NumericT diff(std::vector<std::vector<NumericT> > const & A1, viennacl::matrix<NumericT> const & A2) { std::vector<NumericT> host_values(A2.internal_size()); for (std::size_t i=0; i<A2.size1(); ++i) for (std::size_t j=0; j<A2.size2(); ++j) host_values[i*A2.internal_size2() + j] = A1[i][j]; std::vector<NumericT> device_values(A2.internal_size()); viennacl::fast_copy(A2, &device_values[0]); viennacl::vector<NumericT> vcl_device_values(A2.internal_size()); // workaround to avoid code duplication viennacl::copy(device_values, vcl_device_values); return diff(host_values, vcl_device_values); }
void init_random(viennacl::matrix<T, F> & M) { std::vector<T> cM(M.internal_size()); for (std::size_t i = 0; i < M.size1(); ++i) for (std::size_t j = 0; j < M.size2(); ++j) cM[F::mem_index(i, j, M.internal_size1(), M.internal_size2())] = T(rand())/T(RAND_MAX); viennacl::fast_copy(&cM[0],&cM[0] + cM.size(),M); }
float matrix_compare(viennacl::matrix<ScalarType>& res, viennacl::matrix<ScalarType>& ref) { std::vector<ScalarType> res_std(res.internal_size()); std::vector<ScalarType> ref_std(ref.internal_size()); viennacl::fast_copy(res, &res_std[0]); viennacl::fast_copy(ref, &ref_std[0]); float diff = 0.0; float mx = 0.0; for(std::size_t i = 0; i < res_std.size(); i++) { diff = std::max(diff, std::abs(res_std[i] - ref_std[i])); mx = std::max(mx, res_std[i]); } return diff / mx; }
viennacl::vector_range<viennacl::vector_base<T> > sharedVector(){ viennacl::vector_base<T> tmp(ptr_matrix->handle(), ptr_matrix->internal_size(), 0, 1); viennacl::vector_range<viennacl::vector_base<T> > v_sub(tmp, r); return v_sub; }