diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorContractionBlocking.h b/unsupported/Eigen/CXX11/src/Tensor/TensorContractionBlocking.h index 71fd19774..c51f3f8dd 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorContractionBlocking.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorContractionBlocking.h @@ -51,6 +51,10 @@ class TensorContractionBlocking { else { computeProductBlockingSizes(kc_, nc_, mc_, num_threads); } + + const int rhs_packet_size = internal::packet_traits::size; + kc_ = (rhs_packet_size <= 8 || kc_ <= rhs_packet_size) ? + kc_ : (kc_ / rhs_packet_size) * rhs_packet_size; } EIGEN_DEVICE_FUNC EIGEN_ALWAYS_INLINE StorageIndex kc() const { return kc_; }