Hi Duc Anh, To answer the question about simulation speed, I believe the difference between SE mode and FS mode is minimal. In addition to that, kernel interactions, like process scheduler and page table walks, have significant impact on system performance, so in most cases, I believe it is more appropriate to choose FS over SE mode.
Regards, Hoa Nguyen On 11/12/20, Đức Anh via gem5-users <gem5-users@gem5.org> wrote: > Dear gem5 team, > > I want to use gem5 to simulate a program to measure its execution time. My > goal is to measure the execution time as close as possible to the real > value, and that program is running in a heterogeneous platform, where other > programs on other CPUs can affect the program execution time (memory, bus > contention,...). I found this StackOverflow answer ( > https://stackoverflow.com/a/56371006/9868917) states that it depends on > whether the kernel interaction and system noise matter to us. So in > general, will FS or SE mode gives more accurate execution time? And how the > syscall emulated in SE mode compare to the real syscall in FS mode in term > of speed? I mean, does the syscall in SE always has a fixed speed and > usually faster than FS? > > Best regards, > Duc Anh > _______________________________________________ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s