KOKKOS_INLINE_FUNCTION static void apply( const tensor_type & tensor , const MatrixValue * const a , const VectorValue * const x , VectorValue * const y ) { const size_type nk = tensor.num_k(); // Loop over k for ( size_type k = 0; k < nk; ++k) { const MatrixValue ak = a[k]; const VectorValue xk = x[k]; // Loop over j for this k const size_type nj = tensor.num_j(k); const size_type jBeg = tensor.j_begin(k); const size_type jEnd = jBeg + nj; for (size_type jEntry = jBeg; jEntry < jEnd; ++jEntry) { const size_type j = tensor.j_coord(jEntry); VectorValue tmp = a[j] * xk + ak * x[j]; // Loop over i for this k,j const size_type ni = tensor.num_i(jEntry); const size_type iBeg = tensor.i_begin(jEntry); const size_type iEnd = iBeg + ni; for (size_type iEntry = iBeg; iEntry < iEnd; ++iEntry) { const size_type i = tensor.i_coord(iEntry); y[i] += tensor.value(iEntry) * tmp; } } } }
static void apply( const tensor_type & tensor , const MatrixValue * const a , const VectorValue * const x , VectorValue * const y ) { const size_type nDim = tensor.dimension(); // Loop over i for ( size_type i = 0; i < nDim; ++i) { VectorValue ytmp = 0; // Loop over k for this i const size_type nk = tensor.num_k(i); const size_type kBeg = tensor.k_begin(i); const size_type kEnd = kBeg + nk; for (size_type kEntry = kBeg; kEntry < kEnd; ++kEntry) { const size_type k = tensor.k_coord(kEntry); const MatrixValue ak = a[k]; const VectorValue xk = x[k]; // Loop over j for this i,k const size_type nj = tensor.num_j(kEntry); const size_type jBeg = tensor.j_begin(kEntry); const size_type jEnd = jBeg + nj; for (size_type jEntry = jBeg; jEntry < jEnd; ++jEntry) { const size_type j = tensor.j_coord(jEntry); ytmp += tensor.value(jEntry) * ( a[j] * xk + ak * x[j] ); } } y[i] += ytmp ; } }