[PATCH] X86-64: Add _dl_runtime_resolve_avx[512]_opt [BZ #20508]

[H.J. Lu]

On Tue, Oct 4, 2016 at 2:20 PM, H.J. Lu <hjl.tools@gmail.com> wrote:
> On Tue, Oct 4, 2016 at 2:18 PM, Adhemerval Zanella
> <adhemerval.zanella@linaro.org> wrote:
>>
>>
>> On 04/10/2016 18:00, H.J. Lu wrote:
>>> On Tue, Oct 4, 2016 at 11:13 AM, Adhemerval Zanella
>>> <adhemerval.zanella@linaro.org> wrote:
>>>>
>>>>
>>>> On 04/10/2016 13:08, H.J. Lu wrote:
>>>>> On Tue, Oct 4, 2016 at 8:48 AM, Florian Weimer <fweimer@redhat.com> wrote:
>>>>>> On 10/04/2016 05:34 PM, H.J. Lu wrote:
>>>>>>>
>>>>>>> On Tue, Oct 4, 2016 at 8:24 AM, Florian Weimer <fweimer@redhat.com> wrote:
>>>>>>>>
>>>>>>>> On 10/04/2016 04:47 PM, H.J. Lu wrote:
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> On Tue, Oct 4, 2016 at 3:52 AM, Florian Weimer <fweimer@redhat.com>
>>>>>>>>> wrote:
>>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>> On 09/27/2016 07:35 PM, H.J. Lu wrote:
>>>>>>>>>>
>>>>>>>>>>>> Any comments? I will check it in next week if there is no objection.
>>>>>>>>>>>
>>>>>>>>>>>
>>>>>>>>>>>
>>>>>>>>>>>
>>>>>>>>>>> I'd like to backport it to 2.23 and 2.24 branches.  Any objections?
>>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>> Just this change, or the requirement for an AVX512F-capable assembler
>>>>>>>>>> as
>>>>>>>>>> well?
>>>>>>>>>>
>>>>>>>>>
>>>>>>>>> Good question.  This is also needed:
>>>>>>>>>
>>>>>>>>> commit f43cb35c9b3c35addc6dc0f1427caf51786ca1d2
>>>>>>>>> Author: H.J. Lu <hjl.tools@gmail.com>
>>>>>>>>> Date:   Fri Jul 1 05:54:43 2016 -0700
>>>>>>>>>
>>>>>>>>>     Require binutils 2.24 to build x86-64 glibc [BZ #20139]
>>>>>>
>>>>>>
>>>>>>>> That's not really backportable, I'm afraid.  Our users don't expect we
>>>>>>>> break
>>>>>>>> builds in this way.
>>>>>>>>
>>>>>>>
>>>>>>> Who are those users?
>>>>>>
>>>>>>
>>>>>> We don't know, really.  But moving forward the baseline binutils requirement
>>>>>> in a stable release really contradicts what a stable release is about.
>>>>>>
>>>>>>
>>>>>
>>>>> Do our users expect a broken glibc binary of a stable release on AVX512
>>>>> machine?
>>>>>
>>>>
>>>> I think 2.24 it is ok since it contains the BZ#20139 fix already.  For 2.23,
>>>> although it was not really explicit in NEWS, AVX512 is suppose to be supported
>>>> in a set of different implementation (memmove/memcpy/libmvec).  However my
>>>> understanding of this issue is limited to be a performance one, so I do not
>>>> see a pressing matter to change a release requirements for such change.
>>>
>>> It is a regression from glibc 2.22.
>>
>> Right, but it is functional regression that prevent avx512 binaries to run
>> correctly on glibc 2.23+ or a performance regression?
>
> BZ #20508 is a performance regression.
>

It also caused:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78611

I am backporting the fix to glibc 2.24.

-- 
H.J.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0001-X86-64-Add-_dl_runtime_resolve_avx-512-_-opt-slow-BZ.patch
Type: text/x-patch
Size: 14898 bytes
Desc: not available
URL: <http://sourceware.org/pipermail/libc-alpha/attachments/20161130/175fa823/attachment.bin>