>> Looks like it's Lisa's fault ;-) >> >> http://repo.m5sim.org/m5/diff/ab05e20dc4a7/src/mem/cache/base.cc >> >> I think Nate's point is that all the stats vector lengths should be >> changed to _numCpus or _numCpus+1 instead of maxThreadsPerCpu to be >> consistent. >> >> We should also either (1) always do _numCpus+1 even though the extra >> "device" slot is unnecessary for SE mode > > What does device mean here? I'm not sure why there's a "+1"?
In the end, this isn't the route that we're going, but basically, we're trying to keep track of cache stats on a per cpu basis, but in reality, there are things other than cpus that initiate cache requests. Those things (under this proposal) are binned in that +1. Nate _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
