----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/1073/#review2257 -----------------------------------------------------------
Ship it! Do the stats change at all for Alpha? You might have to generate new reference outputs for some of the O3 tests. - Steve Reinhardt On Feb. 29, 2012, 9:03 a.m., Geoffrey Blake wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/1073/ > ----------------------------------------------------------- > > (Updated Feb. 29, 2012, 9:03 a.m.) > > > Review request for Default. > > > Description > ------- > > Changeset 8864:1fb15da02b20 > --------------------------- > O3/Ozone: Eliminate dead code counting software prefetch insts > > Eliminates dead code in the O3 and Ozone CPU models that counted > software prefetch instructions separately for the ALPHA ISA only. > > > Diffs > ----- > > src/cpu/o3/commit_impl.hh 56d011130987 > src/cpu/o3/iew_impl.hh 56d011130987 > src/cpu/ozone/back_end_impl.hh 56d011130987 > src/cpu/ozone/lw_back_end_impl.hh 56d011130987 > > Diff: http://reviews.gem5.org/r/1073/diff/ > > > Testing > ------- > > Compiles and runs simple Hello World and linux boot regressions. > > > Thanks, > > Geoffrey Blake > > _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
