我刚用了vs2013 + cuda 6.5 编译一个程序出现如下错误，怎讲解决啊？
F:\FFT_test_cuda6.5\Trove_test\Trove_test>“C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\bin\nvcc.exe” -gencode=arch=compute_35,code="sm_35,compute_35" --use-local-env --cl-version 2013 -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\bin” -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include" --keep-dir Release -maxrregcount=0 --machine 32 --compile -cudart static -DWIN32 -DNDEBUG -D_CONSOLE -D_MBCS -Xcompiler “/EHsc /W3 /nologo /O2 /Zi /MD " -o Release\benchmark.cu.obj “F:\FFT_test_cuda6.5\Trove_test\Trove_test\benchmark.cu”
1> benchmark.cu
1>C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/detail/pointer.inl(73): error C2244: “thrust::pointer<Element,Tag,Reference,Derived>::dereference”: 无法将函数定义与现有的声明匹配
1> C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/detail/pointer.h(132) : 参见“thrust::pointer<Element,Tag,Reference,Derived>::dereference”的声明
1> 定义
1> ‘pointer<Element,Tag,Reference,Derived>::super_t::reference thrust::pointer<Element,Tag,Reference,Derived>::dereference(void) const’
1> 现有声明
1> ‘::thrust::detail::pointer_base<Element,Tag,Reference,Derived>::type::reference thrust::pointer<Element,Tag,Reference,Derived>::dereference(void) const’
1>C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/iterator/detail/zip_iterator.inl(70): error C2244: “thrust::zip_iterator::dereference”: 无法将函数定义与现有的声明匹配
1> C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/iterator/zip_iterator.h(190) : 参见“thrust::zip_iterator::dereference”的声明
1> 定义
1> ‘zip_iterator::super_t::reference thrust::zip_iterator::dereference(void) const’
1> 现有声明
1> ‘::thrust::detail::zip_iterator_base::type::reference thrust::zip_iterator::dereference(void) const’
1>C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/iterator/detail/zip_iterator.inl(97): error C2244: “thrust::zip_iterator::advance”: 无法将函数定义与现有的声明匹配
1> C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/iterator/zip_iterator.h(201) : 参见“thrust::zip_iterator::advance”的声明
1> 定义
1> ‘void thrust::zip_iterator::advance(zip_iterator::super_t::difference_type)’
1> 现有声明
1> ‘void thrust::zip_iterator::advance(::thrust::detail::zip_iterator_base::type::difference_type)’
1>C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include\thrust/iterator/detail/reverse_iterator.inl(97): error C2244: “thrust::reverse_iterator::distance_to”: 无法将函数定义与现有的声明匹配
1> 定义
1> ‘detail::reverse_iterator_base::type::difference_type thrust::reverse_iterator::distance_to(const thrust::reverse_iterator &) const’
1> 现有声明
1> ‘reverse_iterator::super_t::difference_type thrust::reverse_iterator::distance_to(const thrust::reverse_iterator &) const’
1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V120\BuildCustomizations\CUDA 6.5.targets(593,9): error MSB3721: 命令““C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\bin\nvcc.exe” -gencode=arch=compute_35,code="sm_35,compute_35" --use-local-env --cl-version 2013 -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\bin” -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include” -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include" --keep-dir Release -maxrregcount=0 --machine 32 --compile -cudart static -DWIN32 -DNDEBUG -D_CONSOLE -D_MBCS -Xcompiler "/EHsc /W3 /nologo /O2 /Zi /MD " -o Release\benchmark.cu.obj “F:\FFT_test_cuda6.5\Trove_test\Trove_test\benchmark.cu””已退出，返回代码为 2。
1>
1>生成失败。