Differenze

Queste sono le differenze tra la revisione selezionata e la versione attuale della pagina.

--- calcoloscientifico:userguide:gromacs [20/08/2025 17:36] – [Job Gromacs GPU] fabio.spataro
+++ calcoloscientifico:userguide:gromacs [20/08/2025 18:00] (versione attuale) – [Job Gromacs CPU] fabio.spataro
@@ Linea 523: / Linea 523: @@
 ==== Examples ====
-The following examples demonstrate using the NGC GROMACS container to run the ''STMV'' benchmark.
+The following examples demonstrate using the [[https://catalog.ngc.nvidia.com/orgs/hpc/containers/gromacs|NGC GROMACS]] container to run the ''STMV'' benchmark.
 Download the ''STMV'' benchmark:
@@ Linea 535: / Linea 535: @@
 ==== Job Gromacs CPU ====
-Script ''slurm-gromacs-2025.1-cpu.sh'' to request one node and start 8 MPI thread and 6 OpenMP threads for each MPI thread (48 threads overall) and run the ''STMV'' benchmark:
+Script ''slurm-gromacs-2025.1-cpu.sh'' to request one node and start 8 thread-MPI tasks and 6 OpenMP threads for each thread-MPI task (48 threads overall) and run the ''STMV'' benchmark:
 <code bash slurm-gromacs-2025.1-cpu.sh>
@@ Linea 546: / Linea 546: @@
 #SBATCH --cpus-per-task=6
 #SBATCH --time=0-04:00:00
-#SBATCH --mem=32G
+#SBATCH --mem=16G
 #SBATCH --partition=cpu_guest
 #SBATCH --qos=cpu_guest
@@ Linea 581: / Linea 581: @@
 ==== Job Gromacs GPU ====
-Script ''slurm-gromacs-2025.1-gpu.sh'' to request one node and start 8 MPI thread and 6 OpenMP threads for each MPI process (48 threads thread) with 8 CUDA GPU's and run the ''STMV'' benchmark:
+Script ''slurm-gromacs-2025.1-gpu.sh'' to request one node and start 8 thread-MPI tasks and 6 OpenMP threads for each thread-MPI task (48 threads thread) with 8 CUDA GPU's and run the ''STMV'' benchmark:
 <code bash slurm-gromacs-2025.1-gpu.sh>
@@ Linea 591: / Linea 591: @@
 #SBATCH --ntasks-per-node=8
 #SBATCH --cpus-per-task=6
-#SBATCH --time=0-04:00:00
+#SBATCH --time=0-00:30:00
 #SBATCH --mem=8G
 #SBATCH --gres=gpu:a5000_mm1:8