pg.ddx.io  pgsql-hackers@postgresql.org mailing list archive  
help / color / mirror / Atom feed
From: Andy Fan <zhihuifan1213@163.com>
To: John Naylor <johncnaylorls@gmail.com>
Cc: Devulapalli, Raghuveer <raghuveer.devulapalli@intel.com>
Cc: Nathan Bossart <nathandbossart@gmail.com>
Cc: Jesper Pedersen <jesperpedersen.db@gmail.com>
Cc: Tomas Vondra <tomas@vondra.me>
Cc: pgsql-hackers@lists.postgresql.org <pgsql-hackers@lists.postgresql.org>
Cc: Shankaran, Akash <akash.shankaran@intel.com>
Subject: Re: Improve CRC32C performance on SSE4.2
Date: Wed, 18 Jun 2025 10:18:15 +0000
Message-ID: <877c19cpzs.fsf@163.com> (raw)
In-Reply-To: <CANWCAZZK0hVk-N71JsuXPOB0ALy8BBOfRjSA4Nz2Kpt2RCLU0Q@mail.gmail.com>
References: <CANWCAZYsfyjcrjhL--zMTV4ERiR3rDGiVZHs_-0y9enc38qtsw@mail.gmail.com>
	<Z_BZ_Xxdu9E2r8SH@nathan>
	<CANWCAZa_iAhjd-6TVY5NfDzyoSJxFgsMrPW0YwKuTMF7a75D9g@mail.gmail.com>
	<87o6uqd3iv.fsf@163.com>
	<e98f1e23-b05b-43e4-a3a1-0967df12ada4@vondra.me>
	<aE1_knL40G9Wq_zp@nathan>
	<029f0848-8bc2-4d99-aebd-345949f97622@gmail.com>
	<87frg1dc3k.fsf@163.com>
	<CANWCAZZ+iVxz5QAadZrTCyps3Wewjy45POnqOkSi4KE_Y4YQtw@mail.gmail.com>
	<PH8PR11MB8286A89AF2B104044187E54DFB70A@PH8PR11MB8286.namprd11.prod.outlook.com>
	<aFCXO7MztuZezdpH@nathan>
	<PH8PR11MB82866B07AA6758D12F699C00FB70A@PH8PR11MB8286.namprd11.prod.outlook.com>
	<87bjqncl24.fsf@163.com>
	<CANWCAZZK0hVk-N71JsuXPOB0ALy8BBOfRjSA4Nz2Kpt2RCLU0Q@mail.gmail.com>

John Naylor <johncnaylorls@gmail.com> writes:

Hi,

>> Just be curious, what kind of optimization (like what -O2 does) could
>> mask this issue?
>
> In case Andy is asking about "how" rather than "under what
> circumstances", my guess is: -O1+  may have just chosen instructions
> that also happen to zero-extend, which are common. -O0 doesn't
> represent the naive straightforward structure of what the programmer
> wrote, it's more like an "exploded" representation suitable for later
> optimization passes. That's why it always looks goofy.

Thanks for the explaination!

>> > Replacing that with _mm512_zextsi128_si512 fixes the problem.
>
> Here's a patch for testing, which also reverts the previous
> workaround. Help welcome, but I still promise to test it in the near
> future regardless.

I verified the your patch, it works for me. 

-- 
Best Regards
Andy Fan






view thread (82+ messages)  latest in thread

Message-ID: <877c19cpzs.fsf@163.com>
Permalink:  ../877c19cpzs.fsf@163.com/
Also on:    postgresql.org/message-id/877c19cpzs.fsf@163.com

 · 

reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Reply to all the recipients from your mail client; the link fills in
  the headers below: reply via email
  Some clients, webmail especially, drop In-Reply-To and References from
  a link, and the reply then starts a new thread: use the mbox below.

  To: pgsql-hackers@postgresql.org
  Cc: zhihuifan1213@163.com, johncnaylorls@gmail.com, raghuveer.devulapalli@intel.com, nathandbossart@gmail.com, jesperpedersen.db@gmail.com, tomas@vondra.me, akash.shankaran@intel.com
  Subject: Re: Improve CRC32C performance on SSE4.2
  In-Reply-To: <877c19cpzs.fsf@163.com>
  References: <CANWCAZYsfyjcrjhL--zMTV4ERiR3rDGiVZHs_-0y9enc38qtsw@mail.gmail.com> <Z_BZ_Xxdu9E2r8SH@nathan> <CANWCAZa_iAhjd-6TVY5NfDzyoSJxFgsMrPW0YwKuTMF7a75D9g@mail.gmail.com> <87o6uqd3iv.fsf@163.com> <e98f1e23-b05b-43e4-a3a1-0967df12ada4@vondra.me> <aE1_knL40G9Wq_zp@nathan> <029f0848-8bc2-4d99-aebd-345949f97622@gmail.com> <87frg1dc3k.fsf@163.com> <CANWCAZZ+iVxz5QAadZrTCyps3Wewjy45POnqOkSi4KE_Y4YQtw@mail.gmail.com> <PH8PR11MB8286A89AF2B104044187E54DFB70A@PH8PR11MB8286.namprd11.prod.outlook.com> <aFCXO7MztuZezdpH@nathan> <PH8PR11MB82866B07AA6758D12F699C00FB70A@PH8PR11MB8286.namprd11.prod.outlook.com> <87bjqncl24.fsf@163.com> <CANWCAZZK0hVk-N71JsuXPOB0ALy8BBOfRjSA4Nz2Kpt2RCLU0Q@mail.gmail.com> <877c19cpzs.fsf@163.com>

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox