updated table and slurm scripts for Using Slurm from a Terminal

Author: orndorffp

content/notes/slurm-from-cli/scripts/array.slurm

@@ -1,7 +1,7 @@
 #!/bin/bash
 #SBATCH --ntasks=1
-#SBATCH --partition=standard
-#SBATCH -A myalloc
+#SBATCH --partition=interactive
+#SBATCH -A hpc_training
 #SBATCH --time=3:00:00
 #SBATCH -o out%A.%a
 #SBATCH -e err%A.%a

content/notes/slurm-from-cli/scripts/hello.slurm

@@ -3,8 +3,8 @@
 #SBATCH --ntasks=1
 #SBATCH --mem=32000 # mb total memory
 #SBATCH --time=1-12:00:00
-#SBATCH --partition=standard
-#SBATCH --account=myalloc
+#SBATCH --partition=interactive
+#SBATCH --account=hpc_training
 
 module purge
 module load anaconda

content/notes/slurm-from-cli/scripts/hybrid.slurm

@@ -1,8 +1,9 @@
+#!/bin/bash
 #SBATCH -N 3
 #SBATCH --ntasks-per-node=4
 #SBATCH -c 10
 #SBATCH -p parallel
-#SBATCH -A myalloc
+#SBATCH -A hpc_training
 #SBATCH -t 05:00:00
 #SBATCH [email protected]
 #SBATCH --mail-type=END

content/notes/slurm-from-cli/scripts/multicore.slurm

@@ -1,7 +1,7 @@
 #SBATCH -n 1
 #SBATCH -c 25
-#SBATCH -p standard
-#SBATCH -A myalloc
+#SBATCH -p interactive
+#SBATCH -A hpc_training
 #SBATCH -t 05:00:00
 #SBATCH [email protected]
 #SBATCH --mail-type=END

content/notes/slurm-from-cli/scripts/multinode.slurm

@@ -1,7 +1,7 @@
 #!/bin/bash
 #SBATCH --nodes=3
 #SBATCH --ntasks-per-node=40
-#SBATCH --account=myalloc
+#SBATCH --account=hpc_training
 #SBATCH -p parallel
 #SBATCH -t 10:00:00
 #SBATCH [email protected]

content/notes/slurm-from-cli/scripts/slow.slurm

@@ -2,8 +2,8 @@
 #SBATCH --nodes=1
 #SBATCH --ntasks=1
 #SBATCH --time=00:30:00
-#SBATCH --partition=standard
-#SBATCH --account=myalloc
+#SBATCH --partition=interactive
+#SBATCH --account=hpc_training
 
 module purge
 

content/notes/slurm-from-cli/section1.md

@@ -47,13 +47,13 @@ Slurm refers to the root process as a **task**. By default, each task is assigne
 SLURM refers to queues as  __partitions__ .  We do not have a default partition; each job must request one explicitly.
 
 {{< table >}}
-| Queue Name | Purpose | Job Time Limit | Memory / Node | Cores / Node |
+| Queue Name | Purpose | Job Time Limit | Max Memory / Node / Job | Max Cores / Node |
 | :-: | :-: | :-: | :-: | :-: |
-| standard | For jobs on a single compute node | 7 days | 384 GB | 40 |
-| gpu | For jobs that can use general purpose GPU’s<br /> (P100,V100,A100) | 3 days | 256 GB<br />384 GB<br />1 TB | 28<br />40<br />128 |
-| parallel | For large parallel jobs on up to 50 nodes (<= 1500 CPU cores) | 3 days | 384 GB | 40<br /> |
-| largemem | For memory intensive jobs | 4 days | 768 GB<br />1 TB | 16 |
-| dev | To run jobs that are quick tests of code | 1 hour | 128 GB |  40  |
+| standard | For jobs on a single compute node | 7 days | 375 GB | 37 |
+| gpu | For jobs that can use general purpose GPU’s<br /> (A40,A100,A6000,V100,RTX3090) | 3 days | 1953 GB | 125 |
+| parallel | For large parallel jobs on up to 50 nodes (<= 1500 CPU cores) | 3 days | 375 GB | 40<br /> |
+| largemem | For memory intensive jobs | 4 days | 768 GB<br />1 TB | 45 |
+| interactive | For quick interactive sessions (up to two RTX2080 GPUs) | 12 hours | 216 GB |  37  |
 {{< /table >}}
 
 To see an online list of available partitions, from a command line type

content/notes/slurm-from-cli/section2.md

@@ -50,8 +50,8 @@ The lines starting with `#SBATCH` are the resource requests.  They are called "p
 #SBATCH --ntasks=1
 #SBATCH --mem=32000 # mb total memory
 #SBATCH –-time=1-12:00:00
-#SBATCH --partition=standard
-#SBATCH --account=myalloc
+#SBATCH --partition=interactive
+#SBATCH --account=hpc_training
 ```
 Here we are requesting
   * 1 node, 1 task