Intel Xeon Optimizations for Elastic Wave Propagators
Albert Farrés, Mauricio Hanzich · 78th EAGE Conference and Exhibition 2016 · 2016
Summary In order to cope with the huge amount of computational resources need by an elastic, anisotropic, wave propagation engine, optimizations must be done taking into account the architecture where it runs. We will show strategies evaluated and applied to an elastic propagator based on a Fully Staggered Grid, running on the Intel R Xeon family processors. The evaluated set of optimizations ranges from memory to compute optimizations. Our results show that it is possible to obtain a total speed-up of 4 on this architecture.