diff --git a/samples/gpu/nccl_run_allreduce_containers_with_ordering.sbatch b/samples/gpu/nccl_run_allreduce_containers_with_ordering.sbatch
index fd7abb7..588197f 100644
--- a/samples/gpu/nccl_run_allreduce_containers_with_ordering.sbatch
+++ b/samples/gpu/nccl_run_allreduce_containers_with_ordering.sbatch
@@ -1,13 +1,12 @@
 #!/bin/bash
 #SBATCH --job-name=nccl-allreduce-slurm-containers
-#SBATCH --nodes=2
+#SBATCH --nodes=32
 #SBATCH --gpus-per-node=8
 #SBATCH --ntasks-per-node=8
 #SBATCH --exclusive
 export PMI_DEBUG=1
 
-
-cd /nfs/scratch
+cd /nfs/cluster
 mkdir $SLURM_JOB_ID
 cd $SLURM_JOB_ID
 
@@ -44,51 +43,49 @@ if [[ "$MPIVARS_PATH" == "" ]]; then
     echo "Could not find MPIPATH"; exit; fi
 
 source $MPIVARS_PATH
-LOCAL_MPI=${MPIVARS_PATH%%/bin*}
-
-#mpirun -d --mca pml ucx -x SLURM_JOB_NODELIST=$host_list --bind-to numa  -x NCCL_DEBUG=WARN  -x NCCL_IB_SL=0 -x NCCL_IB_TC=41 -x NCCL_IB_QPS_PER_CONNECTION=4 -x NCCL_IB_GID_INDEX=3 -x NCCL_ALGO=Ring -x NCCL_TOPO_FILE=/home/opc/topo-flattened-b4.xml -x NCCL_IB_HCA="mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_6,mlx5_7,mlx5_8,mlx5_9,mlx5_10,mlx5_11,mlx5_12,mlx5_13,mlx5_16,mlx5_17,mlx5_18,mlx5_19"   -x UCX_NET_DEVICES=mlx5_0:1 -x HCOLL_ENABLE_MCAST_ALL=0 -x coll_hcoll_enable=0 -x UCX_TLS=ud,self,sm  -np $((SLURM_NNODES*SLURM_NTASKS_PER_NODE)) --rankfile rankfile_system_name  /home/opc/nccl-tests/build/all_reduce_perf -b1G -e10G -i$((1024*1024*1024*9))  -n 100
-# no need to pass:  -x SLURM_JOB_NODELIST=$host_list
+LOCAL_MPI=${MPIVARS_PATH%/*}
 
 shape=`curl -sH "Authorization: Bearer Oracle" -L http://169.254.169.254/opc/v2/instance/ | jq .shape`
-if [ $shape == \"BM.GPU.B4.8\" ] || [ $shape == \"BM.GPU.A100-v2.8\" ]
+if [ $shape == \"BM.GPU.H100.8\" ]
 then
-  var_UCX_NET_DEVICES=mlx5_0:1
-  var_NCCL_IB_HCA="=mlx5_5,mlx5_6,mlx5_7,mlx5_8,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_14,mlx5_15,mlx5_16,mlx5_17,mlx5_9,mlx5_10,mlx5_11,mlx5_12"
-elif [ $shape == \"BM.GPU4.8\" ]
-then
-  var_UCX_NET_DEVICES=mlx5_4:1
-  var_NCCL_IB_HCA="=mlx5_0,mlx5_2,mlx5_6,mlx5_8,mlx5_10,mlx5_12,mlx5_14,mlx5_16,mlx5_1,mlx5_3,mlx5_7,mlx5_9,mlx5_11,mlx5_13,mlx5_15,mlx5_17"
+  var_UCX_NET_DEVICES=eth0
+else
+  echo "Use the appropriate nccl test run script for non H100 nodes"
 fi
 
-export RX_QUEUE_LEN=8192 \
-       IB_RX_QUEUE_LEN=8192 \
-       UCX_TLS=ud,self,sm \
-       HCOLL_ENABLE_MCAST_ALL=0 \
-       coll_hcoll_enable=0 \
-       UCX_NET_DEVICES=${var_UCX_NET_DEVICES} \
-       NCCL_DEBUG=WARN \
-       NCCL_IB_TIMEOUT=16 \
-       NCCL_IB_SL=0 \
+export NCCL_DEBUG=WARN \
+       NCCL_CUMEM_ENABLE=0 \
+       NCCL_IB_SPLIT_DATA_ON_QPS=0 \
+       NCCL_IB_QPS_PER_CONNECTION=4 \
+       NCCL_IB_GID_INDEX=3 \
        NCCL_IB_TC=41 \
+       NCCL_IB_SL=0 \
+       NCCL_IB_TIMEOUT=22 \
+       NCCL_NET_PLUGIN=none \
+       NCCL_SOCKET_IFNAME=eth0 \
        NCCL_IGNORE_CPU_AFFINITY=1 \
-       NCCL_IB_GID_INDEX=3 \
-       NCCL_ALGO=Ring \
-       NCCL_IB_HCA="${var_NCCL_IB_HCA}" \
-       OMPI_MCA_coll=^hcoll \
-       NCCL_IB_QPS_PER_CONNECTION=4
+       NCCL_IB_HCA="=mlx5_0,mlx5_1,mlx5_3,mlx5_4,mlx5_5,mlx5_6,mlx5_7,mlx5_8,mlx5_9,mlx5_10,mlx5_12,mlx5_13,mlx5_14,mlx5_15,mlx5_16,mlx5_17" \
+       HCOLL_ENABLE_MCAST_ALL=0 \
+       coll_hcoll_enable=0 \
+       UCX_TLS=tcp \
+       UCX_NET_DEVICES=eth0 \
+       RX_QUEUE_LEN=8192 \
+       IB_RX_QUEUE_LEN=8192 \
+       OMPI_MCA_coll=^hcoll
 
 env | grep "SLURMD_NODENAME="
 USER=`whoami`
 
-CONTAINER_IMAGE="/nfs/scratch/nvcr.io+nvidia+pytorch+22.12-py3.sqsh"
-CONTAINER_MOUNTS="/home/$USER/nccl-tests:/nccl,$LOCAL_MPI:$LOCAL_MPI"
+CONTAINER_IMAGE="nvcr.io#nvidia/pytorch:24.12-py3"
+CONTAINER_MOUNTS="/opt/oci-hpc/nccl-test:/nccl,$LOCAL_MPI:$LOCAL_MPI,/nfs/cluster:/nfs/cluster"
+echo $LOCAL_MPI
+echo $MPIVARS_PATH
 
 srun --mpi=pmi2 --gpus-per-node=$SBATCH_GPUS_PER_NODE \
      --ntasks-per-node=$SLURM_NTASKS_PER_NODE \
-     --distribution=arbitrary \
      --container-image=$CONTAINER_IMAGE \
      --container-mounts=$CONTAINER_MOUNTS \
      bash -c "
      source $MPIVARS_PATH &&
-     /nccl/build/all_reduce_perf -b 1G -e 10G -i$((1024*1024*1024*9)) -n 100
-     "
\ No newline at end of file
+     /nccl/build/all_reduce_perf -b 8 -e 16G -f 2 -g 1
+     "