def _replicate_edgelist(self):
client = mg_utils.get_client()
comms = Comms.get_comms()
# FIXME: There might be a better way to control it
if client is None:
return
work_futures = replication.replicate_cudf_dataframe(
self.edgelist.edgelist_df, client=client, comms=comms)
self.batch_edgelists = work_futures
def test_replicate_cudf_dataframe_no_weights(input_data_path, mg_device_count):
skip_if_not_enough_devices(mg_device_count)
df = cudf.read_csv(input_data_path,
delimiter=' ',
names=['src', 'dst'],
dtype=['int32', 'int32'])
with MGContext(mg_device_count):
worker_to_futures = replication.replicate_cudf_dataframe(df)
for worker in worker_to_futures:
replicated_df = worker_to_futures[worker].result()
assert df.equals(replicated_df), "There is a mismatch in one " \
"of the replications"
def test_replicate_cudf_dataframe_no_weights(input_data_path, dask_client):
gc.collect()
df = cudf.read_csv(
input_data_path,
delimiter=" ",
names=["src", "dst"],
dtype=["int32", "int32"],
)
worker_to_futures = replication.replicate_cudf_dataframe(df)
for worker in worker_to_futures:
replicated_df = worker_to_futures[worker].result()
assert_frame_equal(df, replicated_df)
def test_replicate_cudf_dataframe_no_weights(input_data_path, mg_device_count):
gc.collect()
skip_if_not_enough_devices(mg_device_count)
df = cudf.read_csv(
input_data_path,
delimiter=" ",
names=["src", "dst"],
dtype=["int32", "int32"],
)
with MGContext(number_of_devices=mg_device_count, p2p=True):
worker_to_futures = replication.replicate_cudf_dataframe(df)
for worker in worker_to_futures:
replicated_df = worker_to_futures[worker].result()
assert df.equals(replicated_df), ("There is a mismatch in one "
"of the replications")