Re: Popcount optimization using AVX512

Nathan Bossart <nathandbossart@gmail.com>

From: Nathan Bossart <nathandbossart@gmail.com>

To: David Rowley <dgrowleyml@gmail.com>

Cc: Ants Aasma <ants.aasma@cybertec.at>, Alvaro Herrera <alvherre@alvh.no-ip.org>, "Amonson, Paul D" <paul.d.amonson@intel.com>, Tom Lane <tgl@sss.pgh.pa.us>, Andres Freund <andres@anarazel.de>, "Shankaran, Akash" <akash.shankaran@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: 2024-04-06T01:17:04Z

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 →

Fix __attribute__((target(...))) usage.
- 41b98ddb77bf 18.0 landed
Use __attribute__((target(...))) for AVX-512 support.
- f78667bd910e 18.0 landed
Fix code for probing availability of AVX-512.
- 598e0114a3b1 17.0 landed
Optimize visibilitymap_count() with AVX-512 instructions.
- 41c51f0c68b2 17.0 landed
Optimize pg_popcount() with AVX-512 instructions.
- 792752af4eb5 17.0 landed
Inline pg_popcount() for small buffers.
- deb1486c7d36 17.0 landed
Avoid function call overhead of pg_popcount() in syslogger.c.
- 4133c1f45c54 17.0 landed
Refactor code for setting pg_popcount* function pointers.
- 6687430c98f3 17.0 landed
Inline pg_popcount{32,64} into pg_popcount().
- cc4826dd5e52 17.0 landed
Remove MSVC scripts
- 1301c80b2167 17.0 cited
Use ARMv8 CRC instructions where available.
- f044d71e331d 11.0 cited
Use Intel SSE 4.2 CRC instructions where available.
- 3dc2d62d0486 9.5.0 cited

On Sat, Apr 06, 2024 at 12:08:14PM +1300, David Rowley wrote:
> Won't Valgrind complain about this?
> 
> +pg_popcount_avx512(const char *buf, int bytes)
> 
> + buf = (const char *) TYPEALIGN_DOWN(sizeof(__m512i), buf);
> 
> + val = _mm512_maskz_loadu_epi8(mask, (const __m512i *) buf);

I haven't been able to generate any complaints, at least with some simple
tests.  But I see your point.  If this did cause such complaints, ISTM we'd
just want to add it to the suppression file.  Otherwise, I think we'd have
to go back to the non-maskz approach (which I really wanted to avoid
because of the weird function overhead juggling) or find another way to do
a partial load into an __m512i.

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