The aim of this project is the exploitation of the capacities offered by multicore architecture in order to improve the performance of the social demographic simulator, Yades (Yet Another DEmographic Simulator), created in inLab in collaboration with Lancaster University and Barcelona Supercomputing Center (BSC)..
To accomplish this objective, ROOT-Sim (ROme OpTimistic Simulator)) library has been used, taking profit of the benefits that a shared memory architecture offers and optimizing the performance of the simulator. This enhancement reduces intra-node communications and provides more advanced capabilities for working with highly extended architecture currently.
To achieve this goal, we initiate a collaboration with High Performance and Dependable Computing Systems Group (DIAG) of Sapienza University, in order to adapt our simulator with ROOT-Sim library, a parallel simulation general purpose library for discrete events (PDES - Parallel Discrete Event Simulation). This static library can be used with any model that uses ANSI-C standard.
With this project not only has been optimized the performance of Yades simulator in multicore architecture but also has contributed in the development of some parts of ROOT-Sim library and its test with a real application.