$ cat bicgstab.cu
#include <cusp/csr_matrix.h>
#include <cusp/krylov/bicgstab.h>

#if defined(__cplusplus)
extern "C" {
#endif

void bicgstab_(int * device_I, int * device_J, float * device_V, float * device_x, float * device_b, int N, int NNZ){

    // *NOTE* raw pointers must be wrapped with thrust::device_ptr!
    thrust::device_ptr<int> wrapped_device_I(device_I);
    thrust::device_ptr<int> wrapped_device_J(device_J);
    thrust::device_ptr<float> wrapped_device_V(device_V);
    thrust::device_ptr<float> wrapped_device_x(device_x);
    thrust::device_ptr<float> wrapped_device_b(device_b);

    // use array1d_view to wrap the individual arrays
    typedef typename cusp::array1d_view< thrust::device_ptr<int> > DeviceIndexArrayView;
    typedef typename cusp::array1d_view< thrust::device_ptr<float> > DeviceValueArrayView;

    DeviceIndexArrayView row_indices (wrapped_device_I, wrapped_device_I + (N+1));
    DeviceIndexArrayView column_indices(wrapped_device_J, wrapped_device_J + NNZ);
    DeviceValueArrayView values (wrapped_device_V, wrapped_device_V + NNZ);
    DeviceValueArrayView x (wrapped_device_x, wrapped_device_x + N);
    DeviceValueArrayView b (wrapped_device_b, wrapped_device_b + N);

    // combine the three array1d_views into a csr_matrix_view
    typedef cusp::csr_matrix_view<DeviceIndexArrayView,
    DeviceIndexArrayView,
    DeviceValueArrayView> DeviceView;

    // construct a csr_matrix_view from the array1d_views
    DeviceView A(N, N, NNZ, row_indices, column_indices, values);

    // set stopping criteria:
    // iteration_limit = 100
    // relative_tolerance = 1e-5
    cusp::verbose_monitor<float> monitor(b, 100, 1e-5);

    // solve the linear system A * x = b with the Conjugate Gradient method
    cusp::krylov::bicgstab(A, x, b, monitor);

}

#if defined(__cplusplus)
}
#endif
$ cat bic.f90
program test

interface
  subroutine bicgstab_(dI, dJ, dV, dx, db, hN, hNNZ) bind(C)
    use, intrinsic :: ISO_C_BINDING, ONLY: C_INT
    implicit none
    integer(C_INT) :: dI,dJ,dV,dx,db,hN,hNNZ
  end subroutine bicgstab_
end interface

integer*4 dI,dJ
integer*4 dV,dx,db
integer*4 hN,hNNZ
call bicgstab_(dI, dJ, dV, dx, db, hN, hNNZ)

end program
$ ifort -c bic.f90
$ nvcc -c bicgstab.cu -o bicgstab.o -I/home-2/robertc/misc/cusp/cusplibrary-master
nvcc warning : The 'compute_10' and 'sm_10' architectures are deprecated, and may be removed in a future release.
$ ifort *.o -L/shared/apps/cuda/CUDA-v6.0.37/lib64 -lcudart  -o program
$