Welcome to the new and improved ROSS website. Over the next few months this site will become the go-to place to learn more about ROSS.
Currently, the best resources for information are the wiki articles. Slowly, these articles will be updated and rewritten here as blog posts.
If you are currently developing a ROSS model and would like to request a new feature, please create an Issue on Github.
By default, ROSS will use MPI_COMM_WORLD for all its communications.
tw_comm_setallows the user to change the communicator used by ROSS, for instance to run ROSS on a subset of the ranks of a larger MPI application.
tw_comm_setshould be called before calling
tw_comm_setis used, then the user is responsible for calling
The ROSS code base is easy to install and has been tested on both MacOS and Linux systems. It is a lightweight, C library with a limited number of dependencies.
These instructions are specifically for users of RPI’s AMOS System (the IBM Blue Gene/Q at the CCI). They could be followed for any system behind a firewall, where direct access to GitHub is not allowed.
Currently several different types of instrumentation have been added to ROSS that can be used to collect data on the simulation engine and/or the model being simulated: GVT-based, real time sampling, and event tracing. For GVT-based and real time-based sampling modes you can now collect simulation engine data and model-level data. For collection of simulation engine data, the models should not require any code changes. Obviously to collect model-level data, this will require adding in some code to the model(s), but we’ve attempted to keep this as simple as possible.
The latest version of the RIO API for ROSS checkpoints has just been released! The RIO project can be found here.