This paper examines our recent experiences and progress in porting an in-house magnetostatic finite-element analysis code, H3D, to multiple-instruction, multiple-data (MIMD) parallel computers using the distributed-memory, message-passing (DMMP) paradigm. Experiments with two different message-passing software libraries were done, one specifically for the Intel iPSC/860 Hypercube, and another called parallel virtual machine (PVM) that runs on many different systems from networks of heterogeneous workstations connected by a local area network to supercomputers with multiple closely coupled CPUs. Techniques are discussed for performing key parts of the finite-element analysis in a parallel environment, including calculation of the source field, matrix assembly, and matrix solution. In conclusion, PVM is the preferable environment for most applications, despite its lack of maturity, because it facilitates porting software to many hardware systems without extensive rewriting.