qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "David S. Miller" <davem@redhat.com>
To: jrydberg@night.trouble.net
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH] Updated Sparc support
Date: Thu, 15 May 2003 13:24:06 -0700 (PDT)	[thread overview]
Message-ID: <20030515.132406.115929721.davem@redhat.com> (raw)
In-Reply-To: <20030515201724.GA19302@bushwacker>

   From: Johan Rydberg <jrydberg@night.trouble.net>
   Date: Thu, 15 May 2003 22:17:24 +0200

   Using global registers for commonly used variables such as the CPU
   structure and current virtual program counter will increase the
   performance with a magnitude I guess.
   
   So, if I understand you correctly, everything should work pretty good
   i you use -fflat and stay away from the input registers?  (I have no
   need for the -fno-delay-slot flag)
   
-mflat SUCKS, it generates the worst code possible.

Also, if you're going to use global register, be forewarned that
if you call into libc you risk them being clobbered.  Sparc-linux
libc clobbers just about every global register in some piece of
assembly somewhere.

There are also very strict rules about which global register an
application can use in this fashion.  Please refer to the standards
documents about exactly which these are (they are different for 32-bit
and 64-bit sparc) and no I don't have time to discuss this further
nor point you at where to get these documents.:-)

      reply	other threads:[~2003-05-15 20:25 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-05-13  4:13 [Qemu-devel] [PATCH] Updated Sparc support David S. Miller
2003-05-13 12:31 ` [Qemu-devel] " Fabrice Bellard
2003-05-13 19:49   ` David S. Miller
2003-05-14  0:13   ` Rusty Russell
2003-05-14 11:48     ` Fabrice Bellard
2003-05-16 13:54       ` [Qemu-devel] Regression tests - syscall note Fabrice Bellard
2003-05-15 13:03 ` [Qemu-devel] [PATCH] Updated Sparc support Johan Rydberg
2003-05-15 20:05   ` David S. Miller
2003-05-15 20:17     ` Johan Rydberg
2003-05-15 20:24       ` David S. Miller [this message]

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=20030515.132406.115929721.davem@redhat.com \
    --to=davem@redhat.com \
    --cc=jrydberg@night.trouble.net \
    --cc=qemu-devel@nongnu.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).