Massively Parallel Genetic Programming
Hugues Juillé, Jordan B. Pollack · The MIT Press eBooks · 1996
Introduction The idea of simulating a MIMD machine using a SIMD architecture is not new ([8, 15]). One of the original ideas for the Connection Machine ([8]) was that it could simulate other parallel architectures. Indeed, in the extreme, each processor on a SIMD architecture can simulate a universal Turing machine (TM). With different turing machine specifications stored in each local memory, each processor would simply have its own tape, tape head, state table and state pointer, and the simulation would be performed by repeating the basic TM operations simultaneously. Of course, such a simulation would be very inefficient, and difficult to program, but would have the advantage of being really MIMD, where no SIMD processor would be in idle state, until its simulated machine halts. Now let us consider an alternative idea, that each SIMD processor would simulate an individual stored program computer using a simple instruction set. For each step of the simulation, the SIMD syste