Hi All, I would like to simulate a set of workloads simultaneously in HPC. Individual workloads will simulated on different non-interacting multicore simulated systems. I have few questions regarding such setup.
1. Do I need to replicate the disk image (x86root.imp and swp img) and kernel (binaries) ? Or is it possible to simulate using a single image. 2. If I create a single system checkpoint initially and then copy the same in individual workload simulation folders and start multiple simulations, will it work? 3. If you have any better idea regarding batch simulation please share. 4. In the rcS files I see multiple checkpointing commands. Why do we need several checkpoints? 5. Is it possible to backtrace the executed commands in the simulated systems from the checkpoint information? Thanks in advance, Regards, Nil _______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
