| From: | Thomas Munro <thomas(dot)munro(at)enterprisedb(dot)com> |
|---|---|
| To: | Heikki Linnakangas <hlinnaka(at)iki(dot)fi> |
| Cc: | Andres Freund <andres(at)anarazel(dot)de>, Yuqi Gu <Yuqi(dot)Gu(at)arm(dot)com>, "pgsql-hackers(at)postgresql(dot)org" <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: Optimize Arm64 crc32c implementation in Postgresql |
| Date: | 2018-04-03 22:07:10 |
| Message-ID: | CAEepm=3aEgkBmuGP6qkvWvnzHZYVKwgEC+enZ6oqnG7eZo3=Rg@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Wed, Apr 4, 2018 at 4:38 AM, Heikki Linnakangas <hlinnaka(at)iki(dot)fi> wrote:
> [armv8-crc32c-2.patch]
This tests OK on my Debian buster aarch64 system (the machine that
runs "eelpout" in the buildfarm), configure tests as expected and I
confirmed that pg_comp_crc32c_armv8 is reached at runtime.
I hope we can figure out a more portable way to detect the
instructions, or failing that a way to detect them on FreeBSD in
userspace. I'll try to send a patch for PG12 if I get a chance.
No opinion on the unaligned memory access question.
--
Thomas Munro
http://www.enterprisedb.com
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tomas Vondra | 2018-04-03 22:11:49 | Re: Online enabling of checksums |
| Previous Message | Andrew Dunstan | 2018-04-03 22:05:18 | Re: [HACKERS] logical decoding of two-phase transactions |