From: Jim Wilson <wilson@tuliptree.org>
To: Richard Kenner <kenner@vlsi1.ultra.nyu.edu>
Cc: gcc@gcc.gnu.org
Subject: Re: Problem in split_basic_block
Date: Sun, 10 Aug 2003 08:06:00 -0000 [thread overview]
Message-ID: <3F35EB93.3020500@tuliptree.org> (raw)
In-Reply-To: <10308080152.AA10195@vlsi1.ultra.nyu.edu>
Richard Kenner wrote:
> Interesting. I don't know the ia64 instruction set, but I'd always
> thought of the addp4 stuff as a horrible kludge. I'm kind of curious
> about this myself now.
The upper three bits of an IA-64 address indicate the segment (region).
This is somewhat similar to the VAX I believe. If you don't want
segments you can define them in the obvious way to get a flat address space.
addp4 does a 32-bit add and then copies the 2 most significant bits of
the 32-bit result (31 and 30) into the 2 most significant bits of the
target register (63 and 62). This gives you access to 4 segments (regions).
You really should have some understanding of the IA-64 ISA if you are
trying to do a port. IA-64 architecture manuals are available here:
http://developer.intel.com/design/itanium/manuals.htm
See Vol 2 Section 4.1.9 32-bit Virtual Addressing. This documents how
to do zero-extend, sign-extend, or pointer-swizzling addressing via
addp4. All 3 are supported by the architecture.
--
Jim Wilson, GNU Tools Support, http://www.SpecifixInc.com
next prev parent reply other threads:[~2003-08-10 6:55 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-08-08 3:04 Richard Kenner
2003-08-10 8:06 ` Jim Wilson [this message]
-- strict thread matches above, loose matches on Subject: below --
2003-08-10 16:35 Richard Kenner
2003-08-08 23:53 Richard Kenner
2003-08-07 21:08 Richard Kenner
2003-08-07 22:45 ` Richard Henderson
2003-08-07 20:30 Richard Kenner
2003-08-07 19:30 Nathanael Nerode
2003-08-07 13:10 Richard Kenner
2003-08-07 7:01 Richard Kenner
2003-08-07 19:33 ` Geoff Keating
2003-08-07 5:32 Richard Kenner
2003-08-06 23:42 Richard Kenner
2003-08-06 23:47 ` Zack Weinberg
2003-08-06 23:56 ` Douglas B Rupp
2003-08-06 23:57 ` Zack Weinberg
2003-08-07 0:16 ` Douglas B Rupp
2003-08-07 0:40 ` Zack Weinberg
2003-08-06 23:57 ` Douglas B Rupp
2003-08-07 0:43 ` Zack Weinberg
2003-08-07 0:38 ` Douglas B Rupp
2003-08-07 1:05 ` Zack Weinberg
2003-08-07 20:59 ` Richard Henderson
2003-08-08 23:41 ` Richard Henderson
2003-09-01 13:18 ` Olivier Hainque
2003-08-01 23:07 Richard Kenner
2003-08-06 22:41 ` Richard Henderson
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=3F35EB93.3020500@tuliptree.org \
--to=wilson@tuliptree.org \
--cc=gcc@gcc.gnu.org \
--cc=kenner@vlsi1.ultra.nyu.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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).