This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH] Don't use SSE4_2 instructions on Intel Silvermont Micro Architecture.


Carlos, ok to commit the current patch?


--
Liubov

On Mon, Jun 24, 2013 at 11:34 AM, Dmitrieva Liubov
<liubov.dmitrieva@gmail.com> wrote:
> Yes, I will send next one for i386 when this is approved and committed.
>
> -
> Liubov
>
> On Fri, Jun 21, 2013 at 8:13 PM, H.J. Lu <hjl.tools@gmail.com> wrote:
>> On Fri, Jun 21, 2013 at 4:07 AM, Dmitrieva Liubov
>> <liubov.dmitrieva@gmail.com> wrote:
>>> I fixed the patch like H.J. suggested and attached results of micro
>>> benchmarks you requested.
>>>
>>> The functions which were impacted are rawmemchr, strchr, strrchr,
>>> strcmp, strcasecmp, strncmp, strncasecmp.
>>> I see just some small regressions on small lengths but huge gains on
>>> big lengths.
>>>
>>> Change Log.
>>>
>>> 2013-06-19  Liubov Dmitrieva  <liubov.dmitrieva@intel.com>
>>>
>>> * sysdeps/x86_64/multiarch/init-arch.c (__init_cpu_features):
>>> Set bit_Slow_SSE4_2 for Intel Silvermont architecture.
>>> Set bit_Prefer_PMINUB_for_stringop for Intel Silvermont.
>>> * sysdeps/x86_64/multiarch/init-arch.h: Define
>>> bit_Slow_SSE4_2 and index_Slow_SSE4_2.
>>> Define index_Prefer_PMINUB_for_stringop which was undefined.
>>> * sysdeps/x86_64/multiarch/strchr.S: Use SSE2 version if
>>> bit_Slow_SSE4_2 is on.
>>> * sysdeps/x86_64/multiarch/strrchr.S: Use SSE2 version if
>>> bit_Slow_SSE4_2 is on.
>>> * sysdeps/x86_64/multiarch/strcmp.S: Use SSSE3 or SSE2 version if
>>> bit_Slow_SSE4_2 is on.
>>>
>>>
>>
>> I assume you have another patch for i386.
>>
>>
>> --
>> H.J.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]