在Ubuntu 18.04上，构建caffe失败，出现以下错误之一，例如“ cuda_runtime_api.h：2316：9：错误：尚未声明'cudaStreamCallback_t'”

如何解决在Ubuntu 18.04上，构建caffe失败，出现以下错误之一，例如“ cuda_runtime_api.h：2316：9：错误：尚未声明'cudaStreamCallback_t'”

我需要一些从源头制作咖啡的帮助。 我直接在Ubuntu 18.04 LTS部分上构建了指向this的caffe。一切正常，直到我输入时出现构建错误

$ make all -j32

和错误摘要

CXX src/caffe/layers/silence_layer.cpp

In file included from /usr/local/cuda/include/channel_descriptor.h:61:0,from /usr/local/cuda/include/cuda_runtime.h:95,from /usr/include/cudnn.h:64,from ./include/caffe/util/cudnn.hpp:5,from src/caffe/util/cudnn.cpp:2:
/usr/local/cuda/include/cuda_runtime_api.h:2248:25: error: expected ‘)’ before ‘*’ token
 typedef void (CUDART_CB *cudaStreamCallback_t)(cudaStream_t stream,cudaError_t status,void *userData);
                         ^
/usr/local/cuda/include/cuda_runtime_api.h:2316:9: error: ‘cudaStreamCallback_t’ has not been declared
         cudaStreamCallback_t callback,void *userData,unsigned int flags);
         ^~~~~~~~~~~~~~~~~~~~
/usr/local/cuda/include/cuda_runtime_api.h:2483:88: error: use of enum ‘cudaStreamCaptureMode’ without previous declaration
 extern __host__ cudaError_t CUDARTAPI cudaStreamBeginCapture(cudaStream_t stream,enum cudaStreamCaptureMode mode);
                                                                                        ^~~~~~~~~~~~~~~~~~~~~
/usr/local/cuda/include/cuda_runtime_api.h:2534:80: error: use of enum ‘cudaStreamCaptureMode’ without previous declaration
 extern __host__ cudaError_t CUDARTAPI cudaThreadExchangeStreamCaptureMode(enum cudaStreamCaptureMode *mode);

我的环境

$ uname -a
Linux svision 5.4.0-47-generic #51~18.04.1-Ubuntu SMP Sat Sep 5 14:35:50 UTC 2020 x86_64 x86_64 x86_64 GNU/Linux

$ g++ --version
g++ (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Copyright (C) 2017 Free Software Foundation,Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE

$cmake --version
cmake version 3.10.2

CMake suite maintained and supported by Kitware (kitware.com/cmake).

当然，下面是我的MakeFile：

## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers
USE_OPENCV := 1
# USE_LEVELDB := 0
# USE_LMDB := 0
# This code is taken from https://github.com/sh1r0/caffe-android-lib
USE_HDF5 := 1

# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
#   You should not set this flag if you will be reading LMDBs with any
#   possibility of simultaneous read and write
# ALLOW_LMDB_NOLOCK := 1

# Uncomment if you're using OpenCV 3
OPENCV_VERSION := 3

# To customize your choice of compiler,uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda-10.1
# On Ubuntu 14.04,if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0,comment the *_50 through *_61 lines for compatibility.
# For CUDA < 8.0,comment the *_60 and *_61 lines for compatibility.
# For CUDA >= 9.0,comment the *_20 and *_21 lines for compatibility.
CUDA_ARCH := \
        -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_52,code=sm_52 \
        -gencode arch=compute_60,code=sm_60 \
        -gencode arch=compute_61,code=sm_61 \
        -gencode arch=compute_61,code=compute_61

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := open
# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
# Leave commented to accept the defaults for your choice of BLAS
# (which should work)!
# BLAS_INCLUDE := /path/to/your/blas
# BLAS_LIB := /path/to/your/blas

# Homebrew puts openblas in a directory that is not on the standard search path
# BLAS_INCLUDE := $(shell brew --prefix openblas)/include
# BLAS_LIB := $(shell brew --prefix openblas)/lib

# This is required only if you will compile the matlab interface.
# MATLAB directory should contain the mex binary in /bin.
# MATLAB_DIR := /usr/local
# MATLAB_DIR := /Applications/MATLAB_R2012b.app

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
PYTHON_INCLUDE := /usr/include/python2.7 \
        /usr/lib/python2.7/dist-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location,sometimes it's in root.
# ANACONDA_HOME := $(HOME)/anaconda
# PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
        # $(ANACONDA_HOME)/include/python2.7 \
        # $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include

# Uncomment to use Python 3 (default is Python 2)
# PYTHON_LIBRARIES := boost_python3 python3.5m
# PYTHON_INCLUDE := /usr/include/python3.5m \
#                 /usr/lib/python3.5/dist-packages/numpy/core/include

# We need to be able to find libpythonX.X.so or .dylib.
PYTHON_LIB := /usr/lib
# PYTHON_LIB := $(ANACONDA_HOME)/lib

# Homebrew installs numpy in a non standard path (keg only)
# PYTHON_INCLUDE += $(dir $(shell python -c 'import numpy.core; print(numpy.core.__file__)'))/include
# PYTHON_LIB += $(shell brew --prefix numpy)/lib

# Uncomment to support layers written in Python (will link against Python libs)
# WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial/ /usr/local/cuda/include /usr/local/cuda-10.1/include
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/x86_64-linux-gnu/hdf5/serial/

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
# INCLUDE_DIRS += $(shell brew --prefix)/include
# LIBRARY_DIRS += $(shell brew --prefix)/lib

# NCCL acceleration switch (uncomment to build with NCCL)
# https://github.com/NVIDIA/nccl (last tested version: v1.2.3-1+cuda8.0)
# USE_NCCL := 1

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

# N.B. both build and distribute dirs are cleared on `make clean`
BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @

如果发现问题，请在 NVIDIA_CUDA-10.1_Samples / 1_Utilities / deviceQuery 中将Nvidia示例中的deviceQuery输出追加：

./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce RTX 2080 Ti"
  CUDA Driver Version / Runtime Version          10.2 / 10.1
  CUDA Capability Major/Minor version number:    7.5
  Total amount of global memory:                 11016 MBytes (11551571968 bytes)
  (68) Multiprocessors,( 64) CUDA Cores/MP:     4352 CUDA Cores
  GPU Max Clock rate:                            1635 MHz (1.63 GHz)
  Memory Clock rate:                             7000 Mhz
  Memory Bus Width:                              352-bit
  L2 Cache Size:                                 5767168 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072),2D=(131072,65536),3D=(16384,16384,16384)
  Maximum Layered 1D Texture Size,(num) layers  1D=(32768),2048 layers
  Maximum Layered 2D Texture Size,(num) layers  2D=(32768,32768),2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  1024
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,z): (1024,1024,64)
  Max dimension size of a grid size    (x,z): (2147483647,65535,65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 3 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Compute Preemption:            Yes
  Supports Cooperative Kernel Launch:            Yes
  Supports MultiDevice Co-op Kernel Launch:      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 8 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery,CUDA Driver = CUDART,CUDA Driver Version = 10.2,CUDA Runtime Version = 10.1,NumDevs = 1
Result = PASS