diff --git a/scripts/benchmark_single_node.sbatch b/scripts/benchmark_single_node.sbatch index a52be2b5a74e9dfb05ea90a342fffdbd901d6e93..30b90b6fa0e7f79ab09d068229042b3f55ba0189 100644 --- a/scripts/benchmark_single_node.sbatch +++ b/scripts/benchmark_single_node.sbatch @@ -6,13 +6,23 @@ #SBATCH --time=0-0:10:00 #SBATCH --reservation=devel - +###################21.11.0 +# This version does not run on multi-node # For apptainer rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json -apptainer exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json'" +apptainer exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json'" rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json -apptainer exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json'" +apptainer exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --amp --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json'" + + +###################22.11.0 +# For apptainer +#rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json +#apptainer exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json'" + +#rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json +#apptainer exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json'" # For enroot #rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json