> On 2010-12-09 00:05:46, Gabe Black wrote: > > src/cpu/o3/iew_impl.hh, line 1298 > > <http://reviews.m5sim.org/r/349/diff/1/?file=5479#file5479line1298> > > > > Wouldn't just checking !inst->isExecuted be sufficient? If it hasn't > > executed yet I don't think it shouldn't be checked for a mispredict no > > matter what else is going on.
Sure. I was fixing a point issue, but I'd be happy for this to just check for !inst->isExecuted(). - Matt ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.m5sim.org/r/349/#review529 ----------------------------------------------------------- On 2010-12-06 16:15:03, Ali Saidi wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.m5sim.org/r/349/ > ----------------------------------------------------------- > > (Updated 2010-12-06 16:15:03) > > > Review request for Default, Ali Saidi, Gabe Black, Steve Reinhardt, and > Nathan Binkert. > > > Summary > ------- > > O3: Don't test misprediction on non-speculative load instructions until > executed. > > > Diffs > ----- > > src/cpu/o3/iew_impl.hh 2b5fbdcbfb5d > > Diff: http://reviews.m5sim.org/r/349/diff > > > Testing > ------- > > > Thanks, > > Ali > >
_______________________________________________ m5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/m5-dev
