This is the mail archive of the
libc-ports@sources.redhat.com
mailing list for the libc-ports project.
Re: [PATCH] sysdeps/arm/armv6t2/strlen.S: strlen implementation for armv6t2.
- From: "Carlos O'Donell" <carlos at redhat dot com>
- To: Will Newton <will dot newton at linaro dot org>
- Cc: "Joseph S. Myers" <joseph at codesourcery dot com>, "libc-ports at sourceware dot org" <libc-ports at sourceware dot org>, Patch Tracking <patches at linaro dot org>
- Date: Fri, 30 Aug 2013 13:38:46 -0400
- Subject: Re: [PATCH] sysdeps/arm/armv6t2/strlen.S: strlen implementation for armv6t2.
- Authentication-results: sourceware.org; auth=none
- References: <52089516 dot 3080304 at linaro dot org> <Pine dot LNX dot 4 dot 64 dot 1308300012560 dot 1487 at digraph dot polyomino dot org dot uk> <CANu=DmjLyGRdmvPABiDJMuPM4YyH=p8QrpvNgQpNiH3-LqXOkg at mail dot gmail dot com> <5220D827 dot 50800 at redhat dot com>
On 08/30/2013 01:36 PM, Carlos O'Donell wrote:
> On 08/30/2013 05:06 AM, Will Newton wrote:
>> On 30 August 2013 01:13, Joseph S. Myers <joseph@codesourcery.com> wrote:
>>> On Mon, 12 Aug 2013, Will Newton wrote:
>>>
>>>> This implementation of strlen is faster than the armv6 version for
>>>> all string lengths greater than 1 on a Cortex-A15.
>>>>
>>>> ports/ChangeLog.arm:
>>>>
>>>> 2013-08-09 Will Newton <will.newton@linaro.org>
>>>>
>>>> * sysdeps/arm/armv6t2/strlen.S: New file.
>>>
>>> OK, presuming you've run the full glibc testsuite with this version used.
>>
>> Yes, testsuite is clean. Committed.
>
> I'm not happy seeing these kinds of patches go in without some
> kind of numbers around "faster" and a reproducible way to get
> those numbers.
I don't say this because I'm just cranky, I want all of us to be
more accountable when it comes to the engineering rigour required
for performance patches. That way I can look back at these numbers
when users report issues with the speed of strlen on A15.
Cheers,
Carlos.