Are you using the default configuration parameters? Are you using the classic cache model or Ruby?
There are a handful of performance model issues with the combination of O3 and x86, particularly if you're using Ruby. We have some patches internally here at AMD that we are working to clean up and post. Steve On Wed, Oct 2, 2013 at 3:04 PM, Yingying Tian <[email protected]>wrote: > Hi, > > I actually ran detailed CPU with caches for spec06 on X86/FS and all the > IPCs are lower than results > from other papers/simulators. I am wondering if there are any options I > should have turned on, for > example, anything in the src/xx/xx.py files that related to o3 > configuration. Does anyone have any > ideas? > > Thanks, > Yingying > > Rodrigo Reynolds Ramírez <rodrigo.rr80 <at> hotmail.com> writes: > > > > > > > Thanks for your answer, > > > > Does that means for results for papers and for comparing with real > systems should I use a > "detailed" cpu? > > > > My problem is that the simulation with detailed CPU for the spec2006 > takes weeks, for complete > execution and ref inputs. > > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
