Discrete event driven simulation of HPC system architectures and subsystems has emerged as a productive and cost-effective means to evaluating potential HPC designs, along with capabilities for executing simulations of extreme scale systems. The goal of the CODES project is use highly parallel simulation to explore the design of exascale storage/network architectures and distributed data-intensive science facilities.
Discrete event driven simulation of HPC system architectures and subsystems has emerged as a productive and cost-effective means to evaluating potential HPC designs, along with capabilities for executing simulations of extreme scale systems. The goal of the CODES project is to use highly parallel simulation to explore the design of exascale storage/network architectures and distributed data-intensive science facilities.
Our simulations build upon the Rensselaer Optimistic Simulation System (ROSS), a discrete event simulation framework that allows simulations to be run in parallel, decreasing the simulation run time of massive simulations to hours. We are using ROSS to explore topics including large-scale storage systems, I/O workloads, HPC network fabrics, distributed science systems, and data-intensive computation environments.