both, and relaunch the VNC window.
*'''Launch Button''': This button will open a new tab with the web based VNC viewer application. Closing the VNC window will NOT terminate the job, only the VNC connection to it. You may return at any time (as long as the job has time remaining) and click the Launch button to reconnect to your session.
*'''View Only''': This will open a new web based VNC viewer application just like the Launch button, with the caveat that no user input is allowed. You can then copy the URL for this window and send it to others, who will be able to view the VNC session, but not interact with it. (e.g. move the mouse, etc) (This is a great function if you want to show multiple people something in a controlled session!)
*'''Delete''': This button will terminate the job, and delete the session.

[[#top|Back to Top]]

==Additional Notes==

===Interactive applications and GPUs (Hardware accelerated rendering)===
Sapelo2 is currently not configured for applications to use hardware GPU for accelerated graphical rendering. This is currently on our "To Do" list.

Requesting a GPU for an interactive application will assign a GPU to the job just as it would requesting one from a normal command line submit script, but the Xserver will not use this GPU for graphical acceleration. (e.g. you can still use the GPU for computation, but it will not accelerate your frame rate.)

===Per-User Experience===
OnDemand will spawn a Per User Nginx session upon successful login. This means that each connection on the OOD server is running as that particular user. Each session is completely separated from other users sessions.

===Troubleshooting===

For any assistance with Open OnDemand, please reach out to us in via the "General Support" form of the "For Users" section at help.gacrc.uga.edu.

[[#top|Back to Top]]

OnDemand

2026-04-05T15:20:44Z

Shtsai: /* Using Open OnDemand */

== Open OnDemand (OOD) ==

Open OnDemand ("OOD") is a web-based service provided by GACRC which provides users an alternative and/or complementary method to access the HPC clusters. It helps computational researchers and students efficiently utilize remote computing resources by making them easy to access from any device, via a convenient web interface. Through Open OnDemand, graphical applications can be utilized on the cluster far more easily and smoothly than using X11 forwarding. It also helps computer center staff support a wide range of clients by simplifying the user interface and experience. A video introduction to Kaltura at UGA can be found '''[https://kaltura.uga.edu/media/t/1_u9d1xrpp/176125031 here]'''.

OOD Features:

* Job submission and monitoring
* File transfer and management
* File editing
* Shell access
* Graphical Desktop on the cluster
* Interactive Applications

{| class="wikitable"
|+Open OnDemand Integration with GACRC Clusters
!Availability
!Cluster
!URL
|-
|Production
|Sapelo2
|https://ondemand.gacrc.uga.edu
|-
|Development Testing
|Sapelo2
|https://oodev.gacrc.uga.edu
|-
|Production
|Teaching
|https://teach-openond.gacrc.uga.edu
|}

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

== How to access Open OnDemand ==

'''In order to access the GACRC OOD login page, You must be connected to the UGA Network, either directly or by [https://eits.uga.edu/access_and_security/infosec/tools/vpn/ VPN].'''

'''Logging in requires a [https://wiki.gacrc.uga.edu/wiki/User_Accounts GACRC Cluster Account].'''

'''GACRC OOD uses UGA Single Sign-On Service (SSO) for authentication.'''

# Open a web browser to the cluster's Open OnDemand URL: https://ondemand.gacrc.uga.edu
# Login with your UGA MyID credentials
===Browser Requirements/Notes===
To have the best experience using OnDemand, GACRC recommends using the latest version of '''Google Chrome, Mozilla Firefox,''' or '''Microsoft Edge'''. Any modern browser that supports ECMAScript 2016 ''should'' work, but GACRC will not support it.

'''Individual browser notes'''

* Google Chrome is currently the ''only'' web browser that natively supports the copy and paste functionality in <code>noVNC</code>. Other browsers can do copy and pasting manually through the <code>noVNC</code> tool drawer.

* Safari users '''''may''''' have issues when using the Shell App or <code>noVNC</code>. If you have issues, make sure your application is up-to-date.
* Internet Explorer 11 is '''NOT''' supported.

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

== Using Open OnDemand ==

Upon logging into Open OnDemand, all of its tools can be accessed via the links in the top menu bar.

[[File: Oodheader.png|alt="image of top menu bar in Open OnDemand"| OOD Menu Bar]]



=== Files ===

Clicking "Files" in the top menu bar will open a drop menu that displays yours and your lab's directories on the cluster. Clicking any of those displayed directories will take you to a new page that allows you to manage the directories contents, as well as navigate to other directories on the cluster to which you have access. In this file browsing interface, there is a menu above the file browsing area that allows you to:

*Open an interactive shell in the current directory
*Create a new file
*Create a new directory
*Upload files
*Download files
*Copy/move files
*Delete files

[[File:Oodfiles2.png |900px]]

Clicking on a directory will navigate the OOD file browser to that directory. Clicking on a text file will open a new read-only window, displaying the file. If you would like to edit a file from within OOD, click the three-vertical-dots button to the right of a file name, and then click "Edit". This will open a new tab that allows you to edit and save changes to a file. The OOD file editor has a plethora of different syntax highlighting options. If the file you're editing has a file extension in its name for which OOD has syntax highlighting, it will pre-select that option, however you can change the syntax highlighting by selecting a different option from the "Mode" drop down menu at the top. Additionally in the top menu of the OOD file editor, you can change the font size, as well as select a different display theme.

==== File Transfer Limitations ====

'''Copy and Moving files'''
When it comes to copying and moving files within the cluster, it is recommended that you only use OOD for smaller files. For anything else, please use the [[Transferring Files|transfer nodes]]. This is due to the OOD server acting as a "man-in-the-middle" for transferring files between the different file systems. For example, if you move something from /home to /scratch, in the background the file first has to be transferred to a temporary storage on the OOD server, before it is then transferred to the destination.

'''Uploading files'''
GACRC '''highly''' recommends using the [[Transferring Files|transfer nodes]] or [[Globus]] for larger file transfers. If you must use OOD for large file transfers, please be aware there is a hard-limit in place of ~10.0 Gib. GACRC reserves the right to lower this limit in the future.

[[#top|Back to Top]]

=== Jobs ===

Clicking "Jobs" will open a drop down menu allowing you to navigate to "Active Jobs" or "Job Composer".

==== Active Jobs ====

In the Active Jobs interface, you're able to view information about your currently running jobs. Clicking the arrow on the left will expand this interface displaying further information about the job, as seen below.

[[File:oodjobs2.png | 1200px]] [[File:Oodjobs.png | 1200px]]

[[#top|Back to Top]]

=== Clusters ===

Clicking "Clusters" will open a drop down menu giving you an option to open a shell for the cluster in your browser, on one of the login nodes. This functions just as if you had connected to a Sapelo2 login node via PuTTY (Windows) or Terminal (Mac/Linux). In the top right of this interface you are able to select a different theme for your shell. Please see [[#Browser | Browser Requirements/Notes]] for possible limitations.

[[File:Oodcli1.png | 600 px]]

[[#top|Back to Top]]

=== Interactive Apps ===

One of the best features of Open OnDemand is the ability to directly launch interactive graphical applications. "Interactive Applications" or "Apps" are wrappers that will schedule a Slurm job with a particular application, and give you direct web based access into the interface.

These apps can be accessed near the bottom of the Open OnDemand main page called "Pinned Apps" or from the "Interactive Apps" in the top menu bar. ''Note that the image below is only an example, as the list of interactive applications will grow over time.''

[[File:Screen Shot 2024-05-30 at 10.37.57 AM.png|1000px]]

'''Notes on Rstudio:'''

1. If you are using the Rstudio application with a version of R that uses the foss/2020b (or newer) toolchain, please request an EDR constraint on the resources page.

2. If the Rstudio application fails to open, please edit the following file in your Sapelo2 home directory ~/.config/RStudio/desktop.ini (create this file if it does not exist) to add the following 2 lines:

<pre class="script">
[General]
desktop.renderingEngine=software
</pre>

Note that .config is a hidden directory in your Sapelo2 home directory. Then try the Rstudio app again.

===Launching an application===
Clicking the icon of the interactive application that you would like to use will take you to a new page in which you define the resources allocated to interactive application.

If the GUI application you want to use has its own interactive app in Open OnDemand, you should use that launcher. If the GUI application you want to use does not have a launcher yet you have two options; You an open a ticket with GACRC and request the application be added to OnDemand (Link TBD), or you can use the "[[#X_Desktop |X Desktop Session]]".

====Configuring the resources====
Resources must be defined like this because an Open OnDemand interactive app is happening within the context of a Slurm job. Each application may allow for the customization of different resources, while some may have static defined resources that cannot be changed. Almost all of the resources available to be configured should be familiar to a user who has submitted a job before.

'''Please note''' that the <code>Number of hours</code> option is equivalent to "wall time". If you do not terminate the job before this limit is reached, Slurm will terminate the job for you.

Once you have defined the resources for your job, click "Launch" to be taken to a new page ([[#Inter |My Interactive Sessions]]). After a small delay, the page will refresh showing the status of the job that your app has scheduled. See [[#Inter |My Interactive Sessions]] section of the wiki for more information.

===X Desktop Session (A.K.A. The Interactive X login app)===
The "X Desktop Session on Sapelo2" is an interactive app that will start an X Desktop GUI session as a job. Launching the VNC session will connect you to an actual X desktop running on a Sapelo2 compute node, in your browser. This desktop is currently configured to run the XFCE lightweight graphical manager.

The Sapelo2 X desktop can be used for graphical applications that do not have a dedicated Open OnDemand interactive app. Please be aware that while it is possible within a Sapelo2 Desktop session to open a terminal, load a module, and run a graphical application, for example grace or gnuplot, some of the computing resources requested for this job would be used by the desktop itself. If you find that you have an application that you do this with regularly, please consider opening a ticket with GACRC requesting an interactive app.

====Copy/Paste in VNC====
If launching an interactive session in the portal, there are a few extra steps that need to be taken. Please reference the media below, or the summary of steps below that for more information.

#Open the toolbar on the left of the screen and select "Clipboard".
#If you want to paste text from your host computer to the remote session, paste the text in the clipboard box. You can then use the middle-mouse button (MMB) to paste it in your terminal.
#If you want to copy text from the remote session to your host computer's clipboard, simply highlight the text in the terminal. It will appear in the Clipboard toolbar pop-out where you can copy it to your host clipboard.

[[#top|Back to Top]]

==My Interactive Sessions==

The last item in Open OnDemand top menu bar is "My Interactive Sessions". This interface will list your current and recent interactive app sessions.

[[File:Interactive Session Example.png|frameless|693x693px]]

'''Notable items:'''

*'''Host''': Click the name of the host to open a shell to the compute node that is running this job.
*'''Time Remaining''': This is how long the job will remain running before terminating. (Can be thought of as remaining wall time.)
*'''Session ID''': The unique ID of this session. Clicking the link will open a file app window to this Ondemand sessions working directory. (Useful for troubleshooting issues with application launch)
*'''Compression/Image Quality''': These sliders allow you to change the amount of graphical compression and quality of the VNC session. If you are on a particularly slow connection, or find that the 'redraw' time is slow, try lowering the Image Quality, increasing the Compression, or both, and relaunch the VNC window.
*'''Launch Button''': This button will open a new tab with the web based VNC viewer application. Closing the VNC window will NOT terminate the job, only the VNC connection to it. You may return at any time (as long as the job has time remaining) and click the Launch button to reconnect to your session.
*'''View Only''': This will open a new web based VNC viewer application just like the Launch button, with the caveat that no user input is allowed. You can then copy the URL for this window and send it to others, who will be able to view the VNC session, but not interact with it. (e.g. move the mouse, etc) (This is a great function if you want to show multiple people something in a controlled session!)
*'''Delete''': This button will terminate the job, and delete the session.

[[#top|Back to Top]]

==Additional Notes==

===Interactive applications and GPUs (Hardware accelerated rendering)===
Sapelo2 is currently not configured for applications to use hardware GPU for accelerated graphical rendering. This is currently on our "To Do" list.

Requesting a GPU for an interactive application will assign a GPU to the job just as it would requesting one from a normal command line submit script, but the Xserver will not use this GPU for graphical acceleration. (e.g. you can still use the GPU for computation, but it will not accelerate your frame rate.)

===Per-User Experience===
OnDemand will spawn a Per User Nginx session upon successful login. This means that each connection on the OOD server is running as that particular user. Each session is completely separated from other users sessions.

===Troubleshooting===

For any assistance with Open OnDemand, please reach out to us in via the "General Support" form of the "For Users" section at help.gacrc.uga.edu.

[[#top|Back to Top]]

Georgia Advanced Computing Resource Center

2026-04-05T14:28:48Z

Shtsai:

__NOTOC__
Welcome to the Georgia Advanced Computing Resource Center wiki. The information provided here is a supplement to the GACRC webpage. The GACRC online information resources include:

*[http://gacrc.uga.edu/ Web Site] – General overview
*[https://wiki.gacrc.uga.edu/ Wiki] – Software docs and how-to’s - "You Are Here"
*[https://kaltura.uga.edu/channel/GACRC/176125031 Kaltura] – Linux and HPC training videos









<div style="width=100%; margin:0; background:white; font-size:120%; font-weight:bold; border:4px solid #00CC33; text-align:left; color:black; padding:0.2em 0.4em;"> Current Status: Online </div>






<h2>Important News</h2>
The following is an important notice for all of our current users:



* [[Rocky 9 Transition Guide]]




<h2> Getting Started </h2>
Welcome to the Georgia Advanced Computing Resource Center at the University of Georgia. If you're new to the GACRC, start with these links to get acquainted with our resources.
*[[User Accounts|User Accounts]]
*[[Instructional Accounts]]
*[[Connecting]]
*[[Transferring Files]]
*[[Password | Changing your Password]]
*[[Frequently Asked Questions | FAQ]]
*[[Quick_Reference_Guide|Command List]]
*[[Getting Help]]
*[[Policies]]
*[[Consulting]]
*[[Training]]

A Webinar introducing the GACRC was presented on March 10, 2025. A recording of this [https://kaltura.uga.edu/media/t/1_jfku2g8l/176125031 webinar] is found on GACRC's Kaltura channel.

<h2> System Information </h2>
Hardware information and operational procedures are described below.
*[[Systems]]
*[[Disk Storage]]



<h2> Job and Data Management </h2>
Information on how to run jobs and data management.
*[[Running Jobs]]
*[[Monitoring Jobs]]
*[[Job Submission Partitions]]
*[[Sample Scripts | Sample Job Submission Scripts]]
*[[Migrating from Torque to Slurm]]
*[[Troubleshooting on Sapelo2]]
*[[Best Practices]]
*[[Globus]]
*[[OnDemand | Open OnDemand]]


<h2> Software and Libraries </h2>
Documentation for software applications, programming tools, and usage.
*[[Software]]
*[[Available Toolchains and Toolchain Compatibility]]
*[[Bioinformatics Databases]]
*[[OpenMP]]
*[[MPI | Message Passing Interface (MPI)]]
*[[Compilers]]
*[[GPU|GPU and CUDA Programming]]
*[[Installing Applications]]

Georgia Advanced Computing Resource Center

2026-04-05T14:28:03Z

Shtsai:

__NOTOC__
Welcome to the Georgia Advanced Computing Resource Center wiki. The information provided here is a supplement to the GACRC webpage. The GACRC online information resources include:

*[http://gacrc.uga.edu/ Web Site] – General overview
*[https://wiki.gacrc.uga.edu/ Wiki] – Software docs and how-to’s - "You Are Here"
*[https://kaltura.uga.edu/channel/GACRC/176125031 Kaltura] – Linux and HPC training videos









<div style="width=100%; margin:0; background:white; font-size:120%; font-weight:bold; border:4px solid #00CC33; text-align:left; color:black; padding:0.2em 0.4em;"> Current Status: Online </div>






<h2>Important News</h2>
The following is an important notice for all of our current users:



* [[Rocky 9 Transition Guide]]




<h2> Getting Started </h2>
Welcome to the Georgia Advanced Computing Resource Center at the University of Georgia. If you're new to the GACRC, start with these links to get acquainted with our resources.
*[[User Accounts]]
*[[Instructional Accounts]]
*[[Connecting]]
*[[Transferring Files]]
*[[Password | Changing your Password]]
*[[Frequently Asked Questions | FAQ]]
*[[Quick_Reference_Guide|Command List]]
*[[Getting Help]]
*[[Policies]]
*[[Consulting]]
*[[Training]]

A Webinar introducing the GACRC was presented on March 10, 2025. A recording of this [https://kaltura.uga.edu/media/t/1_jfku2g8l/176125031 webinar] is found on GACRC's Kaltura channel.

<h2> System Information </h2>
Hardware information and operational procedures are described below.
*[[Systems]]
*[[Disk Storage]]



<h2> Job and Data Management </h2>
Information on how to run jobs and data management.
*[[Running Jobs]]
*[[Monitoring Jobs]]
*[[Job Submission Partitions]]
*[[Sample Scripts | Sample Job Submission Scripts]]
*[[Migrating from Torque to Slurm]]
*[[Troubleshooting on Sapelo2]]
*[[Best Practices]]
*[[Globus]]
*[[OnDemand | Open OnDemand]]


<h2> Software and Libraries </h2>
Documentation for software applications, programming tools, and usage.
*[[Software]]
*[[Available Toolchains and Toolchain Compatibility]]
*[[Bioinformatics Databases]]
*[[OpenMP]]
*[[MPI | Message Passing Interface (MPI)]]
*[[Compilers]]
*[[GPU|GPU and CUDA Programming]]
*[[Installing Applications]]

Globus

2026-04-05T14:20:02Z

Shtsai: /* Sharing data from a multi-user system */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found at '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 GACRC Kaltura video introduction to Globus]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed in the [[Globus Connect Personal]] page.

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/|'''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]


[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T14:19:38Z

Shtsai: /* Sharing data from your desktop or laptop */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found at '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 GACRC Kaltura video introduction to Globus]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed in the [[Globus Connect Personal]] page.

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]


[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T14:18:44Z

Shtsai: /* Sharing data from a multi-user system */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found at '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 GACRC Kaltura video introduction to Globus]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed in the [[Globus Connect Personal]] page.

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]


[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T14:15:18Z

Shtsai: /* Documentation */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found at '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 GACRC Kaltura video introduction to Globus]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed in the [[Globus Connect Personal]] page.

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]


[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T14:13:36Z

Shtsai: /* Sharing data from your desktop or laptop */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found at '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 GACRC Kaltura video introduction to Globus]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed in the [[Globus Connect Personal]] page.

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T14:12:31Z

Shtsai:

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found at '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 GACRC Kaltura video introduction to Globus]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed [[Globus Connect Personal]] page.

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T03:20:51Z

Shtsai: /* Transferring files between Sapelo2 file systems */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 here]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|alt="image of a Globus file transfer between two file systems on Sapelo2"|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed [[Globus Connect Personal|here]].

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T03:20:09Z

Shtsai: /* Many files or large files */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 here]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|alt="image of a Globus file transfer setup"|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|alt="image of a Globus file transfer setup highlighting the Start button in the middle"|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed [[Globus Connect Personal|here]].

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T03:18:08Z

Shtsai: /* Small number of files or small sizes downloaded or uploaded */

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 here]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|alt="image of Globus file manager panel with the Download option highlighted on the right"|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed [[Globus Connect Personal|here]].

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T03:16:47Z

Shtsai:

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 here]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|alt="image of Globus collections"|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|alt="image of Sapelo2 home in the Globus file manager"|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed [[Globus Connect Personal|here]].

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Globus

2026-04-05T03:14:38Z

Shtsai:

===Introduction===
The GACRC, on behalf of UGA, recently procured an institutional subscription to Globus for secure, reliable management of UGA's research data.
Globus is a high-performance data-transfer platform that allows you to perform and/or automate:

*Data transfers between servers in your group.
*Data transfers between a server and your laptop.
*Sharing data with researchers at UGA and at other institutions.
*Sharing data with the world.

Data transfers happen unattended and are faster than SCP/SFTP, data verification is on by default, and automatic restarts or continuation of transfers happen after a disruption. A video introduction to Globus at UGA can be found '''[https://kaltura.uga.edu/media/t/1_vlprwoc7/176125031 here]'''.

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

===Getting Started===

If you are a first time user of Globus, you will need to create an Identity Account. At a minimum you will need to setup your identity using the University of Georgia organizational login in order to access UGA systems.

*Go to https://www.globus.org and choose Login in the upper right corner.
*Search for University of Georgia in the “Use your existing organizational login" box.
*Choose continue and you will be forwarded to a UGA Single Sign-On (SSO) login page. You will also need to authenticate with Duo (two-factor authentication).
[[File:Globus-UGA-login.png|alt="image of Globus login page"|border|700x700px]]

When you login for the first time using an existing organization login associated to UGA:

*Globus will ask if you would like to link to an existing account. If you have already used another account with Globus in the past, you can choose "Link to an existing account". Otherwise, click "Continue" to proceed.

*You will need to accept Globus Terms of Service and Privacy Policy and click Continue to proceed.

*You will need to give Globus permission to use your identity to access information and perform actions (like file transfers) on your behalf.

These 3 steps will not be prompted after your first login.

Detailed information with screenshots are provided by Globus at their [https://docs.globus.org/how-to/get-started/ Getting Started page].



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

===Access GACRC Storage===

GACRC maintains a '''UGA GACRC Collection''' that can be used to access and transfer files in and out of the Sapelo2 /home, /scratch, /work, and /project file systems.

After you have logged in to Globus, click the '''File Manager''' link at the top-left of the window.

In the '''Collection''' search box, enter GACRC and you should see UGA GACRC Collection in the list.

[[File:Globus-UGA-GACRC-Collection.png|border|900x900px]]

Select the '''UGA GACRC Collection''' and authenticate with SSO to access your files on Sapelo2. By default, you will open your home directory on Sapelo2. For example:

[[File:Globus-sapelo2-home.png|border|900x900px]]

To access your /scratch or /project areas, enter the full path in the '''Path''' field under the '''Collection''' name (for example, enter /project/abclab) and then press the Enter or Return key on your keyboard for the change in the path to take effect.

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

===Transfer Data Between GACRC Storage and Desktops/Laptops===

There are two ways to use Globus to transfer files between a GACRC storage and desktops or laptops. The method that is best suited depends on the number and size of the files to be transferred. In both cases you would use a browser to Login into https://www.globus.org, as described above, and open the UGA GACRC Collection in the File Manager panel.
====Small number of files or small sizes downloaded or uploaded====

'''Uploads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can select the "Upload" button to upload a file from your local machine to the UGA GACRC Collection, to the path you select (e.g. your Sapelo2 /scratch dir).

'''Downloads''' - Once you open the UGA GACRC Collection in the File Manager panel, you can navigate to the directory where the files are located and select the files you want to download. Then select the "Download" button to download the file(s) to your local machine.

Here is a sample screenshot to download a file called analysis.txt from the user's home directory on Sapelo2 to the local machine:

[[File:Globus-sapelo2-download-file.png|border|900x900px]]

'''File Size Limitations''' - While Globus itself does not impose strict limits on file sizes, some web browsers may have upload limits, typically around 1-2 GB. If you attempt to upload files larger than 1 GB, you may encounter issues with data transfer. For larger file transfers, it is recommended to use Globus Connect Personal (GCP) instead of the web browser interface, as GCP handles larger files more efficiently. Please refer to the instructions in the '''Many Files or Large Files''' section below.

You do not need to install Globus Connect Personal on your local machine in order to use the Download and Upload features, to transfer files from e.g. the UGA GACRC Collection to your local machine. Please note that not all Collections have the Download and Upload feature. If this feature is not available, you can follow the instructions in the '''Many files or large files''' section below.

====Many files or large files====

Install Globus Connect Personal (GCP) and create a Globus endpoint on your local machine. Globus Connect Personal allows faster and more reliable file transfers. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

Once you have installed GCP and created an endpoint on your local machine, navigate to the UGA GACRC Collection in the File Manager panel, select the files or directories you wish to transfer, and click on the double panel icon (top right), as illustrated here:

[[File:Globus-UGA-GACRC-collection-filetransfer1.png|border|900x900px]]

On the right panel, enter the name of the Collection on your endpoint (e.g. called shtsai-imac in this example) and select the path where to transfer the data to (or from). By default, file integrity will be checked after the transfer is completed. You can enable other options (e.g. file encryption on transfer) by opening the '''Transfer & Sync Options''' menu and selecting the options you wish to use. Once all the settings are chosen, and you are ready to perform the file transfer, click on the '''Start''' button. You can check the status of the transfer by going to the Activity panel.

[[File:Globus-UGA-GACRC-collection-filetransfer2.png|border|900x900px]]

====Transfer files from/to an external hard drive====

It is possible to use Globus to transfer files between an external hard drive connected to your local machine and another system, such as a GACRC storage area. The first step is to install Globus Connect Personal (GCP) on your local machine. Information on how to install GCP on your local machine and create an endpoint are available on the [[Globus Connect Personal|'''Globus Connect Personal''']] page.

After you connect your external hard drive to your computer, you will need to add it to the list of Accessible Folders within the Globus Connect Personal application. Documentation on how to do that from Window and Mac are at

https://docs.globus.org/how-to/globus-connect-personal-windows/#configuration

https://docs.globus.org/how-to/globus-connect-personal-mac/#configuration

Then you should be able to transfer files from the external drive to a GACRC storage (or vice-versa) via Globus.

====Transferring files between Sapelo2 file systems====

To transfer files between two files systems on Sapelo2, navigate to the File Manager two-panel view, and select UGA GACRC Collection on both panels. Enter the path to the location of the files on one panel (e.g. your /project directory) and the location where you want to transfer the file to on the other panel (e.g. your /scratch directory). Select the files to transfer and click '''Start'''. You can check a report of the transfer by going to the Activity panel.

Here is an example where a directory called inputdata is transferred from a /project directory to a /scratch directory:

[[File:Globus-filetransfer-project-scratch.png|border|900x900px]]

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

===Access Storage Not Hosted by GACRC===

Globus can be used to access, share, transfer, or manage data stored on devices outside of the GACRC. The steps described above can also be used to access and transfer data from any endpoint that has been shared with you (for example, shared by a collaborator in another institution). You can either search for an endpoint in the '''File Manager''' panel, or go to the '''Endpoints''' panel and select '''Shared with you''' to see a list of Collections shared with you.

You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

===Access Shared Data===

Collaborators can share data with you by sharing a Collection or an endpoint with you. The shared Collection/Endpoint can be on another institution, on a desktop or laptop, or on their GACRC storage. Once you login into https://www.globus.org, you can view all Collections/Endpoints shared with you by clicking on '''Endpoints''' on the left side of the page and then open the '''Shared with you''' tab. A list of endpoints that have been shared with you will be listed on the page.

You can transfer data from shared endpoints to you desktop or laptop, or directly into your GACRC storage (e.g. your /scratch area or your group's /project area). You can transfer files into your Sapelo2 file systems by using the '''UGA GACRC Collection''' and selecting the appropriate directory (e.g. your /home, /scratch, or /project directories).

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

===Sharing Data===

Globus can be used to share data from your local machine or your GACRC /project area.

====Sharing data from GACRC storage (/project)====

You can allow collaborators to download or transfer files from your /project area into their local endpoints/collections or into their GACRC storage space in the UGA GACRC Collection. Your collaborators do not have to be associated with an institution that has a Globus subscription. They can login into https:///www.globus.org using a Globus ID, a Google Account, an ORCID ID, or with their institutional account if their institution has a Globus subscription.

Steps to share a /project folder with a collaborator:

1. In the '''File Manager''' panel, open the '''UGA GACRC Project Sharing''' collection.

2. Navigate to the folder you wish to share (e.g. /project/abclab/shareddir) and select it.

3. Select '''Share''' and create a guest collection.

4. Add permissions to share the collection with your collaborators (they will need to have a Globus account, as indicated above).

Note that your collaborators will not be able to transfer files into your shared Collection on /project, even if you choose to add '''write''' permission while sharing the Collection.

If you would like your collaborators to transfer data into your GACRC storage for you to use on the cluster, please contact GACRC and we will set up a space where they can write into.

To obtain the data you shared with them, your collaborators can do as follows:

a. If you are only sharing a few small files, they can navigate to the File Manager panel in the Globus page (available after they login into https:///www.globus.org), open the collection you shared with them, select the files and use the Download option.

b. To copy large files or a larger number of files to their desktop or laptop, they should install [[Globus Connect Personal|'''Globus Connect Personal]] on their local machine.

c. If your collaborators are GACRC users, they can transfer the data into their GACRC storage, using the UGA GACRC Collection. This use case does not require that they install Globus Connect Personal on their local machine.

====Sharing data from your desktop or laptop====

If you have a need to share data from your desktop or laptop using a Globus Connect Personal collection, please request to join the University of Georgia Standard (HA) Globus subscription with these steps. Note this is not required for normal Collections/Endpoints provided by GACRC.

*Click on Settings
*Choose the Subscriptions tab
*Click "Find a Subscription" and choose University of Georgia Standard (HA)
*Fill out the information and submit your application

Once your request is approved, Globus Plus will allow you to create shared links to your own Globus Connect Personal client. These are also known as guest collections. Please note that if you allow write access to your Collection, your local hard drive can be inadvertently filled or files stored there could be deleted. Please see the [[Globus Connect Personal|'''Globus Connect Personal''']] page for more information.

If you don't have a collection set up on your local computer yet, please first set one up following the steps detailed [[Globus Connect Personal|here]].

Make sure that your collection on your local computer is set to be "shareable" with the following steps:

*Open the Globus Connect Personal application
*Click Preferences > Access
*Check the box under "Shareable" next to your user directory (i.e. /Users/yourname)

====Sharing data from a multi-user system====

If the data are stored (or will be stored) on a multi-user system, you can install [https://docs.globus.org/globus-connect-server/v5.4/ '''Globus Connect Server'''] and create an endpoint on this system. Please contact GACRC to request that your endpoint be associated with UGA's Globus subscription. Once your endpoint is listed in UGA's subscription, you will be able to share it.

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

===Summary of Collections on GACRC storage===

*'''UGA GACRC Collection (All GACRC filesystems) – GACRC Users Only''': This collection allows you to access data on your Sapelo2 /home and /scratch directories, as well as your group's /work and /project areas. You can use the Upload and Download features (recommended for a few small files) or transfer large files and/or a large number of files from/to a different endpoint.

*'''UGA GACRC Project Sharing (Read Only)''': You can use this collection to share a directory with a collaborator. The data to the shared needs to reside in your group's /project folder and you can select a directory to create a shared collection. Anyone with whom you share the collection will be able to copy the shared files (even if the files don't have Unix read permission open for group or for others), but they will not be able to write into your shared collection.

*'''UGA GACRC read-write Sharing''': This collection has read-write access to allow external (to UGA) users to upload data to GACRC storage for a UGA user. Please contact GACRC if your external collaborator needs to upload data onto GACRC storage for you to use ('''upon request, GACRC staff will configure a space for you''').

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

===Globus Command Line Interface===

The Globus Command Line Interface (CLI) provides an interface to Globus services from the shell, and is suited to both interactive and simple scripting use cases. The CLI can be used to integrate Globus actions into your scripts to automate your data flows.

To use it on Sapelo2, you need to load the module first, for example, to use version 2.1.0, load the module with
<pre class="gcommand">
ml Globus-CLI/3.6.0-GCCcore-11.2.0
</pre>

For more information, please see the [[Globus-CLI]] page.

===Common Issues===

If you reinstall Globus Connect Personal (GCP) on your local machine, it will not be automatically associated with the collections that you might have created on your local machine prior to reinstalling GCP. The resulting issue is that you will not see your collection anymore in Globus.

After GCP is reinstalled on your local machine, please

1.Start GCP on your local machine.

2. Go to Preference, then click on "Delete Globus Connect Personal configuration and exit".

3. Start GCP again and it will prompt you to login into Globus and create a new collection.

If these steps are not done following the reinstallation of the GCP, you might not be able to create a new collection, and the old collection (created with a previous installation of the GCP) is not accessible either.

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

=== Documentation===

[https://docs.globus.org/ Official Globus Documentation]

[https://www.globus.org/subscriber-welcome-kit/key-resource-list Key Resource List]

[https://docs.globus.org/how-to/ How-to]

[https://docs.globus.org/faq/ FAQs]

[https://docs.globus.org/how-to/get-started/ How to get started]

[https://docs.globus.org/how-to/share-files/ How to share data using Globus]

[https://www.youtube.com/channel/UCIuyIEG3U5wla7fV7u4dTdQ Globus youtube channel]

Migrating from Torque to Slurm

2026-04-05T03:10:47Z

Shtsai: /* Training material */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to submit and manage jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a job
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Delete a job
| <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
! scope="row" | Hold a job
| <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
! scope="row" | Release a job
| <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
! scope="row" | Start an interactive job with X forwarding
| <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to view resources on the cluster
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Queue list / info
| <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
! scope="row" | Node list
| <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
! scope="row" | Node details
| <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
! scope="row" | Cluster status
| <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to monitor jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Job status (all)
| <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
! scope="row" | Job status (by job)
| <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
! scope="row" | Job status (by user)
| <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
! scope="row" | Job status (only own jobs)
| <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
! scope="row" | Job status (detailed)
| <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
! scope="row" | Show expected start time
| <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
! scope="row" | Monitor or review a job’s resource usage
| <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
! scope="row" | View job batch script
| || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Valid job states
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
! scope="row" | CA
| Canceled || Job was canceled
|-
! scope="row" | CD
| Completed || Job completed
|-
! scope="row" | CF
| Configuring || Job resources being configured
|-
! scope="row" | CG
| Completing || Job is completing
|-
! scope="row" | F
| Failed || Job terminated with non-zero exit code
|-
! scope="row" | NF
| Node Fail || Job terminated due to failure of node(s)
|-
! scope="row" | PD
| Pending || Job is waiting for compute node(s)
|-
! scope="row" | R
| Running || Job is running on compute node(s)
|-
! scope="row" |-TO
| Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Frequently used environment variables
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
! scope="row" | Version
| <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
! scope="row" | Job name
| <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
! scope="row" | Job ID
| <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
! scope="row" | Batch or interactive
| <code>$PBS_ENVIRONMENT</code> || – ||
|-
! scope="row" | Submit directory
| <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
! scope="row" | Submit host
| <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
! scope="row" | Node file
| <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
! scope="row" | Node list
| <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
! scope="row" | Job array index
| <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
! scope="row" | Walltime
| <code>$PBS_WALLTIME</code> || – ||
|-
! scope="row" | Queue name
| <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
! scope="row" | Number of nodes allocated
| <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
! scope="row" | Number of processes
| <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
! scope="row" | Number of processes per node
| <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
! scope="row" | List of allocated GPUs
| <code>$PBS_GPUFILE</code> || – ||
|-
! scope="row" | Requested tasks per node
| – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
! scope="row" | Requested CPUs per task
| – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
! scope="row" | Scheduling priority
| – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
! scope="row" | Job user
| – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

Migrating from Torque to Slurm

2026-04-05T03:07:39Z

Shtsai: /* Job Environment and Environment Variables */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to submit and manage jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a job
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Delete a job
| <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
! scope="row" | Hold a job
| <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
! scope="row" | Release a job
| <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
! scope="row" | Start an interactive job with X forwarding
| <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to view resources on the cluster
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Queue list / info
| <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
! scope="row" | Node list
| <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
! scope="row" | Node details
| <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
! scope="row" | Cluster status
| <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to monitor jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Job status (all)
| <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
! scope="row" | Job status (by job)
| <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
! scope="row" | Job status (by user)
| <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
! scope="row" | Job status (only own jobs)
| <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
! scope="row" | Job status (detailed)
| <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
! scope="row" | Show expected start time
| <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
! scope="row" | Monitor or review a job’s resource usage
| <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
! scope="row" | View job batch script
| || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Valid job states
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
! scope="row" | CA
| Canceled || Job was canceled
|-
! scope="row" | CD
| Completed || Job completed
|-
! scope="row" | CF
| Configuring || Job resources being configured
|-
! scope="row" | CG
| Completing || Job is completing
|-
! scope="row" | F
| Failed || Job terminated with non-zero exit code
|-
! scope="row" | NF
| Node Fail || Job terminated due to failure of node(s)
|-
! scope="row" | PD
| Pending || Job is waiting for compute node(s)
|-
! scope="row" | R
| Running || Job is running on compute node(s)
|-
! scope="row" |-TO
| Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Frequently used environment variables
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
! scope="row" | Version
| <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
! scope="row" | Job name
| <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
! scope="row" | Job ID
| <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
! scope="row" | Batch or interactive
| <code>$PBS_ENVIRONMENT</code> || – ||
|-
! scope="row" | Submit directory
| <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
! scope="row" | Submit host
| <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
! scope="row" | Node file
| <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
! scope="row" | Node list
| <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
! scope="row" | Job array index
| <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
! scope="row" | Walltime
| <code>$PBS_WALLTIME</code> || – ||
|-
! scope="row" | Queue name
| <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
! scope="row" | Number of nodes allocated
| <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
! scope="row" | Number of processes
| <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
! scope="row" | Number of processes per node
| <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
! scope="row" | List of allocated GPUs
| <code>$PBS_GPUFILE</code> || – ||
|-
! scope="row" | Requested tasks per node
| – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
! scope="row" | Requested CPUs per task
| – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
! scope="row" | Scheduling priority
| – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
! scope="row" | Job user
| – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/

Migrating from Torque to Slurm

2026-04-05T03:04:58Z

Shtsai: /* How to Monitor Jobs */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to submit and manage jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a job
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Delete a job
| <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
! scope="row" | Hold a job
| <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
! scope="row" | Release a job
| <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
! scope="row" | Start an interactive job with X forwarding
| <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to view resources on the cluster
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Queue list / info
| <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
! scope="row" | Node list
| <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
! scope="row" | Node details
| <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
! scope="row" | Cluster status
| <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to monitor jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Job status (all)
| <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
! scope="row" | Job status (by job)
| <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
! scope="row" | Job status (by user)
| <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
! scope="row" | Job status (only own jobs)
| <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
! scope="row" | Job status (detailed)
| <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
! scope="row" | Show expected start time
| <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
! scope="row" | Monitor or review a job’s resource usage
| <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
! scope="row" | View job batch script
| || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Valid job states
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
! scope="row" | CA
| Canceled || Job was canceled
|-
! scope="row" | CD
| Completed || Job completed
|-
! scope="row" | CF
| Configuring || Job resources being configured
|-
! scope="row" | CG
| Completing || Job is completing
|-
! scope="row" | F
| Failed || Job terminated with non-zero exit code
|-
! scope="row" | NF
| Node Fail || Job terminated due to failure of node(s)
|-
! scope="row" | PD
| Pending || Job is waiting for compute node(s)
|-
! scope="row" | R
| Running || Job is running on compute node(s)
|-
! scope="row" |-TO
| Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
| Version || <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
| Job name || <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
| Job ID || <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
| Batch or interactive || <code>$PBS_ENVIRONMENT</code> || – ||
|-
| Submit directory || <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
| Submit host || <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
| Node file || <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
| Node list || <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
| Job array index || <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
| Walltime || <code>$PBS_WALLTIME</code> || – ||
|-
| Queue name || <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
| Number of nodes allocated || <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
| Number of processes || <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
| Number of processes per node || <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
| List of allocated GPUs || <code>$PBS_GPUFILE</code> || – ||
|-
| Requested tasks per node || – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
| Requested CPUs per task || – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
| Scheduling priority || – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
| Job user || – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/

Migrating from Torque to Slurm

2026-04-05T03:03:28Z

Shtsai: /* How to Monitor Jobs */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to submit and manage jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a job
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Delete a job
| <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
! scope="row" | Hold a job
| <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
! scope="row" | Release a job
| <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
! scope="row" | Start an interactive job with X forwarding
| <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to view resources on the cluster
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Queue list / info
| <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
! scope="row" | Node list
| <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
! scope="row" | Node details
| <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
! scope="row" | Cluster status
| <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to monitor jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Job status (all)
| <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
! scope="row" | Job status (by job)
| <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
! scope="row" | Job status (by user)
| <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
! scope="row" | Job status (only own jobs)
| <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
! scope="row" | Job status (detailed)
| <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
! scope="row" | Show expected start time
| <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
! scope="row" | Monitor or review a job’s resource usage
| <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
! scope="row" | View job batch script
| || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
| CA || Canceled || Job was canceled
|-
| CD || Completed || Job completed
|-
| CF || Configuring || Job resources being configured
|-
| CG || Completing || Job is completing
|-
| F || Failed || Job terminated with non-zero exit code
|-
| NF || Node Fail || Job terminated due to failure of node(s)
|-
| PD || Pending || Job is waiting for compute node(s)
|-
| R || Running || Job is running on compute node(s)
|-
|-TO || Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
| Version || <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
| Job name || <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
| Job ID || <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
| Batch or interactive || <code>$PBS_ENVIRONMENT</code> || – ||
|-
| Submit directory || <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
| Submit host || <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
| Node file || <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
| Node list || <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
| Job array index || <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
| Walltime || <code>$PBS_WALLTIME</code> || – ||
|-
| Queue name || <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
| Number of nodes allocated || <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
| Number of processes || <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
| Number of processes per node || <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
| List of allocated GPUs || <code>$PBS_GPUFILE</code> || – ||
|-
| Requested tasks per node || – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
| Requested CPUs per task || – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
| Scheduling priority || – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
| Job user || – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/

Migrating from Torque to Slurm

2026-04-05T03:02:26Z

Shtsai: /* How to View Resources on the Cluster */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to submit and manage jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a job
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Delete a job
| <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
! scope="row" | Hold a job
| <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
! scope="row" | Release a job
| <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
! scope="row" | Start an interactive job with X forwarding
| <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to view resources on the cluster
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Queue list / info
| <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
! scope="row" | Node list
| <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
! scope="row" | Node details
| <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
! scope="row" | Cluster status
| <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Job status (all) || <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
| Job status (by job) || <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
| Job status (by user) || <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
| Job status (only own jobs) || <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
| Job status (detailed) || <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
| Show expected start time || <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
| Monitor or review a job’s resource usage || <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
| View job batch script || || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
| CA || Canceled || Job was canceled
|-
| CD || Completed || Job completed
|-
| CF || Configuring || Job resources being configured
|-
| CG || Completing || Job is completing
|-
| F || Failed || Job terminated with non-zero exit code
|-
| NF || Node Fail || Job terminated due to failure of node(s)
|-
| PD || Pending || Job is waiting for compute node(s)
|-
| R || Running || Job is running on compute node(s)
|-
|-TO || Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
| Version || <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
| Job name || <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
| Job ID || <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
| Batch or interactive || <code>$PBS_ENVIRONMENT</code> || – ||
|-
| Submit directory || <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
| Submit host || <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
| Node file || <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
| Node list || <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
| Job array index || <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
| Walltime || <code>$PBS_WALLTIME</code> || – ||
|-
| Queue name || <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
| Number of nodes allocated || <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
| Number of processes || <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
| Number of processes per node || <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
| List of allocated GPUs || <code>$PBS_GPUFILE</code> || – ||
|-
| Requested tasks per node || – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
| Requested CPUs per task || – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
| Scheduling priority || – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
| Job user || – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/

Migrating from Torque to Slurm

2026-04-05T03:01:37Z

Shtsai: /* How to Submit and Manage Jobs */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Commands to submit and manage jobs
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a job
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Delete a job
| <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
! scope="row" | Hold a job
| <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
! scope="row" | Release a job
| <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
! scope="row" | Start an interactive job with X forwarding
| <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Queue list / info || <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
| Node list || <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
| Node details || <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
| Cluster status || <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Job status (all) || <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
| Job status (by job) || <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
| Job status (by user) || <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
| Job status (only own jobs) || <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
| Job status (detailed) || <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
| Show expected start time || <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
| Monitor or review a job’s resource usage || <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
| View job batch script || || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
| CA || Canceled || Job was canceled
|-
| CD || Completed || Job completed
|-
| CF || Configuring || Job resources being configured
|-
| CG || Completing || Job is completing
|-
| F || Failed || Job terminated with non-zero exit code
|-
| NF || Node Fail || Job terminated due to failure of node(s)
|-
| PD || Pending || Job is waiting for compute node(s)
|-
| R || Running || Job is running on compute node(s)
|-
|-TO || Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
| Version || <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
| Job name || <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
| Job ID || <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
| Batch or interactive || <code>$PBS_ENVIRONMENT</code> || – ||
|-
| Submit directory || <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
| Submit host || <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
| Node file || <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
| Node list || <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
| Job array index || <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
| Walltime || <code>$PBS_WALLTIME</code> || – ||
|-
| Queue name || <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
| Number of nodes allocated || <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
| Number of processes || <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
| Number of processes per node || <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
| List of allocated GPUs || <code>$PBS_GPUFILE</code> || – ||
|-
| Requested tasks per node || – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
| Requested CPUs per task || – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
| Scheduling priority || – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
| Job user || – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/

Migrating from Torque to Slurm

2026-04-05T02:58:58Z

Shtsai: /* Job Submission Options */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
! scope="row" | Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Submit a job || <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
| Delete a job || <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
| Hold a job || <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
| Release a job || <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
| Start an interactive job || <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
| Start an interactive job with X forwarding || <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Queue list / info || <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
| Node list || <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
| Node details || <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
| Cluster status || <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Job status (all) || <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
| Job status (by job) || <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
| Job status (by user) || <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
| Job status (only own jobs) || <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
| Job status (detailed) || <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
| Show expected start time || <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
| Monitor or review a job’s resource usage || <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
| View job batch script || || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
| CA || Canceled || Job was canceled
|-
| CD || Completed || Job completed
|-
| CF || Configuring || Job resources being configured
|-
| CG || Completing || Job is completing
|-
| F || Failed || Job terminated with non-zero exit code
|-
| NF || Node Fail || Job terminated due to failure of node(s)
|-
| PD || Pending || Job is waiting for compute node(s)
|-
| R || Running || Job is running on compute node(s)
|-
|-TO || Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
| Version || <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
| Job name || <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
| Job ID || <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
| Batch or interactive || <code>$PBS_ENVIRONMENT</code> || – ||
|-
| Submit directory || <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
| Submit host || <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
| Node file || <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
| Node list || <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
| Job array index || <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
| Walltime || <code>$PBS_WALLTIME</code> || – ||
|-
| Queue name || <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
| Number of nodes allocated || <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
| Number of processes || <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
| Number of processes per node || <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
| List of allocated GPUs || <code>$PBS_GPUFILE</code> || – ||
|-
| Requested tasks per node || – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
| Requested CPUs per task || – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
| Scheduling priority || – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
| Job user || – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/

Migrating from Torque to Slurm

2026-04-05T02:58:15Z

Shtsai: /* Job Submission Options */

During the Oct.24-28 maintenance window, GACRC implemented the Slurm software
for job scheduling and resource management on Sapelo2. Slurm replaced the Torque (PBS) resource manager and the Moab scheduling system that Sapelo2 used before then.

==How is Slurm different from Torque?==

Slurm is different from Torque in a number of ways, including the commands used to submit and monitor jobs, the syntax used to request resources, and the way environment variables behave.

Some specific ways in which Slurm is different from Torque include:

*Slurm will not allow a job to be submitted whose requested resources exceed the set of resources the job owner has access to--whether or not those resources have been already allocated to other jobs at the moment. Torque will queue the job, but the job would never run.
*What Torque calls queues, Slurm calls partitions.
*Resources in Slurm are assigned per “task”/process.
*In Slurm, environmental variables of the submitting process are passed to the job by default 

==How to Submit Jobs==

To submit jobs in Slurm, replace <code>qsub</code> with one of the commands from the table below.

{| width="60%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission commands
|-
! scope="col" | Info
! scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
! scope="row" | Submit a batch job to the queue
| <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
! scope="row" | Start an interactive job
| <code>qsub -I <options></code> || <code> salloc <options> </code>
|}
where <job script> needs to be replaced by the name of your job submission script (e.g. sub.sh). Note that the syntax in the job submission script for Slurm is different from the Torque syntax.

==Job Submission Options==

As with Torque, job options and resource requests in Slurm can be set in the job submission script or as options to the job submission command. However, the syntax used to request resources is different and the table below summarizes some of the options that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|+ Job submission options
|-
! scope="col" | Option
! scope="col" | Torque (qsub)
! scope="col" | Slurm (sbatch)
|-

|-
! scope="row" | Script directive
| <code>#PBS</code> || <code>#SBATCH</code>
|-
! scope="row" | Job name
| <code>-N <name> </code> || <code>--job-name=<name></code> <code>-J <name></code>
|-
! scope="row" | Queue
| <code>-q <queue> </code>|| <code>--partition=<queue></code>
|-
! scope="row" | Wall time limit
| <code>-l walltime=<hh:mm:ss> </code>|| <code>--time=<hh:mm:ss></code>
|-
! scope="row" | Node count
| <code>-l nodes=<count></code>
| <code>--nodes=<count></code> <code> -N <count></code>
|-
! scope="row" | Process count per node
| <code>-l ppn=<count></code> || <code>--ntasks-per-node=<count></code>
|-
! scope="row" | core count (per process)
| || <code>--cpus-per-task=<cores></code>
|-
! scope="row" | Memory limit
| <code>-l mem=<limit></code> || <code>--mem=<limit> </code> (Memory per node in mega bytes – MB)
|-
! scope="row" | Minimum memory per processor
| <code>-l pmem=<limit> </code>|| <code>--mem-per-cpu=<memory></code>
|-
! scope="row" | Request GPUs
| <code>-l gpus=<count></code> || <code>--gres=gpu:<count></code>
|-
! scope="row" | Request specific nodes
| <code>-l nodes=<node>[,node2[,...]]></code> || <code>-w, --nodelist=<node>[,node2[,...]]></code> <code> -F, --nodefile=<node file></code>
|-
! scope="row" | Request node feature
| <code>-l nodes=<count>:ppn=<count>:<feature></code> || <code>--constraint=<feature></code>
|-
! scope="row" | Job array
| <code>-t <array indices></code> || <code>--array <indexes></code> <code>-a <indexes></code> Where <indexes> is replaced by a range (0-15), a list (0, 6, 16-32), or a step function (0-15:4)
|-
! scope="row" | Standard output file
|<code>-o <file path></code> || <code>--output=<file path></code> (path must exist)
|-
! scope="row" | Standard error file
| <code>-e <file path></code> || <code>--error=<file path></code> (path must exist)
|-
! scope="row" | Combine stdout/stderr to stdout
| <code>-j oe</code> || <code>--output=<combined out and err file path></code>
|-
! scope="row" | Copy environment
| <code>-V </code>|| <code>--export=ALL (default)</code> <code>--export=NONE </code> to not export environment
|-
! scope="row" | Copy environment variable
| <code>-v <variable[=value][,variable2=value2[,...]]></code> || <code>--export=<variable[=value][,variable2=value2[,...]]></code>
|-
! scope="row" | Job dependency
| <code>-W depend=after:jobID[:jobID...]</code> <code>-W depend=afterok:jobID[:jobID...]</code> <code>-W depend=afternotok:jobID[:jobID...]</code> <code>-W depend=afterany:jobID[:jobID...]</code> || <code>--dependency=after:jobID[:jobID...]</code> <code>--dependency=afterok:jobID[:jobID...]</code> <code>--dependency=afternotok:jobID[:jobID...]</code> <code>--dependency=afterany:jobID[:jobID...]</code>
|-
|! scope="row" Request event notification
| <code>-m <events> </code>|| <code>--mail-type=<events></code> Note: multiple mail-type requests may be specified in a comma separated list: <code> --mail-type=BEGIN,END,NONE,FAIL,REQUEUE</code>
|-
! scope="row" | Email address
| <code>-M <email address></code> || <code>--mail-user=<email address></code>
|-
! scope="row" | Defer job until the specified time
| <code>-a <date/time></code> || <code>--begin=<date/time></code>
|-
! scope="row" | Node exclusive job
| <code>qsub -n</code> || <code>--exclusive</code>
|}

==Common Job Commands==

===How to Submit and Manage Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Submit a job || <code>qsub <job script></code> || <code>sbatch <job script></code>
|-
| Delete a job || <code>qdel <job ID></code> || <code>scancel <job ID></code>
|-
| Hold a job || <code>qhold <job ID></code> || <code>scontrol hold <job ID></code>
|-
| Release a job || <code>qrls <job ID></code> || <code>scontrol release <job ID></code>
|-
| Start an interactive job || <code>qsub -I <options></code> || <code>salloc <options></code> <code>srun --pty <options></code>
|-
| Start an interactive job with X forwarding || <code>qsub -I -X <options></code> || <code>srun --x11 <options> </code>

|}

===How to View Resources on the Cluster===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Queue list / info || <code>qstat -q [queue]</code> || <code>scontrol show partition [queue]</code>
|-
| Node list || <code>pbsnodes -a</code> <code>mdiag -n -v </code>|| <code>scontrol show nodes</code>
|-
| Node details || <code>pbsnodes <node></code> || <code>scontrol show node <node></code>
|-
| Cluster status || <code>qstat -B </code>|| <code>sinfo</code>
|}

===How to Monitor Jobs===

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 20%" scope="col" | Info
! style="width: 20%" scope="col" | Torque Command
! scope="col" | Slurm Command
|-

|-
| Job status (all) || <code>qstat</code> <code>showq</code> || <code>squeue</code>
|-
| Job status (by job) || <code>qstat <job ID></code> || <code>squeue -j <job ID></code>
|-
| Job status (by user) || <code>qstat -u <user></code> || <code>squeue -u <user></code>
|-
| Job status (only own jobs) || <code>qstat_me</code> || <code>squeue --me</code> <code>squeue --me -l</code>
|-
| Job status (detailed) || <code>qstat -f <job ID></code> <code>checkjob <job ID> </code>|| <code>scontrol show job -dd <job ID></code>
|-
| Show expected start time || <code>showstart <job ID> </code>|| <code>squeue -j <job ID> --start</code>
|-
| Monitor or review a job’s resource usage || <code>qstat -f <job ID> </code>|| <code>sacct -j <job ID> --format JobID,jobname,NTasks,nodelist,CPUTime,ReqMem,Elapsed </code>
|-
| View job batch script || || <code>scontrol write batch_script <job ID> [filename]</code>

|}

'''Valid Job States'''

Below are the job states you may encounter when monitoring your job(s) in Slurm.

{| width="40%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 5%" scope="col" | Code
! style="width: 30%" scope="col" | State
! scope="col" | Meaning
|-

|-
| CA || Canceled || Job was canceled
|-
| CD || Completed || Job completed
|-
| CF || Configuring || Job resources being configured
|-
| CG || Completing || Job is completing
|-
| F || Failed || Job terminated with non-zero exit code
|-
| NF || Node Fail || Job terminated due to failure of node(s)
|-
| PD || Pending || Job is waiting for compute node(s)
|-
| R || Running || Job is running on compute node(s)
|-
|-TO || Timeout || Job terminated upon reaching its time limit
|}

==Job Environment and Environment Variables==

In Slurm, environment variables will get passed to your job by default.



If you have certain environment variables set that you think might interfere with your job you can either:

*Log out then log back in and submit your job
*Run sbatch with one of these options to override the default behavior:
<pre class="gcommand">
sbatch --export=None
sbatch --export MYPARAM=3
sbatch --export=ALL,MYPARAM=3
</pre>

NOTE: We recommend that you submit sbatch Slurm jobs with the #SBATCH --export=NONE option to establish a clean environment, otherwise Slurm will propagate current environmental variables to the job. This could impact the behavior of the job, particularly for MPI jobs.

Like Torque, Slurm sets its own environment variables within your job. The table below summarizes some environment variables that are frequently used.

{| width="100%" border="1" cellspacing="0" cellpadding="2" align="top" class="wikitable unsortable"
|-
! style="width: 15%" scope="col" | Info
! style="width: 17%" scope="col" | Torque
! style="width: 28%" scope="col" | Slurm
! scope="col" | Notes
|-

|-
| Version || <code>$PBS_VERSION</code> || – || Can extract from <code>sbatch --version</code>
|-
| Job name || <code>$PBS_JOBNAME</code> || <code>$SLURM_JOB_NAME</code> ||
|-
| Job ID || <code>$PBS_JOBID</code> || <code>$SLURM_JOB_ID</code> ||
|-
| Batch or interactive || <code>$PBS_ENVIRONMENT</code> || – ||
|-
| Submit directory || <code>$PBS_O_WORKDIR</code> || <code>$SLURM_SUBMIT_DIR</code> || Slurm jobs start from the submit directory by default.
|-
| Submit host || <code>$PBS_O_HOST</code> || <code>$SLURM_SUBMIT_HOST</code> ||
|-
| Node file || <code>$PBS_NODEFILE</code> || || A filename and path that lists the nodes a job has been allocated.
|-
| Node list || <code>cat $PBS_NODEFILE</code> || <code>$SLURM_JOB_NODELIST</code> || The Slurm variable has a different format to the Torque/PBS one. To get a list of nodes use: <code>scontrol show hostnames $SLURM_JOB_NODELIST</code>
|-
| Job array index || <code>$PBS_ARRAYID</code> <code>$PBS_ARRAY_INDEX</code> || <code>$SLURM_ARRAY_TASK_ID</code> || Only set when submitting a job array (with -a or –array)
|-
| Walltime || <code>$PBS_WALLTIME</code> || – ||
|-
| Queue name || <code>$PBS_QUEUE</code> || <code>$SLURM_JOB_PARTITION</code> ||
|-
| Number of nodes allocated || <code>$PBS_NUM_NODES</code> || <code>$SLURM_JOB_NUM_NODES</code> <code>$SLURM_NNODES</code> ||
|-
| Number of processes || <code>$PBS_NP</code> || <code>$SLURM_NTASKS</code> ||
|-
| Number of processes per node || <code>$PBS_NUM_PPN</code> || <code>$SLURM_TASKS_PER_NODE</code> ||
|-
| List of allocated GPUs || <code>$PBS_GPUFILE</code> || – ||
|-
| Requested tasks per node || – || <code>$SLURM_NTASKS_PER_NODE</code> ||
|-
| Requested CPUs per task || – || <code>$SLURM_CPUS_PER_TASK</code> ||
|-
| Scheduling priority || – || <code>$SLURM_PRIO_PROCESS</code> ||
|-
| Job user || – || <code>$SLURM_JOB_USER</code> ||

|}

==Slurm Documentation==

Extensive documentation on Slurm is available at https://slurm.schedmd.com/documentation.html

==Training material==

To help users familiarize with Slurm and the test cluster environment, we have prepared some training videos that are available from the GACRC's Kaltura channel at https://kaltura.uga.edu/channel/GACRC/176125031 (login with MyID and password is required). Training sessions and slides are available at https://wiki.gacrc.uga.edu/wiki/Training

This page was adapted from https://arc-ts.umich.edu/migrating-from-torque-to-slurm/ and https://hpcc.usc.edu/support/documentation/pbs-to-slurm/