diff options
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h')
-rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h b/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h index 99a09c058..6ddf824e9 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h @@ -316,7 +316,7 @@ struct OuterReducer { #if defined(EIGEN_USE_GPU) && defined(__CUDACC__) template <int B, int N, typename S, typename R, typename I> -__global__ void FullReductionKernel(R, const S, I, typename S::CoeffReturnType*); +__global__ void FullReductionKernel(R, const S, I, typename S::CoeffReturnType*, unsigned int*); #ifdef EIGEN_HAS_CUDA_FP16 @@ -616,7 +616,7 @@ struct TensorEvaluator<const TensorReductionOp<Op, Dims, ArgType>, Device> template <typename S, typename O, bool V> friend struct internal::FullReducerShard; #endif #if defined(EIGEN_USE_GPU) && defined(__CUDACC__) - template <int B, int N, typename S, typename R, typename I> friend void internal::FullReductionKernel(R, const S, I, typename S::CoeffReturnType*); + template <int B, int N, typename S, typename R, typename I> friend void internal::FullReductionKernel(R, const S, I, typename S::CoeffReturnType*, unsigned int*); #ifdef EIGEN_HAS_CUDA_FP16 template <typename S, typename R, typename I> friend void internal::ReductionInitFullReduxKernelHalfFloat(R, const S, I, half2*); template <int B, int N, typename S, typename R, typename I> friend void internal::FullReductionKernelHalfFloat(R, const S, I, half*, half2*); |