Hi, I am trying to add support for saving cache state during checkpointing. I have been able to dump cache contents (all the blocks) when a checkpoint is created. However, when I try to restore from the checkpoint the simulation immediately stops with following message:
**** REAL SIMULATION **** info: Entering event queue @ 2281941320500. Starting simulation... hack: be nice to actually delete the event here Exiting @ tick 2281941334000 because all cpus halted I am running checkpointed PARSEC benchmarks and I am using atomic mode for running simulations, with same cpu and cache configuration, before and after checkpoint. Here are the commands i use for running simulations: build/ALPHA_FS/gem5.opt ./configs/example/fs.py --caches --l2cache --script=../../run_scripts/ckpts/blackscholes_1c_simsmall_ckpts.rcS -n 1 build/ALPHA_FS/gem5.opt ./configs/example/fs.py --caches --l2cache --checkpoint-restore=1 -n 1 Does anyone have a clue why this might be happening ? Thanks, -Abhishek Graduate Student Computer Science University of Virginia --------------------------------------------------------------------------------------------------------------------- simplicity is the ultimate sophistication -Leonardo da Vinci
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
