All of lore.kernel.org
 help / color / mirror / Atom feed
From: "John David Anglin" <dave@hiauly1.hia.nrc.ca>
To: grundler@parisc-linux.org (Grant Grundler)
Cc: James.Bottomley@SteelEye.com, parisc-linux@lists.parisc-linux.org
Subject: Re: [parisc-linux] [PATCH] timer_interrupt and gettimeoffset.
Date: Tue, 5 Sep 2006 20:24:00 -0400 (EDT)	[thread overview]
Message-ID: <200609060024.k860O0Br009253@hiauly1.hia.nrc.ca> (raw)
In-Reply-To: <20060905051247.GB12278@colo.lackof.org> from "Grant Grundler" at Sep 4, 2006 11:12:47 pm

> >  Integer division and multiplation are very expensive, particularly when
> > running in 64-bit mode.  We don't have optimized millicode to do it.
> > So, I don't much like falling into the unlikely case if we are just
> > delayed one tick.
> 
> How many loops would be a reasonable tradeoff? 5? 10?
> We'd need a histogram from a "slow" machine to see that tradeoff.

The decision to loop versus division/multiplication can be made
based on the average number of cycles needed for the former versus
the latter.  If now - next_tick is less than nticks, then loop.
I'm sure the average number of cycles for division/multiplication
depends on whether the code is 32 bits or 64 bits.  Take a look
at __divdi3 if you want to see how horrible integer division is.

Dave
-- 
J. David Anglin                                  dave.anglin@nrc-cnrc.gc.ca
National Research Council of Canada              (613) 990-0752 (FAX: 952-6602)
_______________________________________________
parisc-linux mailing list
parisc-linux@lists.parisc-linux.org
http://lists.parisc-linux.org/mailman/listinfo/parisc-linux

  parent reply	other threads:[~2006-09-06  0:24 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-08-30 16:38 Re:[parisc-linux] [PATCH] timer_interrupt and gettimeoffset Joel Soete
2006-08-30 16:52 ` [parisc-linux] " Grant Grundler
2006-08-30 20:23   ` Carlos O'Donell
2006-09-02 15:52     ` James Bottomley
2006-09-03 15:00       ` Carlos O'Donell
2006-09-03 15:17         ` James Bottomley
2006-09-03 16:14         ` James Bottomley
2006-09-03 19:31           ` Grant Grundler
2006-09-04 15:51             ` James Bottomley
2006-09-04 16:57               ` John David Anglin
2006-09-04 17:23                 ` James Bottomley
2006-09-04 19:12                   ` John David Anglin
2006-09-04 21:21                 ` Grant Grundler
2006-09-04 22:47                   ` James Bottomley
2006-09-04 23:52                     ` John David Anglin
2006-09-05  5:12                       ` Grant Grundler
2006-09-05 15:53                         ` James Bottomley
2006-09-05 22:49                           ` Grant Grundler
2006-09-05 22:59                             ` James Bottomley
2006-09-05 23:41                             ` John David Anglin
2006-09-06  0:24                         ` John David Anglin [this message]
2006-09-03 19:38       ` Grant Grundler
2006-09-03 19:59         ` John David Anglin
2006-09-04  0:09           ` Grant Grundler
2006-09-04  0:58             ` John David Anglin
2006-09-04  3:51             ` John David Anglin
2006-09-04 15:49         ` James Bottomley
     [not found] <44FDE867.3090204@scarlet.be>
2006-09-05 21:35 ` John David Anglin
  -- strict thread matches above, loose matches on Subject: below --
2006-08-30  4:48 Carlos O'Donell
2006-08-31  6:53 ` Grant Grundler
2006-08-31 18:52   ` Carlos O'Donell
2006-08-31 21:46     ` Grant Grundler
2006-09-03 14:54       ` Carlos O'Donell
2006-09-03 19:55         ` Grant Grundler
2006-09-03 20:29           ` James Bottomley
2006-09-03 20:30           ` Carlos O'Donell
2006-09-03 21:22             ` John David Anglin
2006-09-01 22:48   ` Grant Grundler
2006-09-01 22:59     ` Grant Grundler

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=200609060024.k860O0Br009253@hiauly1.hia.nrc.ca \
    --to=dave@hiauly1.hia.nrc.ca \
    --cc=James.Bottomley@SteelEye.com \
    --cc=grundler@parisc-linux.org \
    --cc=parisc-linux@lists.parisc-linux.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.