|
Hello, My simulation has been using FS mode of Gem5 with the disk image "linux-arm-ael.img", where my benchmark executes, when the run-script.rcS is called. To my observation, for the same inputs to a benchmark every execution leaves the same traces. With a multi-threaded application, even the printed 'my-thread-id' is same every time. Thread related information file 'system.task.txt' is also same for each execution. I am just wondering: How far or close is this to the real system simulation? Is this the CoW layer that is making it to produce same result every time? But how about the underneath hardware (in this case Gem5), shouldn't it behave randomly at every boot-up to at least make a difference in the pattern of execution? or If I am missing something? Thank you for your reading. Any help will be greatly appreciated. Best Regards, tod |
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
