As parallel systems have to undergo an unprecedented transition towards more parallelism and hybridization, we propose to discuss the consequences on programming models. In particular, MPI and OpenMP may face some complexity barriers due to the added complexity required by such hardware. We propose to build from the ground up a new way to program a parallel system, relying both on a distributed runtime, unifying multiple nodes in a coherent ensemble, and on advanced tools from the Polyhedral model. We first describe the Distributed Virtual Machine (DVM) runtime establishing a data-flow environment suitable to the polyhedral transformations. We present and identify what we have seen as key components in such a system, transposing loop nests to a distributed set of machines thanks to a pragma notation combined with an automatic tiling approach. Eventually, while presenting results we open the discussion of remaining challenges and some potential mitigation.