TensorFlow: Removal of large assets and small other fixes.

Changes:

- Remove all large assets from the repoistory, incuding the other 50MiB
  model protobuf and a lot of images in our g3doc directory. We will
  maintain these assets externally for now.  g3doc images may be
  broken for a little bit, but the website will be fine, which
  is the important resource. By @vrv and @petewarden.  Updates
  READMES to reflect the external model resources.

- Fix to saver's latest_checkpoint function by Zhifeng

- Made protos visibility public by @vrv

- Updates to docs by @mrry, Andy

- Embed tensorboard resource for summary icon by Daniel

- More updates to backwars compat by @josh11b

Base CL: 108194981

2 files changed, 20 insertions, 18 deletions

diff --git a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h
index b6eeb73832..a62682c728 100644
--- a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h
+++ b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h
@@ -760,11 +760,15 @@ struct GpuDevice {
   GpuDevice()
       : stream_(perftools::gputools::MachineManager::singleton()->stream_for_device(0)),
         allocator_(nullptr),
-        stream_exec_(stream_->parent()) {}
+        stream_exec_(stream_->parent()),
+        device_descr_(&(stream_exec_->GetDeviceDescription())) {}
 
   GpuDevice(perftools::gputools::Stream* stream,
             const Allocator* alloc = nullptr)
-      : stream_(stream), allocator_(alloc), stream_exec_(stream_->parent()) { }
+      : stream_(stream),
+        allocator_(alloc),
+        stream_exec_(stream_->parent()),
+        device_descr_(&(stream_exec_->GetDeviceDescription())) {}
 
   EIGEN_STRONG_INLINE perftools::gputools::Stream* stream() const {
     return stream_;
@@ -873,28 +877,25 @@ struct GpuDevice {
     stream_->BlockHostUntilDone();
   }
 
-  // A gpu::DeviceDescription is cached inside a StreamExecutor, so these calls
-  // aren't expensive/wasteful.
   EIGEN_DEVICE_FUNC inline int getNumCudaMultiProcessors() const {
-    return stream_exec_->GetDeviceDescription().core_count();
+    return device_descr_->core_count();
   }
 
   EIGEN_DEVICE_FUNC inline int maxCudaThreadsPerBlock() const {
-    return stream_exec_->GetDeviceDescription().threads_per_block_limit();
+    return device_descr_->threads_per_block_limit();
   }
 
   EIGEN_DEVICE_FUNC inline int maxCudaThreadsPerMultiProcessor() const {
-    return stream_exec_->GetDeviceDescription().threads_per_core_limit();
+    return device_descr_->threads_per_core_limit();
   }
 
   EIGEN_DEVICE_FUNC inline int sharedMemPerBlock() const {
-    return stream_exec_->GetDeviceDescription().shared_memory_per_block();
+    return device_descr_->shared_memory_per_block();
   }
 
   EIGEN_DEVICE_FUNC inline int majorDeviceVersion() const {
     int major, minor;
-    if (stream_exec_->GetDeviceDescription().cuda_compute_capability(&major,
-                                                                  &minor)) {
+    if (device_descr_->cuda_compute_capability(&major, &minor)) {
       return major;
     } else {
       return 0;
@@ -906,6 +907,7 @@ struct GpuDevice {
  private:
   perftools::gputools::Stream* stream_;
   perftools::gputools::StreamExecutor* stream_exec_;
+  const perftools::gputools::DeviceDescription* device_descr_;
   const Allocator* allocator_;
 };
 
diff --git a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h
index 3e90b08c99..6d63b23b2f 100644
--- a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h
+++ b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h
@@ -115,7 +115,7 @@ namespace {
 }
 
 
-template <typename T>
+template <typename T, bool div_gt_one = false>
 struct TensorIntDivisor {
  public:
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() {
@@ -166,7 +166,7 @@ struct TensorIntDivisor {
 // Optimized version for signed 32 bit integers.
 // Derived from Hacker's Delight.
 template <>
-class TensorIntDivisor<int32_t> {
+class TensorIntDivisor<int32_t, true> {
  public:
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() {
     magic = 0;
@@ -225,15 +225,15 @@ private:
 };
 
 
-template <typename T>
-static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T>& divisor) {
+template <typename T, bool div_gt_one>
+static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T, div_gt_one>& divisor) {
   return divisor.divide(numerator);
 }
 
 
 #else
 // Reverse to the old code since gcudacc doesn't support the code above.
-template <typename T>
+template <typename T, bool div_gt_one = false>
 struct TensorIntDivisor {
  public:
    EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() {
@@ -285,7 +285,7 @@ struct TensorIntDivisor {
 // Optimized version for signed 32 bit integers.
 // Derived from Hacker's Delight.
 template <>
-class TensorIntDivisor<int> {
+class TensorIntDivisor<int, true> {
  public:
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() {
     magic = 0;
@@ -344,8 +344,8 @@ private:
 };
 
 
-template <typename T>
-static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T>& divisor) {
+template <typename T, bool div_gt_one>
+static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T, div_gt_one>& divisor) {
   return divisor.divide(numerator);
 }