def test_alloc_memset_0():
i = tensor.iscalar()
z = numpy.zeros((1,), dtype='float32')
o = numpy.ones((1,), dtype='float32')
ones = numpy.ones((2,), dtype='float32')
# Test with 0
a = basic_ops.gpu_alloc(cuda.gpu_from_host(tensor.constant(z)), i)
f = theano.function([i], a, mode=mode_with_gpu)
topo = f.maker.fgraph.toposort()
assert len(topo) == 1
assert isinstance(topo[0].op, basic_ops.GpuAlloc) and topo[0].op.memset_0
assert (numpy.asarray(f(6)) == 0).all()
# Test with 1
a = basic_ops.gpu_alloc(cuda.gpu_from_host(tensor.constant(o)), i)
f = theano.function([i], a, mode=mode_with_gpu)
topo = f.maker.fgraph.toposort()
assert len(topo) == 1
assert isinstance(topo[0].op, basic_ops.GpuAlloc)
assert not topo[0].op.memset_0
assert (numpy.asarray(f(6)) == 1).all()
# Test with 1, 1
a = basic_ops.gpu_alloc(cuda.gpu_from_host(tensor.constant(ones)), i)
f = theano.function([i], a, mode=mode_with_gpu)
topo = f.maker.fgraph.toposort()
assert len(topo) == 1
assert isinstance(topo[0].op, basic_ops.GpuAlloc)
assert not topo[0].op.memset_0
assert (numpy.asarray(f(2)) == 1).all()
def test_alloc_memset_0():
i = tensor.iscalar()
z = numpy.zeros((1, ), dtype='float32')
o = numpy.ones((1, ), dtype='float32')
ones = numpy.ones((2, ), dtype='float32')
# Test with 0
a = basic_ops.gpu_alloc(cuda.gpu_from_host(tensor.constant(z)), i)
f = theano.function([i], a, mode=mode_with_gpu)
topo = f.maker.fgraph.toposort()
assert len(topo) == 1
assert isinstance(topo[0].op, basic_ops.GpuAlloc) and topo[0].op.memset_0
assert (numpy.asarray(f(6)) == 0).all()
# Test with 1
a = basic_ops.gpu_alloc(cuda.gpu_from_host(tensor.constant(o)), i)
f = theano.function([i], a, mode=mode_with_gpu)
topo = f.maker.fgraph.toposort()
assert len(topo) == 1
assert isinstance(topo[0].op, basic_ops.GpuAlloc)
assert not topo[0].op.memset_0
assert (numpy.asarray(f(6)) == 1).all()
# Test with 1, 1
a = basic_ops.gpu_alloc(cuda.gpu_from_host(tensor.constant(ones)), i)
f = theano.function([i], a, mode=mode_with_gpu)
topo = f.maker.fgraph.toposort()
assert len(topo) == 1
assert isinstance(topo[0].op, basic_ops.GpuAlloc)
assert not topo[0].op.memset_0
assert (numpy.asarray(f(2)) == 1).all()
def setUp(self):
super(Test_local_elemwise_alloc, self).setUp()
self.fast_run_mode = mode_with_gpu
# self.vec = tensor.vector('vec', dtype=dtype)
# self.mat = tensor.matrix('mat', dtype=dtype)
# self.tens = tensor.tensor3('tens', dtype=dtype)
# self.alloc_wo_dep = basic_ops.gpu_alloc(self.vec, 2, 2)
# self.alloc_w_dep = basic_ops.gpu_alloc(self.vec, *self.mat.shape)
self.alloc_wo_dep = basic_ops.gpu_alloc(self.vec, 2, 2)
self.alloc_w_dep = basic_ops.gpu_alloc(self.vec, *self.mat.shape)
self.alloc_w_dep_tens = basic_ops.gpu_alloc(
self.vec,
self.tens.shape[0],
self.tens.shape[1]
)
self.tv_wo_dep = basic_ops.gpu_alloc(self.vec, 5, 5)
self.tm_wo_dep = basic_ops.gpu_alloc(self.mat, 5, 5, 5)
self.s = tensor.iscalar('s')
self.tv_w_dep = basic_ops.gpu_alloc(self.vec, self.s, self.s)
self.tm_w_dep = basic_ops.gpu_alloc(self.mat, 5, 5, 5)
self.row = tensor.row(dtype=self.dtype)
self.o = basic_ops.gpu_alloc(self.row, 5, 5)
def setUp(self):
super(Test_local_elemwise_alloc, self).setUp()
self.fast_run_mode = mode_with_gpu
# self.vec = tensor.vector('vec', dtype=dtype)
# self.mat = tensor.matrix('mat', dtype=dtype)
# self.tens = tensor.tensor3('tens', dtype=dtype)
# self.alloc_wo_dep = basic_ops.gpu_alloc(self.vec, 2, 2)
# self.alloc_w_dep = basic_ops.gpu_alloc(self.vec, *self.mat.shape)
self.alloc_wo_dep = basic_ops.gpu_alloc(self.vec, 2, 2)
self.alloc_w_dep = basic_ops.gpu_alloc(self.vec, *self.mat.shape)
self.alloc_w_dep_tens = basic_ops.gpu_alloc(
self.vec,
self.tens.shape[0],
self.tens.shape[1]
)
self.tv_wo_dep = basic_ops.gpu_alloc(self.vec, 5, 5)
self.tm_wo_dep = basic_ops.gpu_alloc(self.mat, 5, 5, 5)
self.s = tensor.iscalar('s')
self.tv_w_dep = basic_ops.gpu_alloc(self.vec, self.s, self.s)
self.tm_w_dep = basic_ops.gpu_alloc(self.mat, 5, 5, 5)
self.row = tensor.row(dtype=self.dtype)
self.o = basic_ops.gpu_alloc(self.row, 5, 5)