Group Algorithms not supported on host device

Question

Hi so I want to run a parallel reduction operation on my host device.

When I compile using clang++ -fsycl it compiles fine but when I run it I get the following:

terminate called after throwing an instance of 'cl::sycl::runtime_error'
  what():  Group algorithms are not supported on host device. -33 (CL_INVALID_DEVICE) 

This is my parallel reduction operation, which works fine on my GPU:

#include "ddot.hpp"
#include <CL/sycl.hpp>

using namespace sycl;
int ddot (sycl::queue& q, const int n, const double * const x, const double * const y, 
      double * const result, double & time_allreduce)
{
  
    // Buffer with just 1 element to get the reduction results
    double sumResult = 0.0;
    buffer<double> sumBuf { &sumResult, 1 };

    sycl::buffer X(x, sycl::range<1> (n));
    sycl::buffer Y(y, sycl::range<1> (n)); 

    q.submit([&](handler& cgh) {
      sycl::accessor xAcc{X, cgh};
      sycl::accessor yAcc{Y, cgh};

      auto sumReduction = reduction(sumBuf, cgh, plus<>());

      
      unsigned long size = static_cast<unsigned long>(n);

      cgh.parallel_for(range<1>(size), sumReduction,
                      [=](id<1> idx, auto& sum) {
                          sum +=  xAcc[idx] * yAcc[idx];
                      });
    });
    q.wait();

    *result = sumBuf.get_host_access()[0];
    return(0);
}