[dpdk-stable] [dpdk-dev] AVX512 bug on SkyLake

[Ferruh Yigit]

On 11/9/2018 6:27 AM, Christian Ehrhardt wrote:
> On Fri, Nov 9, 2018 at 12:01 AM Yongseok Koh <yskoh at mellanox.com> wrote:
>>
>>
>>> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit <ferruh.yigit at intel.com> wrote:
>>>
>>> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
>>>> Hi,
>>>>
>>>> We need to gather more information about this bug.
>>>> More below.
>>>>
> 
> Thanks Thomas for looping us in!
> 
>>>> 07/11/2018 10:04, Wiles, Keith:
>>>>>> On Nov 6, 2018, at 9:30 PM, Yongseok Koh <yskoh at mellanox.com> wrote:
>>>>>>> On Nov 5, 2018, at 6:06 AM, Wiles, Keith <keith.wiles at intel.com> wrote:
>>>>>>>> On Nov 2, 2018, at 9:04 PM, Yongseok Koh <yskoh at mellanox.com> wrote:
>>>>>>>>
>>>>>>>> This is a workaround to prevent a crash, which might be caused by
>>>>>>>> optimization of newer gcc (7.3.0) on Intel Skylake.
>>>>>>>
>>>>>>> Should the code below not also test for the gcc version and
>>>>>>> the Sky Lake processor, maybe I am wrong but it seems it is
>>>>>>> turning AVX512 for all GCC builds
>>>>>>
>>>>>> I didn't want to check gcc version as 7.3.0 is very new. Only gcc 8 is newly up since then (gcc 8.2).
>>>>>> Also, I wasn't able to test every gcc versions and I wanted to be a bit conservative for this crash.
>>>>>> Performance drop (if any) by disabling a new (experimental) feature would be less risky than unaccountable crash.
>>>>>> And, it does disable the feature only if CONFIG_RTE_ENABLE_AVX512=n. Please refer to v3.
>>>>>
>>>>> Are you not turning off all of the GCC versions for AVX512.
>>>>> And you can test for range or greater then GCC version and
>>>>> it just seems like we are turning off every gcc version, is that true?
>>>>
>>>> Do we know exactly which GCC versions are affected?
>>>>
>>>>>>> Also bug 97 seems a bit obscure reference, maybe you know
>>>>>>> the bug report, but more details would be good?
>>>>>>
>>>>>> I sent out the report to dev list two month ago.
>>>>>> And I created the Bug 97 in order to reference it
>>>>>> in the commit message.
>>>>>> I didn't want to repeat same message here and there,
>>>>>> but it would've been better to have some sort of summary
>>>>>> of the Bug, although v3 has a few more words.
>>>>>> However, v3 has been merged.
>>>>>
>>>>> Still this is too obscure if nothing else give a link to
>>>>> a specific bug not just 97.
>>>>
>>>> The URL is
>>>>      https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fbugs.dpdk.org%2Fshow_bug.cgi%3Fid%3D97&data=02%7C01%7Cyskoh%40mellanox.com%7C90ff6c361faf422b976108d6459eb490%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C636772945282345908&sdata=2o%2Fg203aWrKCYg16S6oI4BcS41igpLu1DloS%2FrRnknc%3D&reserved=0
>>>> The bug is also pointing to an email:
>>>>      https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmails.dpdk.org%2Farchives%2Fdev%2F2018-September%2F111522.html&data=02%7C01%7Cyskoh%40mellanox.com%7C90ff6c361faf422b976108d6459eb490%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C636772945282345908&sdata=NCFKxaREd69iZ8eyFKg%2FWBP73CLTXkxrNQQeii%2Bbsao%3D&reserved=0
>>>>
>>>> Summary:
>>>>      - CPU: Intel Skylake
>>>>      - Linux environment: Ubuntu 18.04
>>>>      - Compiler: gcc-7.3 (Ubuntu 7.3.0-16ubuntu3)
>>>
>>> Is it possible to test a few other gcc versions to check if the issue is
>>> specific to this compiler version?
>>
>> Nothing's impossible but even with my quick search in gcc.gnu.org,
>> I could find the following documents mention mavx512f support:
>>
>> GCC 4.9.0
>> April 22, 2014 (changes, documentation)
>>
>> GCC 5.1
>> April 22, 2015 (changes, documentation)
>>
>> GCC 6.4
>> July 4, 2017 (changes, documentation)
>>
>> GCC 7.1
>> May 2, 2017 (changes, documentation)
>>
>> GCC 8.1
>> May 2, 2018 (changes, documentation)
>>
>> We altogether have to put quite large resource to verify all of the versions.
>>
>> I assumed older than gcc 7 would have the same issue. I know it was a speculation
>> but like I mentioned I wanted to be more conservative. I didn't mean this is a permanent fix.
>> For two months, we couldn't have any tangible solution (actually nobody cared including myself),
>> so I submitted the patch to temporarily disable mavx512f.
>>
>> I'm still not sure what the best option is...
>>
> 
> What I wonder in all of this as I don't understand that part of it yet is this.
> I assume you are building on Ubuntu as that is your gcc reference.
> FYI: as people asked for bug references, there also is [1] which seems
> pretty much the same issue.
> 
> It builds with mostly defaults, that means per
> mk/machine/default/rte.vars.mk and similar it sets -march=corei7
> 
> But when I look at what that implies all avx512 is disabled
> $ gcc -Q --help=target -m64 -march=corei7 | grep avx512f
>  -mavx512f                             [disabled]

This is output is the "corei7" architecture. Defect is for "native" build on
Skylake.

For "native" arch:
gcc -Q --help=target -m64 -march=native | grep avx512f
  -mavx512f                             [enabled]


Also I can confirm from disassembly output that avx512 instructions are used
without '-mno-avx512f' provided.

> 
> So I wonder what/why -mno-avx512f should help at all.
> I used the full list of gcc args we have for the build (e.g. [2] of a
> 18.05 build), but that doesn't change that (mostly -W, -I and -D).
> So I wonder, did people do a custom build and bump up march or enable
> -mavx512f on their own to hit that?
> Or are we facing a real gcc issue where " -mavx512f [disabled]" is not
> the same as -mno-avx512f ?
> Maybe someone who hit the bug could clarify that please?
> 
> BTW: per reports I've seen it also seems to apply to the latest
> compiler update of the same series - at least it was said to be fully
> updated, that would be 7.3.0-27ubuntu1~18.04
> But this is 2nd grade information as I don't have a system with the
> right combo MLX5+Skylake available atm, so I can't confirm for sure
> :-/
> 
> [1]: https://bugs.launchpad.net/ubuntu/+source/dpdk/+bug/1799397
> [2]: https://launchpadlibrarian.net/373589345/buildlog_ubuntu-bionic-amd64.dpdk_18.05-1~ubuntu0.18.04.1_BUILDING.txt.gz
>