Fault-tolerance and energy have become important design issues in multiprocessor system-on-chips (SoCs) with the technology scaling and the proUferation of battery-pow�red mul tiprocessor SoCs. This paper proposed �n energy effiCl�t fault tolerance task allocation scheme for multiprocessor SoCs ID real time energy harvesting systems. The proposed fault-tolerance scheme is based on the principle of the primiarylbackup task scheduling, and can tolerate at most one single transient fault.Extensive simulated experiment shows that the proposed scheme can save up to 30 % energy consumption and reduce the miss ratio to about 10 % in the presence of faults.