In this paper we propose an autonomous chaotic optimization algorithm, called Tornado, for high dimensional global optimization problems. The algorithm introduces advanced symmetrization, levelling and fine search strategies for an efficient and effective exploration of the search space and exploitation of the best found solutions. To our knowledge, this is the first accurate and fast autonomous chaotic algorithm solving large scale optimization problems. A panel of various benchmark problems with different properties was used to assess the performance of the proposed chaotic algorithm. The obtained results have shown the scalability of the algorithm in contrast to chaotic optimization algorithms encountered in the literature. Moreover, in comparison with some state-of-the-art metaheuristics (e.g. evolutionary algorithms, swarm intelligence), the computational results revealed that the proposed Tornado algorithm is an effective and efficient optimization algorithm. A panel of various benchmark problems with different properties was used to assess the performance of the proposed chaotic algorithm. The obtained results have shown the scalability of the algorithm in contrast to chaotic optimization algorithms encountered in the literature. Moreover, in comparison with some state-of-the-art metaheuristics (e.g. evolutionary algorithms, swarm intelligence), the computational results revealed that the proposed Tornado algorithm is an effective and efficient optimization algorithm.