Thanks Arthur Perais. -- Regards, Abhishek Rajgadia Electrical Engineering, IIT Bombay
On Tue, Mar 29, 2016 at 8:22 PM, Arthur Perais <[email protected]> wrote: > Abhishek, > > You are quite right regarding store-store, but note that the function does > not only check store-load ordering. > > As far as I understand, the function checks if younger loads to the same > address have issued when an older store executes (store-load ordering), as > well as if younger loads to the same address that got invalidated in the > cache have issued when an older *load* executes (load-load ordering *to > the same address*). The variable needsTSO (true in x86, false otherwise) > changes what is considered a violation and what is not. Basically, if > needsTSO is set, then enforcing full load-load ordering is required and > handled in checkSnoop(). If it is not set, then load-load ordering to the > same address only is required, and this is enforced in checkViolations() if > a younger inflight load to the same address was touched by a snoop request > in checkSnoop(). > > Best, > > Arthur Perais. > > > Le 29/03/2016 15:41, Abhishek Rajgadia a écrit : > > In the checkViolations() function in lsq_unit_impl.hh , it is mentioned in > a comment that it checks if load/store incorrectly passed a store. Does it > really check if store incorrectly passed a store? Since it checks the > LoadQueue, isn't it checking only for loads incorrectly passing a store? > > -- > Regards, > Abhishek Rajgadia > Electrical Engineering, > IIT Bombay > > > > _______________________________________________ > gem5-users mailing > [email protected]http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > > > -- > Arthur Perais > INRIA Bretagne Atlantique > Bâtiment 12E, Bureau E303, Campus de Beaulieu > 35042 Rennes, France > > > _______________________________________________ > 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
