Merge with upstream

7 files changed, 16 insertions, 47 deletions

diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorAssign.h b/unsupported/Eigen/CXX11/src/Tensor/TensorAssign.h
index f1f877c16..bcaf5c97f 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorAssign.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorAssign.h
@@ -187,7 +187,7 @@ struct TensorEvaluator<const TensorAssignOp<LeftArgType, RightArgType>, Device>
 
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE void evalBlock(TensorBlock* block) {
     if (TensorEvaluator<LeftArgType, Device>::RawAccess &&
-        m_leftImpl.data() != nullptr) {
+        m_leftImpl.data() != NULL) {
       TensorBlock left_block(block->first_coeff_index(), block->block_sizes(),
                              block->tensor_strides(), block->tensor_strides(),
                              m_leftImpl.data() + block->first_coeff_index());
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorBase.h b/unsupported/Eigen/CXX11/src/Tensor/TensorBase.h
index ab3731952..9b9d330c1 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorBase.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorBase.h
@@ -200,9 +200,9 @@ class TensorBase<Derived, ReadOnlyAccessors>
     }
 
     EIGEN_DEVICE_FUNC
-    EIGEN_STRONG_INLINE const TensorCwiseUnaryOp<internal::scalar_sigmoid_op<Scalar>, const Derived>
+    EIGEN_STRONG_INLINE const TensorCwiseUnaryOp<internal::scalar_logistic_op<Scalar>, const Derived>
     sigmoid() const {
-      return unaryExpr(internal::scalar_sigmoid_op<Scalar>());
+      return unaryExpr(internal::scalar_logistic_op<Scalar>());
     }
 
     EIGEN_DEVICE_FUNC
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorBlock.h b/unsupported/Eigen/CXX11/src/Tensor/TensorBlock.h
index cbf91013b..21a6b66e8 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorBlock.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorBlock.h
@@ -155,8 +155,8 @@ struct TensorBlockCopyOp {
     typedef const Eigen::Array<Scalar, Dynamic, 1> Src;
     typedef Eigen::Array<Scalar, Dynamic, 1> Dst;
 
-    typedef Eigen::Map<Src, 0, InnerStride<>> SrcMap;
-    typedef Eigen::Map<Dst, 0, InnerStride<>> DstMap;
+    typedef Eigen::Map<Src, 0, InnerStride<> > SrcMap;
+    typedef Eigen::Map<Dst, 0, InnerStride<> > DstMap;
 
     const SrcMap src(src_base, num_coeff_to_copy, InnerStride<>(src_stride));
     DstMap dst(dst_base, num_coeff_to_copy, InnerStride<>(dst_stride));
@@ -405,9 +405,9 @@ struct TensorBlockCwiseBinaryOp {
     typedef const Eigen::Array<RightScalar, Dynamic, 1> Rhs;
     typedef Eigen::Array<OutputScalar, Dynamic, 1> Out;
 
-    typedef Eigen::Map<Lhs, 0, InnerStride<>> LhsMap;
-    typedef Eigen::Map<Rhs, 0, InnerStride<>> RhsMap;
-    typedef Eigen::Map<Out, 0, InnerStride<>> OutMap;
+    typedef Eigen::Map<Lhs, 0, InnerStride<> > LhsMap;
+    typedef Eigen::Map<Rhs, 0, InnerStride<> > RhsMap;
+    typedef Eigen::Map<Out, 0, InnerStride<> > OutMap;
 
     const LeftScalar* lhs_base = &left_data[left_index];
     const RightScalar* rhs_base = &right_data[right_index];
@@ -501,7 +501,7 @@ struct TensorBlockCwiseBinaryIO {
       if (size == 1) {
         continue;
       }
-      auto& state = block_iter_state[num_squeezed_dims];
+      BlockIteratorState& state = block_iter_state[num_squeezed_dims];
       state.output_stride = block_strides[dim];
       state.left_stride = left_strides[dim];
       state.right_stride = right_strides[dim];
@@ -523,7 +523,7 @@ struct TensorBlockCwiseBinaryIO {
                                     right_stride, right_data);
       // Update index.
       for (int j = 0; j < num_squeezed_dims; ++j) {
-        auto& state = block_iter_state[j];
+        BlockIteratorState& state = block_iter_state[j];
         if (++state.count < state.size) {
           output_index += state.output_stride;
           left_index += state.left_stride;
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceThreadPool.h b/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceThreadPool.h
index cc134228a..3e3665efb 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceThreadPool.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceThreadPool.h
@@ -102,7 +102,7 @@ class Allocator {
 // Build a thread pool device on top the an existing pool of threads.
 struct ThreadPoolDevice {
   // The ownership of the thread pool remains with the caller.
-  ThreadPoolDevice(ThreadPoolInterface* pool, int num_cores, Allocator* allocator = nullptr)
+  ThreadPoolDevice(ThreadPoolInterface* pool, int num_cores, Allocator* allocator = NULL)
       : pool_(pool), num_threads_(num_cores), allocator_(allocator) { }
 
   EIGEN_STRONG_INLINE void* allocate(size_t num_bytes) const {
@@ -282,7 +282,7 @@ struct ThreadPoolDevice {
   // Convenience wrapper for parallelFor that does not align blocks.
   void parallelFor(Index n, const TensorOpCost& cost,
                    std::function<void(Index, Index)> f) const {
-    parallelFor(n, cost, nullptr, std::move(f));
+    parallelFor(n, cost, NULL, std::move(f));
   }
 
   // Thread pool accessor.
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h b/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
index 3f3b5685d..0cefe42dd 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
@@ -227,7 +227,7 @@ class TensorExecutor<Expression, ThreadPoolDevice, Vectorizable, Tileable> {
     typedef EvalRange<Evaluator, StorageIndex, Vectorizable> EvalRange;
 
     Evaluator evaluator(expr, device);
-    const bool needs_assign = evaluator.evalSubExprsIfNeeded(nullptr);
+    const bool needs_assign = evaluator.evalSubExprsIfNeeded(NULL);
     if (needs_assign) {
       const StorageIndex PacketSize =
           Vectorizable
@@ -257,7 +257,6 @@ class TensorExecutor<Expression, ThreadPoolDevice, Vectorizable, /*Tileable*/ tr
 
   static EIGEN_STRONG_INLINE void run(const Expression& expr,
                          const ThreadPoolDevice& device) {
-    typedef TensorBlock<ScalarNoConst, StorageIndex, NumDims, Evaluator::Layout> TensorBlock;
     typedef TensorBlockMapper<ScalarNoConst, StorageIndex, NumDims, Evaluator::Layout> TensorBlockMapper;
 
     Evaluator evaluator(expr, device);
@@ -271,7 +270,7 @@ class TensorExecutor<Expression, ThreadPoolDevice, Vectorizable, /*Tileable*/ tr
       return;
     }
 
-    const bool needs_assign = evaluator.evalSubExprsIfNeeded(nullptr);
+    const bool needs_assign = evaluator.evalSubExprsIfNeeded(NULL);
     if (needs_assign) {
       TensorBlockShapeType block_shape = TensorBlockShapeType::kSkewedInnerDims;
       Index block_total_size = 0;
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorFunctors.h b/unsupported/Eigen/CXX11/src/Tensor/TensorFunctors.h
index 7ecd4d1ac..cd666c173 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorFunctors.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorFunctors.h
@@ -54,36 +54,6 @@ struct functor_traits<scalar_fmod_op<Scalar> > {
          PacketAccess = false };
 };
 
-
-/** \internal
-  * \brief Template functor to compute the sigmoid of a scalar
-  * \sa class CwiseUnaryOp, ArrayBase::sigmoid()
-  */
-template <typename T>
-struct scalar_sigmoid_op {
-  EIGEN_EMPTY_STRUCT_CTOR(scalar_sigmoid_op)
-  EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator()(const T& x) const {
-    const T one = T(1);
-    return one / (one + numext::exp(-x));
-  }
-
-  template <typename Packet> EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE
-  Packet packetOp(const Packet& x) const {
-    const Packet one = pset1<Packet>(T(1));
-    return pdiv(one, padd(one, pexp(pnegate(x))));
-  }
-};
-
-template <typename T>
-struct functor_traits<scalar_sigmoid_op<T> > {
-  enum {
-    Cost = NumTraits<T>::AddCost * 2 + NumTraits<T>::MulCost * 6,
-    PacketAccess = packet_traits<T>::HasAdd && packet_traits<T>::HasDiv &&
-                   packet_traits<T>::HasNegate && packet_traits<T>::HasExp
-  };
-};
-
-
 template<typename Reducer, typename Device>
 struct reducer_traits {
   enum {
diff --git a/unsupported/test/cxx11_tensor_thread_pool.cpp b/unsupported/test/cxx11_tensor_thread_pool.cpp
index 5c3aae482..dd163c18a 100644
--- a/unsupported/test/cxx11_tensor_thread_pool.cpp
+++ b/unsupported/test/cxx11_tensor_thread_pool.cpp
@@ -428,7 +428,7 @@ void test_threadpool_allocate(TestAllocator* allocator)
     void* ptr = device.allocate(512);
     device.deallocate(ptr);
   }
-  VERIFY(allocator != nullptr);
+  VERIFY(allocator != NULL);
   VERIFY_IS_EQUAL(allocator->alloc_count(), num_allocs);
   VERIFY_IS_EQUAL(allocator->dealloc_count(), num_allocs);
 }
@@ -460,7 +460,7 @@ EIGEN_DECLARE_TEST(cxx11_tensor_thread_pool)
   CALL_SUBTEST_6(test_multithread_random());
 
   TestAllocator test_allocator;
-  CALL_SUBTEST_6(test_multithread_shuffle<ColMajor>(nullptr));
+  CALL_SUBTEST_6(test_multithread_shuffle<ColMajor>(NULL));
   CALL_SUBTEST_6(test_multithread_shuffle<RowMajor>(&test_allocator));
   CALL_SUBTEST_6(test_threadpool_allocate(&test_allocator));
 }