Horton

RE: Improve CRC32C performance on SSE4.2

Devulapalli, Raghuveer <raghuveer.devulapalli@intel.com>

View thread
From: "Devulapalli, Raghuveer" <raghuveer.devulapalli@intel.com>
To: Nathan Bossart <nathandbossart@gmail.com>
Cc: John Naylor <johncnaylorls@gmail.com>, "pgsql-hackers@lists.postgresql.org" <pgsql-hackers@lists.postgresql.org>, "Shankaran, Akash" <akash.shankaran@intel.com>
Date: 2025-02-12T22:46:59Z
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. Include _mm512_zextsi128_si512() in AVX-512 configure probes.

  2. Properly fix AVX-512 CRC calculation bug

  3. Workaround code generation bug in clang

  4. Compute CRC32C using AVX-512 instructions where available

  5. Inline CRC computation for small fixed-length input on x86

  6. Be more paranoid in configure's checks for CRC and POPCNT intrinsics.

> > Sounds good to me. Although, users building with just -msse4.2 will
> > now encounter an an additional pclmul runtime check. That would be a
> > regression unless they update to building with both -msse4.2 and -mpclmul.
> 
> My thinking was that building with just -msse4.2 would cause the existing SSE 4.2
> implementation to be used (without the function pointer).  That's admittedly a bit
> goofy because they'd miss out on the PCLMUL optimization, but things at least
> don't get any worse for them.

Right. We are only talking about a regression for small potion of people who build
with -msse4.2 and run on Nehalem/VM with pclmul disabled where we will run 
the cpuid check for pclmul and still pick the sse4.2 version.

Raghuveer