Three-dimensional integrated circuits (3D ICs) have become an emerging technology because of advantages of higher packaging density and more flexible in heterogeneous integration. However, due to the heat dissipation problem in 3D ICs, thermal issues must be considered when maximizing the throughput of 3D Multi-Core Processors (MCPs). Furthermore, since the thermal behavior of a core in 3D MCPs strongly depends on its location, a proper task allocation can reduce potential thermal problems and improve the throughput. In this thesis, to enable the possibility of on-line scheduling, we present a very high performance task allocation algorithm to solve the problem of throughput optimization under thermal constraints for 3D MCPs. The experimental results show our fast algorithm can finish in less than 1ms for 128 cores. Compared to solutions obtained from LINGO, our algorithm only has 0.85% throughput loss on average.