diff options
author | Artem Belevich <tra@google.com> | 2019-12-09 11:10:29 -0800 |
---|---|---|
committer | Artem Belevich <tra@google.com> | 2019-12-09 11:10:29 -0800 |
commit | 8056a05b5485442ebc5c087a25f8ee027eb9a338 (patch) | |
tree | d0e01d0489995f507255db4f8f60a825fec508a9 /unsupported/Eigen/CXX11/src/Tensor | |
parent | dbb703d44e4ccc27f3d467adfecb49ac5ca21426 (diff) |
Undo the block size change.
.z *is* used by the EigenContractionKernelInternal().
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor')
-rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorContractionGpu.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorContractionGpu.h b/unsupported/Eigen/CXX11/src/Tensor/TensorContractionGpu.h index 2a224eddf..bb990b378 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorContractionGpu.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorContractionGpu.h @@ -1335,7 +1335,7 @@ struct TensorEvaluator<const TensorContractionOp<Indices, LeftArgType, RightArgT const Index m_blocks = (m + 63) / 64; const Index n_blocks = (n + 63) / 64; const dim3 num_blocks(m_blocks, n_blocks, 1); - const dim3 block_size(8, 8, 1); + const dim3 block_size(8, 8, 8); LAUNCH_GPU_KERNEL((EigenContractionKernel<Scalar, Index, LhsMapper, RhsMapper, OutputMapper>), num_blocks, block_size, 0, device, lhs, rhs, output, m, n, k); } }; |