def testInitialWithInputs(self):
import numpy as np
from mars.tensor.expressions.random import TensorRandint
from mars.tensor.expressions.arithmetic import TensorTreeAdd
n1 = TensorRandint(dtype=np.float32()).new_chunk(None, (10, 10))
n2 = TensorRandint(dtype=np.float32()).new_chunk(None, (10, 10))
n3 = TensorTreeAdd(dtype=np.float32()).new_chunk(None, (10, 10))
n3.op._inputs = [n1, n2]
n4 = TensorTreeAdd(dtype=np.float32()).new_chunk(None, (10, 10))
n4.op._inputs = [n3]
graph = DAG()
graph.add_node(n1)
graph.add_node(n3)
graph.add_node(n4)
graph.add_edge(n1, n3)
graph.add_edge(n3, n4)
analyzer = GraphAnalyzer(graph, {})
ext_chunks = analyzer.collect_external_input_chunks(initial=False)
self.assertListEqual(ext_chunks[n3.op.key], [n2.key])
self.assertEqual(
len(analyzer.collect_external_input_chunks(initial=True)), 0)
def testFullInitialAssign(self):
import numpy as np
from mars.tensor.expressions.random import TensorRandint
from mars.tensor.expressions.arithmetic import TensorTreeAdd
graph = DAG()
r"""
Proper initial allocation should divide the graph like
U U U U | U U U U | U U U U
\ / \ / | \ / \ / | \ / \ /
U U | U U | U U
"""
inputs = [
tuple(
TensorRandint(dtype=np.float32()).new_chunk(None, (10, 10))
for _ in range(2)) for _ in range(6)
]
results = [
TensorTreeAdd(dtype=np.float32()).new_chunk(None, (10, 10))
for _ in range(6)
]
for inp, r in zip(inputs, results):
r.op._inputs = list(inp)
graph.add_node(r)
for n in inp:
graph.add_node(n)
graph.add_edge(n, r)
analyzer = GraphAnalyzer(graph, dict(w1=24, w2=24, w3=24))
assignments = analyzer.calc_initial_assignments()
for inp in inputs:
self.assertEqual(1, len(set(assignments[n.op.key] for n in inp)))
def testSameKeyAssign(self):
import numpy as np
from mars.tensor.expressions.random import TensorRandint
from mars.tensor.expressions.arithmetic import TensorTreeAdd
graph = DAG()
r"""
Proper initial allocation should divide the graph like
U U | U U | U U
| | | | | | | | | | | | | |
U U | U U | U U
"""
inputs = [
tuple(
TensorRandint(_key=str(i), dtype=np.float32()).new_chunk(
None, (10, 10)) for _ in range(2)) for i in range(6)
]
results = [
TensorTreeAdd(dtype=np.float32()).new_chunk(None, (10, 10))
for _ in range(6)
]
for inp, r in zip(inputs, results):
r.op._inputs = list(inp)
graph.add_node(r)
for n in inp:
graph.add_node(n)
graph.add_edge(n, r)
analyzer = GraphAnalyzer(graph, dict(w1=24, w2=24, w3=24))
assignments = analyzer.calc_operand_assignments(
analyzer.get_initial_operand_keys())
self.assertEqual(len(assignments), 6)
def testMockExecuteSize(self):
import mars.tensor as mt
from mars.graph import DAG
from mars.tensor.expressions.fetch import TensorFetch
from mars.tensor.expressions.arithmetic import TensorTreeAdd
graph_add = DAG()
input_chunks = []
for _ in range(2):
fetch_op = TensorFetch(dtype=np.dtype('int64'))
inp_chunk = fetch_op.new_chunk(None, shape=(100, 100)).data
input_chunks.append(inp_chunk)
add_op = TensorTreeAdd(dtype=np.dtype('int64'))
add_chunk = add_op.new_chunk(input_chunks,
shape=(100, 100),
dtype=np.dtype('int64')).data
graph_add.add_node(add_chunk)
for inp_chunk in input_chunks:
graph_add.add_node(inp_chunk)
graph_add.add_edge(inp_chunk, add_chunk)
executor = Executor()
res = executor.execute_graph(graph_add, [add_chunk.key],
compose=False,
mock=True)[0]
self.assertEqual(res, (80000, 80000))
self.assertEqual(executor.mock_max_memory, 80000)
for _ in range(3):
new_add_op = TensorTreeAdd(dtype=np.dtype('int64'))
new_add_chunk = new_add_op.new_chunk([add_chunk],
shape=(100, 100),
dtype=np.dtype('int64')).data
graph_add.add_node(new_add_chunk)
graph_add.add_edge(add_chunk, new_add_chunk)
add_chunk = new_add_chunk
executor = Executor()
res = executor.execute_graph(graph_add, [add_chunk.key],
compose=False,
mock=True)[0]
self.assertEqual(res, (80000, 80000))
self.assertEqual(executor.mock_max_memory, 160000)
a = mt.random.rand(10, 10, chunk_size=10)
b = a[:, mt.newaxis, :] - a
r = mt.triu(mt.sqrt(b**2).sum(axis=2))
executor = Executor()
res = executor.execute_tensor(r, concat=False, mock=True)
# larger than maximal memory size in calc procedure
self.assertGreaterEqual(res[0][0], 800)
self.assertGreaterEqual(executor.mock_max_memory, 8000)
def testCompose(self):
"""
test compose in build graph and optimize
"""
"""
graph(@: node, #: composed_node):
@ --> @ --> @ ========> #
"""
chunks = [
TensorTreeAdd(_key=str(n)).new_chunk(None, None) for n in range(3)
]
graph = DirectedGraph()
lmap(graph.add_node, chunks[:3])
graph.add_edge(chunks[0], chunks[1])
graph.add_edge(chunks[1], chunks[2])
composed_nodes = graph.compose()
self.assertTrue(composed_nodes[0].composed == chunks[:3])
# make the middle one as result chunk, thus the graph cannot be composed
composed_nodes = graph.compose(keys=[chunks[1].key])
self.assertEqual(len(composed_nodes), 0)
"""
graph(@: node, #: composed_node):
@ @ @ @
\ / \ /
@ --> @ ========> #
/ \ / \
@ @ @ @
"""
chunks = [
TensorTreeAdd(_key=str(n)).new_chunk(None, None) for n in range(6)
]
graph = DirectedGraph()
lmap(graph.add_node, chunks[:6])
chunks[2].op._inputs = [chunks[0], chunks[1]]
chunks[3].op._inputs = [chunks[2]]
chunks[4].op._inputs = [chunks[3]]
chunks[5].op._inputs = [chunks[3]]
graph.add_edge(chunks[0], chunks[2])
graph.add_edge(chunks[1], chunks[2])
graph.add_edge(chunks[2], chunks[3])
graph.add_edge(chunks[3], chunks[4])
graph.add_edge(chunks[3], chunks[5])
composed_nodes = graph.compose()
self.assertTrue(composed_nodes[0].composed == chunks[2:4])
# to make sure the predecessors and successors of compose are right
# 0 and 1's successors must be composed
self.assertIn(composed_nodes[0], graph.successors(chunks[0]))
self.assertIn(composed_nodes[0], graph.successors(chunks[1]))
# check composed's inputs
self.assertIn(chunks[0].data, composed_nodes[0].inputs)
self.assertIn(chunks[1].data, composed_nodes[0].inputs)
# check composed's predecessors
self.assertIn(chunks[0], graph.predecessors(composed_nodes[0]))
self.assertIn(chunks[1], graph.predecessors(composed_nodes[0]))
# check 4 and 5's inputs
self.assertIn(composed_nodes[0].data,
graph.successors(composed_nodes[0])[0].inputs)
self.assertIn(composed_nodes[0].data,
graph.successors(composed_nodes[0])[0].inputs)
# check 4 and 5's predecessors
self.assertIn(composed_nodes[0], graph.predecessors(chunks[4]))
self.assertIn(composed_nodes[0], graph.predecessors(chunks[5]))
# test optimizer compose
"""
graph(@: node, S: Slice Chunk, #: composed_node):
@ @ @ @
\ / \ /
@ --> @ --> S ========> # --> S
/ \ / \
@ @ @ @
compose stopped at S, because numexpr don't support Slice op
"""
chunks = [
TensorTreeAdd(_key=str(n)).new_chunk(None, None) for n in range(6)
]
chunk_slice = TensorSlice().new_chunk([None], None)
graph = DirectedGraph()
lmap(graph.add_node, chunks[:6])
graph.add_node(chunk_slice)
graph.add_edge(chunks[0], chunks[2])
graph.add_edge(chunks[1], chunks[2])
graph.add_edge(chunks[2], chunks[3])
graph.add_edge(chunks[3], chunk_slice)
graph.add_edge(chunk_slice, chunks[4])
graph.add_edge(chunk_slice, chunks[5])
optimizer = NeOptimizer(graph)
composed_nodes = optimizer.compose()
self.assertTrue(composed_nodes[0].composed == chunks[2:4])
"""
graph(@: node, S: Slice Chunk, #: composed_node):
@ --> @ --> S --> @ ========> # --> S --> @
compose stopped at S, because numexpr don't support Slice op
"""
chunks = [
TensorTreeAdd(_key=str(n)).new_chunk(None, None) for n in range(4)
]
graph = DirectedGraph()
lmap(graph.add_node, chunks[:3])
graph.add_node(chunk_slice)
graph.add_edge(chunks[0], chunks[1])
graph.add_edge(chunks[1], chunk_slice)
graph.add_edge(chunk_slice, chunks[2])
optimizer = NeOptimizer(graph)
composed_nodes = optimizer.compose()
self.assertTrue(composed_nodes[0].composed == chunks[:2])
self.assertTrue(len(composed_nodes) == 1)
"""
graph(@: node, S: Slice Chunk, #: composed_node):
@ --> @ --> S --> @ --> @ ========> # --> S --> #
compose stopped at S, because numexpr don't support Slice op
"""
chunks = [
TensorTreeAdd(_key=str(n)).new_chunk(None, None) for n in range(4)
]
graph = DirectedGraph()
lmap(graph.add_node, chunks[:4])
graph.add_node(chunk_slice)
graph.add_edge(chunks[0], chunks[1])
graph.add_edge(chunks[1], chunk_slice)
graph.add_edge(chunk_slice, chunks[2])
graph.add_edge(chunks[2], chunks[3])
optimizer = NeOptimizer(graph)
composed_nodes = optimizer.compose()
self.assertTrue(composed_nodes[0].composed == chunks[:2])
self.assertTrue(composed_nodes[1].composed == chunks[2:4])
def testAssignOnWorkerLost(self):
import numpy as np
from mars.scheduler import OperandState
from mars.tensor.expressions.random import TensorRandint
from mars.tensor.expressions.arithmetic import TensorTreeAdd
graph = DAG()
r"""
Proper initial allocation should divide the graph like
FL FL F F R R | FL FL F F R R
| x | | x | | x | | | x | | x | | x |
R R R R U U | R R R R U U
U: UNSCHEDULED F: FINISHED R: READY L: LOST
"""
op_states = dict()
inputs = [
tuple(
TensorRandint(dtype=np.float32()).new_chunk(None, (10, 10))
for _ in range(2)) for _ in range(6)
]
results = [
tuple(
TensorTreeAdd(_key='%d_%d' % (i, j),
dtype=np.float32()).new_chunk(None, (10, 10))
for j in range(2)) for i in range(6)
]
for inp, outp in zip(inputs, results):
for o in outp:
o.op._inputs = list(inp)
op_states[o.op.key] = OperandState.UNSCHEDULED
graph.add_node(o)
for n in inp:
op_states[n.op.key] = OperandState.UNSCHEDULED
graph.add_node(n)
for o in outp:
graph.add_edge(n, o)
fixed_assigns = dict()
for idx in range(4):
for i in range(2):
fixed_assigns[inputs[idx][i].op.key] = 'w%d' % (idx % 2 + 1)
op_states[inputs[idx][i].op.key] = OperandState.FINISHED
fixed_assigns[results[idx][i].op.key] = 'w%d' % (idx % 2 + 1)
op_states[results[idx][i].op.key] = OperandState.READY
for inp in inputs:
for n in inp:
if n.op.key in fixed_assigns:
continue
op_states[n.op.key] = OperandState.READY
lost_chunks = [c.key for inp in (inputs[0], inputs[2]) for c in inp]
worker_metrics = dict(w2=24, w3=24)
analyzer = GraphAnalyzer(graph, worker_metrics, fixed_assigns,
op_states, lost_chunks)
changed_states = analyzer.analyze_state_changes()
self.assertEqual(len(changed_states), 8)
self.assertTrue(
all(changed_states[c.op.key] == OperandState.READY
for inp in (inputs[0], inputs[2]) for c in inp))
self.assertTrue(
all(changed_states[c.op.key] == OperandState.UNSCHEDULED
for res in (results[0], results[2]) for c in res))
assignments = analyzer.calc_initial_assignments()
for inp in inputs:
if any(n.op.key in fixed_assigns for n in inp):
continue
self.assertEqual(1, len(set(assignments[n.op.key] for n in inp)))
worker_assigns = dict((k, 0) for k in worker_metrics)
for w in assignments.values():
worker_assigns[w] += 1
self.assertEqual(2, worker_assigns['w2'])
self.assertEqual(6, worker_assigns['w3'])
def testAssignOnWorkerAdd(self):
import numpy as np
from mars.scheduler import OperandState
from mars.tensor.expressions.random import TensorRandint
from mars.tensor.expressions.arithmetic import TensorTreeAdd
graph = DAG()
r"""
Proper initial allocation should divide the graph like
F F R R | F F R R | R R R R
| x | | x | | | x | | x | | | x | | x |
R R U U | R R U U | U U U U
U: UNSCHEDULED F: FINISHED R: READY
"""
inputs = [
tuple(
TensorRandint(dtype=np.float32()).new_chunk(None, (10, 10))
for _ in range(2)) for _ in range(6)
]
results = [
tuple(
TensorTreeAdd(_key='%d_%d' % (i, j),
dtype=np.float32()).new_chunk(None, (10, 10))
for j in range(2)) for i in range(6)
]
for inp, outp in zip(inputs, results):
for o in outp:
o.op._inputs = list(inp)
graph.add_node(o)
for n in inp:
graph.add_node(n)
for o in outp:
graph.add_edge(n, o)
# mark initial assigns
fixed_assigns = dict()
op_states = dict()
for idx in range(2):
for i in range(2):
fixed_assigns[inputs[idx][i].op.key] = 'w%d' % (idx + 1)
op_states[results[idx][i].op.key] = OperandState.READY
fixed_assigns[results[idx][i].op.key] = 'w%d' % (idx + 1)
for inp in inputs:
for n in inp:
if n.op.key in fixed_assigns:
continue
op_states[n.op.key] = OperandState.READY
worker_metrics = dict(w1=24, w2=24, w3=24)
analyzer = GraphAnalyzer(graph, worker_metrics, fixed_assigns,
op_states)
assignments = analyzer.calc_initial_assignments()
for inp in inputs:
if any(n.op.key in fixed_assigns for n in inp):
continue
self.assertEqual(1, len(set(assignments[n.op.key] for n in inp)))
worker_assigns = dict((k, 0) for k in worker_metrics)
for w in assignments.values():
worker_assigns[w] += 1
self.assertEqual(2, worker_assigns['w1'])
self.assertEqual(2, worker_assigns['w2'])
self.assertEqual(4, worker_assigns['w3'])
def testAssignWithPreviousData(self):
import numpy as np
from mars.scheduler.chunkmeta import WorkerMeta
from mars.tensor.expressions.random import TensorRandint
from mars.tensor.expressions.arithmetic import TensorTreeAdd
graph = DAG()
r"""
Proper initial allocation should divide the graph like
U U | U U | U U
\ / | \ / | \ /
U | U | U
"""
inputs = [
tuple(
TensorRandint(_key=str(i * 2 + j),
dtype=np.float32()).new_chunk(None, (10, 10))
for j in range(2)) for i in range(3)
]
results = [
TensorTreeAdd(dtype=np.float32()).new_chunk(None, (10, 10))
for _ in range(3)
]
for inp, r in zip(inputs, results):
r.op._inputs = list(inp)
graph.add_node(r)
for n in inp:
graph.add_node(n)
graph.add_edge(n, r)
# assign with partial mismatch
data_dist = {
'0':
dict(c00=WorkerMeta(chunk_size=5, workers=('w1', )),
c01=WorkerMeta(chunk_size=5, workers=('w2', ))),
'1':
dict(c10=WorkerMeta(chunk_size=10, workers=('w1', ))),
'2':
dict(c20=WorkerMeta(chunk_size=10, workers=('w3', ))),
'3':
dict(c30=WorkerMeta(chunk_size=10, workers=('w3', ))),
'4':
dict(c40=WorkerMeta(chunk_size=7, workers=('w3', ))),
}
analyzer = GraphAnalyzer(graph, dict(w1=24, w2=24, w3=24))
assignments = analyzer.calc_initial_assignments(
input_chunk_metas=data_dist)
self.assertEqual(len(assignments), 6)
# explanation of the result:
# for '1', all data are in w1, hence assigned to w1
# '0' assigned to w1 according to connectivity
# '2' and '3' assigned to w3 according to connectivity
# '4' assigned to w2 because it has fewer data, and the slots of w3 is used up
self.assertEqual(assignments['0'], 'w1')
self.assertEqual(assignments['1'], 'w1')
self.assertEqual(assignments['2'], 'w3')
self.assertEqual(assignments['3'], 'w3')
self.assertEqual(assignments['4'], 'w2')
self.assertEqual(assignments['5'], 'w2')
# assign with full mismatch
data_dist = {
'0':
dict(c00=WorkerMeta(chunk_size=5, workers=('w1', )),
c01=WorkerMeta(chunk_size=5, workers=(
'w1',
'w2',
))),
'1':
dict(c10=WorkerMeta(chunk_size=10, workers=('w1', ))),
'2':
dict(c20=WorkerMeta(chunk_size=10, workers=('w3', ))),
'3':
dict(c30=WorkerMeta(chunk_size=10, workers=('w3', ))),
'4':
dict(c40=WorkerMeta(chunk_size=7, workers=('w2', ))),
'5':
dict(c50=WorkerMeta(chunk_size=7, workers=('w2', ))),
}
analyzer = GraphAnalyzer(graph, dict(w1=24, w2=24, w3=24))
assignments = analyzer.calc_initial_assignments(
input_chunk_metas=data_dist)
self.assertEqual(len(assignments), 6)
self.assertEqual(assignments['0'], 'w1')
self.assertEqual(assignments['1'], 'w1')
self.assertEqual(assignments['2'], 'w3')
self.assertEqual(assignments['3'], 'w3')
self.assertEqual(assignments['4'], 'w2')
self.assertEqual(assignments['5'], 'w2')
