def test_win_mutex_full(self):
size = bf.size()
rank = bf.rank()
if size <= 2:
fname = inspect.currentframe().f_code.co_name
warnings.warn(
"Skip {} because it only supports test over at least 3 nodes".
format(fname))
return
bf.set_topology(topology_util.FullyConnectedGraph(size))
dtypes = [torch.FloatTensor, torch.DoubleTensor]
if TEST_ON_GPU:
dtypes += [torch.cuda.FloatTensor, torch.cuda.DoubleTensor]
for dtype in dtypes:
tensor = torch.FloatTensor([DIM_SIZE]).fill_(1).mul_(rank)
tensor = self.cast_and_place(tensor, dtype)
window_name = "win_mutex_full_{}".format(dtype)
bf.win_create(tensor, window_name)
if rank == 0:
with bf.win_mutex(window_name, for_self=True):
bf.barrier()
time.sleep(1.01)
else:
bf.barrier()
t_start = time.time()
with bf.win_mutex(window_name):
time.sleep(0.001)
t_end = time.time()
assert (t_end - t_start) > 1, \
"The mutex acquire time should be longer than 1 second"
assert (t_end - t_start) < 2, \
"The mutex acquire time should be shorter than 2 second"
if args.virtual_topology == "expo2":
pass
elif args.virtual_topology == "expo3":
bf.set_topology(topology_util.ExponentialGraph(bf.size(), base=3))
elif args.virtual_topology == "expo4":
bf.set_topology(topology_util.ExponentialGraph(bf.size(), base=4))
elif args.virtual_topology == "ring":
bf.set_topology(topology_util.RingGraph(bf.size(), connect_style=1))
elif args.virtual_topology == "mesh":
bf.set_topology(topology_util.RingGraph(bf.size(), connect_style=0),
is_weighted=True)
elif args.virtual_topology == "star":
bf.set_topology(topology_util.StarGraph(bf.size()), is_weighted=True)
elif args.virtual_topology == "full":
bf.set_topology(topology_util.FullyConnectedGraph(bf.size()))
else:
raise ValueError("Unknown args.virtual_topology, supporting options are " +
"[expo2(Default), ring, mesh, star].")
x_bar = bf.allreduce(x, average=True)
mse = [torch.norm(x - x_bar, p=2) / torch.norm(x_bar, p=2)]
if not args.asynchronous_mode:
self_weight = None
neighbor_weights = None
send_neighbors = None
if args.enable_dynamic_topology:
if args.virtual_topology == "InnerOuterExpo2":
dynamic_neighbor_allreduce_gen = topology_util.GetInnerOuterExpo2DynamicSendRecvRanks(