The model-based transformation of loop programs is a way of detecting fine-grained parallelism in sequential programs. One of the challenges is to agglomerate the parallelism to a coarser grain, in order to map the operations of the program to the available cores in a multicore architecture. We consider shared-memory multicores as target architecture for space-time mapped loop programs and make some observations concerning code generation, load balancing and cache effects. Keywords. Multicore, automatic parallelization, loop transformations, polyhedron model