from theano import function, config, shared, sandbox, tensor, Out
import numpy
import time

vlen = 10 * 30 * 768  # 10 x # cores x # threads per core
iters = 1000

rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
f1 = function([], sandbox.cuda.basic_ops.gpu_from_host(tensor.exp(x)))
f2 = function([],
              Out(sandbox.cuda.basic_ops.gpu_from_host(tensor.exp(x)),
                  borrow=True))
t0 = time.time()
for i in range(iters):
    r = f1()
t1 = time.time()
no_borrow = t1 - t0
t0 = time.time()
for i in range(iters):
    r = f2()
t1 = time.time()
print(
    "Looping %s times took %s seconds without borrow "
    "and %s seconds with borrow" % (iters, no_borrow, (t1 - t0))
)
if numpy.any([isinstance(x.op, tensor.Elemwise) and
              ('Gpu' not in type(x.op).__name__)
              for x in f1.maker.fgraph.toposort()]):
    print('Used the cpu')
else:
    print('Used the gpu')