Linux MIPS Architecture development
 help / color / mirror / Atom feed
From: Joe deBlaquiere <jadb@redhat.com>
To: "Maciej W. Rozycki" <macro@ds2.pg.gda.pl>
Cc: Jun Sun <jsun@mvista.com>, Florian Lohoff <flo@rfc822.org>,
	ralf@oss.sgi.com, Pete Popov <ppopov@mvista.com>,
	George Gensure <werkt@csh.rit.edu>,
	linux-mips@oss.sgi.com
Subject: Re: MIPS_ATOMIC_SET again (Re: newest kernel
Date: Wed, 23 May 2001 12:48:40 -0500	[thread overview]
Message-ID: <3B0BF7F8.3050306@redhat.com> (raw)
In-Reply-To: Pine.GSO.3.96.1010523152429.5196A-100000@delta.ds2.pg.gda.pl

Hi Maciej, Jun,

	Didn't mean to bring up a sore point, but it seems that we haven't yet 
come to a consensus on what policy to have here. I think you both make 
valid points that I don't necesarily disagree with, but I would like to 
follow the counterpoint a little further.

Maciej W. Rozycki wrote:

> On Wed, 23 May 2001, Joe deBlaquiere wrote:
> 
> 
>> I would vote for option #4 - make sure the ll/sc emulation stuff works 
>> and use ll/sc in glibc instead of sysmips. Beyond the pthreads mutex 
> 
> 
>  Please don't.  The emulation is an overkill here and the overhead is
> painful for ISA I systems, which are usually not the fastest ones.  This
> has already been discussed here.
> 

There's overhead to sysmips also, so neither one is going to give 
stunning performance. All out performance isn't likely an issue on one 
of these systems anyways.


>  If you want to go for speed and use ll/sc on an ISA II+ system, then
> compile glibc for ISA II or better.  It will never call sysmips() then. 

	The problem here is that now I have mips, mipsel, and mipselnollsc 
configurations of the cross-tools, the c library and the binary 
applications. It's one extra configuration to maintain.

	There's no way to solve the endianness issues, but using emulation to 
handle missing instructions (be they floating point or ll/sc, or 
what-have-you) solves the minor differences in the instruction set from 
the library/application standpoint. If all MIPS processors used the same 
instruction set then we wouldn't have the problem at all. Of course 
there are very good reasons (and probably some silly ones too...) why 
ISAs are tailored.

	The kernel is already going to have to adjust some anyway, so keeping the 
differences in the kernel doesn't increase the testing burden. Throwing 
the problem over to glibc (and the toolchain) does increase the number 
of active configurations.

Just my opinion.

-- 
Joe deBlaquiere
Red Hat, Inc.
307 Wynn Drive
Huntsville AL, 35805
voice : (256)-704-9200
fax   : (256)-837-3839

  reply	other threads:[~2001-05-23 18:04 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-05-21 22:45 newest kernel George Gensure
2001-05-21 23:10 ` Pete Popov
2001-05-21 23:23   ` Jun Sun
2001-05-21 23:25     ` Pete Popov
2001-05-22 12:33     ` Florian Lohoff
2001-05-22 17:04       ` George Gensure
2001-05-22 17:04         ` George Gensure
2001-05-22 22:46       ` MIPS_ATOMIC_SET again (Re: " Jun Sun
2001-05-23  6:37         ` Joe deBlaquiere
2001-05-23 13:34           ` Maciej W. Rozycki
2001-05-23 17:48             ` Joe deBlaquiere [this message]
2001-05-23 18:20               ` Kevin D. Kissell
2001-05-23 18:20                 ` Kevin D. Kissell
2001-05-23 19:37                 ` Maciej W. Rozycki
2001-05-23 23:49                   ` Kevin D. Kissell
2001-05-23 23:49                     ` Kevin D. Kissell
2001-05-24  4:11                     ` Joe deBlaquiere
2001-05-24 10:56                       ` Maciej W. Rozycki
2001-05-24 10:44                     ` Maciej W. Rozycki
2001-05-24 15:15                       ` Kevin D. Kissell
2001-05-24 15:15                         ` Kevin D. Kissell
2001-05-24 16:21                         ` Maciej W. Rozycki
2001-05-24 22:46                           ` Joe deBlaquiere
2001-05-25 17:19                             ` Maciej W. Rozycki
2001-05-25 22:02                             ` Surprise! (Re: " Jun Sun
2001-05-25 23:56                               ` Jun Sun
2001-05-28 15:34                               ` Maciej W. Rozycki
2001-05-29 22:32                                 ` Jun Sun
2001-05-30  6:46                                   ` Kevin D. Kissell
2001-05-30  6:46                                     ` Kevin D. Kissell
2001-05-30 13:42                                   ` Maciej W. Rozycki
2001-05-30 17:39                                     ` Jun Sun
2001-05-31  8:37                                       ` Maciej W. Rozycki
2001-05-31 11:54                                 ` Ralf Baechle
2001-05-31 19:16                                   ` Jun Sun
2001-05-23 18:41               ` Jun Sun
2001-05-23 18:54                 ` Florian Lohoff
2001-05-23 18:55                   ` Florian Lohoff
2001-05-23 20:04                     ` Joe deBlaquiere
2001-05-24  9:32                       ` Maciej W. Rozycki
2001-05-26 13:14                         ` Florian Lohoff
2001-05-28 15:37                           ` Maciej W. Rozycki
2001-05-26 13:15                       ` Florian Lohoff
2001-05-28 15:43                         ` Maciej W. Rozycki
2001-05-28 16:25                           ` Kevin D. Kissell
2001-05-28 16:25                             ` Kevin D. Kissell
2001-05-28 17:10                             ` Maciej W. Rozycki
2001-05-29  6:57                               ` Geert Uytterhoeven
2001-05-29 10:45                                 ` Maciej W. Rozycki
2001-05-29 13:02                               ` Joe deBlaquiere
2001-05-29 15:45                                 ` Mike McDonald
2001-05-30  1:32                                   ` Mike McDonald
2001-05-30  7:09                                   ` Kevin D. Kissell
2001-05-30  7:09                                     ` Kevin D. Kissell
2001-05-30 14:48                                   ` J. Scott Kasten
2001-05-30 14:48                                     ` J. Scott Kasten
2001-05-29 22:37                               ` Jun Sun
2001-05-30 12:01                                 ` Maciej W. Rozycki
2001-05-30 17:54                                   ` Jun Sun
2001-05-31  7:39                                     ` Maciej W. Rozycki
2001-05-23 19:44                   ` Maciej W. Rozycki
2001-05-24  4:25                     ` Keith M Wesolowski
2001-05-23 21:06                   ` Jun Sun
2001-05-23 19:29               ` Maciej W. Rozycki
2001-05-23 17:10           ` Jun Sun
2001-05-23 13:18         ` Maciej W. Rozycki
2001-05-23 17:38           ` Jun Sun
2001-05-23 18:47             ` Maciej W. Rozycki
2001-05-23 20:58               ` Jun Sun
2001-05-23 13:45         ` wrt irc joshua
2001-05-23 15:19           ` porting from headers Keith M Wesolowski
2001-05-23 15:55           ` wrt irc nick
2001-05-23 15:57             ` Keith M Wesolowski
2001-05-23 16:03               ` nick

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=3B0BF7F8.3050306@redhat.com \
    --to=jadb@redhat.com \
    --cc=flo@rfc822.org \
    --cc=jsun@mvista.com \
    --cc=linux-mips@oss.sgi.com \
    --cc=macro@ds2.pg.gda.pl \
    --cc=ppopov@mvista.com \
    --cc=ralf@oss.sgi.com \
    --cc=werkt@csh.rit.edu \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox