----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/1911/#review4421 -----------------------------------------------------------
Ship it! Nice, thanks! - Steve Reinhardt On June 11, 2013, 2:17 a.m., Andreas Sandberg wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/1911/ > ----------------------------------------------------------- > > (Updated June 11, 2013, 2:17 a.m.) > > > Review request for Default and Gabe Black. > > > Description > ------- > > Changeset 9758:d33941abaf0c > --------------------------- > x86: Make fprem like the fprem on a real x87 > > The current implementation of fprem simply does an fmod and doesn't > simulate any of the iterative behavior in a real fprem. This isn't > normally a problem, however, it can lead to problems when switching > between CPU models. If switching from a real CPU in the middle of an > fprem loop to a simulated CPU, the output of the fprem loop becomes > correupted. This changeset changes the fprem implementation to work > like the one on real hardware. > > > Diffs > ----- > > src/arch/x86/isa/insts/x87/arithmetic/partial_remainder.py 9df73385c878 > src/arch/x86/isa/microops/fpop.isa 9df73385c878 > > Diff: http://reviews.gem5.org/r/1911/diff/ > > > Testing > ------- > > Quick regressions pass. Solves a switching bug when switching between a > virtualized CPU and a simulated CPU while a benchmark is in the middle of a > fprem loop calculating a % b. > > > Thanks, > > Andreas Sandberg > > _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
