On 1/10/2022 5:21 AM, nitesh--- via gem5-users wrote:
> Hi
>
> I am trying to run a TensorflowLite CPP application on gem5-ARM. I see that the application runs
perfectly fine when I run it on a native ARM machine. However, its not the case when I try running
it through gem5 SE run. I get the following error:
>
> Error in cpuinfo: failed to parse the list of possible processors in
/sys/devices/system/cpu/possible
> Error in cpuinfo: failed to parse the list of present processors in
/sys/devices/system/cpu/present
> Error in cpuinfo: failed to parse both lists of possible and present
processors
>
> It's a very simple program consisting of a model with just one simple FCN
layer.
>
> I am supposing it's because I am trying to run it using SE Mode. If that's the case how can one
run such TF applications on gem5, because I see that most ML applications try parsing the cpuinfo (I
might be wrong)? Could anyone please help me with this issue?
>
> I am also open to suggestions that are concerned with running different TF/Pytorch etc ML CPP
applications on gem5.
>
> Thanks in advance!
Curious. I wonder what happens if you write a trivial script that tries just
to "cat" those two files. I was not previously aware of them, but they seem
to exist and contain something sensible on all of my systems, including
VirtualBox VMs. Maybe it's an unintentional omission from SE mode, which
might require a tweak to gem5. Things in that hierarchy are all virtual files
"faked up" by the kernel.
HTH - Eliot Moss
_______________________________________________
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
