/usr/include/caffe/util/device_alternate.hpp is in libcaffe-cpu-dev 1.0.0-6.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | #ifndef CAFFE_UTIL_DEVICE_ALTERNATE_H_
#define CAFFE_UTIL_DEVICE_ALTERNATE_H_
#ifdef CPU_ONLY // CPU-only Caffe.
#include <vector>
// Stub out GPU calls as unavailable.
#define NO_GPU LOG(FATAL) << "Cannot use GPU in CPU-only Caffe: check mode."
#define STUB_GPU(classname) \
template <typename Dtype> \
void classname<Dtype>::Forward_gpu(const vector<Blob<Dtype>*>& bottom, \
const vector<Blob<Dtype>*>& top) { NO_GPU; } \
template <typename Dtype> \
void classname<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top, \
const vector<bool>& propagate_down, \
const vector<Blob<Dtype>*>& bottom) { NO_GPU; } \
#define STUB_GPU_FORWARD(classname, funcname) \
template <typename Dtype> \
void classname<Dtype>::funcname##_##gpu(const vector<Blob<Dtype>*>& bottom, \
const vector<Blob<Dtype>*>& top) { NO_GPU; } \
#define STUB_GPU_BACKWARD(classname, funcname) \
template <typename Dtype> \
void classname<Dtype>::funcname##_##gpu(const vector<Blob<Dtype>*>& top, \
const vector<bool>& propagate_down, \
const vector<Blob<Dtype>*>& bottom) { NO_GPU; } \
#else // Normal GPU + CPU Caffe.
#include <cublas_v2.h>
#include <cuda.h>
#include <cuda_runtime.h>
#include <curand.h>
#include <driver_types.h> // cuda driver types
#ifdef USE_CUDNN // cuDNN acceleration library.
#include "caffe/util/cudnn.hpp"
#endif
//
// CUDA macros
//
// CUDA: various checks for different function calls.
#define CUDA_CHECK(condition) \
/* Code block avoids redefinition of cudaError_t error */ \
do { \
cudaError_t error = condition; \
CHECK_EQ(error, cudaSuccess) << " " << cudaGetErrorString(error); \
} while (0)
#define CUBLAS_CHECK(condition) \
do { \
cublasStatus_t status = condition; \
CHECK_EQ(status, CUBLAS_STATUS_SUCCESS) << " " \
<< caffe::cublasGetErrorString(status); \
} while (0)
#define CURAND_CHECK(condition) \
do { \
curandStatus_t status = condition; \
CHECK_EQ(status, CURAND_STATUS_SUCCESS) << " " \
<< caffe::curandGetErrorString(status); \
} while (0)
// CUDA: grid stride looping
#define CUDA_KERNEL_LOOP(i, n) \
for (int i = blockIdx.x * blockDim.x + threadIdx.x; \
i < (n); \
i += blockDim.x * gridDim.x)
// CUDA: check for error after kernel execution and exit loudly if there is one.
#define CUDA_POST_KERNEL_CHECK CUDA_CHECK(cudaPeekAtLastError())
namespace caffe {
// CUDA: library error reporting.
const char* cublasGetErrorString(cublasStatus_t error);
const char* curandGetErrorString(curandStatus_t error);
// CUDA: use 512 threads per block
const int CAFFE_CUDA_NUM_THREADS = 512;
// CUDA: number of blocks for threads.
inline int CAFFE_GET_BLOCKS(const int N) {
return (N + CAFFE_CUDA_NUM_THREADS - 1) / CAFFE_CUDA_NUM_THREADS;
}
} // namespace caffe
#endif // CPU_ONLY
#endif // CAFFE_UTIL_DEVICE_ALTERNATE_H_
|