diff --git a/configure.py b/configure.py
index ea732c64e2a..22b9abedd77 100644
--- a/configure.py
+++ b/configure.py
@@ -40,7 +40,7 @@ _DEFAULT_CUDA_PATH = '/usr/local/cuda'
 _DEFAULT_CUDA_PATH_LINUX = '/opt/cuda'
 _DEFAULT_CUDA_PATH_WIN = ('C:/Program Files/NVIDIA GPU Computing '
                           'Toolkit/CUDA/v%s' % _DEFAULT_CUDA_VERSION)
-_DEFAULT_TENSORRT_PATH_LINUX = '/usr/lib/x86_64-linux-gnu'
+_DEFAULT_TENSORRT_PATH_LINUX = '/usr/lib/%s-linux-gnu' % platform.machine()
 _TF_OPENCL_VERSION = '1.2'
 _DEFAULT_COMPUTECPP_TOOLKIT_PATH = '/usr/local/computecpp'
 _DEFAULT_TRISYCL_INCLUDE_DIR = '/usr/local/triSYCL/include'
diff --git a/tensorflow/contrib/data/python/ops/grouping.py b/tensorflow/contrib/data/python/ops/grouping.py
index a19be222545..ae10d2eb22d 100644
--- a/tensorflow/contrib/data/python/ops/grouping.py
+++ b/tensorflow/contrib/data/python/ops/grouping.py
@@ -42,7 +42,7 @@ def group_by_window(key_func,
   This transformation maps each consecutive element in a dataset to a key
   using `key_func` and groups the elements by key. It then applies
   `reduce_func` to at most `window_size_func(key)` elements matching the same
-  key. All execpt the final window for each key will contain
+  key. All except the final window for each key will contain
   `window_size_func(key)` elements; the final window may be smaller.
 
   You may provide either a constant `window_size` or a window size determined by
diff --git a/tensorflow/contrib/lite/toco/g3doc/python_api.md b/tensorflow/contrib/lite/toco/g3doc/python_api.md
index 440f9c367c2..36e2d9c3723 100644
--- a/tensorflow/contrib/lite/toco/g3doc/python_api.md
+++ b/tensorflow/contrib/lite/toco/g3doc/python_api.md
@@ -28,7 +28,7 @@ val = img + tf.constant([1., 2., 3.]) + tf.constant([1., 4., 4.])
 out = tf.identity(val, name="out")
 with tf.Session() as sess:
   tflite_model = tf.contrib.lite.toco_convert(sess.graph_def, [img], [out])
-  open("test.tflite", "wb").write(tflite_modeL)
+  open("test.tflite", "wb").write(tflite_model)
 ```
 
 **NOTE** Currently, the TOCO command will cause a fatal error to the Python
diff --git a/tensorflow/core/platform/default/logging.h b/tensorflow/core/platform/default/logging.h
index f0efa31d557..2c134f1be93 100644
--- a/tensorflow/core/platform/default/logging.h
+++ b/tensorflow/core/platform/default/logging.h
@@ -64,11 +64,11 @@ class LogMessageFatal : public LogMessage {
 };
 
 #define _TF_LOG_INFO \
-  ::tensorflow::internal::LogMessage(__FILE__, __LINE__, tensorflow::INFO)
+  ::tensorflow::internal::LogMessage(__FILE__, __LINE__, ::tensorflow::INFO)
 #define _TF_LOG_WARNING \
-  ::tensorflow::internal::LogMessage(__FILE__, __LINE__, tensorflow::WARNING)
+  ::tensorflow::internal::LogMessage(__FILE__, __LINE__, ::tensorflow::WARNING)
 #define _TF_LOG_ERROR \
-  ::tensorflow::internal::LogMessage(__FILE__, __LINE__, tensorflow::ERROR)
+  ::tensorflow::internal::LogMessage(__FILE__, __LINE__, ::tensorflow::ERROR)
 #define _TF_LOG_FATAL \
   ::tensorflow::internal::LogMessageFatal(__FILE__, __LINE__)
 
diff --git a/tensorflow/docs_src/extend/add_filesys.md b/tensorflow/docs_src/extend/add_filesys.md
index 06f11de4eb0..bc0f662f0cf 100644
--- a/tensorflow/docs_src/extend/add_filesys.md
+++ b/tensorflow/docs_src/extend/add_filesys.md
@@ -225,7 +225,7 @@ it will use the `FooBarFileSystem` implementation.
 Next, you must build a shared object containing this implementation. An example
 of doing so using bazel's `cc_binary` rule can be found
 [here](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/BUILD#L244),
-but you may use any build system to do so. See the section on @{$adding_an_op#build-the-op-library$building the op library} for similar
+but you may use any build system to do so. See the section on @{$adding_an_op#build_the_op_library$building the op library} for similar
 instructions.
 
 The result of building this target is a `.so` shared object file.
diff --git a/tensorflow/docs_src/extend/new_data_formats.md b/tensorflow/docs_src/extend/new_data_formats.md
index b3cc9680474..10e717c280f 100644
--- a/tensorflow/docs_src/extend/new_data_formats.md
+++ b/tensorflow/docs_src/extend/new_data_formats.md
@@ -167,7 +167,7 @@ REGISTER_KERNEL_BUILDER(Name("TextLineReader").Device(DEVICE_CPU),
 ```
 
 The last step is to add the Python wrapper.  You can either do this by
-@{$adding_an_op#building_the_op_library$compiling a dynamic library}
+@{$adding_an_op#build_the_op_library$compiling a dynamic library}
 or, if you are building TensorFlow from source, adding to `user_ops.py`.
 For the latter, you will import `tensorflow.python.ops.io_ops` in
 [`tensorflow/python/user_ops/user_ops.py`](https://www.tensorflow.org/code/tensorflow/python/user_ops/user_ops.py)
diff --git a/tensorflow/docs_src/tutorials/layers.md b/tensorflow/docs_src/tutorials/layers.md
index 9b17d0d4d52..aeb746f29c2 100644
--- a/tensorflow/docs_src/tutorials/layers.md
+++ b/tensorflow/docs_src/tutorials/layers.md
@@ -198,9 +198,9 @@ Classifier"](#training_and_evaluating_the_cnn_mnist_classifier).
 ### Input Layer
 
 The methods in the `layers` module for creating convolutional and pooling layers
-for two-dimensional image data expect input tensors to have a shape of
-<code>[<em>batch_size</em>, <em>image_width</em>, <em>image_height</em>,
-<em>channels</em>]</code>, defined as follows:
+for two-dimensional image data expect input tensors to have a `channels_last` shape of
+<code>[<em>batch_size</em>, <em>image_height</em>, <em>image_width</em>, <em>channels</em>]</code>
+or a `channels_first` shape of <code>[<em>batch_size</em>, <em>channels</em>, <em>image_height</em>, <em>image_width</em>]</code>, defined as follows:
 
 *   _`batch_size`_. Size of the subset of examples to use when performing
     gradient descent during training.
diff --git a/tensorflow/python/client/session.py b/tensorflow/python/client/session.py
index 6e9ce9b0806..da5dc6f5998 100644
--- a/tensorflow/python/client/session.py
+++ b/tensorflow/python/client/session.py
@@ -889,6 +889,8 @@ class BaseSession(SessionInterface):
       Either a single value if `fetches` is a single graph element, or
       a list of values if `fetches` is a list, or a dictionary with the
       same keys as `fetches` if that is a dictionary (described above).
+      Order in which `fetches` operations are evaluated inside the call
+      is undefined.
 
     Raises:
       RuntimeError: If this `Session` is in an invalid state (e.g. has been
diff --git a/tensorflow/python/ops/math_ops.py b/tensorflow/python/ops/math_ops.py
index 4699e05269d..276897ab99e 100644
--- a/tensorflow/python/ops/math_ops.py
+++ b/tensorflow/python/ops/math_ops.py
@@ -167,6 +167,7 @@ from tensorflow.python.ops import gen_math_ops
 from tensorflow.python.ops import gen_nn_ops
 from tensorflow.python.ops import gen_sparse_ops
 from tensorflow.python.ops import gen_spectral_ops
+from tensorflow.python.platform import tf_logging as logging
 # go/tf-wildcard-import
 # pylint: disable=wildcard-import
 from tensorflow.python.ops.gen_math_ops import *
@@ -775,16 +776,18 @@ def cast(x, dtype, name=None):
   with ops.name_scope(name, "Cast", [x]) as name:
     if isinstance(x, sparse_tensor.SparseTensor):
       values_cast = cast(x.values, base_type, name=name)
-      return sparse_tensor.SparseTensor(x.indices, values_cast, x.dense_shape)
+      x = sparse_tensor.SparseTensor(x.indices, values_cast, x.dense_shape)
     else:
       # TODO(josh11b): If x is not already a Tensor, we could return
       # ops.convert_to_tensor(x, dtype=dtype, ...)  here, but that
       # allows some conversions that cast() can't do, e.g. casting numbers to
       # strings.
       x = ops.convert_to_tensor(x, name="x")
-      if x.dtype.base_dtype == base_type:
-        return x
-      return gen_math_ops.cast(x, base_type, name=name)
+      if x.dtype.base_dtype != base_type:
+        x = gen_math_ops.cast(x, base_type, name=name)
+    if x.dtype.is_complex and base_type.is_floating:
+      logging.warn("Casting complex to real discards imaginary part.")
+    return x
 
 
 @tf_export("saturate_cast")
diff --git a/tensorflow/python/ops/sets_impl.py b/tensorflow/python/ops/sets_impl.py
index b0eecd8a1e8..21e08d03d21 100644
--- a/tensorflow/python/ops/sets_impl.py
+++ b/tensorflow/python/ops/sets_impl.py
@@ -247,7 +247,7 @@ def set_difference(a, b, aminusb=True, validate_indices=True):
     #
     # collections.OrderedDict([
     #     ((0, 0, 0), 2),
-    #     ((0, 0, 1), 3),
+    #     ((0, 1, 0), 3),
     # ])
   ```
 
diff --git a/tensorflow/tools/test/upload_test_benchmarks.py b/tensorflow/tools/test/upload_test_benchmarks.py
index c0305751092..9c45359ee1b 100644
--- a/tensorflow/tools/test/upload_test_benchmarks.py
+++ b/tensorflow/tools/test/upload_test_benchmarks.py
@@ -89,6 +89,7 @@ import shutil
 
 from six import text_type
 from google.cloud import datastore
+from six import text_type
 
 
 def is_real_file(dirpath, fname):
diff --git a/third_party/sycl/sycl/BUILD.tpl b/third_party/sycl/sycl/BUILD.tpl
index 21b1a2bbf7d..b7e9aa8edb4 100755
--- a/third_party/sycl/sycl/BUILD.tpl
+++ b/third_party/sycl/sycl/BUILD.tpl
@@ -21,7 +21,7 @@ config_setting(
     name = "using_sycl_trisycl",
     define_values = {
         "using_sycl": "true",
-        "using_trisycl": "false",
+        "using_trisycl": "true",
     },
 )