/* Copyright 2015 The TensorFlow Authors. All Rights Reserved.
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
you may not use this file except in compliance with the License.
|
You may obtain a copy of the License at
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
Unless required by applicable law or agreed to in writing, software
|
distributed under the License is distributed on an "AS IS" BASIS,
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
See the License for the specific language governing permissions and
|
limitations under the License.
|
==============================================================================*/
|
|
#if GOOGLE_CUDA
|
#define EIGEN_USE_GPU
|
#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
|
#include "tensorflow/core/util/cuda_launch_config.h"
|
|
__global__ void AddOneKernel(const int* in, const int N, int* out) {
|
for (int i = blockIdx.x * blockDim.x + threadIdx.x; i < N;
|
i += blockDim.x * gridDim.x) {
|
out[i] = in[i] + 1;
|
}
|
}
|
|
void AddOneKernelLauncher(const int* in, const int N, int* out) {
|
TF_CHECK_OK(::tensorflow::CudaLaunchKernel(AddOneKernel, 32, 256, 0, nullptr,
|
in, N, out));
|
}
|
|
#endif
|
