def test_p3(in_transient, out_transient):
sdfg = reduction_test_3.to_sdfg()
sdfg.apply_strict_transformations()
state = sdfg.nodes()[0]
A = np.random.rand(M.get(), N.get()).astype(np.float64)
B = np.random.rand(M.get(), N.get()).astype(np.float64)
C1 = np.zeros([N.get()], dtype=np.float64)
C2 = np.zeros([N.get()], dtype=np.float64)
C3 = np.zeros([N.get()], dtype=np.float64)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C1, N=N, M=M)
del csdfg
expand_reduce(sdfg,
state,
create_in_transient=in_transient,
create_out_transient=out_transient)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C2, N=N, M=M)
del csdfg
expand_maps(sdfg, state)
fusion(sdfg, state)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C3, N=N, M=M)
del csdfg
assert np.linalg.norm(C1) > 0.01
assert np.allclose(C1, C2)
assert np.allclose(C1, C3)
def test_p1(in_transient, out_transient):
sdfg = reduction_test_1.to_sdfg()
sdfg.apply_strict_transformations()
state = sdfg.nodes()[0]
for node in state.nodes():
if isinstance(node, dace.libraries.standard.nodes.Reduce):
reduce_node = node
assert ReduceExpansion.can_be_applied(state, \
{ReduceExpansion._reduce: state.nodes().index(reduce_node)}, \
0, \
sdfg) == True
A = np.random.rand(M.get(), N.get()).astype(np.float64)
B = np.random.rand(M.get(), N.get()).astype(np.float64)
C1 = np.zeros([N.get()], dtype=np.float64)
C2 = np.zeros([N.get()], dtype=np.float64)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C1, N=N, M=M)
del csdfg
expand_reduce(sdfg,
state,
create_in_transient=in_transient,
create_out_transient=out_transient)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C2, N=N, M=M)
del csdfg
assert np.linalg.norm(C1) > 0.01
assert np.allclose(C1, C2)
def test_quantitatively(sdfg, graph):
A = np.random.rand(N.get()).astype(np.float64)
B = np.random.rand(M.get()).astype(np.float64)
C = np.random.rand(O.get()).astype(np.float64)
out1_base = np.ndarray((N.get(), M.get()), np.float64)
out2_base = np.ndarray((1), np.float64)
out3_base = np.ndarray((N.get(), M.get(), O.get()), np.float64)
out1 = np.ndarray((N.get(), M.get()), np.float64)
out2 = np.ndarray((1), np.float64)
out3 = np.ndarray((N.get(), M.get(), O.get()), np.float64)
csdfg = sdfg.compile()
csdfg(A=A,
B=B,
C=C,
out1=out1_base,
out2=out2_base,
out3=out3_base,
N=N,
M=M,
O=O)
expand_reduce(sdfg, graph)
expand_maps(sdfg, graph)
subgraph = SubgraphView(graph, [node for node in graph.nodes()])
assert SubgraphFusion.match(sdfg, subgraph) == True
fusion(sdfg, graph)
sdfg.validate()
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C, out1=out1, out2=out2, out3=out3, N=N, M=M, O=O)
assert np.allclose(out1, out1_base)
assert np.allclose(out2, out2_base)
assert np.allclose(out3, out3_base)
print('PASS')
def test_p1(in_transient, out_transient):
sdfg = reduction_test_1.to_sdfg()
sdfg.simplify()
state = sdfg.nodes()[0]
for node in state.nodes():
if isinstance(node, dace.libraries.standard.nodes.Reduce):
reduce_node = node
rexp = ReduceExpansion()
rexp.setup_match(sdfg, sdfg.sdfg_id, 0,
{ReduceExpansion.reduce: state.node_id(reduce_node)}, 0)
assert rexp.can_be_applied(state, 0, sdfg) == True
A = np.random.rand(M.get(), N.get()).astype(np.float64)
B = np.random.rand(M.get(), N.get()).astype(np.float64)
C1 = np.zeros([N.get()], dtype=np.float64)
C2 = np.zeros([N.get()], dtype=np.float64)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C1, N=N, M=M)
del csdfg
expand_reduce(sdfg,
state,
create_in_transient=in_transient,
create_out_transient=out_transient)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C2, N=N, M=M)
del csdfg
assert np.linalg.norm(C1) > 0.01
assert np.allclose(C1, C2)
def test_p1():
sdfg = test_program.to_sdfg()
sdfg.apply_strict_transformations()
state = sdfg.nodes()[0]
for node in state.nodes():
if isinstance(node, dace.libraries.standard.nodes.Reduce):
reduce_node = node
assert ReduceExpansion.can_be_applied(state, \
{ReduceExpansion._reduce: state.nodes().index(reduce_node)}, \
0, \
sdfg) == True
A = np.random.rand(M.get(), N.get()).astype(np.float64)
B = np.random.rand(M.get(), N.get()).astype(np.float64)
C1 = np.zeros([N.get()], dtype=np.float64)
C2 = np.zeros([N.get()], dtype=np.float64)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C1, N=N, M=M)
expand_reduce(sdfg, state)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C2, N=N, M=M)
assert np.allclose(C1, C2)
print(np.linalg.norm(C1))
print(np.linalg.norm(C2))
print("PASS")
def test_p2():
sdfg = test_program2.to_sdfg()
sdfg.apply_strict_transformations()
state = sdfg.nodes()[0]
A = np.random.rand(M.get(), N.get()).astype(np.float64)
B = np.random.rand(M.get(), N.get()).astype(np.float64)
C1 = np.zeros([N.get()], dtype=np.float64)
C2 = np.zeros([N.get()], dtype=np.float64)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C1, N=N, M=M)
expand_reduce(sdfg, state)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C2, N=N, M=M)
assert np.allclose(C1, C2)
print(np.linalg.norm(C1))
print(np.linalg.norm(C2))
print("PASS")
def test_2fuse():
sdfg = softmax.to_sdfg()
sdfg._name = 'softmax_2part'
sdfg.apply_strict_transformations()
X_in = np.random.rand(H.get(), B.get(), SN.get(),
SM.get()).astype(np.float32)
csdfg = sdfg.compile()
res1 = csdfg(X_in=X_in, H=H, B=B, SN=SN, SM=SM)
subgraph = get_partition(sdfg, sdfg.nodes()[0])
expand_reduce(sdfg, sdfg.nodes()[0], subgraph)
expand_maps(sdfg, sdfg.nodes()[0], subgraph)
fusion(sdfg, sdfg.nodes()[0], subgraph)
csdfg = sdfg.compile()
res2 = csdfg(X_in=X_in, H=H, B=B, SN=SN, SM=SM)
assert np.allclose(res1, res2)
print("PASS")
return
def test_p2(in_transient, out_transient):
sdfg = reduction_test_2.to_sdfg()
sdfg.simplify()
state = sdfg.nodes()[0]
A = np.random.rand(M.get(), N.get()).astype(np.float64)
B = np.random.rand(M.get(), N.get()).astype(np.float64)
C1 = np.zeros([N.get()], dtype=np.float64)
C2 = np.zeros([N.get()], dtype=np.float64)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C1, N=N, M=M)
del csdfg
expand_reduce(sdfg,
state,
create_in_transient=in_transient,
create_out_transient=out_transient)
csdfg = sdfg.compile()
csdfg(A=A, B=B, C=C2, N=N, M=M)
assert np.linalg.norm(C1) > 0.01
assert np.allclose(C1, C2)
def test_1fuse():
sdfg = softmax.to_sdfg()
sdfg._name = 'softmax_fused'
sdfg.apply_strict_transformations()
X_in = np.random.rand(H.get(), B.get(), SN.get(),
SM.get()).astype(np.float32)
csdfg = sdfg.compile()
res1 = csdfg(X_in=X_in, H=H, B=B, SN=SN, SM=SM)
expand_reduce(sdfg, sdfg.nodes()[0])
expand_maps(sdfg, sdfg.nodes()[0])
fusion(sdfg, sdfg.nodes()[0])
#sdfg.specialize({'SM':SM})
csdfg = sdfg.compile()
res2 = csdfg(X_in=X_in, H=H, B=B, SN=SN, SM=SM)
print(np.linalg.norm(res1))
print(np.linalg.norm(res2))
assert np.allclose(res1, res2)
print("PASS")
return
def test_1fuse():
sdfg = softmax.to_sdfg()
sdfg.name = 'softmax_fused'
sdfg.simplify()
X_in = np.random.rand(H.get(), B.get(), SN.get(), SM.get()).astype(np.float32)
csdfg = sdfg.compile()
res1 = csdfg(X_in=X_in, H=H, B=B, SN=SN, SM=SM)
del csdfg
expand_reduce(sdfg, sdfg.nodes()[0])
expand_maps(sdfg, sdfg.nodes()[0])
fusion(sdfg, sdfg.nodes()[0])
csdfg = sdfg.compile()
res2 = csdfg(X_in=X_in, H=H, B=B, SN=SN, SM=SM)
del csdfg
print(np.linalg.norm(res1))
print(np.linalg.norm(res2))
assert np.allclose(res1, res2)
print("PASS")
return
def test_qualitatively(sdfg, graph):
expand_reduce(sdfg, graph)
expand_maps(sdfg, graph)
fusion(sdfg, graph)
sdfg.validate()
print("PASS")
