Skip to content

P
pytensor
提交 3a6d2fcb authored 作者: Arnaud Bergeron's avatar Arnaud Bergeron
浏览文件
操作

Fixup tutorial/using_gpu.txt

上级 a3d76ad2
隐藏空白字符变更
内嵌 并排
正在显示 包含 6 行增加 和 162 行删除
doc/tutorial/using_gpu.txt
浏览文件 @ 3a6d2fcb
......@@ -33,9 +33,6 @@ Testing Theano with GPU
To see if your GPU is being used, cut and paste the following program into a
file and run it.
.. If you modify this code, also change :
.. theano/tests/test_tutorial.py:T_using_gpu.test_using_gpu_1
.. testcode::
from theano import function, config, shared, sandbox
......@@ -111,9 +108,6 @@ the graph to express a computation with a GPU-stored result. The ``gpu_from_hos
op means "copy the input from the host to the GPU" and it is optimized away
after the ``T.exp(x)`` is replaced by a GPU version of ``exp()``.
.. If you modify this code, also change :
.. theano/tests/test_tutorial.py:T_using_gpu.test_using_gpu_2
.. testcode::
from theano import function, config, shared, sandbox
......@@ -466,7 +460,6 @@ If you don't mind a loss of flexibility, you can ask theano to return
the GPU object directly. The following code is modifed to do just that.
.. testcode::
:emphasize-lines: 10,17
from theano import function, config, shared, tensor, sandbox
import numpy
......@@ -501,14 +494,13 @@ The output is
.. testoutput::
:hide:
:options: +ELLIPSIS
:options: +ELLIPSIS, +SKIP
$ THEANO_FLAGS=device=cuda0 python check2.py
Using device cuda0: GeForce GTX 275
[GpuElemwise{exp,no_inplace}(<GpuArray<float64>>)]
Looping 1000 times took ... seconds
Result is ...
Used the gpu
Using device cuda0: ...
[GpuElemwise{exp,no_inplace}(<GpuArray<float64>>)]
Looping 1000 times took ... seconds
Result is ...
Used the gpu
.. code-block:: none
......
theano/tests/test_tutorial.py
浏览文件 @ 3a6d2fcb
......@@ -21,154 +21,6 @@ from theano.tests import unittest_tools as utt
from theano.sandbox.rng_mrg import MRG_RandomStreams
from theano.tensor.shared_randomstreams import RandomStreams
class T_using_gpu(unittest.TestCase):
# All tests here belog to
# http://deeplearning.net/software/theano/tutorial/using_gpu.html
# Theano/doc/tutorial/using_gpu.txt
# Any change you do here also add it to the tutorial !
def test_using_gpu_1(self):
# I'm checking if this compiles and runs
from theano import function, config, shared, sandbox
import theano.tensor as T
import numpy
import time
vlen = 10 * 30 * 70 # 10 x #cores x # threads per core
iters = 10
rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
f = function([], T.exp(x))
# print f.maker.fgraph.toposort()
t0 = time.time()
for i in xrange(iters):
r = f()
t1 = time.time()
print('Looping %d times took' % iters, t1 - t0, 'seconds')
print('Result is', r)
if numpy.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()]):
print('Used the cpu')
else:
print('Used the gpu')
if theano.config.device.find('gpu') > -1:
assert not numpy.any( [isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()])
else:
assert numpy.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()])
def test_using_gpu_2(self):
if theano.config.device.find('gpu') > -1:
from theano import function, config, shared, sandbox
import theano.tensor as T
import numpy
import time
vlen = 10 * 30 * 70 # 10 x #cores x # threads per core
iters = 10
rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
f = function([], sandbox.cuda.basic_ops.gpu_from_host(T.exp(x)))
# print f.maker.fgraph.toposort()
t0 = time.time()
for i in xrange(iters):
r = f()
t1 = time.time()
print('Looping %d times took' % iters, t1 - t0, 'seconds')
print('Result is', r)
print('Numpy result is', numpy.asarray(r))
if numpy.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()]):
print('Used the cpu')
else:
print('Used the gpu')
assert not numpy.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()])
def test_using_gpu_3(self):
if theano.config.device.find('gpu') > -1:
from theano import function, config, shared, sandbox, Out
import theano.tensor as T
import numpy
import time
vlen = 10 * 30 * 70 # 10 x #cores x # threads per core
iters = 10
rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
f = function([],
Out(sandbox.cuda.basic_ops.gpu_from_host(T.exp(x)),
borrow=True))
# print f.maker.fgraph.toposort()
t0 = time.time()
for i in xrange(iters):
r = f()
t1 = time.time()
print('Looping %d times took' % iters, t1 - t0, 'seconds')
print('Result is', r)
print('Numpy result is', numpy.asarray(r))
if numpy.any([isinstance(x.op, T.Elemwise)
for x in f.maker.fgraph.toposort()]):
print('Used the cpu')
else:
print('Used the gpu')
assert not numpy.any([isinstance(x.op, T.Elemwise)
for x in f.maker.fgraph.toposort()])
def test_using_gpu_pycudaop(self):
import theano.misc.pycuda_init
if not theano.misc.pycuda_init.pycuda_available:
raise SkipTest("Pycuda not installed. Skip test of theano op"
" with pycuda code.")
from pycuda.compiler import SourceModule
import theano.sandbox.cuda as cuda
import theano.sandbox.cuda as cuda_ndarray
if not cuda_ndarray.cuda_available:
raise SkipTest('Optional package cuda disabled')
class PyCUDADoubleOp(theano.Op):
__props__ = ()
def make_node(self, inp):
inp = cuda.basic_ops.gpu_contiguous(
cuda.basic_ops.as_cuda_ndarray_variable(inp))
assert inp.dtype == "float32"
return theano.Apply(self, [inp], [inp.type()])
def make_thunk(self, node, storage_map, _, _2):
mod = SourceModule("""
__global__ void my_fct(float * i0, float * o0, int size) {
int i = blockIdx.x*blockDim.x + threadIdx.x;
if(i<size){
o0[i] = i0[i]*2;
}
}""")
pycuda_fct = mod.get_function("my_fct")
inputs = [storage_map[v] for v in node.inputs]
outputs = [storage_map[v] for v in node.outputs]
def thunk():
z = outputs[0]
if z[0] is None or z[0].shape != inputs[0][0].shape:
z[0] = cuda.CudaNdarray.zeros(inputs[0][0].shape)
grid = (int(numpy.ceil(inputs[0][0].size / 512.)), 1)
pycuda_fct(inputs[0][0], z[0],
numpy.intc(inputs[0][0].size),
block=(512, 1, 1), grid=grid)
return thunk
x = theano.tensor.fmatrix()
f = theano.function([x], PyCUDADoubleOp()(x))
xv = numpy.ones((4, 5), dtype="float32")
assert numpy.allclose(f(xv), xv*2)
class T_typedlist(unittest.TestCase):
# All tests here belong to
# http://deeplearning.net/software/theano/library/typed_list.html
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论