Hi, The only change I made in the code is as follows:
in src/mem/cache/cache_impl.hh: the original code is : Tick time = curTick() + hitLatency; after change, the new code is Tick time = curTick() + hitLatency + hitLatency; The command line I used for both runs are the same: build/ALPHA/gem5.opt configs/example/fs.py -n 4 --cpu-type=detailed --caches --l2cache -r 1 On Wed, Jul 11, 2012 at 10:27 AM, Nilay <[email protected]> wrote: > On Tue, July 10, 2012 7:52 pm, Jiachen Xue wrote: > > Hi, > > > > I am running ALPHA FS with classic memory system (no ruby). I am trying > to > > add some extra delays to > > "timingAccess" function in src/mem/cache/cache_impl.hh. What I have tried > > is that, instead of adding just > > one hitLatency to time, I added two hitLantency to time. However, I found > > the simulated benchmarks > > finished earlier by adding the extra hitLantency delay. I am using > > sim_ticks as the measurement. Could someone > > explain the reason behind this? > > > > It would help if you can post your changes, and the command lines used for > the two runs. > > -- > Nilay > > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > -- > Sincerely, > Jiachen Xue > > <http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users>
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
