Differences

This shows you the differences between two versions of the page.

--- doku:vsc5quickstart [2022/06/24 09:53] – [Submit a Job] jz
+++ doku:vsc5quickstart [2023/01/05 21:09] – [SLURM] goldenberg
@@ Line 155: / Line 155: @@
 ===== SLURM =====
+For the exact partition/queue setup see [[doku:vsc5_queue|Queue | Partition setup on VSC-5]]
 The following partitions are currently available:
@@ Line 160: / Line 161: @@
 $ sinfo -o %P
 PARTITION
-gpu_a100_dual* -> Currently the default partition. AMD CPU nodes with 2x AMD Epyc (Milan) and 2x NIVIDA A100 and 512GB RAM
+zen2_0256_a40x2 -> AMD CPU nodes with 2x AMD Epyc (Milan) and 2x NIVIDA A40 and 256GB RAM
-cascadelake_0384 -> Intel CPU nodes with 2x Intel Cascadelake and 384GB RAM
+jupyter -> reserved for the jupyterhub
-zen3_0512 -> AMD CPU nodes with 2x AMD Epyc (Milan) and 512GB RAM
+login5 -> login nodes, not an actual slurm partition
-zen3_1024 -> AMD CPU nodes with 2x AMD Epyc (Milan) and 1TB RAM
 zen3_2048 -> AMD CPU nodes with 2x AMD Epyc (Milan) and 2TB RAM
+zen3_1024 -> AMD CPU nodes with 2x AMD Epyc (Milan) and 1TB RAM
+zen3_0512* -> The default partition. AMD CPU nodes with 2x AMD Epyc (Milan) and 512GB RAM
+cascadelake_0384 -> Intel CPU nodes with 2x Intel Cascadelake and 384GB RAM
+zen3_0512_a100x2 -> AMD CPU nodes with 2x AMD Epyc (Milan) and 2x NIVIDA A100 and 512GB RAM
 </code>
@@ Line 257: / Line 262: @@
 ===== Intel MPI =====
-When using Intel-MPI and mpirun please set the following environment variable in your job script to allow for correct process pinning:
+When **using Intel-MPI on the AMD nodes and mpirun** please set the following environment variable in your job script to allow for correct process pinning:
 <code>