I'm not entirely sure what you're trying to do, but it sounds like you could build a tracer which just plugs into the CPU. The one you get with "Exec" is set up by default, but it's designed so you can easily swap something else in. This may not work for some reason since I don't quite get what you're trying to measure, but it's probably worth looking at. I was thinking it would be handy to have a tracer that only printed the symbol you were executing near and only when it changed so you could follow function calls more easily.
Gabe On Mon, 20 Oct 2008, Ali Saidi wrote: > I've started hacking on a little bit of code that will capture all the > symbol names and ticks in a sqlite database that can be used to > visualize CPU activity after a simulation. The big question is what > should the interface look like. Currently, I have two ideas: > > a) A SimObject that is attached to the root. In this case you would > get all the systems or none of them. The benefit is that the check is > simple as there can be one global object that gathers the data. > > b) A SimObject that is attached to a system. Each system would record > data separately. The check is more expensive and in this case you > probably would get one database per file (as opposed to per experiment)> > > c) ?? > > Thoughts? > > Ali > > _______________________________________________ > m5-dev mailing list > [email protected] > http://m5sim.org/mailman/listinfo/m5-dev > _______________________________________________ m5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/m5-dev
