Remove dead code from TensorReduction.h
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h b/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h
index ad14d82..5ca6940 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h
@@ -452,70 +452,6 @@
#endif
};
-template <typename Self, typename Op,
- bool Vectorizable =
- (Self::InputPacketAccess & Self::ReducerTraits::PacketAccess)>
-class BlockReducer {
- public:
- typedef typename Self::Index Index;
- typedef typename Self::Scalar Scalar;
- typedef typename Self::CoeffReturnType CoeffReturnType;
- typedef typename Self::PacketReturnType PacketReturnType;
- explicit BlockReducer(const Op& reducer) : op_(reducer) {
- accum_ = op_.initialize();
- }
- void Reduce(Index index, Index num_values_to_reduce, Scalar* data) {
- for (Index i = 0; i < num_values_to_reduce; ++i) {
- op_.reduce(data[index + i], &accum_);
- }
- }
- CoeffReturnType Finalize() { return op_.finalize(accum_); }
- PacketReturnType FinalizePacket() {
- // TODO(andydavis) This function should not be called for Scalar
- // reductions: clean this up or add an assert here.
- return PacketReturnType();
- }
-
- private:
- CoeffReturnType accum_;
- Op op_;
-};
-
-template <typename Self, typename Op>
-class BlockReducer<Self, Op, true> {
- public:
- typedef typename Self::Index Index;
- typedef typename Self::Scalar Scalar;
- typedef typename Self::CoeffReturnType CoeffReturnType;
- typedef typename Self::PacketReturnType PacketReturnType;
- static const Index PacketSize =
- internal::unpacket_traits<PacketReturnType>::size;
-
- explicit BlockReducer(const Op& reducer) : op_(reducer) {
- vaccum_ = op_.template initializePacket<PacketReturnType>();
- accum_ = op_.initialize();
- }
- void Reduce(Index index, Index num_values_to_reduce, Scalar* data) {
- const Index vectorized_size =
- (num_values_to_reduce / PacketSize) * PacketSize;
- for (Index i = 0; i < vectorized_size; i += PacketSize) {
- op_.reducePacket(
- internal::ploadt<PacketReturnType, Unaligned>(&data[index + i]),
- &vaccum_);
- }
- for (Index i = vectorized_size; i < num_values_to_reduce; ++i) {
- op_.reduce(data[index + i], &accum_);
- }
- }
- CoeffReturnType Finalize() { return op_.finalizeBoth(accum_, vaccum_); }
- PacketReturnType FinalizePacket() { return op_.finalizePacket(vaccum_); }
-
- private:
- PacketReturnType vaccum_;
- CoeffReturnType accum_;
- Op op_;
-};
-
} // end namespace internal
@@ -993,73 +929,6 @@
return startInput;
}
- EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE void GetInputCoordsForOutputIndex(
- Index index,
- DSizes<Index, NumInputDims>* coords) const {
- for (int i = 0; i < NumInputDims; ++i) {
- (*coords)[i] = 0;
- }
- if (static_cast<int>(Layout) == static_cast<int>(ColMajor)) {
- for (int i = NumOutputDims - 1; i > 0; --i) {
- const Index idx = index / m_fastOutputStrides[i];
- (*coords)[m_output_to_input_dim_map[i]] = idx;
- index -= idx * m_outputStrides[i];
- }
- (*coords)[m_output_to_input_dim_map[0]] = index;
- } else {
- for (int i = 0; i < NumOutputDims - 1; ++i) {
- const Index idx = index / m_fastOutputStrides[i];
- (*coords)[m_output_to_input_dim_map[i]] = idx;
- index -= idx * m_outputStrides[i];
- }
- (*coords)[m_output_to_input_dim_map[NumOutputDims-1]] = index;
- }
- }
-
- EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE void CalculateTargetInputBlockShape(
- const Index max_coeff_count,
- const DSizes<Index, NumInputDims>& input_slice_sizes,
- DSizes<Index, NumInputDims>* target_input_block_sizes) const {
- typedef internal::BlockReducer<Self, Op> BlockReducer;
- // TODO(andydavis) Compute reducer overhead correctly for the case where
- // we are preserving the inner most dimension, and a single reducer
- // reduces a packet's worth of output coefficients.
- const Index reducer_overhead = sizeof(BlockReducer) / sizeof(Scalar);
-
- Index coeff_to_allocate = max_coeff_count;
- bool first_preserved_dim_allocated = false;
- bool first_reduced_dim_allocated = false;
- for (int i = 0; i < NumInputDims; ++i) {
- const int dim = static_cast<int>(Layout) == static_cast<int>(ColMajor)
- ? i
- : NumInputDims - i - 1;
- (*target_input_block_sizes)[dim] = 1;
- if (m_reduced[dim]) {
- // TODO(andydavis) Consider allocating to multiple reduced dimensions.
- // Watch out for cases where reduced dimensions are not contiguous,
- // which induces scattered reads.
- if (!first_reduced_dim_allocated) {
- (*target_input_block_sizes)[dim] =
- numext::mini(input_slice_sizes[dim], coeff_to_allocate);
- coeff_to_allocate /= (*target_input_block_sizes)[dim];
- first_reduced_dim_allocated = true;
- }
- } else if (!first_preserved_dim_allocated) {
- // TODO(andydavis) Include output block size in this L1 working set
- // calculation.
- const Index alloc_size = numext::maxi(
- static_cast<Index>(1), coeff_to_allocate / reducer_overhead);
- (*target_input_block_sizes)[dim] =
- numext::mini(input_slice_sizes[dim], alloc_size);
- coeff_to_allocate = numext::maxi(
- static_cast<Index>(1),
- coeff_to_allocate /
- ((*target_input_block_sizes)[dim] * reducer_overhead));
- first_preserved_dim_allocated = true;
- }
- }
- }
-
// Bitmap indicating if an input dimension is reduced or not.
array<bool, NumInputDims> m_reduced;
// Dimensions of the output of the operation.
