diff options
| author |  Deven Desai <deven.desai.amd@gmail.com> | 2018-06-20 16:44:58 -0400 |
|---|---|---|
| committer | Deven Desai <deven.desai.amd@gmail.com> | 2018-06-20 16:44:58 -0400 |
| commit | 1bb6fa99a31d2dcf5431087d3f238e2dcca03084 (patch) | |
| tree | e62d41b8d6430849aea4bf97785a54488bf542d4 /unsupported/Eigen/CXX11/src/Tensor/TensorScan.h | |
| parent | cfdabbcc8f708c06da2bfa4e924edc25619f013a (diff) | |
merging the CUDA and HIP implementation for the Tensor directory and the unit tests
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor/TensorScan.h')
| -rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorScan.h | 8 |
1 files changed, 2 insertions, 6 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorScan.h b/unsupported/Eigen/CXX11/src/Tensor/TensorScan.h index 6d68e256f..39717efaa 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorScan.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorScan.h @@ -278,12 +278,8 @@ struct ScanLauncher<Self, Reducer, GpuDevice> { Index total_size = internal::array_prod(self.dimensions()); Index num_blocks = (total_size / self.size() + 63) / 64; Index block_size = 64; -#if defined(EIGEN_HIPCC) - hipLaunchKernelGGL(HIP_KERNEL_NAME(ScanKernel<Self, Reducer>), dim3(num_blocks), - dim3(block_size), 0, self.device().stream(), self, total_size, data); -#else - LAUNCH_CUDA_KERNEL((ScanKernel<Self, Reducer>), num_blocks, block_size, 0, self.device(), self, total_size, data); -#endif + + LAUNCH_GPU_KERNEL((ScanKernel<Self, Reducer>), num_blocks, block_size, 0, self.device(), self, total_size, data); } }; #endif // EIGEN_USE_GPU && (EIGEN_GPUCC) |