dpct giving error in thrust files

Shukla__Gagandeep — Fri, 05 Jun 2020 11:33:05 GMT
Hi,
I am trying to convert h2o4gpu code using dpct and it is giving following errors while parsing thrust files. Is there any solution to these errors.
File I am trying to convert is src/gpu/h2o4gpuglm.cu. Though I received similar in many other files that include thrust library files.
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu>dpct --cuda-include-path="C:\nvcc\include" --extra-arg="-I.\..\include" --extra-arg="-I.\include"  --extra-arg="-D_CRT_SECURE_NO_WARNINGS" --out-root=dpct h2o4gpuglm.cu
NOTE: Could not auto-detect compilation database for file 'h2o4gpuglm.cu' in 'C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu' or any parent directory.
Processing: C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:27:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cuda_utils.h:7:
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cuda_utils2.h:42:9: warning: 'CUDACHECK' macro redefined [-Wmacro-redefined]
#define CUDACHECK(cmd) \
        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cuda_utils2.h:9:9: note: previous definition is here
#define CUDACHECK(cmd)                                        \
        ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:29:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.h:240:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.inl:22:
In file included from C:\nvcc\include\thrust\detail\allocator\copy_construct_range.h:46:
In file included from C:\nvcc\include\thrust\detail\allocator\copy_construct_range.inl:22:
In file included from C:\nvcc\include\thrust\tuple.h:34:
C:\nvcc\include\thrust\detail\tuple.inl:256:20: error: implicit instantiation of undefined template 'thrust::device_reference<const double>'
  stored_head_type head;
                   ^
C:\nvcc\include\thrust\tuple.h:198:12: note: in instantiation of template class 'thrust::detail::cons<thrust::device_reference<const double>, thrust::detail::cons<thrust::device_reference<const double>, thrust::null_type> >' requested here
    public detail::map_tuple_to_cons<T0, T1, T2, T3, T4, T5, T6, T7, T8, T9>::type
           ^
C:\nvcc\include\thrust\tuple.h:90:52: note: in instantiation of template class 'thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>' requested here
  static const int value = 1 + tuple_size<typename T::tail_type>::value;
                                                   ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:299:14: note: in instantiation of template class 'thrust::tuple_size<thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
        (i < tuple_size<Tuple>::value),
             ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:309:20: note: in instantiation of template class 'thrust::detail::zip_iterator_base_ns::tuple_elements_helper<0, thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
  typedef typename tuple_elements_helper<0,Tuple>::type T0;
                   ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:336:14: note: in instantiation of template class 'thrust::detail::zip_iterator_base_ns::tuple_elements<thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
    typename elements::T0,
             ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:365:44: note: in instantiation of template class 'thrust::detail::zip_iterator_base_ns::tuple_of_iterator_references<thrust::tuple<thrust::device_ptr<const double>, thrust::device_ptr<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
    typedef typename zip_iterator_base_ns::tuple_of_iterator_references<IteratorTuple>::type reference;
                                           ^
C:\nvcc\include\thrust\iterator\zip_iterator.h:141:22: note: in instantiation of template class 'thrust::detail::zip_iterator_base<thrust::tuple<thrust::device_ptr<const double>, thrust::device_ptr<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
    : public detail::zip_iterator_base<IteratorTuple>::type
                     ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:729:7: note: in instantiation of template class 'thrust::zip_iterator<thrust::tuple<thrust::device_ptr<const double>, thrust::device_ptr<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
      thrust::make_zip_iterator(thrust::make_tuple(
      ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:367:4: note: in instantiation of function template specialization 'ProjSubgradEval<double>' requested here
                        ProjSubgradEval(g_gpu, xprev.data, x.data, xtemp.data);
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:29:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.h:240:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.inl:22:
In file included from C:\nvcc\include\thrust\detail\allocator\copy_construct_range.h:46:
In file included from C:\nvcc\include\thrust\detail\allocator\copy_construct_range.inl:22:
In file included from C:\nvcc\include\thrust\tuple.h:34:
C:\nvcc\include\thrust\detail\tuple.inl:373:20: error: implicit instantiation of undefined template 'thrust::device_reference<const double>'
  stored_head_type head;
                   ^
C:\nvcc\include\thrust\detail\tuple.inl:257:13: note: in instantiation of template class 'thrust::detail::cons<thrust::device_reference<const double>, thrust::null_type>' requested here
  tail_type tail;
            ^
C:\nvcc\include\thrust\tuple.h:198:12: note: in instantiation of template class 'thrust::detail::cons<thrust::device_reference<const double>, thrust::detail::cons<thrust::device_reference<const double>, thrust::null_type> >' requested here
    public detail::map_tuple_to_cons<T0, T1, T2, T3, T4, T5, T6, T7, T8, T9>::type
           ^
C:\nvcc\include\thrust\tuple.h:90:52: note: in instantiation of template class 'thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>' requested here
  static const int value = 1 + tuple_size<typename T::tail_type>::value;
                                                   ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:299:14: note: in instantiation of template class 'thrust::tuple_size<thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
        (i < tuple_size<Tuple>::value),
             ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:309:20: note: in instantiation of template class 'thrust::detail::zip_iterator_base_ns::tuple_elements_helper<0, thrust::tuple<thrust::device_reference<const double>, thrust::device_reference<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
  typedef typename tuple_elements_helper<0,Tuple>::type T0;
                   ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:336:14: note: (skipping 1 context in backtrace; use -ftemplate-backtrace-limit=0 to see all)
    typename elements::T0,
             ^
C:\nvcc\include\thrust\iterator\detail\zip_iterator_base.h:365:44: note: in instantiation of template class 'thrust::detail::zip_iterator_base_ns::tuple_of_iterator_references<thrust::tuple<thrust::device_ptr<const double>, thrust::device_ptr<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
    typedef typename zip_iterator_base_ns::tuple_of_iterator_references<IteratorTuple>::type reference;
                                           ^
C:\nvcc\include\thrust\iterator\zip_iterator.h:141:22: note: in instantiation of template class 'thrust::detail::zip_iterator_base<thrust::tuple<thrust::device_ptr<const double>, thrust::device_ptr<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
    : public detail::zip_iterator_base<IteratorTuple>::type
                     ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:729:7: note: in instantiation of template class 'thrust::zip_iterator<thrust::tuple<thrust::device_ptr<const double>, thrust::device_ptr<const double>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type> >' requested here
      thrust::make_zip_iterator(thrust::make_tuple(
      ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:367:4: note: in instantiation of function template specialization 'ProjSubgradEval<double>' requested here
                        ProjSubgradEval(g_gpu, xprev.data, x.data, xtemp.data);
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:700:7: error: no matching conversion for functional-style cast from 'double' to 'ProxEvalF<double>'
      ProxEvalF<T>(rho));
      ^~~~~~~~~~~~~~~~
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:443:3: note: in instantiation of function template specialization 'ProxEval<double>' requested here
                ProxEval(g_gpu, _rho, x.data, x12.data); // Evaluate g(rho,x)->x12 (x^{1/2} in paper)
                ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:687:8: note: candidate constructor (the implicit copy constructor) not viable: no known conversion from 'double' to 'const ProxEvalF<double>' for 1st argument
struct ProxEvalF : thrust::binary_function<FunctionObj<T>, T, T> {
       ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:687:8: note: candidate constructor (the implicit move constructor) not viable: no known conversion from 'double' to 'ProxEvalF<double>' for 1st argument
struct ProxEvalF : thrust::binary_function<FunctionObj<T>, T, T> {
       ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:689:14: note: candidate constructor not viable: call to __device__ function from __host__ function
  __device__ ProxEvalF(T rho) : rho(rho) { }
             ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:29:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.h:240:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.inl:22:
In file included from C:\nvcc\include\thrust\detail\allocator\copy_construct_range.h:46:
In file included from C:\nvcc\include\thrust\detail\allocator\copy_construct_range.inl:26:
In file included from C:\nvcc\include\thrust\for_each.h:279:
In file included from C:\nvcc\include\thrust\detail\for_each.inl:27:
In file included from C:\nvcc\include\thrust\system\detail\adl\for_each.h:42:
In file included from C:\nvcc\include\thrust\system\cuda\detail\for_each.h:34:
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    return op(input);
              ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:290:32: note: in instantiation of member function 'thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >::operator[]' requested here
            thread_aggregate = d_wrapped_in[block_offset + thread_offset];
                               ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:322:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeTile<1, 0>' requested here
            ConsumeTile<true>(thread_aggregate, even_share.block_offset, valid_items, Int2Type<false>(), can_vectorize);
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:360:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeRange<0>' requested here
            ConsumeRange(even_share, Int2Type<true && ATTEMPT_VECTORIZATION>()) :
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\device\dispatch\dispatch_reduce.cuh:141:78: note: in instantiation of member function 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeRange' requested here
    OutputT block_aggregate = AgentReduceT(temp_storage, d_in, reduction_op).ConsumeRange(
                                                                             ^
C:\nvcc\include\thrust\system\cuda\detail\cub\device\dispatch\dispatch_reduce.cuh:599:17: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::DeviceReduceSingleTileKernel<thrust::cuda_cub::cub::DeviceReducePolicy<double, int, thrust::plus<double> >::Policy600, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double>, double>' requested here
                DeviceReduceSingleTileKernel<MaxPolicyT, InputIteratorT, OutputIteratorT, OffsetT, ReductionOpT, OutputT>);
                ^
C:/nvcc/include\thrust/system/cuda/detail/cub/device/dispatch/../../util_device.cuh:332:28: note: (skipping 10 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
        return op.template Invoke<PolicyT>();
                           ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:326:15: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    reference operator[](difference_type n) const
              ^
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator[]' requested here
    return op(input);
              ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:290:32: note: in instantiation of member function 'thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >::operator[]' requested here
            thread_aggregate = d_wrapped_in[block_offset + thread_offset];
                               ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:322:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeTile<1, 0>' requested here
            ConsumeTile<true>(thread_aggregate, even_share.block_offset, valid_items, Int2Type<false>(), can_vectorize);
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:360:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeRange<0>' requested here
            ConsumeRange(even_share, Int2Type<true && ATTEMPT_VECTORIZATION>()) :
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\device\dispatch\dispatch_reduce.cuh:141:78: note: in instantiation of member function 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeRange' requested here
    OutputT block_aggregate = AgentReduceT(temp_storage, d_in, reduction_op).ConsumeRange(
                                                                             ^
C:\nvcc\include\thrust\system\cuda\detail\cub\device\dispatch\dispatch_reduce.cuh:599:17: note: (skipping 11 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
                DeviceReduceSingleTileKernel<MaxPolicyT, InputIteratorT, OutputIteratorT, OffsetT, ReductionOpT, OutputT>);
                ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:328:14: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
      return *(this->derived() + n);
             ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:308:15: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    reference operator*() const
              ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:328:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(this->derived() + n);
             ^
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator[]' requested here
    return op(input);
              ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:290:32: note: in instantiation of member function 'thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >::operator[]' requested here
            thread_aggregate = d_wrapped_in[block_offset + thread_offset];
                               ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:322:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeTile<1, 0>' requested here
            ConsumeTile<true>(thread_aggregate, even_share.block_offset, valid_items, Int2Type<false>(), can_vectorize);
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:360:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeRange<0>' requested here
            ConsumeRange(even_share, Int2Type<true && ATTEMPT_VECTORIZATION>()) :
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\device\dispatch\dispatch_reduce.cuh:141:78: note: (skipping 12 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
    OutputT block_aggregate = AgentReduceT(temp_storage, d_in, reduction_op).ConsumeRange(
                                                                             ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:14: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
      return iterator_core_access::dereference(this->derived());
             ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:126:39: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    static typename Facade::reference dereference(Facade const& f)
                                      ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:36: note: in instantiation of function template specialization 'thrust::iterator_core_access::dereference<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> > >' requested here
      return iterator_core_access::dereference(this->derived());
                                   ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:328:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(this->derived() + n);
             ^
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator[]' requested here
    return op(input);
              ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:290:32: note: in instantiation of member function 'thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >::operator[]' requested here
            thread_aggregate = d_wrapped_in[block_offset + thread_offset];
                               ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:322:13: note: in instantiation of function template specialization 'thrust::cuda_cub::cub::AgentReduce<thrust::cuda_cub::cub::AgentReducePolicy<64, 8, 2, thrust::cuda_cub::cub::BLOCK_REDUCE_RAKING, thrust::cuda_cub::cub::LOAD_DEFAULT>, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, double *, int, thrust::plus<double> >::ConsumeTile<1, 0>' requested here
            ConsumeTile<true>(thread_aggregate, even_share.block_offset, valid_items, Int2Type<false>(), can_vectorize);
            ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:360:13: note: (skipping 13 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
            ConsumeRange(even_share, Int2Type<true && ATTEMPT_VECTORIZATION>()) :
            ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:128:16: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
      return f.dereference();
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:16:
In file included from C:\nvcc\include\thrust\inner_product.h:263:
In file included from C:\nvcc\include\thrust\detail\inner_product.inl:26:
In file included from C:\nvcc\include\thrust\system\detail\generic\inner_product.h:58:
In file included from C:\nvcc\include\thrust\system\detail\generic\inner_product.inl:21:
In file included from C:\nvcc\include\thrust\transform_reduce.h:197:
In file included from C:\nvcc\include\thrust\detail\transform_reduce.inl:25:
In file included from C:\nvcc\include\thrust\system\detail\generic\transform_reduce.h:52:
In file included from C:\nvcc\include\thrust\system\detail\generic\transform_reduce.inl:19:
In file included from C:\nvcc\include\thrust\reduce.h:784:
In file included from C:\nvcc\include\thrust\detail\reduce.inl:26:
In file included from C:\nvcc\include\thrust\system\detail\generic\reduce_by_key.h:88:
In file included from C:\nvcc\include\thrust\system\detail\generic\reduce_by_key.inl:30:
In file included from C:\nvcc\include\thrust\scatter.h:422:
In file included from C:\nvcc\include\thrust\detail\scatter.inl:25:
In file included from C:\nvcc\include\thrust\system\detail\generic\scatter.h:80:
In file included from C:\nvcc\include\thrust\system\detail\generic\scatter.inl:22:
C:\nvcc\include\thrust\iterator\permutation_iterator.h:177:33: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    typename super_t::reference dereference() const
                                ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:128:16: note: in instantiation of member function 'thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >::dereference' requested here
      return f.dereference();
               ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:36: note: in instantiation of function template specialization 'thrust::iterator_core_access::dereference<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> > >' requested here
      return iterator_core_access::dereference(this->derived());
                                   ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:328:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(this->derived() + n);
             ^
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator[]' requested here
    return op(input);
              ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:290:32: note: in instantiation of member function 'thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >::operator[]' requested here
            thread_aggregate = d_wrapped_in[block_offset + thread_offset];
                               ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:322:13: note: (skipping 14 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
            ConsumeTile<true>(thread_aggregate, even_share.block_offset, valid_items, Int2Type<false>(), can_vectorize);
            ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:16:
In file included from C:\nvcc\include\thrust\inner_product.h:263:
In file included from C:\nvcc\include\thrust\detail\inner_product.inl:26:
In file included from C:\nvcc\include\thrust\system\detail\generic\inner_product.h:58:
In file included from C:\nvcc\include\thrust\system\detail\generic\inner_product.inl:21:
In file included from C:\nvcc\include\thrust\transform_reduce.h:197:
In file included from C:\nvcc\include\thrust\detail\transform_reduce.inl:25:
In file included from C:\nvcc\include\thrust\system\detail\generic\transform_reduce.h:52:
In file included from C:\nvcc\include\thrust\system\detail\generic\transform_reduce.inl:19:
In file included from C:\nvcc\include\thrust\reduce.h:784:
In file included from C:\nvcc\include\thrust\detail\reduce.inl:26:
In file included from C:\nvcc\include\thrust\system\detail\generic\reduce_by_key.h:88:
In file included from C:\nvcc\include\thrust\system\detail\generic\reduce_by_key.inl:30:
In file included from C:\nvcc\include\thrust\scatter.h:422:
In file included from C:\nvcc\include\thrust\detail\scatter.inl:25:
In file included from C:\nvcc\include\thrust\system\detail\generic\scatter.h:80:
In file included from C:\nvcc\include\thrust\system\detail\generic\scatter.inl:22:
C:\nvcc\include\thrust\iterator\permutation_iterator.h:179:14: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
      return *(m_element_iterator + *this->base());
             ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:308:15: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    reference operator*() const
              ^
C:\nvcc\include\thrust\iterator\permutation_iterator.h:179:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::device_ptr<double>, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(m_element_iterator + *this->base());
             ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:128:16: note: in instantiation of member function 'thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >::dereference' requested here
      return f.dereference();
               ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:36: note: in instantiation of function template specialization 'thrust::iterator_core_access::dereference<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> > >' requested here
      return iterator_core_access::dereference(this->derived());
                                   ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:328:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(this->derived() + n);
             ^
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator[]' requested here
    return op(input);
              ^
C:\nvcc\include\thrust\system\cuda\detail\cub\agent\agent_reduce.cuh:290:32: note: (skipping 15 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
            thread_aggregate = d_wrapped_in[block_offset + thread_offset];
                               ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:14: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
      return iterator_core_access::dereference(this->derived());
             ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:126:39: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
    static typename Facade::reference dereference(Facade const& f)
                                      ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:36: note: in instantiation of function template specialization 'thrust::iterator_core_access::dereference<thrust::device_ptr<double> >' requested here
      return iterator_core_access::dereference(this->derived());
                                   ^
C:\nvcc\include\thrust\iterator\permutation_iterator.h:179:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::device_ptr<double>, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(m_element_iterator + *this->base());
             ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:128:16: note: in instantiation of member function 'thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >::dereference' requested here
      return f.dereference();
               ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:36: note: in instantiation of function template specialization 'thrust::iterator_core_access::dereference<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> > >' requested here
      return iterator_core_access::dereference(this->derived());
                                   ^
C:\nvcc\include\thrust\iterator\iterator_facade.h:328:14: note: in instantiation of member function 'thrust::iterator_facade<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, double, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::device_reference<double>, long long>::operator*' requested here
      return *(this->derived() + n);
             ^
C:\nvcc\include\thrust\system\cuda\detail\util.h:311:15: note: (skipping 16 contexts in backtrace; use -ftemplate-backtrace-limit=0 to see all)
    return op(input);
              ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:128:16: error: implicit instantiation of undefined template 'thrust::device_reference<double>'
      return f.dereference();
               ^
C:\nvcc\include\thrust\device_ptr.h:37:28: note: template is declared here
template<typename T> class device_reference;
                           ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:29:
In file included from C:\nvcc\include\thrust\detail\contiguous_storage.h:240:
C:\nvcc\include\thrust\detail\contiguous_storage.inl:159:11: error: implicit instantiation of undefined template 'thrust::reference<unsigned char, thrust::pointer<unsigned char, thrust::cuda_cub::tag, thrust::use_default, thrust::use_default>, thrust::use_default>'
  return &*m_begin;
          ^
C:\nvcc\include\thrust\system\cuda\detail\reduce.h:966:65: note: in instantiation of member function 'thrust::detail::contiguous_storage<unsigned char, thrust::detail::no_throw_allocator<thrust::detail::temporary_allocator<unsigned char, thrust::cuda_cub::tag> > >::data' requested here
  T* ret_ptr = thrust::detail::aligned_reinterpret_cast<T*>(tmp.data().get());
                                                                ^
C:\nvcc\include\thrust\system\cuda\detail\reduce.h:1017:38: note: in instantiation of function template specialization 'thrust::cuda_cub::detail::reduce_n_impl<thrust::cuda_cub::tag, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, long long, double, thrust::plus<double> >' requested here
    return thrust::cuda_cub::detail::reduce_n_impl(
                                     ^
C:\nvcc\include\thrust\system\cuda\detail\transform_reduce.h:58:20: note: in instantiation of function template specialization 'thrust::cuda_cub::reduce_n<thrust::cuda_cub::tag, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, long long, double, thrust::plus<double> >' requested here
  return cuda_cub::reduce_n(policy,
                   ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\detail\reference_forward_declaration.h:25:84: note: template is declared here
template<typename Element, typename Pointer, typename Derived = use_default> class reference;
                                                                                   ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:308:15: error: implicit instantiation of undefined template 'thrust::reference<unsigned char, thrust::pointer<unsigned char, thrust::cuda_cub::tag, thrust::use_default, thrust::use_default>, thrust::use_default>'
    reference operator*() const
              ^
C:\nvcc\include\thrust\detail\contiguous_storage.inl:159:11: note: in instantiation of member function 'thrust::iterator_facade<thrust::detail::normal_iterator<thrust::pointer<unsigned char, thrust::cuda_cub::tag, thrust::use_default, thrust::use_default> >, unsigned char, thrust::cuda_cub::tag, thrust::random_access_traversal_tag, thrust::reference<unsigned char, thrust::pointer<unsigned char, thrust::cuda_cub::tag, thrust::use_default, thrust::use_default>, thrust::use_default>, long long>::operator*' requested here
  return &*m_begin;
          ^
C:\nvcc\include\thrust\system\cuda\detail\reduce.h:966:65: note: in instantiation of member function 'thrust::detail::contiguous_storage<unsigned char, thrust::detail::no_throw_allocator<thrust::detail::temporary_allocator<unsigned char, thrust::cuda_cub::tag> > >::data' requested here
  T* ret_ptr = thrust::detail::aligned_reinterpret_cast<T*>(tmp.data().get());
                                                                ^
C:\nvcc\include\thrust\system\cuda\detail\reduce.h:1017:38: note: in instantiation of function template specialization 'thrust::cuda_cub::detail::reduce_n_impl<thrust::cuda_cub::tag, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, long long, double, thrust::plus<double> >' requested here
    return thrust::cuda_cub::detail::reduce_n_impl(
                                     ^
C:\nvcc\include\thrust\system\cuda\detail\transform_reduce.h:58:20: note: in instantiation of function template specialization 'thrust::cuda_cub::reduce_n<thrust::cuda_cub::tag, thrust::cuda_cub::transform_input_iterator_t<double, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double> >, long long, double, thrust::plus<double> >' requested here
  return cuda_cub::reduce_n(policy,
                   ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:47:10: note: in instantiation of function template specialization 'thrust::cuda_cub::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return transform_reduce(thrust::detail::derived_cast(thrust::detail::strip_const(exec)), first, last, unary_op, init, binary_op);
         ^
C:\nvcc\include\thrust\detail\transform_reduce.inl:67:18: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::cuda_cub::tag, thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  return thrust::transform_reduce(select_system(system), first, last, unary_op, init, binary_op);
                 ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\include\cml\cml_blas.cuh:155:25: note: in instantiation of function template specialization 'thrust::transform_reduce<thrust::permutation_iterator<thrust::device_ptr<double>, thrust::transform_iterator<cml::strided_range<thrust::device_ptr<double> >::StrideF, thrust::counting_iterator<long long, thrust::use_default, thrust::use_default, thrust::use_default>, thrust::use_default, thrust::use_default> >, cml::Square<double>, double, thrust::plus<double> >' requested here
  T nrm2 = sqrt(thrust::transform_reduce(strided_x.begin(), strided_x.end(),
                        ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:453:23: note: in instantiation of function template specialization 'cml::blas_nrm2<double>' requested here
                                + _rel_tol * cml::blas_nrm2(hdl, &z)
                                                  ^
C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:989:16: note: in instantiation of member function 'h2o4gpu::H2O4GPU<double, h2o4gpu::MatrixDense<double>, h2o4gpu::ProjectorDirect<double, h2o4gpu::MatrixDense<double> > >::Solve' requested here
template class H2O4GPU<double, MatrixDense<double>,
               ^
C:\nvcc\include\thrust\detail\reference_forward_declaration.h:25:84: note: template is declared here
template<typename Element, typename Pointer, typename Derived = use_default> class reference;
                                                                                   ^
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu:4:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\solver\glm.h:77:
In file included from C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\include\prox_lib.h:14:
In file included from C:\nvcc\include\thrust\device_vector.h:25:
In file included from C:\nvcc\include\thrust\detail\vector_base.h:25:
In file included from C:\nvcc\include\thrust\iterator\detail\normal_iterator.h:25:
In file included from C:\nvcc\include\thrust\iterator\iterator_adaptor.h:36:
C:\nvcc\include\thrust\iterator\iterator_facade.h:310:14: error: implicit instantiation of undefined template 'thrust::reference<unsigned char, thrust::pointer<unsigned char, thrust::cuda_cub::tag, thrust::use_default, thrust::use_default>, thrust::use_default>'
      return iterator_core_access::dereference(this->derived());
             ^
C:\nvcc\include\thrust\detail\reference_forward_declaration.h:25:84: note: template is declared here
template<typename Element, typename Pointer, typename Derived = use_default> class reference;
                                                                                   ^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
1 warning and 20 errors generated when compiling for host.
Error while processing C:\Users\intel\Downloads\cuda code\h2o4gpu-master\src\gpu\h2o4gpuglm.cu.
dpct exited with code: -17 (Error: Cannot parse input file(s))
Any help is appreciated.
Gagan
topic dpct giving error in thrust files in Intel® oneAPI DPC++/C++ Compiler

dpct giving error in thrust files

Hi Gagan,

Re: dpct giving error in thrust files
