def test_split_even():
prepare_dist()
g = create_random_graph(10000)
num_parts = 4
num_hops = 2
partition_graph(g, 'dist_graph_test', num_parts, '/tmp/dist_graph', num_hops=num_hops, part_method='metis')
node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
selected_nodes = np.nonzero(node_mask)[0]
selected_edges = np.nonzero(edge_mask)[0]
all_nodes1 = []
all_nodes2 = []
all_edges1 = []
all_edges2 = []
for i in range(num_parts):
dgl.distributed.set_num_client(num_parts)
part_g, node_feats, edge_feats, gpb = load_partition('/tmp/dist_graph/dist_graph_test.json', i)
local_nids = F.nonzero_1d(part_g.ndata['inner_node'])
local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
nodes = node_split(node_mask, gpb, i, force_even=True)
all_nodes1.append(nodes)
subset = np.intersect1d(F.asnumpy(nodes), F.asnumpy(local_nids))
print('part {} get {} nodes and {} are in the partition'.format(i, len(nodes), len(subset)))
dgl.distributed.set_num_client(num_parts * 2)
nodes1 = node_split(node_mask, gpb, i * 2, force_even=True)
nodes2 = node_split(node_mask, gpb, i * 2 + 1, force_even=True)
nodes3 = F.cat([nodes1, nodes2], 0)
all_nodes2.append(nodes3)
subset = np.intersect1d(F.asnumpy(nodes), F.asnumpy(nodes3))
print('intersection has', len(subset))
dgl.distributed.set_num_client(num_parts)
local_eids = F.nonzero_1d(part_g.edata['inner_edge'])
local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
edges = edge_split(edge_mask, gpb, i, force_even=True)
all_edges1.append(edges)
subset = np.intersect1d(F.asnumpy(edges), F.asnumpy(local_eids))
print('part {} get {} edges and {} are in the partition'.format(i, len(edges), len(subset)))
dgl.distributed.set_num_client(num_parts * 2)
edges1 = edge_split(edge_mask, gpb, i * 2, force_even=True)
edges2 = edge_split(edge_mask, gpb, i * 2 + 1, force_even=True)
edges3 = F.cat([edges1, edges2], 0)
all_edges2.append(edges3)
subset = np.intersect1d(F.asnumpy(edges), F.asnumpy(edges3))
print('intersection has', len(subset))
all_nodes1 = F.cat(all_nodes1, 0)
all_edges1 = F.cat(all_edges1, 0)
all_nodes2 = F.cat(all_nodes2, 0)
all_edges2 = F.cat(all_edges2, 0)
all_nodes = np.nonzero(node_mask)[0]
all_edges = np.nonzero(edge_mask)[0]
assert np.all(all_nodes == F.asnumpy(all_nodes1))
assert np.all(all_edges == F.asnumpy(all_edges1))
assert np.all(all_nodes == F.asnumpy(all_nodes2))
assert np.all(all_edges == F.asnumpy(all_edges2))
def test_split():
#prepare_dist()
g = create_random_graph(10000)
num_parts = 4
num_hops = 2
partition_graph(g, 'dist_graph_test', num_parts, '/tmp/dist_graph', num_hops=num_hops, part_method='metis')
node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
selected_nodes = np.nonzero(node_mask)[0]
selected_edges = np.nonzero(edge_mask)[0]
# The code now collects the roles of all client processes and use the information
# to determine how to split the workloads. Here is to simulate the multi-client
# use case.
def set_roles(num_clients):
dgl.distributed.role.CUR_ROLE = 'default'
dgl.distributed.role.GLOBAL_RANK = {i:i for i in range(num_clients)}
dgl.distributed.role.PER_ROLE_RANK['default'] = {i:i for i in range(num_clients)}
for i in range(num_parts):
set_roles(num_parts)
part_g, node_feats, edge_feats, gpb, _, _, _ = load_partition('/tmp/dist_graph/dist_graph_test.json', i)
local_nids = F.nonzero_1d(part_g.ndata['inner_node'])
local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
nodes1 = np.intersect1d(selected_nodes, F.asnumpy(local_nids))
nodes2 = node_split(node_mask, gpb, rank=i, force_even=False)
assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes2)))
local_nids = F.asnumpy(local_nids)
for n in nodes1:
assert n in local_nids
set_roles(num_parts * 2)
nodes3 = node_split(node_mask, gpb, rank=i * 2, force_even=False)
nodes4 = node_split(node_mask, gpb, rank=i * 2 + 1, force_even=False)
nodes5 = F.cat([nodes3, nodes4], 0)
assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes5)))
set_roles(num_parts)
local_eids = F.nonzero_1d(part_g.edata['inner_edge'])
local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
edges1 = np.intersect1d(selected_edges, F.asnumpy(local_eids))
edges2 = edge_split(edge_mask, gpb, rank=i, force_even=False)
assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges2)))
local_eids = F.asnumpy(local_eids)
for e in edges1:
assert e in local_eids
set_roles(num_parts * 2)
edges3 = edge_split(edge_mask, gpb, rank=i * 2, force_even=False)
edges4 = edge_split(edge_mask, gpb, rank=i * 2 + 1, force_even=False)
edges5 = F.cat([edges3, edges4], 0)
assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges5)))
def test_split():
prepare_dist()
g = create_random_graph(10000)
num_parts = 4
num_hops = 2
partition_graph(g,
'dist_graph_test',
num_parts,
'/tmp/dist_graph',
num_hops=num_hops,
part_method='metis')
node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
selected_nodes = np.nonzero(node_mask)[0]
selected_edges = np.nonzero(edge_mask)[0]
for i in range(num_parts):
dgl.distributed.set_num_client(num_parts)
part_g, node_feats, edge_feats, gpb, _ = load_partition(
'/tmp/dist_graph/dist_graph_test.json', i)
local_nids = F.nonzero_1d(part_g.ndata['inner_node'])
local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
nodes1 = np.intersect1d(selected_nodes, F.asnumpy(local_nids))
nodes2 = node_split(node_mask, gpb, i, force_even=False)
assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes2)))
local_nids = F.asnumpy(local_nids)
for n in nodes1:
assert n in local_nids
dgl.distributed.set_num_client(num_parts * 2)
nodes3 = node_split(node_mask, gpb, i * 2, force_even=False)
nodes4 = node_split(node_mask, gpb, i * 2 + 1, force_even=False)
nodes5 = F.cat([nodes3, nodes4], 0)
assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes5)))
dgl.distributed.set_num_client(num_parts)
local_eids = F.nonzero_1d(part_g.edata['inner_edge'])
local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
edges1 = np.intersect1d(selected_edges, F.asnumpy(local_eids))
edges2 = edge_split(edge_mask, gpb, i, force_even=False)
assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges2)))
local_eids = F.asnumpy(local_eids)
for e in edges1:
assert e in local_eids
dgl.distributed.set_num_client(num_parts * 2)
edges3 = edge_split(edge_mask, gpb, i * 2, force_even=False)
edges4 = edge_split(edge_mask, gpb, i * 2 + 1, force_even=False)
edges5 = F.cat([edges3, edges4], 0)
assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges5)))
def run_client_hierarchy(graph_name, part_id, server_count, node_mask, edge_mask, return_dict):
os.environ['DGL_NUM_SERVER'] = str(server_count)
dgl.distributed.initialize("kv_ip_config.txt")
gpb, graph_name, _, _ = load_partition_book('/tmp/dist_graph/{}.json'.format(graph_name),
part_id, None)
g = DistGraph(graph_name, gpb=gpb)
node_mask = F.tensor(node_mask)
edge_mask = F.tensor(edge_mask)
nodes = node_split(node_mask, g.get_partition_book(), node_trainer_ids=g.ndata['trainer_id'])
edges = edge_split(edge_mask, g.get_partition_book(), edge_trainer_ids=g.edata['trainer_id'])
rank = g.rank()
return_dict[rank] = (nodes, edges)
def test_split():
prepare_dist()
g = create_random_graph(10000)
num_parts = 4
num_hops = 2
partition_graph(g,
'test',
num_parts,
'/tmp',
num_hops=num_hops,
part_method='metis')
node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
selected_nodes = np.nonzero(node_mask)[0]
selected_edges = np.nonzero(edge_mask)[0]
for i in range(num_parts):
part_g, node_feats, edge_feats, meta = load_partition(
'/tmp/test.json', i)
num_nodes, num_edges, node_map, edge_map, num_partitions = meta
gpb = GraphPartitionBook(part_id=i,
num_parts=num_partitions,
node_map=node_map,
edge_map=edge_map,
part_graph=part_g)
local_nids = F.nonzero_1d(part_g.ndata['local_node'])
local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
nodes1 = np.intersect1d(selected_nodes, F.asnumpy(local_nids))
nodes2 = node_split(node_mask, gpb, i)
assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes2)))
local_nids = F.asnumpy(local_nids)
for n in nodes1:
assert n in local_nids
local_eids = F.nonzero_1d(part_g.edata['local_edge'])
local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
edges1 = np.intersect1d(selected_edges, F.asnumpy(local_eids))
edges2 = edge_split(edge_mask, gpb, i)
assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges2)))
local_eids = F.asnumpy(local_eids)
for e in edges1:
assert e in local_eids
def test_split_even():
g = create_random_graph(10000)
num_parts = 4
num_hops = 2
partition_graph(g,
'dist_graph_test',
num_parts,
'/tmp/dist_graph',
num_hops=num_hops,
part_method='metis')
node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
selected_nodes = np.nonzero(node_mask)[0]
selected_edges = np.nonzero(edge_mask)[0]
all_nodes1 = []
all_nodes2 = []
all_edges1 = []
all_edges2 = []
# The code now collects the roles of all client processes and use the information
# to determine how to split the workloads. Here is to simulate the multi-client
# use case.
def set_roles(num_clients):
dgl.distributed.role.CUR_ROLE = 'default'
dgl.distributed.role.GLOBAL_RANK = {i: i for i in range(num_clients)}
dgl.distributed.role.PER_ROLE_RANK['default'] = {
i: i
for i in range(num_clients)
}
for i in range(num_parts):
set_roles(num_parts)
part_g, node_feats, edge_feats, gpb, _, _, _ = load_partition(
'/tmp/dist_graph/dist_graph_test.json', i)
local_nids = F.nonzero_1d(part_g.ndata['inner_node'])
local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
nodes = node_split(node_mask, gpb, rank=i, force_even=True)
all_nodes1.append(nodes)
subset = np.intersect1d(F.asnumpy(nodes), F.asnumpy(local_nids))
print('part {} get {} nodes and {} are in the partition'.format(
i, len(nodes), len(subset)))
set_roles(num_parts * 2)
nodes1 = node_split(node_mask, gpb, rank=i * 2, force_even=True)
nodes2 = node_split(node_mask, gpb, rank=i * 2 + 1, force_even=True)
nodes3, _ = F.sort_1d(F.cat([nodes1, nodes2], 0))
all_nodes2.append(nodes3)
subset = np.intersect1d(F.asnumpy(nodes), F.asnumpy(nodes3))
print('intersection has', len(subset))
set_roles(num_parts)
local_eids = F.nonzero_1d(part_g.edata['inner_edge'])
local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
edges = edge_split(edge_mask, gpb, rank=i, force_even=True)
all_edges1.append(edges)
subset = np.intersect1d(F.asnumpy(edges), F.asnumpy(local_eids))
print('part {} get {} edges and {} are in the partition'.format(
i, len(edges), len(subset)))
set_roles(num_parts * 2)
edges1 = edge_split(edge_mask, gpb, rank=i * 2, force_even=True)
edges2 = edge_split(edge_mask, gpb, rank=i * 2 + 1, force_even=True)
edges3, _ = F.sort_1d(F.cat([edges1, edges2], 0))
all_edges2.append(edges3)
subset = np.intersect1d(F.asnumpy(edges), F.asnumpy(edges3))
print('intersection has', len(subset))
all_nodes1 = F.cat(all_nodes1, 0)
all_edges1 = F.cat(all_edges1, 0)
all_nodes2 = F.cat(all_nodes2, 0)
all_edges2 = F.cat(all_edges2, 0)
all_nodes = np.nonzero(node_mask)[0]
all_edges = np.nonzero(edge_mask)[0]
assert np.all(all_nodes == F.asnumpy(all_nodes1))
assert np.all(all_edges == F.asnumpy(all_edges1))
assert np.all(all_nodes == F.asnumpy(all_nodes2))
assert np.all(all_edges == F.asnumpy(all_edges2))
