Hi, Andreas !

Actually, while running some benchmarks in full system mode, I observed
some differences in total number of committed instructions on detailed and
functional mode. It seems like the execution path is not the same in both
cases and I am not sure of the reasons. So, I generate BBV on detailed
mode, so that I can later use them in detailed mode simulation.

But, I tried to compare detailed mode BBV profile with atomic mode BBV
profile (in this case, the benchmark is run on system emulation mode and
there is no difference in number of instructions committed in both cases).
Surprisingly the genrated BBV profiles are not same. As the BBV generation
code that I use with detailed mode cpu is same as in atomic mode (with
minor modifications), so I am not sure what's going wrong here !

Thanks
Ayaz


On Sun, Mar 13, 2016 at 4:04 AM, Andreas Hansson <andreas.hans...@arm.com>
wrote:

> Hi,
>
> There is nothing wrong with it…but the question is why you would do BBV
> generation with the o3 CPU? The atomic mode CPU is much faster. Why would
> you not just use that?
>
> Andreas
>
> From: gem5-users <gem5-users-boun...@gem5.org> on behalf of Ayaz Akram <
> aaq...@gmail.com>
> Reply-To: gem5 users mailing list <gem5-users@gem5.org>
> Date: Saturday, 12 March 2016 at 19:51
> To: gem5 users mailing list <gem5-users@gem5.org>
> Subject: [gem5-users] Detailed Mode BBV Generation
>
> Gem5 supports creation of basic block vector profile in atomic mode with
> fastmem. I have ported the same code to detailed mode so that I can
> generate basic block vector profile in detailed mode (as in full system
> mode, I was seeing some differences in execution path in detailed and
> atomic mode). This functionality seems to be working but I am not sure
> about the accuracy. I wonder, if there is something potentially wrong with
> this approach (I mean using the same bbv gen. code with detailed mode) ?
> IMPORTANT NOTICE: The contents of this email and any attachments are
> confidential and may also be privileged. If you are not the intended
> recipient, please notify the sender immediately and do not disclose the
> contents to any other person, use it for any purpose, or store or copy the
> information in any medium. Thank you.
>
> _______________________________________________
> gem5-users mailing list
> gem5-users@gem5.org
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to