This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] Bump up the runtime for "short" benchmarks
On 6/27/19 5:33 AM, Anton Youdkevitch wrote:
> On 6/26/2019 11:32 PM, Carlos O'Donell wrote:
>> On 6/26/19 11:38 AM, Anton Youdkevitch wrote:
>>> Some benchmarks with a very short runtime shows significantly
>>> different results across runs on Aarch64 - up to tens of percents.
>>> Increasing the runtime to 100ms+ makes the deviation under 5%.
>>>
>>> Tested on Aarch64 and x86-64.
>>>
>>> * benchtests/bench-memccpy.c: replace INNER_LOOP_ITERS
>>> with INNER_LOOP_ITERS_LARGE
>>> * benchtests/bench-memchr.c: Likewise
>>> * benchtests/bench-rawmemchr.c: Likewise
>>> * benchtests/bench-strcat.c: Likewise
>>> * benchtests/bench-strchr.c: Likewise
>>> * benchtests/bench-string.h: Likewise
>>> * benchtests/bench-strlen.c: Likewise
>>> * benchtests/bench-strncpy.c: Likewise
>>> * benchtests/bench-strnlen.c: Likewise
>>>
>>> Looks OK?
>> Do you have commit or copyright assignment?
> I don't. Previously my colleague that has did it on my behalf.
The modern FSF assignment process is fairly painless (all digital
depending on your country).
If you setup a "futures" assignment then we could just review and
take all future patches you post.
http://git.savannah.gnu.org/cgit/gnulib.git/plain/doc/Copyright/request-assign.future
https://sourceware.org/glibc/wiki/Contribution%20checklist#FSF_copyright_Assignment
--
Cheers,
Carlos.