This is the mail archive of the
mailing list for the glibc project.
Re: [PATCH] aarch64: optimize the unaligned case of memcmp
- From: Ramana Radhakrishnan <ramana dot gcc at googlemail dot com>
- To: Sebastian Pop <sebpop at gmail dot com>
- Cc: Sebastian Pop <s dot pop at samsung dot com>, GNU C Library <libc-alpha at sourceware dot org>, Marcus Shawcroft <Marcus dot Shawcroft at arm dot com>, Maxim Kuvyrkov <maxim dot kuvyrkov at linaro dot org>, Ramana Radhakrishnan <ramana dot radhakrishnan at arm dot com>, Ryan Arnold <ryan dot arnold at linaro dot org>, Adhemerval Zanella <adhemerval dot zanella at linaro dot org>
- Date: Fri, 23 Jun 2017 23:50:30 +0100
- Subject: Re: [PATCH] aarch64: optimize the unaligned case of memcmp
- Authentication-results: sourceware.org; auth=none
- References: <firstname.lastname@example.org> <CAJA7tRYukYwo-iZDHYWtp2_bMHRaeuhz3kUWMBo7sgjrkZTQHw@mail.gmail.com> <CAFk3UF8=Kv2uxHXvs7QzFN4vOzFb+i++9gbjMq-TsV1nEQTjMQ@mail.gmail.com>
On Fri, Jun 23, 2017 at 11:41 PM, Sebastian Pop <email@example.com> wrote:
> On Fri, Jun 23, 2017 at 5:38 PM, Ramana Radhakrishnan
> <firstname.lastname@example.org> wrote:
>> Is there a chance you can add a benchmark to the glibc benchmarking
>> framework ? For most changes like this it would be good to see if the
>> existing benchmarks handle these cases and provide equivalent
>> improvements so that any changes to this can be rationalized in the
> Sure, I can adapt the benchmark that we submitted to AOSP to fit in
> the glibc benchmark.
> Do you have a pointer to where memcmp is currently benchmarked?
> That would be a good place for the unaligned memcmp testcase.
IIRC you just run make bench or benchtests - haven't done this for a while now.
I couldn't find the information on the wiki easily - is there
something that can link to this in the contribution checklist ?