Hi all, I'm quite new to using gem5 for research and had a few questions regarding the KVM CPU and switching between fastforwarding and detailed simulation on the fly.
I am interested in running some long benchmarks. However I essentially want to skip the execution of certain functions in the benchmark. To that end, is it possible in (SE mode), to switch to using the X86KvmCPU for certain periodic functions (for example `malloc`) and then switching back to the Warmup/Detailed CPUs for the rest of the code? The idea is that I would like to invert the "region of interest" so to speak. The se.py script does not seem to offer such functionality. Unfortunately I have not found a guide or documentation for how to use the KVM CPU, but my understanding is that it requires checkpoints to have been previously created via the Atomic CPU? Is it possible to accelerate this process (specially with the above constraint, i.e. every checkpoint is either a call to or return from `malloc`, for example)? Any help on the above would be greatly appreciated. Thank you for your time. Kind regards, Kunal _______________________________________________ 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
