Differences

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

--- doku:ai_intro [2024/03/15 08:13] – alindner
+++ doku:ai_intro [2024/03/15 08:56] – Improve readability of example SLURM script mpfister
@@ Line 17: / Line 17: @@
 <file bash gpu_job_template.slurm>
 #!/bin/bash
-#
-#SBATCH --job-name=GPU_job  # Job name
+## Specify job name:
+#SBATCH --job-name=GPU_job
+## Specify GPU:
 ## For Nvidia A40:
-#SBATCH --partition=zen2_0256_a40x2  # Type of hardware
+##SBATCH --partition=zen2_0256_a40x2
-#SBATCH --qos=zen2_0256_a40x2  # Quality of service, for VSC often identical to partition
+##SBATCH --qos=zen2_0256_a40x2
 ## For Nvidia A100:
-##SBATCH --partition=zen3_0512_a100x2  # Type of hardware
+#SBATCH --partition=zen3_0512_a100x2
-##SBATCH --qos=zen3_0512_a100x2  # Quality of service, for VSC often identical to partition
+#SBATCH --qos=zen3_0512_a100x2
-#SBATCH --time=0-01:00:00  # Maximum run time in format days-hours:minutes:seconds (up to 3 days)
+## Specify run time limit in format days-hours:minutes:seconds (up to 3 days)
+## Note: Job will be killed once the run time limit is reached.
+## Shorter values might reduce queuing time.
+#SBATCH --time=0-01:00:00
+## Specify number of GPUs (1 or 2):
 #SBATCH --gres=gpu:1  # Number of GPUs
-##Optional: Get notified via mail when the job runs and finishes:
+## Optional: Get notified via mail when the job runs and finishes:
 ##SBATCH --mail-type=ALL    # BEGIN, END, FAIL, REQUEUE, ALL
-##SBATCH --mail-user=martin.pfister@tuwien.ac.at
+##SBATCH --mail-user=user@example.com
+# Start in a clean environment
+module purge
-module purge  # Start in a clean environment
+# List available GPUs:
 nvidia-smi
+# Load conda:
 module load miniconda3
 eval "$(conda shell.bash hook)"
+# Load a conda environment with Python 3.11.6, PyTorch 2.1.0, TensorFlow 2.13.1 and other packages:
+export XLA_FLAGS=--xla_gpu_cuda_data_dir=/gpfs/opt/sw/cuda-zen/spack-0.19.0/opt/spack/linux-almalinux8-zen/gcc-12.2.0/cuda-11.8.0-knnuyxtpma52vhp6zhj72nbjfbrcvb7f
 conda activate /opt/sw/jupyterhub/envs/conda/vsc5/jupyterhub-horovod-v1
+# Run AI scripts:
 python -c "import torch;print(torch.__version__);print(torch.cuda.get_device_properties(0))"
 </file>