void trsm_copy_microkernel(uview< const T, Abi, OA > A, uview< const T, Abi, OB > B, uview< T, Abi, OD > D, index_t k) noexcept
void trsm_copy_register(view< const T, Abi, OA > A, view< const T, Abi, OB > B, view< T, Abi, OD > D) noexcept
Triangular solve D = (A⁽ᵀ⁾)⁻¹ B⁽ᵀ⁾ where A⁽ᵀ⁾ is lower triangular.