Gem5 is almost fully deterministic in SE mode. I only know of one exception (load linked/store conditional instruction pairs) and that is being fixed. The committed instruction sequence should be the same every time. I'd think you'd have to save the outcomes of all branches.
It might be easier to grab the "proper" path by just probing instructions @ commit (since they should have a valid pc, you could tell if they were branching, and they would have the next pc set in their PCState). On Tue, Oct 23, 2012 at 4:01 AM, mihai pricopi <mihai.pric...@gmail.com>wrote: > Should I save the results only for the mispredicted ones or for all > branches ? > If I only have to save the results for the mispredicted ones then the > condition is that gem5 to be deterministic (so the miss happens at the same > simulation cycle between multiple SE cycles). Is gem5 SE deterministic ? > > > On Tue, Oct 23, 2012 at 10:02 AM, Mitch Hayenga < > mitch.hayenga+g...@gmail.com> wrote: > >> Since gem5 the O3 cpu model actually executes instructions @ execute (not >> fetch/decode) a perfect branch predictor is a bit tricky. Assuming you are >> running a single-threaded app in SE mode (so you don't have >> OS/multi-threaded time variance issues), you could simply run the >> application twice. Save the branch outcomes from the first run. Then >> re-run the app, with a "predictor" that just uses the branch results from >> the first time you ran the application. >> >> On Mon, Oct 22, 2012 at 8:43 PM, mihai pricopi >> <mihai.pric...@gmail.com>wrote: >> >>> Hi, >>> >>> I am using arm_detailed SE mode. >>> Is there a simple way to force the branch predictor to do perfect >>> prediction ? >>> >>> Thanks >>> >>> _______________________________________________ >>> gem5-users mailing list >>> gem5-users@gem5.org >>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >>> >> >> >> _______________________________________________ >> gem5-users mailing list >> gem5-users@gem5.org >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> > > > _______________________________________________ > gem5-users mailing list > gem5-users@gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
