Horton

Re: Popcount optimization using AVX512

Nathan Bossart <nathandbossart@gmail.com>

View thread
From: Nathan Bossart <nathandbossart@gmail.com>
To: Andres Freund <andres@anarazel.de>
Cc: "Devulapalli, Raghuveer" <raghuveer.devulapalli@intel.com>, "Shankaran, Akash" <akash.shankaran@intel.com>, Tom Lane <tgl@sss.pgh.pa.us>, David Rowley <dgrowleyml@gmail.com>, Ants Aasma <ants.aasma@cybertec.at>, Alvaro Herrera <alvherre@alvh.no-ip.org>, "Amonson, Paul D" <paul.d.amonson@intel.com>, Noah Misch <noah@leadboat.com>, Matthias van de Meent <boekewurm+postgres@gmail.com>, "pgsql-hackers@lists.postgresql.org" <pgsql-hackers@lists.postgresql.org>
Date: 2024-10-16T21:04:04Z
Lists: pgsql-hackers

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

  1. Fix __attribute__((target(...))) usage.

  2. Use __attribute__((target(...))) for AVX-512 support.

  3. Fix code for probing availability of AVX-512.

  4. Optimize visibilitymap_count() with AVX-512 instructions.

  5. Optimize pg_popcount() with AVX-512 instructions.

  6. Inline pg_popcount() for small buffers.

  7. Avoid function call overhead of pg_popcount() in syslogger.c.

  8. Refactor code for setting pg_popcount* function pointers.

  9. Inline pg_popcount{32,64} into pg_popcount().

  10. Remove MSVC scripts

  11. Use ARMv8 CRC instructions where available.

  12. Use Intel SSE 4.2 CRC instructions where available.

Attachments

On Tue, Oct 08, 2024 at 09:36:03PM -0500, Nathan Bossart wrote:
> On Wed, Jul 31, 2024 at 04:43:02PM -0500, Nathan Bossart wrote:
>> On Wed, Jul 31, 2024 at 01:52:54PM -0700, Andres Freund wrote:
>>> I think we'd be better off enabling architectural features on a per-function
>>> basis, roughly like this:
>>>
>>> [...]
>>> 
>>> /* FIXME: Should be gated by configure check of -mavx512vpopcntdq -mavx512bw support */
>>> pg_enable_target("avx512vpopcntdq,avx512bw")
>>> uint64_t
>>> pg_popcount_avx512(const char *buf, int bytes)
>>> ...
>> 
>> I remember wondering why the CRC-32C code wasn't already doing something
>> like this (old compiler versions? non-gcc-like compilers?), and I'm not
>> sure I ever discovered the reason, so out of an abundance of caution I used
>> the same approach for AVX-512.  If we can convince ourselves that
>> __attribute__((target("..."))) is standard enough at this point, +1 for
>> moving to that.
> 
> [...]
> 
> So, at least for the CRC code, __attribute__((target("..."))) was probably
> not widely available enough yet when it was first added.  Unfortunately,
> the ARMv8 CRC target support (without -march) is still pretty new, but it
> might be possible to switch the others to a per-function approach in v18.

Here is a first attempt at using __attribute__((target("..."))) for the
AVX-512 stuff.  Besides allowing us to consolidate the code into a single
file, this simplifies the build file changes quite a bit.

-- 
nathan