This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH RFC] Imporve 64bit memcpy performance for Haswell CPU with AVX instruction
- From: "H.J. Lu" <hjl dot tools at gmail dot com>
- To: Ling Ma <ling dot ma dot program at gmail dot com>
- Cc: OndÅej BÃlka <neleai at seznam dot cz>, GNU C Library <libc-alpha at sourceware dot org>, Liubov Dmitrieva <liubov dot dmitrieva at gmail dot com>, yumkam at gmail dot com, Ling Ma <ling dot ml at alibaba-inc dot com>
- Date: Tue, 29 Jul 2014 08:01:01 -0700
- Subject: Re: [PATCH RFC] Imporve 64bit memcpy performance for Haswell CPU with AVX instruction
- Authentication-results: sourceware.org; auth=none
- References: <CAOGi=dOJX3saKoa5YiDdveOqAb_=Sev4cBKyh7_gkXBU8_4=+g at mail dot gmail dot com> <CAMe9rOpEhNffr5iZUZLFp4QyBAE-Xrxna8-BQFv=tZXEXdSLSg at mail dot gmail dot com> <CAOGi=dNk7H2+aWh=+3_qwVH9LvWN-eNKcLciW=0J7x1dVL9v+g at mail dot gmail dot com> <CAOGi=dMsSdQi8SuXi2pzCbMm6bCrwJru0rAjtg=cn24CLgOgRg at mail dot gmail dot com> <CAMe9rOqZpj4BE7kXABOAueaD-o1PgRjL_R48KeDcJBDSmHXPdg at mail dot gmail dot com> <20140625163416 dot GA14763 at domone dot podge> <CAOGi=dMn+zr3u_1YJvmxOO0NF9BTGKeCJNV0nkDTBd7x2dx4eg at mail dot gmail dot com> <CAOGi=dPjVosbXjX9k2kB_o_dsDpHk6DAZXMjyqEVXS3g-dpejA at mail dot gmail dot com> <20140710133648 dot GA18783 at domone dot podge> <CAOGi=dM6iALQNc40=2rpojj49is9e5ms44phtVcrpcwBPAhNbQ at mail dot gmail dot com> <20140711095404 dot GA4897 at domone dot podge> <CAOGi=dN9GtsJQQ7fLyN5KsgRKE3mM0qcB6QPjgp+0dFKRrjQOg at mail dot gmail dot com> <CAOGi=dPatnMawKwPPGHcX_+jy101EA7m=2mvFpe5cPae=aA5FA at mail dot gmail dot com> <CAMe9rOrPBDxSeGfVot-BQoOVE=in4_WNn70rP-4RyNK_trhqAw at mail dot gmail dot com>
On Thu, Jul 17, 2014 at 8:33 AM, H.J. Lu <hjl.tools@gmail.com> wrote:
> On Tue, Jul 15, 2014 at 11:54 PM, Ling Ma <ling.ma.program@gmail.com> wrote:
>> Any comments please.
>>
>> Thanks
>> Ling
>>
>> 2014-07-14 12:28 GMT+08:00, Ling Ma <ling.ma.program@gmail.com>:
>>> In this patch we take advantage of HSW memory bandwidth, manage to
>>> reduce miss branch prediction by avoiding using branch instructions and
>>> force destination to be aligned with avx instruction.
>>>
>>> The CPU2006 403.gcc benchmark indicates this patch improves the whole
>>> performance from 2% to 10%, and 12~ 60% when copy size is over 256bytes.
>>>
>>> This version is based on latest ChangeLog, and simplified memmove
>>> according to Ondra's comment.
>>>
>>> Thanks
>>> Ling
>>>
>
> Any more feedbacks on the latest version:
>
> https://sourceware.org/ml/libc-alpha/2014-07/msg00302.html
>
I will check it in after 24 hours. Thanks for everyone.
--
H.J.