in ppo_ewma/torch_util.py [0:0]
def _get_local_rank_size(comm):
"""
Returns the rank of each process on its machine
The processes on a given machine will be assigned ranks
0, 1, 2, ..., N-1,
where N is the number of processes on this machine.
Useful if you want to assign one gpu per machine
"""
this_node = platform.node()
ranks_nodes = comm.allgather((comm.Get_rank(), this_node))
node2rankssofar = collections.defaultdict(int)
local_rank = None
for (rank, node) in ranks_nodes:
if rank == comm.Get_rank():
local_rank = node2rankssofar[node]
node2rankssofar[node] += 1
assert local_rank is not None
return local_rank, node2rankssofar[this_node]