Re: [libc/string] State of PAGE_COPY_FWD / PAGE_COPY_THRESHOLD

[Andrew Pinski <pinskia@gmail.com>]

On Thu, Nov 10, 2016 at 12:34 AM, Andrew Pinski <pinskia@gmail.com> wrote:
> On Thu, Nov 10, 2016 at 12:25 AM, Florian Weimer <fweimer@redhat.com> wrote:
>> On 11/10/2016 09:05 AM, Andrew Pinski wrote:
>>
>>> Also memcpy/memset is useful to optimize for each micro-arch instead
>>> of doing this kind of optimization is better in general.  I have a
>>> semi-optimized memcpy for ThunderX (T88, not T81 or T83; still have
>>> not looked into an optimized version for T83/T81 yet) and have an idea
>>> how to optimize it for another core but there is no way to handle this
>>> in glibc because of kernel or glibc infrastructure for arm64.
>>
>>
>> We do this all the time on x86_64 (and presumably POWER).  What's missing on
>>
>
> Unless you want to read a file (either /proc/cpuinfo or
> /sys/devices/system/cpu/cpuN/regs/identification/midr_el1) the arch
> does not provide a way to identify what processor you are running on
> in userspace.  There has been some discussions already on the kernel
> list and I was going to have another discussion with the arm folks but
> I can't find the email thread where the meeting was setup for :).

I found the email thread, it is setup for this Friday.

Thanks,
Andrew

>
> Thanks,
> Andrew
>
>>
>> Thanks,
>> Florian
>>