Re: New CRC algorithm: Slicing by 8

From: "Gregory Maxwell" <gmaxwell(at)gmail(dot)com>
To: "Tom Lane" <tgl(at)sss(dot)pgh(dot)pa(dot)us>
Cc: "Bruce Momjian" <bruce(at)momjian(dot)us>, "Gurjeet Singh" <singh(dot)gurjeet(at)gmail(dot)com>, "PGSQL Hackers" <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: New CRC algorithm: Slicing by 8
Date: 2006-10-22 02:22:10
Message-ID: e692861c0610211922g7216d74fr21084095942a6251@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On 10/21/06, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> wrote:
[snip]
> It hasn't even been tested. One thing I'd want to know about is the
> performance effect on non-Intel machines.

On Opteron 265 his test code shows SB8 (the intel alg) is 2.48x faster
for checksum and 1.95x faster for verify for the 800 * 1024 blocks of
1 KB each workload. For 100000 blocks of 8k I got simmlar results as
well.

It looks like the new code may have a larger cache footprint, so
actual performance may differ from the microbenchmark.

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Mark Kirkwood 2006-10-22 06:30:18 pg_buffercache tidyup
Previous Message Tom Lane 2006-10-21 23:24:29 Re: xlogdump fixups and WAL log question.