Date: Thu, 25 Aug 2022 21:51:15 -0700
From: Nathan Bossart <nathandbossart@gmail.com>
To: John Naylor <john.naylor@enterprisedb.com>
Cc: Andres Freund <andres@anarazel.de>,
	pgsql-hackers <pgsql-hackers@postgresql.org>
Subject: Re: use ARM intrinsics in pg_lfind32() where available
Message-ID: <20220826045115.GA1638993@nathanxps13>
References: <20220819200829.GA395728@nathanxps13>
 <20220819212602.brjkd6ppgbohvo6g@awork3.anarazel.de>
 <20220819222814.GA401294@nathanxps13>
 <CAFBsxsEvzdUZe3WqojHDTT28HOopR4eibARdH2eCkdBEnM__qQ@mail.gmail.com>
 <20220822211547.GA1126462@nathanxps13>
 <CAFBsxsEN5nW3uRh=jrs-QexDrC1btu0ZfriD3FFfb=3J6tAngg@mail.gmail.com>
 <20220824180111.GB1302810@nathanxps13>
 <CAFBsxsE-mCC4Dxb6wmgEZTynyKtER0Y0ha_Rw_rLMY_u2j2oqg@mail.gmail.com>
 <20220825045729.GA1458024@nathanxps13>
 <CAFBsxsHa9QmLk33c5C-12Uuh35Ofv+qzbT+auGrqC3fQCorqBg@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: 
 <CAFBsxsHa9QmLk33c5C-12Uuh35Ofv+qzbT+auGrqC3fQCorqBg@mail.gmail.com>
Archived-At: 
 <https://www.postgresql.org/message-id/20220826045115.GA1638993%40nathanxps13>
Precedence: bulk

On Fri, Aug 26, 2022 at 10:45:10AM +0700, John Naylor wrote:
> On Thu, Aug 25, 2022 at 11:57 AM Nathan Bossart
> <nathandbossart@gmail.com> wrote:
>> The ARM literature appears to indicate that Neon support is pretty standard
>> on aarch64, and AFAICT it's pretty common to just assume it's available.
> 
> This doesn't exactly rise to the level of "find out for sure", so I
> went looking myself. This is the language I found [1]:
> 
> "Both floating-point and NEON are required in all standard ARMv8
> implementations. However, implementations targeting specialized
> markets may support the following combinations:
> 
> No NEON or floating-point.
> Full floating-point and SIMD support with exception trapping.
> Full floating-point and SIMD support without exception trapping."

Sorry, I should've linked to the documentation I found.  I saw similar
language in a couple of manuals, which is what led me to the conclusion
that Neon support is relatively standard.

> Since we assume floating-point, I see no reason not to assume NEON,
> but a case could be made for documenting that we require NEON on
> aarch64, in addition to exception trapping (for CRC runtime check) and
> floating point on any Arm. Or even just say "standard". I don't
> believe anyone will want to run Postgres on specialized hardware
> lacking these features, so maybe it's a moot point.

I'm okay with assuming Neon support for now.  It's probably easier to add
the __ARM_NEON check if/when someone complains than it is to justify
removing it once it's there.

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com