def test_overflow_gpu_new_backend():
# run with THEANO_FLAGS=mode=FAST_RUN,init_gpu_device=cuda1,device=cpu
from theano.sandbox.gpuarray.tests.test_basic_ops import \
mode_with_gpu as mode
from theano.sandbox.gpuarray.type import gpuarray_shared_constructor
seed = 12345
n_substreams = 7
curr_rstate = numpy.array([seed] * 6, dtype='int32')
rstate = [curr_rstate.copy()]
for j in range(1, n_substreams):
rstate.append(rng_mrg.ff_2p72(rstate[-1]))
rstate = numpy.asarray(rstate)
rstate = gpuarray_shared_constructor(rstate)
fct = functools.partial(rng_mrg.GPUA_mrg_uniform.new, rstate,
ndim=None, dtype='float32')
# should raise error as the size overflows
sizes = [(2**31, ), (2**32, ), (2**15, 2**16,), (2, 2**15, 2**15)]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=True)
# should not raise error
sizes = [(2**5, ), (2**5, 2**5), (2**5, 2**5, 2**5)]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=False)
# should support int32 sizes
sizes = [(numpy.int32(2**10), ),
(numpy.int32(2), numpy.int32(2**10), numpy.int32(2**10))]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=False)
def test_overflow_gpu_new_backend():
# run with THEANO_FLAGS=mode=FAST_RUN,init_gpu_device=cuda1,device=cpu
from theano.sandbox.gpuarray.tests.test_basic_ops import \
mode_with_gpu as mode
from theano.sandbox.gpuarray.type import gpuarray_shared_constructor
seed = 12345
n_substreams = 7
curr_rstate = numpy.array([seed] * 6, dtype='int32')
rstate = [curr_rstate.copy()]
for j in range(1, n_substreams):
rstate.append(rng_mrg.ff_2p72(rstate[-1]))
rstate = numpy.asarray(rstate)
rstate = gpuarray_shared_constructor(rstate)
fct = functools.partial(rng_mrg.GPUA_mrg_uniform.new,
rstate,
ndim=None,
dtype='float32')
# should raise error as the size overflows
sizes = [(2**31, ), (2**32, ), (
2**15,
2**16,
), (2, 2**15, 2**15)]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=True)
# should not raise error
sizes = [(2**5, ), (2**5, 2**5), (2**5, 2**5, 2**5)]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=False)
# should support int32 sizes
sizes = [(numpy.int32(2**10), ),
(numpy.int32(2), numpy.int32(2**10), numpy.int32(2**10))]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=False)
def test_consistency_GPUA_serial():
"""
Verify that the random numbers generated by GPUA_mrg_uniform, serially,
are the same as the reference (Java) implementation by L'Ecuyer et al.
"""
from theano.sandbox.gpuarray.tests.test_basic_ops import \
mode_with_gpu as mode
from theano.sandbox.gpuarray.type import gpuarray_shared_constructor
seed = 12345
n_samples = 5
n_streams = 12
n_substreams = 7
samples = []
curr_rstate = numpy.array([seed] * 6, dtype='int32')
for i in range(n_streams):
stream_rstate = curr_rstate.copy()
for j in range(n_substreams):
substream_rstate = numpy.array([stream_rstate.copy()],
dtype='int32')
# Transfer to device
rstate = gpuarray_shared_constructor(substream_rstate)
new_rstate, sample = rng_mrg.GPUA_mrg_uniform.new(rstate,
ndim=None,
dtype='float32',
size=(1, ))
rstate.default_update = new_rstate
# Not really necessary, just mimicking
# rng_mrg.MRG_RandomStreams' behavior
sample.rstate = rstate
sample.update = (rstate, new_rstate)
# We need the sample back in the main memory
cpu_sample = tensor.as_tensor_variable(sample)
f = theano.function([], cpu_sample, mode=mode)
for k in range(n_samples):
s = f()
samples.append(s)
# next substream
stream_rstate = rng_mrg.ff_2p72(stream_rstate)
# next stream
curr_rstate = rng_mrg.ff_2p134(curr_rstate)
samples = numpy.array(samples).flatten()
assert (numpy.allclose(samples, java_samples))
def test_consistency_GPUA_parallel():
"""
Verify that the random numbers generated by GPUA_mrg_uniform, in
parallel, are the same as the reference (Java) implementation by
L'Ecuyer et al.
"""
from theano.sandbox.gpuarray.tests.test_basic_ops import \
mode_with_gpu as mode
from theano.sandbox.gpuarray.type import gpuarray_shared_constructor
seed = 12345
n_samples = 5
n_streams = 12
n_substreams = 7 # 7 samples will be drawn in parallel
samples = []
curr_rstate = numpy.array([seed] * 6, dtype='int32')
for i in range(n_streams):
stream_samples = []
rstate = [curr_rstate.copy()]
for j in range(1, n_substreams):
rstate.append(rng_mrg.ff_2p72(rstate[-1]))
rstate = numpy.asarray(rstate)
rstate = gpuarray_shared_constructor(rstate)
new_rstate, sample = rng_mrg.GPUA_mrg_uniform.new(rstate, ndim=None,
dtype='float32',
size=(n_substreams,))
rstate.default_update = new_rstate
# Not really necessary, just mimicking
# rng_mrg.MRG_RandomStreams' behavior
sample.rstate = rstate
sample.update = (rstate, new_rstate)
# We need the sample back in the main memory
cpu_sample = tensor.as_tensor_variable(sample)
f = theano.function([], cpu_sample, mode=mode)
for k in range(n_samples):
s = f()
stream_samples.append(s)
samples.append(numpy.array(stream_samples).T.flatten())
# next stream
curr_rstate = rng_mrg.ff_2p134(curr_rstate)
samples = numpy.array(samples).flatten()
assert(numpy.allclose(samples, java_samples))
