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.
There are several different modes of instrumentation have been added to ROSS that can be used to collect data on the simulation engine and/or the model being simulated:
This collects data at real time intervals specified by the user. The runtime option
--rt-interval=nsets the sampling interval, where n is the number of milliseconds between sampling points. The default is set to 1000 ms. This collects all of the same data as the GVT-based instrumentation, as well as some other metrics, which is the difference in GVT and local virtual time for each KP as well as the cycle counters for the PEs (e.g., how much time is spent in event processing, roll back processing, GVT, etc). The difference in GVT and KP virtual time is always recorded per KP, regardless of how
--granularityis set. For the other metrics, the granularity can be switched as described in the section on the GVT-based instrumentation.
This collects data immediately after each GVT. By default, the data is collected on a PE basis, but some metrics can be changed to tracking on a KP or LP basis (depending on the metric). To turn on instrumentation for the KP/LP granularity, use
NOTE: Currently the virtual time sampling is only available in the
analysis-lpsbranch. We expect to merge it into master soon, but for now you must switch to this branch to use it. It should be stable enough to use without issues.
For event tracing, ROSS can directly access the source and destination LP IDs for each event, as well as the sent and received virtual timestamps. It will also record the real time that the event is computed at.