diff options
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h')
| -rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h b/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h index ac6717977..b148dae39 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h @@ -174,6 +174,7 @@ class TensorCostModel { static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE int numThreads( double output_size, const TensorOpCost& cost_per_coeff, int max_threads) { double cost = totalCost(output_size, cost_per_coeff); + double threads = (cost - kStartupCycles) / kPerThreadCycles + 0.9; // Make sure we don't invoke undefined behavior when we convert to an int. threads = numext::mini<double>(threads, GenericNumTraits<int>::highest()); return numext::mini(max_threads, numext::maxi<int>(1, threads)); |