[PATCH RFC] Imporve 64bit memcpy performance for Haswell CPU with AVX instruction

[Ling Ma]

I have no additional update on it currently.

Thanks
Ling

2014-06-19 0:46 GMT+08:00, H.J. Lu <hjl.tools@gmail.com>:
> On Tue, Jun 10, 2014 at 6:54 AM, Ling Ma <ling.ma.program@gmail.com> wrote:
>> In this patch as gziped attachment, 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 performance
>> from 2% to 8% compared with pending sse2 version.
>>
>> Appreciate your comment
>
> Any feedback?  I'd like to check it in before 2.20 code freeze?
>
> Thanks.
>
>
> --
> H.J.
>