mpirun --map-by ppr:1:numa:PE=80 --bind-to core --report-bindings \
  -x LD_PRELOAD=/home/aocc/aocl/5.2.0/aocc/lib_LP64/libblis-mt.so.5 \
  -x BLIS_NUM_THREADS=80 \
  -x OMP_NUM_THREADS=80 \
  -x MKL_NUM_THREADS=80 \
  -x OMP_PROC_BIND=close \
  -x OMP_PLACES=cores \
  -np 4 \
  -host node-0:2,node-1:2,node-2:2,node-3:2 \
  .venv/bin/python -u tools/tn_contest_runner.py contract \
  --mpi \
  --case main1 \
  --nqubits 34 \
  --nlayers 20 \
  --observables long_z_string \
  --tree-dir trees/contest_tn \
  --torch-threads 80 \
  --dtype complex64


SEARCH_TIME=300  NQUBITS=40 TN_DEBUG_TRIALS=1 SCHEDULER_HOST=10.20.1.102 DASK_ADDRESS=tcp://10.20.1.102:8786 WORKER_HOSTS="10.20.1.102 10.20.1.103" CASE=main1 OBSERVABLES=long_z_string TORCH_THREADS=80 MPI_PE=80 MPI_MAP_BY=ppr:1:numa:PE=80 MPI_BIND_TO=core OMP_NUM_THREADS=80 MKL_NUM_THREADS=80 BLIS_NUM_THREADS=80 MPI_HOSTS="node-2:2,node-3:2" MPI_RANKS=4 NWORKERS=128  TN_TARGET_SIZE=17179869184 tools/run_tn_dask_mpi_all.sh


NQUBITS=40 \
TN_DEBUG_TRIALS=1 \
SCHEDULER_HOST=10.20.1.102 \
DASK_ADDRESS=tcp://10.20.1.102:8786 \
WORKER_HOSTS="10.20.1.102 10.20.1.103" \
CASE=main1 \
OBSERVABLES=long_z_string \
TORCH_THREADS=80 \
MPI_PE=80 \
MPI_MAP_BY=ppr:1:numa:PE=80 \
MPI_BIND_TO=core \
OMP_NUM_THREADS=80 \
MKL_NUM_THREADS=80 \
BLIS_NUM_THREADS=80 \
MPI_HOSTS="node-2:2,node-3:2" \
MPI_RANKS=4 \
NWORKERS=96 \
TN_TARGET_SIZE=17179869184 \
tools/run_tn_dask_mpi_all.sh