DOWNLOAD PRESENTATIONWATCH VIDEOMost of the seismic imaging techniques are based on wave propagation simulations. 3D anisotropic elastodynamics is a generally accepted accurate candidate for the modeling of the subsurface. A Discontinuous Galerkin space discretization, associated with a Leap-Frog time scheme, leads to a quasi-explicit matrix linear system involving only local computations (i.e. cell by cell) at every half-timestep. The original, message passing parallel implementation uses a domain decomposition with one domain per process, and lead to a uneven work balance between processes. As a result, the optimization for each architecture is time consuming and the solution is never portable. In a previous work, we successfully overcame this problem on shared memory architectures (ccNUMA node and Intel Xeon Phi accelerator) by changing the programming paradigm with a task-based approach and the use of the PaRSEC runtime system. The two key-features for efficient task scheduling are finer granularity than one subdomain per core and work-stealing depending on data locality. The results showed very good parallel efficiency and were portable on these machines. We now plan to address distributed memory architectures in order to target clusters of hybrid multicore nodes and coprocessors.
