| From: | Kenneth Marshall <ktm(at)it(dot)is(dot)rice(dot)edu> |
|---|---|
| To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
| Cc: | Mark Kirkwood <markir(at)paradise(dot)net(dot)nz>, Benny Amorsen <benny+usenet(at)amorsen(dot)dk>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: New CRC algorithm: Slicing by 8 |
| Date: | 2006-10-23 21:52:18 |
| Message-ID: | 20061023215218.GI6179@it.is.rice.edu |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Mon, Oct 23, 2006 at 05:23:27PM -0400, Tom Lane wrote:
> Mark Kirkwood <markir(at)paradise(dot)net(dot)nz> writes:
> > Right - I think the regression is caused by libc and kernel being built
> > with gcc 3.4.6 and the test program being built with gcc 4.1.2.
>
> Why do you think that? The performance of the CRC loop shouldn't depend
> at all on either libc or the kernel, because they're not invoked inside
> the loop.
>
I can believe that not re-building GCC 4.1.x with the 4.1.x compiler
could result in it not taking full advantage of new features and functions.
Ken
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Matthew O'Connor | 2006-10-23 22:39:23 | Re: [PATCHES] smartvacuum() instead of autovacuum |
| Previous Message | Tom Lane | 2006-10-23 21:23:27 | Re: New CRC algorithm: Slicing by 8 |