This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] powerpc64: strrchr optimization for power8
- From: Carlos O'Donell <carlos at redhat dot com>
- To: Tulio Magno Quites Machado Filho <tuliom at linux dot vnet dot ibm dot com>, Rajalakshmi Srinivasaraghavan <raji at linux dot vnet dot ibm dot com>, libc-alpha at sourceware dot org
- Date: Mon, 17 Apr 2017 11:20:42 -0400
- Subject: Re: [PATCH] powerpc64: strrchr optimization for power8
- Authentication-results: sourceware.org; auth=none
- References: <1487070321-27700-1-git-send-email-raji@linux.vnet.ibm.com> <52479e2b-f675-9d6e-7b34-27e24ee48081@redhat.com> <55dfbdb0-3776-caa9-e87b-10c297b4b496@linux.vnet.ibm.com> <139ea9b7-005d-fd33-a223-fe36fc995f4d@redhat.com> <00958c35-0b2d-60c9-f618-cfcd185710e8@linux.vnet.ibm.com> <5af3baaf-a340-cf07-10fc-f877d803dd6c@linux.vnet.ibm.com> <3e1454d4-ce03-f3a5-ac6f-6d9a7a0151f8@redhat.com> <877f314ihc.fsf@totoro.br.ibm.com>
On 04/03/2017 11:29 AM, Tulio Magno Quites Machado Filho wrote:
> Carlos O'Donell <carlos@redhat.com> writes:
>
>> Now I plotted the power8 performance and there is a big bump in the middle,
>> any idea why?
>
> I remember that we discussed this on #glibc and you noticed the same behavior
> on simple_strrchr and we agreed this could be raw hardware behavior.
>
> Do you think this question is still blocking this patch?
My question does not block the patch.
At this point the patch looks good to me.
You just have an unexplained issue with performance, but it appears to impact
_all_ the algorithms, simple, and the new POWER8 one, so it must be some semantic
of the hardware showing up in the algorithm. It's odd to see that consistent bump.
--
Cheers,
Carlos.