diff options
| author |  Rasmus Munk Larsen <rmlarsen@google.com> | 2018-09-13 16:20:57 -0700 |
|---|---|---|
| committer | Rasmus Munk Larsen <rmlarsen@google.com> | 2018-09-13 16:20:57 -0700 |
| commit | 0db590d22db198154f4302d85fbbd892316d36da (patch) | |
| tree | f84f6682bc909955e1c6e460fdcaea983fdb3851 | |
| parent | b3f4c067d96ccac919a2789113c3ac87eda43a00 (diff) | |
Backed out changeset 01197e44527941c95f9a63e4f60ab3a989f12cbe
| -rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h | 2 | ||||
| -rw-r--r-- | unsupported/test/cxx11_tensor_executor.cpp | 8 |
2 files changed, 6 insertions, 4 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h b/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h index 8d93aacee..e8c47c5b5 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h @@ -1205,6 +1205,7 @@ struct TensorEvaluator<const TensorReductionOp<Op, Dims, ArgType, MakePointer_>, const Index max_coeff_count, const DSizes<Index, NumInputDims>& input_slice_sizes, DSizes<Index, NumInputDims>* target_input_block_sizes) const { + typedef typename internal::packet_traits<Scalar>::type Packet; 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 @@ -1232,6 +1233,7 @@ struct TensorEvaluator<const TensorReductionOp<Op, Dims, ArgType, MakePointer_>, } else if (!first_preserved_dim_allocated) { // TODO(andydavis) Include output block size in this L1 working set // calculation. + const Index allocated = max_coeff_count - coeff_to_allocate; const Index alloc_size = numext::maxi( static_cast<Index>(1), coeff_to_allocate / reducer_overhead); (*target_input_block_sizes)[dim] = diff --git a/unsupported/test/cxx11_tensor_executor.cpp b/unsupported/test/cxx11_tensor_executor.cpp index 1bb99854c..8639e7b38 100644 --- a/unsupported/test/cxx11_tensor_executor.cpp +++ b/unsupported/test/cxx11_tensor_executor.cpp @@ -27,7 +27,7 @@ static array<Index, NumDims> RandomDims(int min_dim = 1, int max_dim = 20) { dims[i] = internal::random<int>(min_dim, max_dim); } return dims; -} +}; template <typename T, int NumDims, typename Device, bool Vectorizable, bool Tileable, int Layout> @@ -117,7 +117,7 @@ static void test_execute_broadcasting(Device d) for (Index i = 0; i < dst.dimensions().TotalSize(); ++i) { VERIFY_IS_EQUAL(dst.coeff(i), golden.coeff(i)); } -} +}; template <typename T, int NumDims, typename Device, bool Vectorizable, bool Tileable, int Layout> @@ -155,7 +155,7 @@ static void test_execute_chipping_rvalue(Device d) { TEST_CHIPPING(5) #undef TEST_CHIPPING -} +}; template <typename T, int NumDims, typename Device, bool Vectorizable, bool Tileable, int Layout> @@ -207,7 +207,7 @@ static void test_execute_chipping_lvalue(Device d) { TEST_CHIPPING(5) #undef TEST_CHIPPING -} +}; template <typename T, int NumDims, typename Device, bool Vectorizable, bool Tileable, int Layout> |