|
Hello everyone, The Context-switch traces have been achieved through applying the given Linux kernel patch and doing the necessary modifications to run it on Gem5. For num-cpu = 4, these traces show a list of context switches, combined for all cpu in a sequence of their respective ticks. Each tick is unique, does that mean only one context switch at any given tick?? Although there are four cpus. Is this always the case, no matter how many cpus are there? i.e. Only one context switch at a time? OR This is (can be) the otherwise which has not taken place in my execution of a program? Although my question might sound like more about Linux kernel scheduler, but I am wondering if the fact is opposite to my experience then there might be something wrong with my traces/settings achieved through experimenting on Gem5? Any help will be appreciated. Thanks. |
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
