add AVX2 support to simd.h

From: Nathan Bossart <nathandbossart(at)gmail(dot)com>
To: Ants Aasma <ants(at)cybertec(dot)at>
Cc: John Naylor <johncnaylorls(at)gmail(dot)com>, pgsql-hackers(at)postgresql(dot)org
Subject: add AVX2 support to simd.h
Date: 2023-11-29 17:15:26
Message-ID: 20231129171526.GA857928@nathanxps13
Views: Raw Message | Whole Thread | Download mbox | Resend email
Lists: pgsql-hackers

On Wed, Nov 22, 2023 at 12:49:35PM -0600, Nathan Bossart wrote:
> On Wed, Nov 22, 2023 at 02:54:13PM +0200, Ants Aasma wrote:
>> For reference, executing the page checksum 10M times on a AMD 3900X CPU:
>> clang-14 -O2 4.292s (17.8 GiB/s)
>> clang-14 -O2 -msse4.1 2.859s (26.7 GiB/s)
>> clang-14 -O2 -msse4.1 -mavx2 1.378s (55.4 GiB/s)
> Nice. I've noticed similar improvements with AVX2 intrinsics in simd.h.

I've alluded to this a few times now, so I figured I'd park the patch and
preliminary benchmarks in a new thread while we iron out how to support
newer instructions (see discussion here [0]).

Using the same benchmark as we did for the SSE2 linear searches in
XidInMVCCSnapshot() (commit 37a6e5d) [1] [2], I see the following:

writers sse2 avx2 %
256 1195 1188 -1
512 928 1054 +14
1024 633 716 +13
2048 332 420 +27
4096 162 203 +25
8192 162 182 +12

It's been a while since I ran these benchmarks, but I vaguely recall also
seeing something like a 50% improvement for a dedicated pg_lfind32()
benchmark on long arrays.

As is, the patch likely won't do anything unless you add -mavx2 or
-march=native to your CFLAGS. I don't intend for this patch to be
seriously considered until we have better support for detecting/compiling
AVX2 instructions and a buildfarm machine that uses them.

I plan to start another thread for AVX2 support for the page checksums.


Nathan Bossart
Amazon Web Services:

Attachment Content-Type Size
v1-0001-add-avx2-support-in-simd.h.patch text/x-diff 4.1 KB


Browse pgsql-hackers by date

  From Date Subject
Next Message Tristan Partin 2023-11-29 17:30:25 Whose Cirrus CI credits are used when making a PR to the GitHub mirror?
Previous Message Andrew Dunstan 2023-11-29 17:03:04 Re: remaining sql/json patches