devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge with upstream

Browse Source
This commit is contained in:
Mehdi Goli
2018-08-14 09:43:45 +01:00
parent 1aa86aad14 501be70b27
commit 8ba799805b
11 changed files with 66 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
unsupported/Eigen/CXX11/src/Tensor/TensorAssign.h
View File

@@ -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());

4
unsupported/Eigen/CXX11/src/Tensor/TensorBase.h
View File

@@ -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

14
unsupported/Eigen/CXX11/src/Tensor/TensorBlock.h
View File

@@ -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;

4
unsupported/Eigen/CXX11/src/Tensor/TensorDeviceThreadPool.h
View File

@@ -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.

5
unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
View File

@@ -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;

30
unsupported/Eigen/CXX11/src/Tensor/TensorFunctors.h
View File

@@ -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 {