> On June 1, 2013, 9:33 a.m., Nilay Vaish wrote: > > I think there is no need for this ruby clock. Just set it to cpu clock. > > Andreas Hansson wrote: > Really? I am not sure what the Ruby clock corresponds to in a real > system, but if it is interconnect + L2 caches (and beyond) then surely it > should not be the CPU clock? > > Perhaps I'm missing something about how Ruby treats the clock. > > Andreas Hansson wrote: > Do we need a more in-depth discussion of what clock domains there should > be in a Ruby "system" and what their counterpart is in a real system?
Ruby devs what's your take on this? Is this a good starting point? Perhaps we can break Ruby into multiple clock domains at a later stage. - Andreas ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/1882/#review4362 ----------------------------------------------------------- On May 24, 2013, 3:33 a.m., Andreas Hansson wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/1882/ > ----------------------------------------------------------- > > (Updated May 24, 2013, 3:33 a.m.) > > > Review request for Default. > > > Description > ------- > > Changeset 9739:fe7bac6a2f25 > --------------------------- > config: Rename clock option to Ruby clock > > This patch changes the 'clock' option to 'ruby-clock' as it is only > used by Ruby. > > > Diffs > ----- > > configs/common/Options.py 782b7284de21 > configs/ruby/Ruby.py 782b7284de21 > > Diff: http://reviews.gem5.org/r/1882/diff/ > > > Testing > ------- > > All regressions pass > > > Thanks, > > Andreas Hansson > > _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
