def perform(self, node, inputs, outputs):
context = inputs[0][0].context
# Input matrix.
A = inputs[0]
l, n = A.shape
if l != n:
raise ValueError('A must be a square matrix')
lda = max(1, n)
# cusolver operates on F ordered matrices, but A is expected
# to be symmetric so it does not matter.
# We copy A if needed
if self.inplace:
L = A
else:
L = pygpu.array(A, copy=True)
# The output matrix will contain only the upper or lower
# triangular factorization of A. If L is C ordered (it
# probably is as it is the default in Theano) we just switch
# the fill mode parameter of cusolver
l_parameter = 0 if self.lower else 1
if L.flags['C_CONTIGUOUS']:
l_parameter = 1 - l_parameter
L_ptr = L.gpudata
with context:
workspace_size = cusolver.cusolverDnSpotrf_bufferSize(
context.cusolver_handle, l_parameter, n, L_ptr, lda)
workspace = pygpu.zeros(workspace_size,
dtype='float32',
context=context)
dev_info = pygpu.zeros((1, ), dtype='int32', context=context)
workspace_ptr = workspace.gpudata
dev_info_ptr = dev_info.gpudata
cusolver.cusolverDnSpotrf(context.cusolver_handle, l_parameter, n,
L_ptr, lda, workspace_ptr,
workspace_size, dev_info_ptr)
val_dev_info = np.asarray(dev_info)[0]
if val_dev_info > 0:
raise LinAlgError('Cholesky decomposition failed (is A SPD?)')
# cusolver leaves the elements in the matrix outside the considered
# upper or lower triangle unchanged, so we need to put zeros outside
# the triangle
if self.lower:
tril(L)
else:
triu(L)
outputs[0][0] = L
def perform(self, node, inputs, outputs):
context = inputs[0][0].context
# Input matrix.
A = inputs[0]
l, n = A.shape
if l != n:
raise ValueError('A must be a square matrix')
lda = max(1, n)
# cusolver operates on F ordered matrices, but A is expected
# to be symmetric so it does not matter.
# We copy A if needed
if self.inplace:
L = A
else:
L = pygpu.array(A, copy=True)
# The output matrix will contain only the upper or lower
# triangular factorization of A. If L is C ordered (it
# probably is as it is the default in Theano) we just switch
# the fill mode parameter of cusolver
l_parameter = 0 if self.lower else 1
if L.flags['C_CONTIGUOUS']:
l_parameter = 1 - l_parameter
L_ptr = L.gpudata
with context:
workspace_size = cusolver.cusolverDnSpotrf_bufferSize(
context.cusolver_handle, l_parameter, n, L_ptr, lda)
workspace = pygpu.zeros(workspace_size, dtype='float32',
context=context)
dev_info = pygpu.zeros((1,), dtype='int32', context=context)
workspace_ptr = workspace.gpudata
dev_info_ptr = dev_info.gpudata
cusolver.cusolverDnSpotrf(
context.cusolver_handle, l_parameter, n, L_ptr, lda, workspace_ptr,
workspace_size, dev_info_ptr)
val_dev_info = np.asarray(dev_info)[0]
if val_dev_info > 0:
raise LinAlgError('Cholesky decomposition failed (is A SPD?)')
# cusolver leaves the elements in the matrix outside the considered
# upper or lower triangle unchanged, so we need to put zeros outside
# the triangle
if self.lower:
tril(L)
else:
triu(L)
outputs[0][0] = L
def run_tril(dtype, shape, order, inplace):
ac, ag = gen_gpuarray(shape, dtype, order=order, ctx=context)
result = tril(ag, inplace=inplace)
assert numpy.all(numpy.tril(ac) == result)
if inplace:
assert numpy.all(numpy.tril(ac) == ag)
else:
assert numpy.all(ac == ag)
def test_tril():
for shape in [(10, 5), (5, 10), (10, 10)]:
for order in ['c', 'f']:
for inplace in [True, False]:
ac, ag = gen_gpuarray(shape, 'float32',
order=order, ctx=context)
result = tril(ag, inplace=inplace)
assert numpy.all(numpy.tril(ac) == result)
if inplace:
assert numpy.all(numpy.tril(ac) == ag)
else:
assert numpy.all(ac == ag)
def test_tril():
for shape in [(10, 5), (5, 10), (10, 10)]:
for order in ['c', 'f']:
for inplace in [True, False]:
ac, ag = gen_gpuarray(shape,
'float32',
order=order,
ctx=context)
result = tril(ag, inplace=inplace)
assert numpy.all(numpy.tril(ac) == result)
if inplace:
assert numpy.all(numpy.tril(ac) == ag)
else:
assert numpy.all(ac == ag)
def run_noncontiguous_tril(self):
a = numpy.random.rand(5, 5)
b = pygpu.array(a, context=context)
b = b[::-1]
assert b.flags.c_contiguous is b.flags.f_contiguous is False
tril(b)
def run_3d_tril(self):
ac, ag = gen_gpuarray((10, 10, 10), 'float32', ctx=context)
tril(ag)
def run_noncontiguous_tril(self):
a = numpy.random.rand(5, 5)
a = a[::-1]
b = pygpu.array(a, context=context)
assert b.flags.c_contiguous is b.flags.f_contiguous is False
tril(b)
def run_3d_tril(self):
ac, ag = gen_gpuarray((10, 10, 10), 'float32', ctx=context)
tril(ag)
