void syomv_microkernel(uview< const T, Abi, OA > A, uview< const T, Abi, OB > B, uview< T, Abi, OD > D, index_t l0, index_t k) noexcept
Symmetric off-diagonal block multiply. Single register block.
void syomv_register(view< const T, Abi, OA > A, view< const T, Abi, OB > B, view< T, Abi, OD > D) noexcept
Generalized matrix multiplication D = C ± A⁽ᵀ⁾ B⁽ᵀ⁾. Using register blocking.