[llvm-dev] Enable vectorizer-maximize-bandwidth by default?

Wed Jun 21 15:03:34 PDT 2017

The patch is committed in r305960. Please let me know if there is
unexpected perf impact after this change.

Cheers,
Dehao

On Mon, Jun 12, 2017 at 5:43 PM, Dehao Chen <dehao at google.com> wrote:

> Thanks for the update. I think overall consensus is supportive for this
> change. If no one objects by then end of tomorrow (Tuesday), I will submit
> the patch to make vectorizer-maximize-bandwidth on by default.
>
> Thanks,
> Dehao
>
>
> On Mon, Jun 12, 2017 at 3:41 AM, Agabaria, Mohammed <
> mohammed.agabaria at intel.com> wrote:
>
>> Guys, Just to clarify that with the current fix in SLM there is no need
>> to wait for other issues to be fixed (minor issue).
>>
>> So you can move on with your patch.
>>
>>
>>
>> *From:* Agabaria, Mohammed
>> *Sent:* Wednesday, June 07, 2017 15:24
>> *To:* Zaks, Ayal <ayal.zaks at intel.com>; Chandler Carruth <
>> chandlerc at gmail.com>; Flamedoge <code.kchoi at gmail.com>; Dehao Chen <
>> dehao at google.com>
>> *Cc:* llvm-dev <llvm-dev at lists.llvm.org>
>> *Subject:* RE: [llvm-dev] Enable vectorizer-maximize-bandwidth by
>> default?
>>
>>
>>
>> Guys I have uploaded a fix on phabricator which fix the issue in SLM:
>> https://reviews.llvm.org/D33983
>>
>>
>>
>> *From:* Zaks, Ayal
>> *Sent:* Tuesday, June 06, 2017 22:32
>> *To:* Chandler Carruth <chandlerc at gmail.com>; Agabaria, Mohammed <
>> mohammed.agabaria at intel.com>; Flamedoge <code.kchoi at gmail.com>; Dehao
>> Chen <dehao at google.com>
>> *Cc:* llvm-dev <llvm-dev at lists.llvm.org>
>> *Subject:* RE: [llvm-dev] Enable vectorizer-maximize-bandwidth by
>> default?
>>
>>
>>
>> Chandler> Have you considered contributing these benchmarks to the LLVM
>> test suite?
>>
>>
>>
>> These benchmarks are not ours to contribute; they’re from the EEMBC
>> standard, whose availability is similar in nature to that of SPEC.
>>
>>
>>
>>
>>
>> *From:* llvm-dev [mailto:llvm-dev-bounces at lists.llvm.org
>> <llvm-dev-bounces at lists.llvm.org>] *On Behalf Of *Chandler Carruth via
>> llvm-dev
>> *Sent:* Tuesday, May 30, 2017 23:07
>> *To:* Agabaria, Mohammed <mohammed.agabaria at intel.com>; Flamedoge <
>> code.kchoi at gmail.com>; Dehao Chen <dehao at google.com>
>> *Cc:* llvm-dev <llvm-dev at lists.llvm.org>
>> *Subject:* Re: [llvm-dev] Enable vectorizer-maximize-bandwidth by
>> default?
>>
>>
>>
>> On Tue, May 30, 2017 at 1:40 AM Agabaria, Mohammed via llvm-dev <
>> llvm-dev at lists.llvm.org> wrote:
>>
>> We’re seeing nice improvements but also significant degradations on IA,
>> which we would like to investigate before the patch is committed.
>>
>>
>>
>> Major degradations we see:
>>
>>
>>
>> networking
>>
>>    ip_pktcheckb1m          -6.80 %
>>
>>    ip_pktcheckb2m          -6.74 %
>>
>>    ip_pktcheckb4m          -7.57 %
>>
>>    ip_pktcheckb512k       -6.58 %
>>
>> Telecom
>>
>>    autcor00data_1          -78.02 %
>>
>>    autcor00data_2          -76.80 %
>>
>>    autcor00data_3          -77.00 %
>>
>> (on Atom)
>>
>>
>>
>> We still working on creating reproducers.
>>
>> In general we support this patch, just want to have a chance to
>> investigate the issues. We need a few days for that.
>>
>>
>>
>> I mean, OK... but keep in mind that Dehao's original email went out over
>> a week ago, so this patch has already been held up a while. As these
>> benchmarks aren't readily available, we also can't do anything to help
>> until a test case is posted.
>>
>>
>>
>> Have you considered contributing these benchmarks to the LLVM test suite?
>>
>>
>>
>>
>>
>>
>>
>>
>>
>> *From:* llvm-dev [mailto:llvm-dev-bounces at lists.llvm.org
>> <llvm-dev-bounces at lists.llvm.org>] *On Behalf Of *Chandler Carruth via
>> llvm-dev
>> *Sent:* Tuesday, May 30, 2017 11:27
>> *To:* Flamedoge <code.kchoi at gmail.com>; Dehao Chen <dehao at google.com>
>> *Cc:* llvm-dev <llvm-dev at lists.llvm.org>
>> *Subject:* Re: [llvm-dev] Enable vectorizer-maximize-bandwidth by
>> default?
>>
>>
>>
>> If you care about such hardware, please run benchmarks with the flag?
>>
>>
>>
>> Dehao has made this flag available. It is important that those who care
>> about particular hardware provid ebenchmark results. Not everyone in the
>> community will have access to particular hardware variants.
>>
>>
>>
>> On Tue, May 30, 2017 at 1:14 AM Flamedoge <code.kchoi at gmail.com> wrote:
>>
>> Thank you for running these.
>>
>>
>>
>> May I suggest testing on AVX2 capable hardware? That would be Intel
>> Haswell, AMD Carrizo and up.
>>
>> I'm not sure what "vectorizer-maximize-bandwidth" implies, but doubling
>> the vector lanes may help light up parallel regions.
>>
>>
>>
>> Kevin
>>
>>
>>
>> On Tue, May 30, 2017 at 12:58 AM, Chandler Carruth via llvm-dev <
>> llvm-dev at lists.llvm.org> wrote:
>>
>> On Fri, May 19, 2017 at 4:01 PM Adam Nemet via llvm-dev <
>> llvm-dev at lists.llvm.org> wrote:
>>
>> I will run it on Cyclone/AArch64 next week.
>>
>>
>>
>> FYI, we're still waiting on these Adam...
>>
>>
>>
>> _______________________________________________
>> LLVM Developers mailing list
>> llvm-dev at lists.llvm.org
>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>
>> ---------------------------------------------------------------------
>> Intel Israel (74) Limited
>>
>> This e-mail and any attachments may contain confidential material for
>> the sole use of the intended recipient(s). Any review or distribution
>> by others is strictly prohibited. If you are not the intended
>> recipient, please contact the sender and delete all copies.
>>
>> _______________________________________________
>> LLVM Developers mailing list
>> llvm-dev at lists.llvm.org
>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>
>> ---------------------------------------------------------------------
>> Intel Israel (74) Limited
>>
>> This e-mail and any attachments may contain confidential material for
>> the sole use of the intended recipient(s). Any review or distribution
>> by others is strictly prohibited. If you are not the intended
>> recipient, please contact the sender and delete all copies.
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20170621/183bc514/attachment.html>