Re: Warm-cache prefetching

From: Qingqing Zhou <zhouqq(at)cs(dot)toronto(dot)edu>
To: "Min Xu (Hsu)" <xu(at)cs(dot)wisc(dot)edu>
Subject: Re: Warm-cache prefetching
Date: 2005-12-09 19:20:57
Message-ID: Pine.LNX.4.58.0512091402440.22607@eon.cs
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers


On Thu, 8 Dec 2005, Min Xu (Hsu) wrote:

> Perhaps because P4 is already doing H/W prefetching?
>
> http://www.tomshardware.com/2000/11/20/intel/page5.html
>
> I ran the test program on an opteron 2.2G:
> Got slowdown.
>
> I ran it on a PIII 650M:
> looks like some speedup to me.
>

Ok, I see ... so this optimization relies on the CPU type and even speed.
If many programs are fighting for L2 cache, then things will be screwed
up.

Regards,
Qingqing

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Tom Lane 2005-12-09 19:21:28 Re: Min Xid problem proposal
Previous Message Alvaro Herrera 2005-12-09 19:19:39 Re: Min Xid problem proposal