/usr/include/caffe/util/cudnn.hpp is in libcaffe-cpu-dev 1.0.0~rc4-1.
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 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | #ifndef CAFFE_UTIL_CUDNN_H_
#define CAFFE_UTIL_CUDNN_H_
#ifdef USE_CUDNN
#include <cudnn.h>
#include "caffe/common.hpp"
#include "caffe/proto/caffe.pb.h"
#define CUDNN_VERSION_MIN(major, minor, patch) \
(CUDNN_VERSION >= (major * 1000 + minor * 100 + patch))
#define CUDNN_CHECK(condition) \
do { \
cudnnStatus_t status = condition; \
CHECK_EQ(status, CUDNN_STATUS_SUCCESS) << " "\
<< cudnnGetErrorString(status); \
} while (0)
inline const char* cudnnGetErrorString(cudnnStatus_t status) {
switch (status) {
case CUDNN_STATUS_SUCCESS:
return "CUDNN_STATUS_SUCCESS";
case CUDNN_STATUS_NOT_INITIALIZED:
return "CUDNN_STATUS_NOT_INITIALIZED";
case CUDNN_STATUS_ALLOC_FAILED:
return "CUDNN_STATUS_ALLOC_FAILED";
case CUDNN_STATUS_BAD_PARAM:
return "CUDNN_STATUS_BAD_PARAM";
case CUDNN_STATUS_INTERNAL_ERROR:
return "CUDNN_STATUS_INTERNAL_ERROR";
case CUDNN_STATUS_INVALID_VALUE:
return "CUDNN_STATUS_INVALID_VALUE";
case CUDNN_STATUS_ARCH_MISMATCH:
return "CUDNN_STATUS_ARCH_MISMATCH";
case CUDNN_STATUS_MAPPING_ERROR:
return "CUDNN_STATUS_MAPPING_ERROR";
case CUDNN_STATUS_EXECUTION_FAILED:
return "CUDNN_STATUS_EXECUTION_FAILED";
case CUDNN_STATUS_NOT_SUPPORTED:
return "CUDNN_STATUS_NOT_SUPPORTED";
case CUDNN_STATUS_LICENSE_ERROR:
return "CUDNN_STATUS_LICENSE_ERROR";
}
return "Unknown cudnn status";
}
namespace caffe {
namespace cudnn {
template <typename Dtype> class dataType;
template<> class dataType<float> {
public:
static const cudnnDataType_t type = CUDNN_DATA_FLOAT;
static float oneval, zeroval;
static const void *one, *zero;
};
template<> class dataType<double> {
public:
static const cudnnDataType_t type = CUDNN_DATA_DOUBLE;
static double oneval, zeroval;
static const void *one, *zero;
};
template <typename Dtype>
inline void createTensor4dDesc(cudnnTensorDescriptor_t* desc) {
CUDNN_CHECK(cudnnCreateTensorDescriptor(desc));
}
template <typename Dtype>
inline void setTensor4dDesc(cudnnTensorDescriptor_t* desc,
int n, int c, int h, int w,
int stride_n, int stride_c, int stride_h, int stride_w) {
CUDNN_CHECK(cudnnSetTensor4dDescriptorEx(*desc, dataType<Dtype>::type,
n, c, h, w, stride_n, stride_c, stride_h, stride_w));
}
template <typename Dtype>
inline void setTensor4dDesc(cudnnTensorDescriptor_t* desc,
int n, int c, int h, int w) {
const int stride_w = 1;
const int stride_h = w * stride_w;
const int stride_c = h * stride_h;
const int stride_n = c * stride_c;
setTensor4dDesc<Dtype>(desc, n, c, h, w,
stride_n, stride_c, stride_h, stride_w);
}
template <typename Dtype>
inline void createFilterDesc(cudnnFilterDescriptor_t* desc,
int n, int c, int h, int w) {
CUDNN_CHECK(cudnnCreateFilterDescriptor(desc));
#if CUDNN_VERSION_MIN(5, 0, 0)
CUDNN_CHECK(cudnnSetFilter4dDescriptor(*desc, dataType<Dtype>::type,
CUDNN_TENSOR_NCHW, n, c, h, w));
#else
CUDNN_CHECK(cudnnSetFilter4dDescriptor_v4(*desc, dataType<Dtype>::type,
CUDNN_TENSOR_NCHW, n, c, h, w));
#endif
}
template <typename Dtype>
inline void createConvolutionDesc(cudnnConvolutionDescriptor_t* conv) {
CUDNN_CHECK(cudnnCreateConvolutionDescriptor(conv));
}
template <typename Dtype>
inline void setConvolutionDesc(cudnnConvolutionDescriptor_t* conv,
cudnnTensorDescriptor_t bottom, cudnnFilterDescriptor_t filter,
int pad_h, int pad_w, int stride_h, int stride_w) {
CUDNN_CHECK(cudnnSetConvolution2dDescriptor(*conv,
pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
}
template <typename Dtype>
inline void createPoolingDesc(cudnnPoolingDescriptor_t* pool_desc,
PoolingParameter_PoolMethod poolmethod, cudnnPoolingMode_t* mode,
int h, int w, int pad_h, int pad_w, int stride_h, int stride_w) {
switch (poolmethod) {
case PoolingParameter_PoolMethod_MAX:
*mode = CUDNN_POOLING_MAX;
break;
case PoolingParameter_PoolMethod_AVE:
*mode = CUDNN_POOLING_AVERAGE_COUNT_INCLUDE_PADDING;
break;
default:
LOG(FATAL) << "Unknown pooling method.";
}
CUDNN_CHECK(cudnnCreatePoolingDescriptor(pool_desc));
#if CUDNN_VERSION_MIN(5, 0, 0)
CUDNN_CHECK(cudnnSetPooling2dDescriptor(*pool_desc, *mode,
CUDNN_PROPAGATE_NAN, h, w, pad_h, pad_w, stride_h, stride_w));
#else
CUDNN_CHECK(cudnnSetPooling2dDescriptor_v4(*pool_desc, *mode,
CUDNN_PROPAGATE_NAN, h, w, pad_h, pad_w, stride_h, stride_w));
#endif
}
template <typename Dtype>
inline void createActivationDescriptor(cudnnActivationDescriptor_t* activ_desc,
cudnnActivationMode_t mode) {
CUDNN_CHECK(cudnnCreateActivationDescriptor(activ_desc));
CUDNN_CHECK(cudnnSetActivationDescriptor(*activ_desc, mode,
CUDNN_PROPAGATE_NAN, Dtype(0)));
}
} // namespace cudnn
} // namespace caffe
#endif // USE_CUDNN
#endif // CAFFE_UTIL_CUDNN_H_
|