Hey Anouk, I'd recommend trying to collect a checkpoint using the default MOESI_hammer topology (i.e. don't use the --topology parameter) and see if you can restore from that checkpoint into simulation with and without your topology. This should help tease apart where the issue is. Can you let us know what you find?
Thanks, Joel On Wed, Sep 5, 2012 at 7:24 AM, Anouk <[email protected]> wrote: > Hi Nilay, > > To take the checkpoints I use > > /scratch/uceevan/GEM5/build/X86_FS/gem5.opt configs/example/ruby_fs.py > -n 8 --num-dirs 8 --topology DistributedPt2Pt > --kernel=/scratch/uceevan/GEM5/inputs/binaries/x86_64-vmlinux-2.6.28.smp > --script=/scratch/uceevan/GEM5/inputs/scripts/x264_8c_8t.rCs > --checkpoint-dir=/scratch/uceevan/GEM5/Checkpoints/X264/8cores/ > --max-checkpoints 1 > > > And to restore from the checkpoint > > /scratch/uceevan/GEM5/build/X86_FS/gem5.opt configs/example/ruby_fs.py > -n 8 --num-dirs 8 --topology DistributedPt2Pt > --kernel=/scratch/uceevan/GEM5/inputs/binaries/x86_64-vmlinux-2.6.28.smp > --script=/scratch/uceevan/GEM5/inputs/scripts/x264_8c_8t.rCs > --checkpoint-dir=/scratch/uceevan/GEM5/Checkpoints/X264/8cores/ > -r 0 > > > I use the disk images from UTexas for Parsec. The DistributedPt2Pt is a > topology > I added to Ruby. The protocol is MOESI_hammer and it is a timingCPU. > > Thanks for your help, > Anouk > > > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > -- Joel Hestness PhD Student, Computer Architecture Dept. of Computer Science, University of Wisconsin - Madison http://www.cs.utexas.edu/~hestness
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
