bash_diagnose_leak.sh

#!/bin/bash -l
#SBATCH --job-name=xpu-leak-diag
#SBATCH --account=AIRR-P51-DAWN-GPU
#SBATCH --partition=pvc9
#SBATCH --nodes=1
#SBATCH --gres=gpu:1
#SBATCH --ntasks-per-node=1
#SBATCH --cpus-per-task=12
#SBATCH --time=01:00:00
#SBATCH --output=Logs/diagnose_leak_%j.out
#SBATCH --error=Logs/diagnose_leak_%j.err

. /etc/profile.d/modules.sh
module purge
module load rhel9/default-dawn

source ~/miniconda3/etc/profile.d/conda.sh
conda activate ~/rds/rds-airr-p51-TWhPgQVLKbA/Env/pub_env/pytorch-xpu

export CCL_WORKER_AFFINITY=auto
export I_MPI_PMI_LIBRARY=/usr/local/software/slurm/current-rhel8/lib/libpmi2.so

# Run all tests sequentially on a single XPU tile
python tests/diagnose_xpu_leak.py --test 1
python tests/diagnose_xpu_leak.py --test 2
python tests/diagnose_xpu_leak.py --test 3
python tests/diagnose_xpu_leak.py --test 4