A novel approach to parallelize the well-known Hoshen-Kopelman algorithm has been chosen, suitable for simulating huge lattices in high dimensions on massively-parallel computers with distributed memory and message passing. This method consists of domain decomposition of the simulated lattice into strips perpendicular to the hyperplane of investigation that is used in the Hoshen-Kopelman algorithm. Systems of world record sizes, up to L = 4000256 in two dimensions, L = 20224 in three, and L = 1036 in four, gave precise estimates for the Fisher exponent τ , the corrections to scaling ∆1, and for the critical number density nc.Percolation is a thoroughly studied model in statistical physics [2]. The algorithm invented by Hoshen and Kopelman in 1976 allows for examining large percolation lattices using Monte Carlo methods [3]. Unfortunately, this algorithm was invented for traditional sequential computers, and implementation on modern parallel computers is far from trivial.The normal way to parallelize an algorithm which works on regular data structures is domain decomposition. In this case, the investigated lattice is cut into strips, and each processor is assigned one such strip for investigation. As the Hoshen-Kopelman algorithm investigates the lattice hyperplane by hyperplane (line by line in two dimensions; plane by plane in three dimensions), various ways of domain decomposition can be characterized by this hyperplane: for example, strips parallel or perpendicular to that plane.The easiest way would be to choose parallel strips, as in that case the simulation of each strip can be carried out locally on each processor, only after that communication is neccessary (exchanging the borders). Unfortunately, this means that each processor has to store a full hyperplane ofsystem. In two dimensions, this no problem at all, but in higher dimensions this limits the size of systems that can be simulated. When decomposing the system in perpendicular strips, each processor has to store only a part of the hyperplane, and thus larger system sizes can be 1